diff --git a/.ci/windows_amd_base_files/run_amd_gpu_disable_smart_memory.bat b/.ci/windows_amd_base_files/run_amd_gpu_enable_dynamic_vram.bat similarity index 66% rename from .ci/windows_amd_base_files/run_amd_gpu_disable_smart_memory.bat rename to .ci/windows_amd_base_files/run_amd_gpu_enable_dynamic_vram.bat index cece0aeb2..94ad31942 100755 --- a/.ci/windows_amd_base_files/run_amd_gpu_disable_smart_memory.bat +++ b/.ci/windows_amd_base_files/run_amd_gpu_enable_dynamic_vram.bat @@ -1,2 +1,2 @@ -.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --disable-smart-memory +.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --enable-dynamic-vram pause diff --git a/.ci/windows_intel_base_files/run_intel_gpu.bat b/.ci/windows_intel_base_files/run_intel_gpu.bat new file mode 100755 index 000000000..274d7c948 --- /dev/null +++ b/.ci/windows_intel_base_files/run_intel_gpu.bat @@ -0,0 +1,2 @@ +.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build +pause diff --git a/.github/workflows/release-stable-all.yml b/.github/workflows/release-stable-all.yml index 8f07a7b1c..d7cf69fe2 100644 --- a/.github/workflows/release-stable-all.yml +++ b/.github/workflows/release-stable-all.yml @@ -20,29 +20,12 @@ jobs: git_tag: ${{ inputs.git_tag }} cache_tag: "cu130" python_minor: "13" - python_patch: "11" + python_patch: "12" rel_name: "nvidia" rel_extra_name: "" test_release: true secrets: inherit - release_nvidia_cu128: - permissions: - contents: "write" - packages: "write" - pull-requests: "read" - name: "Release NVIDIA cu128" - uses: ./.github/workflows/stable-release.yml - with: - git_tag: ${{ inputs.git_tag }} - cache_tag: "cu128" - python_minor: "12" - python_patch: "10" - rel_name: "nvidia" - rel_extra_name: "_cu128" - test_release: true - secrets: inherit - release_nvidia_cu126: permissions: contents: "write" @@ -76,3 +59,20 @@ jobs: rel_extra_name: "" test_release: false secrets: inherit + + release_xpu: + permissions: + contents: "write" + packages: "write" + pull-requests: "read" + name: "Release Intel XPU" + uses: ./.github/workflows/stable-release.yml + with: + git_tag: ${{ inputs.git_tag }} + cache_tag: "xpu" + python_minor: "13" + python_patch: "12" + rel_name: "intel" + rel_extra_name: "" + test_release: true + secrets: inherit diff --git a/.github/workflows/tag-dispatch-cloud.yml b/.github/workflows/tag-dispatch-cloud.yml new file mode 100644 index 000000000..53a0e91d6 --- /dev/null +++ b/.github/workflows/tag-dispatch-cloud.yml @@ -0,0 +1,45 @@ +name: Tag Dispatch to Cloud + +on: + push: + tags: + - 'v*' + +jobs: + dispatch-cloud: + runs-on: ubuntu-latest + steps: + - name: Send repository dispatch to cloud + env: + DISPATCH_TOKEN: ${{ secrets.CLOUD_REPO_DISPATCH_TOKEN }} + RELEASE_TAG: ${{ github.ref_name }} + run: | + set -euo pipefail + + if [ -z "${DISPATCH_TOKEN:-}" ]; then + echo "::error::CLOUD_REPO_DISPATCH_TOKEN is required but not set." + exit 1 + fi + + RELEASE_URL="https://github.com/${{ github.repository }}/releases/tag/${RELEASE_TAG}" + + PAYLOAD="$(jq -n \ + --arg release_tag "$RELEASE_TAG" \ + --arg release_url "$RELEASE_URL" \ + '{ + event_type: "comfyui_tag_pushed", + client_payload: { + release_tag: $release_tag, + release_url: $release_url + } + }')" + + curl -fsSL \ + -X POST \ + -H "Accept: application/vnd.github+json" \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer ${DISPATCH_TOKEN}" \ + https://api.github.com/repos/Comfy-Org/cloud/dispatches \ + -d "$PAYLOAD" + + echo "✅ Dispatched ComfyUI tag ${RELEASE_TAG} to Comfy-Org/cloud" diff --git a/.gitignore b/.gitignore index 2700ad5c2..0ab4ba75e 100644 --- a/.gitignore +++ b/.gitignore @@ -21,6 +21,5 @@ venv*/ *.log web_custom_versions/ .DS_Store -openapi.yaml filtered-openapi.yaml uv.lock diff --git a/CODEOWNERS b/CODEOWNERS index 4d5448636..946dbf946 100644 --- a/CODEOWNERS +++ b/CODEOWNERS @@ -1,2 +1,2 @@ # Admins -* @comfyanonymous @kosinkadink @guill +* @comfyanonymous @kosinkadink @guill @alexisrolland @rattus128 @kijai diff --git a/QUANTIZATION.md b/QUANTIZATION.md index 1693e13f3..300822029 100644 --- a/QUANTIZATION.md +++ b/QUANTIZATION.md @@ -139,9 +139,9 @@ Example: "_quantization_metadata": { "format_version": "1.0", "layers": { - "model.layers.0.mlp.up_proj": "float8_e4m3fn", - "model.layers.0.mlp.down_proj": "float8_e4m3fn", - "model.layers.1.mlp.up_proj": "float8_e4m3fn" + "model.layers.0.mlp.up_proj": {"format": "float8_e4m3fn"}, + "model.layers.0.mlp.down_proj": {"format": "float8_e4m3fn"}, + "model.layers.1.mlp.up_proj": {"format": "float8_e4m3fn"} } } } @@ -165,4 +165,4 @@ Activation quantization (e.g., for FP8 Tensor Core operations) requires `input_s 3. **Compute scales**: Derive `input_scale` from collected statistics 4. **Store in checkpoint**: Save `input_scale` parameters alongside weights -The calibration dataset should be representative of your target use case. For diffusion models, this typically means a diverse set of prompts and generation parameters. \ No newline at end of file +The calibration dataset should be representative of your target use case. For diffusion models, this typically means a diverse set of prompts and generation parameters. diff --git a/README.md b/README.md index 62c4f528c..a3bd3ba0a 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@
# ComfyUI -**The most powerful and modular visual AI engine and application.** +**The most powerful and modular AI engine for content creation.** [![Website][website-shield]][website-url] @@ -31,10 +31,16 @@ [github-downloads-latest-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/latest/total?style=flat&label=downloads%40latest [github-downloads-link]: https://github.com/comfyanonymous/ComfyUI/releases -![ComfyUI Screenshot](https://github.com/user-attachments/assets/7ccaf2c1-9b72-41ae-9a89-5688c94b7abe) +ComfyUI Screenshot +
-ComfyUI lets you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface. Available on Windows, Linux, and macOS. +ComfyUI is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. Its powerful and modular node graph interface empowers creatives to generate images, videos, 3D models, audio, and more... +- ComfyUI natively supports the latest open-source state of the art models. +- API nodes provide access to the best closed source models such as Nano Banana, Seedance, Hunyuan3D, etc. +- It is available on Windows, Linux, and macOS, locally with our desktop application or on our cloud. +- The most sophisticated workflows can be exposed through a simple UI thanks to App Mode. +- It integrates seamlessly into production pipelines with our API endpoints. ## Get Started @@ -61,6 +67,7 @@ See what ComfyUI can do with the [newer template workflows](https://comfy.org/wo ## Features - Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. +- NOTE: There are many more models supported than the list below, if you want to see what is supported see our templates list inside ComfyUI. - Image Models - SD1.x, SD2.x ([unCLIP](https://comfyanonymous.github.io/ComfyUI_examples/unclip/)) - [SDXL](https://comfyanonymous.github.io/ComfyUI_examples/sdxl/), [SDXL Turbo](https://comfyanonymous.github.io/ComfyUI_examples/sdturbo/) @@ -76,6 +83,7 @@ See what ComfyUI can do with the [newer template workflows](https://comfy.org/wo - [Hunyuan Image 2.1](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_image/) - [Flux 2](https://comfyanonymous.github.io/ComfyUI_examples/flux2/) - [Z Image](https://comfyanonymous.github.io/ComfyUI_examples/z_image/) + - Ernie Image - Image Editing Models - [Omnigen 2](https://comfyanonymous.github.io/ComfyUI_examples/omnigen/) - [Flux Kontext](https://comfyanonymous.github.io/ComfyUI_examples/flux/#flux-kontext-image-editing-model) @@ -136,7 +144,7 @@ ComfyUI follows a weekly release cycle targeting Monday but this regularly chang - Builds a new release using the latest stable core version 3. **[ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend)** - - Weekly frontend updates are merged into the core repository + - Every 2+ weeks frontend updates are merged into the core repository - Features are frozen for the upcoming core release - Development continues for the next release cycle @@ -192,11 +200,15 @@ If you have trouble extracting it, right click the file -> properties -> unblock The portable above currently comes with python 3.13 and pytorch cuda 13.0. Update your Nvidia drivers if it doesn't start. -#### Alternative Downloads: +#### All Official Portable Downloads: -[Experimental portable for AMD GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z) +[Portable for AMD GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z) -[Portable with pytorch cuda 12.6 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu126.7z) (Supports Nvidia 10 series and older GPUs). +[Portable for Intel GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_intel.7z) + +[Portable for Nvidia GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia.7z) (supports 20 series and above). + +[Portable for Nvidia GPUs with pytorch cuda 12.6 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu126.7z) (Supports Nvidia 10 series and older GPUs). #### How do I share models between another UI and ComfyUI? @@ -232,7 +244,7 @@ Put your VAE in: models/vae AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version: -```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.1``` +```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.2``` This is the command to install the nightly with ROCm 7.2 which might have some performance improvements: @@ -275,7 +287,7 @@ Nvidia users should install stable pytorch using this command: This is the command to install pytorch nightly instead which might have performance improvements. -```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu130``` +```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu132``` #### Troubleshooting diff --git a/api_server/routes/internal/internal_routes.py b/api_server/routes/internal/internal_routes.py index b224306da..1477afa01 100644 --- a/api_server/routes/internal/internal_routes.py +++ b/api_server/routes/internal/internal_routes.py @@ -67,7 +67,7 @@ class InternalRoutes: (entry for entry in os.scandir(directory) if is_visible_file(entry)), key=lambda entry: -entry.stat().st_mtime ) - return web.json_response([entry.name for entry in sorted_files], status=200) + return web.json_response([f"{entry.name} [{directory_type}]" for entry in sorted_files], status=200) def get_app(self): diff --git a/blueprints/.glsl/Glow_30.frag b/blueprints/.glsl/Glow_30.frag index 0ee152628..f3c85a212 100644 --- a/blueprints/.glsl/Glow_30.frag +++ b/blueprints/.glsl/Glow_30.frag @@ -2,7 +2,6 @@ precision mediump float; uniform sampler2D u_image0; -uniform vec2 u_resolution; uniform int u_int0; // Blend mode uniform int u_int1; // Color tint uniform float u_float0; // Intensity @@ -75,7 +74,7 @@ void main() { float t0 = threshold - 0.15; float t1 = threshold + 0.15; - vec2 texelSize = 1.0 / u_resolution; + vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0)); float radius2 = radius * radius; float sampleScale = clamp(radius * 0.75, 0.35, 1.0); diff --git a/blueprints/.glsl/Image_Blur_1.frag b/blueprints/.glsl/Image_Blur_1.frag index 83238111d..1819e1695 100644 --- a/blueprints/.glsl/Image_Blur_1.frag +++ b/blueprints/.glsl/Image_Blur_1.frag @@ -12,7 +12,6 @@ const int RADIAL_SAMPLES = 12; const float RADIAL_STRENGTH = 0.0003; uniform sampler2D u_image0; -uniform vec2 u_resolution; uniform int u_int0; // Blur type (BLUR_GAUSSIAN, BLUR_BOX, BLUR_RADIAL) uniform float u_float0; // Blur radius/amount uniform int u_pass; // Pass index (0 = horizontal, 1 = vertical) @@ -25,7 +24,7 @@ float gaussian(float x, float sigma) { } void main() { - vec2 texelSize = 1.0 / u_resolution; + vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0)); float radius = max(u_float0, 0.0); // Radial (angular) blur - single pass, doesn't use separable diff --git a/blueprints/.glsl/Sharpen_23.frag b/blueprints/.glsl/Sharpen_23.frag index c03f94b66..e7463a329 100644 --- a/blueprints/.glsl/Sharpen_23.frag +++ b/blueprints/.glsl/Sharpen_23.frag @@ -2,14 +2,13 @@ precision highp float; uniform sampler2D u_image0; -uniform vec2 u_resolution; uniform float u_float0; // strength [0.0 – 2.0] typical: 0.3–1.0 in vec2 v_texCoord; layout(location = 0) out vec4 fragColor0; void main() { - vec2 texel = 1.0 / u_resolution; + vec2 texel = 1.0 / vec2(textureSize(u_image0, 0)); // Sample center and neighbors vec4 center = texture(u_image0, v_texCoord); diff --git a/blueprints/.glsl/Unsharp_Mask_26.frag b/blueprints/.glsl/Unsharp_Mask_26.frag index f5990cb4a..d968c9c03 100644 --- a/blueprints/.glsl/Unsharp_Mask_26.frag +++ b/blueprints/.glsl/Unsharp_Mask_26.frag @@ -2,7 +2,6 @@ precision highp float; uniform sampler2D u_image0; -uniform vec2 u_resolution; uniform float u_float0; // amount [0.0 - 3.0] typical: 0.5-1.5 uniform float u_float1; // radius [0.5 - 10.0] blur radius in pixels uniform float u_float2; // threshold [0.0 - 0.1] min difference to sharpen @@ -19,7 +18,7 @@ float getLuminance(vec3 color) { } void main() { - vec2 texel = 1.0 / u_resolution; + vec2 texel = 1.0 / vec2(textureSize(u_image0, 0)); float radius = max(u_float1, 0.5); float amount = u_float0; float threshold = u_float2; diff --git a/blueprints/Brightness and Contrast.json b/blueprints/Brightness and Contrast.json index 2c7e60eb1..90bfe999d 100644 --- a/blueprints/Brightness and Contrast.json +++ b/blueprints/Brightness and Contrast.json @@ -1 +1,439 @@ -{"revision": 0, "last_node_id": 140, "last_link_id": 0, "nodes": [{"id": 140, "type": "916dff42-6166-4d45-b028-04eaf69fbb35", "pos": [500, 1440], "size": [250, 178], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["4", "value"], ["5", "value"]]}, "widgets_values": [], "title": "Brightness and Contrast"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "916dff42-6166-4d45-b028-04eaf69fbb35", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 143, "lastLinkId": 118, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Brightness and Contrast", "inputNode": {"id": -10, "bounding": [360, -176, 120, 60]}, "outputNode": {"id": -20, "bounding": [1410, -176, 120, 60]}, "inputs": [{"id": "a5aae7ea-b511-4045-b5da-94101e269cd7", "name": "images.image0", "type": "IMAGE", "linkIds": [117], "localized_name": "images.image0", "label": "image", "pos": [460, -156]}], "outputs": [{"id": "30b72604-69b3-4944-b253-a9099bbd73a9", "name": "IMAGE0", "type": "IMAGE", "linkIds": [118], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [1430, -156]}], "widgets": [], "nodes": [{"id": 4, "type": "PrimitiveFloat", "pos": [540, -280], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "brightness", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [115]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "precision": 1, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 0, 0]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [50]}, {"id": 5, "type": "PrimitiveFloat", "pos": [540, -170], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "contrast", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [116]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "precision": 1, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [136, 136, 136]}, {"offset": 0.4, "color": [68, 68, 68]}, {"offset": 0.6, "color": [187, 187, 187]}, {"offset": 0.8, "color": [0, 0, 0]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [0]}, {"id": 143, "type": "GLSLShader", "pos": [840, -280], "size": [400, 212], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 117}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 115}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 116}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [118]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // Brightness slider -100..100\nuniform float u_float1; // Contrast slider -100..100\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst float MID_GRAY = 0.18; // 18% reflectance\n\n// sRGB gamma 2.2 approximation\nvec3 srgbToLinear(vec3 c) {\n return pow(max(c, 0.0), vec3(2.2));\n}\n\nvec3 linearToSrgb(vec3 c) {\n return pow(max(c, 0.0), vec3(1.0/2.2));\n}\n\nfloat mapBrightness(float b) {\n return clamp(b / 100.0, -1.0, 1.0);\n}\n\nfloat mapContrast(float c) {\n return clamp(c / 100.0 + 1.0, 0.0, 2.0);\n}\n\nvoid main() {\n vec4 orig = texture(u_image0, v_texCoord);\n\n float brightness = mapBrightness(u_float0);\n float contrast = mapContrast(u_float1);\n\n vec3 lin = srgbToLinear(orig.rgb);\n\n lin = (lin - MID_GRAY) * contrast + brightness + MID_GRAY;\n\n // Convert back to sRGB\n vec3 result = linearToSrgb(clamp(lin, 0.0, 1.0));\n\n fragColor = vec4(result, orig.a);\n}\n", "from_input"]}], "groups": [], "links": [{"id": 115, "origin_id": 4, "origin_slot": 0, "target_id": 143, "target_slot": 2, "type": "FLOAT"}, {"id": 116, "origin_id": 5, "origin_slot": 0, "target_id": 143, "target_slot": 3, "type": "FLOAT"}, {"id": 117, "origin_id": -10, "origin_slot": 0, "target_id": 143, "target_slot": 0, "type": "IMAGE"}, {"id": 118, "origin_id": 143, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}, "extra": {}} +{ + "revision": 0, + "last_node_id": 140, + "last_link_id": 0, + "nodes": [ + { + "id": 140, + "type": "916dff42-6166-4d45-b028-04eaf69fbb35", + "pos": [ + 500, + 1440 + ], + "size": [ + 250, + 178 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "4", + "value" + ], + [ + "5", + "value" + ] + ] + }, + "widgets_values": [], + "title": "Brightness and Contrast" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "916dff42-6166-4d45-b028-04eaf69fbb35", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 143, + "lastLinkId": 118, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Brightness and Contrast", + "inputNode": { + "id": -10, + "bounding": [ + 360, + -176, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1410, + -176, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "a5aae7ea-b511-4045-b5da-94101e269cd7", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 117 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 460, + -156 + ] + } + ], + "outputs": [ + { + "id": "30b72604-69b3-4944-b253-a9099bbd73a9", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 118 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 1430, + -156 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 4, + "type": "PrimitiveFloat", + "pos": [ + 540, + -280 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "brightness", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 115 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "precision": 1, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 5, + "type": "PrimitiveFloat", + "pos": [ + 540, + -170 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "contrast", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 116 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "precision": 1, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 136, + 136, + 136 + ] + }, + { + "offset": 0.4, + "color": [ + 68, + 68, + 68 + ] + }, + { + "offset": 0.6, + "color": [ + 187, + 187, + 187 + ] + }, + { + "offset": 0.8, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 143, + "type": "GLSLShader", + "pos": [ + 840, + -280 + ], + "size": [ + 400, + 212 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 117 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 115 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 116 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 118 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // Brightness slider -100..100\nuniform float u_float1; // Contrast slider -100..100\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst float MID_GRAY = 0.18; // 18% reflectance\n\n// sRGB gamma 2.2 approximation\nvec3 srgbToLinear(vec3 c) {\n return pow(max(c, 0.0), vec3(2.2));\n}\n\nvec3 linearToSrgb(vec3 c) {\n return pow(max(c, 0.0), vec3(1.0/2.2));\n}\n\nfloat mapBrightness(float b) {\n return clamp(b / 100.0, -1.0, 1.0);\n}\n\nfloat mapContrast(float c) {\n return clamp(c / 100.0 + 1.0, 0.0, 2.0);\n}\n\nvoid main() {\n vec4 orig = texture(u_image0, v_texCoord);\n\n float brightness = mapBrightness(u_float0);\n float contrast = mapContrast(u_float1);\n\n vec3 lin = srgbToLinear(orig.rgb);\n\n lin = (lin - MID_GRAY) * contrast + brightness + MID_GRAY;\n\n // Convert back to sRGB\n vec3 result = linearToSrgb(clamp(lin, 0.0, 1.0));\n\n fragColor = vec4(result, orig.a);\n}\n", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 115, + "origin_id": 4, + "origin_slot": 0, + "target_id": 143, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 116, + "origin_id": 5, + "origin_slot": 0, + "target_id": 143, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 117, + "origin_id": -10, + "origin_slot": 0, + "target_id": 143, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 118, + "origin_id": 143, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + }, + "extra": {} +} diff --git a/blueprints/Canny to Image (Z-Image-Turbo).json b/blueprints/Canny to Image (Z-Image-Turbo).json index 8b78a834a..ff9717308 100644 --- a/blueprints/Canny to Image (Z-Image-Turbo).json +++ b/blueprints/Canny to Image (Z-Image-Turbo).json @@ -1 +1,1577 @@ -{"id": "e046dd74-e2a7-4f31-a75b-5e11a8c72d4e", "revision": 0, "last_node_id": 18, "last_link_id": 32, "nodes": [{"id": 18, "type": "c84f7959-3738-422b-ba6e-5808b5e90101", "pos": [300, 3830], "size": [400, 460], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "control image", "name": "image", "type": "IMAGE", "link": null}, {"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"label": "canny low threshold", "name": "low_threshold", "type": "FLOAT", "widget": {"name": "low_threshold"}, "link": null}, {"label": "canny high threshold", "name": "high_threshold", "type": "FLOAT", "widget": {"name": "high_threshold"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}, {"name": "name", "type": "COMBO", "widget": {"name": "name"}, "link": null}], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": null}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "low_threshold"], ["-1", "high_threshold"], ["7", "seed"], ["7", "control_after_generate"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"], ["-1", "name"]], "cnr_id": "comfy-core", "ver": "0.11.0"}, "widgets_values": ["", 0.3, 0.4, null, null, "z_image_turbo_bf16.safetensors", "qwen_3_4b.safetensors", "ae.safetensors", "Z-Image-Turbo-Fun-Controlnet-Union.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "c84f7959-3738-422b-ba6e-5808b5e90101", "version": 1, "state": {"lastGroupId": 3, "lastNodeId": 18, "lastLinkId": 32, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Canny to Image (Z-Image-Turbo)", "inputNode": {"id": -10, "bounding": [-280, 4960, 158.880859375, 200]}, "outputNode": {"id": -20, "bounding": [1598.6038576146689, 4936.043696127976, 120, 60]}, "inputs": [{"id": "29ca271b-8f63-4e7b-a4b8-c9b4192ada0b", "name": "image", "type": "IMAGE", "linkIds": [26], "label": "control image", "pos": [-141.119140625, 4980]}, {"id": "b6549f90-39ee-4b79-9e00-af4d9df969fe", "name": "text", "type": "STRING", "linkIds": [16], "label": "prompt", "pos": [-141.119140625, 5000]}, {"id": "6bd34d18-79f6-470f-94df-ca14c84ef3d8", "name": "low_threshold", "type": "FLOAT", "linkIds": [24], "label": "canny low threshold", "pos": [-141.119140625, 5020]}, {"id": "bbced993-057f-4d2d-909c-d791be73d1d2", "name": "high_threshold", "type": "FLOAT", "linkIds": [25], "label": "canny high threshold", "pos": [-141.119140625, 5040]}, {"id": "db7969bf-4b05-48a0-9598-87d3ac85b505", "name": "unet_name", "type": "COMBO", "linkIds": [29], "pos": [-141.119140625, 5060]}, {"id": "925b611c-5edf-406f-8dc5-7fec07d049a7", "name": "clip_name", "type": "COMBO", "linkIds": [30], "pos": [-141.119140625, 5080]}, {"id": "b4cf508b-4753-40d2-8c83-5a424237ee07", "name": "vae_name", "type": "COMBO", "linkIds": [31], "pos": [-141.119140625, 5100]}, {"id": "bd948f38-3a11-4091-99fc-bb2b3511bcd2", "name": "name", "type": "COMBO", "linkIds": [32], "pos": [-141.119140625, 5120]}], "outputs": [{"id": "47f9a22d-6619-4917-9447-a7d5d08dceb5", "name": "IMAGE", "type": "IMAGE", "linkIds": [18], "pos": [1618.6038576146689, 4956.043696127976]}], "widgets": [], "nodes": [{"id": 1, "type": "CLIPLoader", "pos": [228.60376290329597, 4700.188357350136], "size": [270, 106], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 30}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [14]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_3_4b.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_3_4b.safetensors", "lumina2", "default"]}, {"id": 2, "type": "UNETLoader", "pos": [228.60376290329597, 4550.1883046176445], "size": [270, 82], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 29}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [9]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "UNETLoader", "models": [{"name": "z_image_turbo_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["z_image_turbo_bf16.safetensors", "default"]}, {"id": 3, "type": "VAELoader", "pos": [228.60376290329597, 4880.18831633181], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 31}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [2, 11]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "VAELoader", "models": [{"name": "ae.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ae.safetensors"]}, {"id": 4, "type": "ModelPatchLoader", "pos": [228.60376290329597, 5010.1884895078], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "name", "name": "name", "type": "COMBO", "widget": {"name": "name"}, "link": 32}], "outputs": [{"localized_name": "MODEL_PATCH", "name": "MODEL_PATCH", "type": "MODEL_PATCH", "links": [10]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "ModelPatchLoader", "models": [{"name": "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", "url": "https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union/resolve/main/Z-Image-Turbo-Fun-Controlnet-Union.safetensors", "directory": "model_patches"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["Z-Image-Turbo-Fun-Controlnet-Union.safetensors"]}, {"id": 6, "type": "ModelSamplingAuraFlow", "pos": [998.6039930366841, 4490.18831829042], "size": [290, 58], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 3}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [4]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "ModelSamplingAuraFlow", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 7, "type": "KSampler", "pos": [998.6039930366841, 4600.188351166619], "size": [300, 460], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 4}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 5}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 6}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 7}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [1]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize", 9, 1, "res_multistep", "simple", 1]}, {"id": 8, "type": "ConditioningZeroOut", "pos": [748.2704434516113, 5044.855005348689], "size": [204.134765625, 26.000000000000004], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 8}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [6]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "ConditioningZeroOut", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 9, "type": "QwenImageDiffsynthControlnet", "pos": [608.2704174118008, 5204.85499785943], "size": [290, 138], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 9}, {"localized_name": "model_patch", "name": "model_patch", "type": "MODEL_PATCH", "link": 10}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 11}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 22}, {"localized_name": "mask", "name": "mask", "shape": 7, "type": "MASK", "link": null}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [3]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.76", "Node name for S&R": "QwenImageDiffsynthControlnet", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 12, "type": "CLIPTextEncode", "pos": [548.2704310845766, 4544.854974431101], "size": [400, 330], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 14}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 16}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [5, 8]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 5, "type": "VAEDecode", "pos": [1338.6038576146689, 4500.188344983101], "size": [200, 46], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 1}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 2}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [18]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 15, "type": "ImageScaleToTotalPixels", "pos": [220, 5220], "size": [270, 106], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 26}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "megapixels", "name": "megapixels", "type": "FLOAT", "widget": {"name": "megapixels"}, "link": null}, {"localized_name": "resolution_steps", "name": "resolution_steps", "type": "INT", "widget": {"name": "resolution_steps"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [27]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "ImageScaleToTotalPixels"}, "widgets_values": ["nearest-exact", 1, 1]}, {"id": 11, "type": "GetImageSize", "pos": [540, 5450], "size": [140, 66], "flags": {"collapsed": false}, "order": 10, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 23}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [12]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [13]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": null}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.76", "Node name for S&R": "GetImageSize", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 10, "type": "EmptySD3LatentImage", "pos": [760, 5430], "size": [260, 106], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 12}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 13}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [7]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "EmptySD3LatentImage", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1024, 1024, 1]}, {"id": 14, "type": "Canny", "pos": [220, 5380], "size": [270, 82], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 27}, {"localized_name": "low_threshold", "name": "low_threshold", "type": "FLOAT", "widget": {"name": "low_threshold"}, "link": 24}, {"localized_name": "high_threshold", "name": "high_threshold", "type": "FLOAT", "widget": {"name": "high_threshold"}, "link": 25}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [22, 23, 28]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "Canny"}, "widgets_values": [0.3, 0.4]}, {"id": 16, "type": "PreviewImage", "pos": [220, 5520], "size": [260, 270], "flags": {}, "order": 14, "mode": 4, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 28}], "outputs": [], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "PreviewImage"}, "widgets_values": []}], "groups": [{"id": 1, "title": "Prompt", "bounding": [530, 4460, 440, 630], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Models", "bounding": [210, 4460, 300, 640], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Apple ControlNet", "bounding": [530, 5120, 440, 260], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 1, "origin_id": 7, "origin_slot": 0, "target_id": 5, "target_slot": 0, "type": "LATENT"}, {"id": 2, "origin_id": 3, "origin_slot": 0, "target_id": 5, "target_slot": 1, "type": "VAE"}, {"id": 3, "origin_id": 9, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "MODEL"}, {"id": 4, "origin_id": 6, "origin_slot": 0, "target_id": 7, "target_slot": 0, "type": "MODEL"}, {"id": 5, "origin_id": 12, "origin_slot": 0, "target_id": 7, "target_slot": 1, "type": "CONDITIONING"}, {"id": 6, "origin_id": 8, "origin_slot": 0, "target_id": 7, "target_slot": 2, "type": "CONDITIONING"}, {"id": 7, "origin_id": 10, "origin_slot": 0, "target_id": 7, "target_slot": 3, "type": "LATENT"}, {"id": 8, "origin_id": 12, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "CONDITIONING"}, {"id": 9, "origin_id": 2, "origin_slot": 0, "target_id": 9, "target_slot": 0, "type": "MODEL"}, {"id": 10, "origin_id": 4, "origin_slot": 0, "target_id": 9, "target_slot": 1, "type": "MODEL_PATCH"}, {"id": 11, "origin_id": 3, "origin_slot": 0, "target_id": 9, "target_slot": 2, "type": "VAE"}, {"id": 12, "origin_id": 11, "origin_slot": 0, "target_id": 10, "target_slot": 0, "type": "INT"}, {"id": 13, "origin_id": 11, "origin_slot": 1, "target_id": 10, "target_slot": 1, "type": "INT"}, {"id": 14, "origin_id": 1, "origin_slot": 0, "target_id": 12, "target_slot": 0, "type": "CLIP"}, {"id": 16, "origin_id": -10, "origin_slot": 1, "target_id": 12, "target_slot": 1, "type": "STRING"}, {"id": 18, "origin_id": 5, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 22, "origin_id": 14, "origin_slot": 0, "target_id": 9, "target_slot": 3, "type": "IMAGE"}, {"id": 23, "origin_id": 14, "origin_slot": 0, "target_id": 11, "target_slot": 0, "type": "IMAGE"}, {"id": 24, "origin_id": -10, "origin_slot": 2, "target_id": 14, "target_slot": 1, "type": "FLOAT"}, {"id": 25, "origin_id": -10, "origin_slot": 3, "target_id": 14, "target_slot": 2, "type": "FLOAT"}, {"id": 26, "origin_id": -10, "origin_slot": 0, "target_id": 15, "target_slot": 0, "type": "IMAGE"}, {"id": 27, "origin_id": 15, "origin_slot": 0, "target_id": 14, "target_slot": 0, "type": "IMAGE"}, {"id": 28, "origin_id": 14, "origin_slot": 0, "target_id": 16, "target_slot": 0, "type": "IMAGE"}, {"id": 29, "origin_id": -10, "origin_slot": 4, "target_id": 2, "target_slot": 0, "type": "COMBO"}, {"id": 30, "origin_id": -10, "origin_slot": 5, "target_id": 1, "target_slot": 0, "type": "COMBO"}, {"id": 31, "origin_id": -10, "origin_slot": 6, "target_id": 3, "target_slot": 0, "type": "COMBO"}, {"id": 32, "origin_id": -10, "origin_slot": 7, "target_id": 4, "target_slot": 0, "type": "COMBO"}], "extra": {"frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true}, "category": "Image generation and editing/Canny to image"}]}, "config": {}, "extra": {"frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true, "ds": {"scale": 0.967267584583181, "offset": [444.759060017523, -3564.372163194443]}}, "version": 0.4} +{ + "id": "e046dd74-e2a7-4f31-a75b-5e11a8c72d4e", + "revision": 0, + "last_node_id": 18, + "last_link_id": 32, + "nodes": [ + { + "id": 18, + "type": "c84f7959-3738-422b-ba6e-5808b5e90101", + "pos": [ + 300, + 3830 + ], + "size": [ + 400, + 460 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "control image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "label": "canny low threshold", + "name": "low_threshold", + "type": "FLOAT", + "widget": { + "name": "low_threshold" + }, + "link": null + }, + { + "label": "canny high threshold", + "name": "high_threshold", + "type": "FLOAT", + "widget": { + "name": "high_threshold" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "name": "name", + "type": "COMBO", + "widget": { + "name": "name" + }, + "link": null + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "low_threshold" + ], + [ + "-1", + "high_threshold" + ], + [ + "7", + "seed" + ], + [ + "7", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ], + [ + "-1", + "name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.11.0" + }, + "widgets_values": [ + "", + 0.3, + 0.4, + null, + null, + "z_image_turbo_bf16.safetensors", + "qwen_3_4b.safetensors", + "ae.safetensors", + "Z-Image-Turbo-Fun-Controlnet-Union.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "c84f7959-3738-422b-ba6e-5808b5e90101", + "version": 1, + "state": { + "lastGroupId": 3, + "lastNodeId": 18, + "lastLinkId": 32, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Canny to Image (Z-Image-Turbo)", + "inputNode": { + "id": -10, + "bounding": [ + -280, + 4960, + 158.880859375, + 200 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1598.6038576146689, + 4936.043696127976, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "29ca271b-8f63-4e7b-a4b8-c9b4192ada0b", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 26 + ], + "label": "control image", + "pos": [ + -141.119140625, + 4980 + ] + }, + { + "id": "b6549f90-39ee-4b79-9e00-af4d9df969fe", + "name": "text", + "type": "STRING", + "linkIds": [ + 16 + ], + "label": "prompt", + "pos": [ + -141.119140625, + 5000 + ] + }, + { + "id": "6bd34d18-79f6-470f-94df-ca14c84ef3d8", + "name": "low_threshold", + "type": "FLOAT", + "linkIds": [ + 24 + ], + "label": "canny low threshold", + "pos": [ + -141.119140625, + 5020 + ] + }, + { + "id": "bbced993-057f-4d2d-909c-d791be73d1d2", + "name": "high_threshold", + "type": "FLOAT", + "linkIds": [ + 25 + ], + "label": "canny high threshold", + "pos": [ + -141.119140625, + 5040 + ] + }, + { + "id": "db7969bf-4b05-48a0-9598-87d3ac85b505", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 29 + ], + "pos": [ + -141.119140625, + 5060 + ] + }, + { + "id": "925b611c-5edf-406f-8dc5-7fec07d049a7", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 30 + ], + "pos": [ + -141.119140625, + 5080 + ] + }, + { + "id": "b4cf508b-4753-40d2-8c83-5a424237ee07", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 31 + ], + "pos": [ + -141.119140625, + 5100 + ] + }, + { + "id": "bd948f38-3a11-4091-99fc-bb2b3511bcd2", + "name": "name", + "type": "COMBO", + "linkIds": [ + 32 + ], + "pos": [ + -141.119140625, + 5120 + ] + } + ], + "outputs": [ + { + "id": "47f9a22d-6619-4917-9447-a7d5d08dceb5", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 18 + ], + "pos": [ + 1618.6038576146689, + 4956.043696127976 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 1, + "type": "CLIPLoader", + "pos": [ + 228.60376290329597, + 4700.188357350136 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 30 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 14 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_3_4b.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_3_4b.safetensors", + "lumina2", + "default" + ] + }, + { + "id": 2, + "type": "UNETLoader", + "pos": [ + 228.60376290329597, + 4550.1883046176445 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 29 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 9 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "z_image_turbo_bf16.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "z_image_turbo_bf16.safetensors", + "default" + ] + }, + { + "id": 3, + "type": "VAELoader", + "pos": [ + 228.60376290329597, + 4880.18831633181 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 31 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 2, + 11 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 4, + "type": "ModelPatchLoader", + "pos": [ + 228.60376290329597, + 5010.1884895078 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "name", + "name": "name", + "type": "COMBO", + "widget": { + "name": "name" + }, + "link": 32 + } + ], + "outputs": [ + { + "localized_name": "MODEL_PATCH", + "name": "MODEL_PATCH", + "type": "MODEL_PATCH", + "links": [ + 10 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "ModelPatchLoader", + "models": [ + { + "name": "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", + "url": "https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union/resolve/main/Z-Image-Turbo-Fun-Controlnet-Union.safetensors", + "directory": "model_patches" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "Z-Image-Turbo-Fun-Controlnet-Union.safetensors" + ] + }, + { + "id": 6, + "type": "ModelSamplingAuraFlow", + "pos": [ + 998.6039930366841, + 4490.18831829042 + ], + "size": [ + 290, + 58 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 3 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 4 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 7, + "type": "KSampler", + "pos": [ + 998.6039930366841, + 4600.188351166619 + ], + "size": [ + 300, + 460 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 4 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 5 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 6 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 7 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 1 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize", + 9, + 1, + "res_multistep", + "simple", + 1 + ] + }, + { + "id": 8, + "type": "ConditioningZeroOut", + "pos": [ + 748.2704434516113, + 5044.855005348689 + ], + "size": [ + 204.134765625, + 26.000000000000004 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 8 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 6 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "ConditioningZeroOut", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 9, + "type": "QwenImageDiffsynthControlnet", + "pos": [ + 608.2704174118008, + 5204.85499785943 + ], + "size": [ + 290, + 138 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 9 + }, + { + "localized_name": "model_patch", + "name": "model_patch", + "type": "MODEL_PATCH", + "link": 10 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 11 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 22 + }, + { + "localized_name": "mask", + "name": "mask", + "shape": 7, + "type": "MASK", + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 3 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.76", + "Node name for S&R": "QwenImageDiffsynthControlnet", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 12, + "type": "CLIPTextEncode", + "pos": [ + 548.2704310845766, + 4544.854974431101 + ], + "size": [ + 400, + 330 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 14 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 16 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 5, + 8 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 5, + "type": "VAEDecode", + "pos": [ + 1338.6038576146689, + 4500.188344983101 + ], + "size": [ + 200, + 46 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 1 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 2 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 18 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 15, + "type": "ImageScaleToTotalPixels", + "pos": [ + 220, + 5220 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 26 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "megapixels", + "name": "megapixels", + "type": "FLOAT", + "widget": { + "name": "megapixels" + }, + "link": null + }, + { + "localized_name": "resolution_steps", + "name": "resolution_steps", + "type": "INT", + "widget": { + "name": "resolution_steps" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 27 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.0", + "Node name for S&R": "ImageScaleToTotalPixels" + }, + "widgets_values": [ + "nearest-exact", + 1, + 1 + ] + }, + { + "id": 11, + "type": "GetImageSize", + "pos": [ + 540, + 5450 + ], + "size": [ + 140, + 66 + ], + "flags": { + "collapsed": false + }, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 23 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 12 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 13 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.76", + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 10, + "type": "EmptySD3LatentImage", + "pos": [ + 760, + 5430 + ], + "size": [ + 260, + 106 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 12 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 13 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 7 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "EmptySD3LatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 14, + "type": "Canny", + "pos": [ + 220, + 5380 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 27 + }, + { + "localized_name": "low_threshold", + "name": "low_threshold", + "type": "FLOAT", + "widget": { + "name": "low_threshold" + }, + "link": 24 + }, + { + "localized_name": "high_threshold", + "name": "high_threshold", + "type": "FLOAT", + "widget": { + "name": "high_threshold" + }, + "link": 25 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 22, + 23, + 28 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.0", + "Node name for S&R": "Canny" + }, + "widgets_values": [ + 0.3, + 0.4 + ] + }, + { + "id": 16, + "type": "PreviewImage", + "pos": [ + 220, + 5520 + ], + "size": [ + 260, + 270 + ], + "flags": {}, + "order": 14, + "mode": 4, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 28 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.0", + "Node name for S&R": "PreviewImage" + }, + "widgets_values": [] + } + ], + "groups": [ + { + "id": 1, + "title": "Prompt", + "bounding": [ + 530, + 4460, + 440, + 630 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Models", + "bounding": [ + 210, + 4460, + 300, + 640 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Apple ControlNet", + "bounding": [ + 530, + 5120, + 440, + 260 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 1, + "origin_id": 7, + "origin_slot": 0, + "target_id": 5, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 2, + "origin_id": 3, + "origin_slot": 0, + "target_id": 5, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 3, + "origin_id": 9, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 4, + "origin_id": 6, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 5, + "origin_id": 12, + "origin_slot": 0, + "target_id": 7, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 6, + "origin_id": 8, + "origin_slot": 0, + "target_id": 7, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 7, + "origin_id": 10, + "origin_slot": 0, + "target_id": 7, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 8, + "origin_id": 12, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 9, + "origin_id": 2, + "origin_slot": 0, + "target_id": 9, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 10, + "origin_id": 4, + "origin_slot": 0, + "target_id": 9, + "target_slot": 1, + "type": "MODEL_PATCH" + }, + { + "id": 11, + "origin_id": 3, + "origin_slot": 0, + "target_id": 9, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 12, + "origin_id": 11, + "origin_slot": 0, + "target_id": 10, + "target_slot": 0, + "type": "INT" + }, + { + "id": 13, + "origin_id": 11, + "origin_slot": 1, + "target_id": 10, + "target_slot": 1, + "type": "INT" + }, + { + "id": 14, + "origin_id": 1, + "origin_slot": 0, + "target_id": 12, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 16, + "origin_id": -10, + "origin_slot": 1, + "target_id": 12, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 18, + "origin_id": 5, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 22, + "origin_id": 14, + "origin_slot": 0, + "target_id": 9, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 23, + "origin_id": 14, + "origin_slot": 0, + "target_id": 11, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 24, + "origin_id": -10, + "origin_slot": 2, + "target_id": 14, + "target_slot": 1, + "type": "FLOAT" + }, + { + "id": 25, + "origin_id": -10, + "origin_slot": 3, + "target_id": 14, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 26, + "origin_id": -10, + "origin_slot": 0, + "target_id": 15, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 27, + "origin_id": 15, + "origin_slot": 0, + "target_id": 14, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 28, + "origin_id": 14, + "origin_slot": 0, + "target_id": 16, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 29, + "origin_id": -10, + "origin_slot": 4, + "target_id": 2, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 30, + "origin_id": -10, + "origin_slot": 5, + "target_id": 1, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 31, + "origin_id": -10, + "origin_slot": 6, + "target_id": 3, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 32, + "origin_id": -10, + "origin_slot": 7, + "target_id": 4, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "category": "Image generation and editing/Canny to image" + } + ] + }, + "config": {}, + "extra": { + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ds": { + "scale": 0.967267584583181, + "offset": [ + 444.759060017523, + -3564.372163194443 + ] + } + }, + "version": 0.4 +} diff --git a/blueprints/Canny to Video (LTX 2.0).json b/blueprints/Canny to Video (LTX 2.0).json index cd2c4e594..fae8321b9 100644 --- a/blueprints/Canny to Video (LTX 2.0).json +++ b/blueprints/Canny to Video (LTX 2.0).json @@ -1 +1,3619 @@ -{"id": "02f6166f-32f8-4673-b861-76be1464cba5", "revision": 0, "last_node_id": 155, "last_link_id": 391, "nodes": [{"id": 1, "type": "884e1862-7567-4e72-bd2a-fd4fdfd06320", "pos": [1519.643633934233, 3717.5350173634242], "size": [400, 500], "flags": {"collapsed": false}, "order": 0, "mode": 0, "inputs": [{"name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"label": "canny_images", "name": "image", "type": "IMAGE", "link": null}, {"label": "image_strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}, {"label": "disable_first_frame", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": null}, {"label": "first_frame", "name": "image_1", "type": "IMAGE", "link": null}, {"name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": null}, {"name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"name": "text_encoder", "type": "COMBO", "widget": {"name": "text_encoder"}, "link": null}, {"label": "distlled_lora", "name": "lora_name_1", "type": "COMBO", "widget": {"name": "lora_name_1"}, "link": null}, {"label": "upscale_model", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "strength"], ["143", "noise_seed"], ["126", "control_after_generate"], ["-1", "bypass"], ["-1", "ckpt_name"], ["-1", "lora_name"], ["-1", "text_encoder"], ["-1", "lora_name_1"], ["-1", "model_name"]], "cnr_id": "comfy-core", "ver": "0.7.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", 1, null, null, false, "ltx-2-19b-dev-fp8.safetensors", "ltx-2-19b-ic-lora-canny-control.safetensors", "gemma_3_12B_it_fp4_mixed.safetensors", "ltx-2-19b-distilled-lora-384.safetensors", "ltx-2-spatial-upscaler-x2-1.0.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "884e1862-7567-4e72-bd2a-fd4fdfd06320", "version": 1, "state": {"lastGroupId": 11, "lastNodeId": 155, "lastLinkId": 391, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Canny to Video (LTX 2.0)", "inputNode": {"id": -10, "bounding": [-2180, 4070, 146.8515625, 240]}, "outputNode": {"id": -20, "bounding": [1750, 4090, 120, 60]}, "inputs": [{"id": "0f1d2f96-933a-4a7b-8f1a-7b49fc4ade09", "name": "text", "type": "STRING", "linkIds": [345], "pos": [-2053.1484375, 4090]}, {"id": "35a07084-3ecf-482a-a330-b40278770ca3", "name": "image", "type": "IMAGE", "linkIds": [348, 349], "label": "canny_images", "pos": [-2053.1484375, 4110]}, {"id": "59430efe-1090-4e36-8afe-b21ce7f4268b", "name": "strength", "type": "FLOAT", "linkIds": [370, 371], "label": "image_strength", "pos": [-2053.1484375, 4130]}, {"id": "6145a9b9-68ed-4956-89f7-7a5ebdd5c99e", "name": "bypass", "type": "BOOLEAN", "linkIds": [363, 368], "label": "disable_first_frame", "pos": [-2053.1484375, 4150]}, {"id": "bea20802-d654-4287-a8ef-0f834314bcf9", "name": "image_1", "type": "IMAGE", "linkIds": [364, 379], "label": "first_frame", "pos": [-2053.1484375, 4170]}, {"id": "4e2f26b5-9ad6-49a6-8e90-0ed24fc6a423", "name": "ckpt_name", "type": "COMBO", "linkIds": [385, 386, 387], "pos": [-2053.1484375, 4190]}, {"id": "81fdfcf3-92ca-4f8d-b13d-d22758231530", "name": "lora_name", "type": "COMBO", "linkIds": [388], "pos": [-2053.1484375, 4210]}, {"id": "3fa7991e-4419-44a7-9377-1b6125fef355", "name": "text_encoder", "type": "COMBO", "linkIds": [389], "pos": [-2053.1484375, 4230]}, {"id": "b9277d33-2f18-47bb-95ab-666799e8730f", "name": "lora_name_1", "type": "COMBO", "linkIds": [390], "label": "distlled_lora", "pos": [-2053.1484375, 4250]}, {"id": "80b2e9cf-e1a7-462f-ae0d-ffb4ba668a65", "name": "model_name", "type": "COMBO", "linkIds": [391], "label": "upscale_model", "pos": [-2053.1484375, 4270]}], "outputs": [{"id": "4e837941-de2d-4df8-8f94-686e24036897", "name": "VIDEO", "type": "VIDEO", "linkIds": [304], "localized_name": "VIDEO", "pos": [1770, 4110]}], "widgets": [], "nodes": [{"id": 93, "type": "CFGGuider", "pos": [-698, 3670], "size": [270, 106.66666666666667], "flags": {}, "order": 16, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 326}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 309}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 311}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "links": [261]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "CFGGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 94, "type": "KSamplerSelect", "pos": [-698, 3840], "size": [270, 68.88020833333334], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "links": [262]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["euler"]}, {"id": 99, "type": "ManualSigmas", "pos": [410, 3850], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "sigmas", "name": "sigmas", "type": "STRING", "widget": {"name": "sigmas"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "links": [278]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "ManualSigmas", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["0.909375, 0.725, 0.421875, 0.0"]}, {"id": 101, "type": "LTXVConcatAVLatent", "pos": [410, 4100], "size": [270, 110], "flags": {}, "order": 18, "mode": 0, "inputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "link": 365}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "link": 266}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [279]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVConcatAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 108, "type": "CFGGuider", "pos": [410, 3700], "size": [270, 98], "flags": {}, "order": 22, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 280}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 281}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 282}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "links": [276]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.71", "Node name for S&R": "CFGGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 111, "type": "LTXVEmptyLatentAudio", "pos": [-1100, 4810], "size": [270, 120], "flags": {}, "order": 24, "mode": 0, "inputs": [{"localized_name": "audio_vae", "name": "audio_vae", "type": "VAE", "link": 383}, {"localized_name": "frames_number", "name": "frames_number", "type": "INT", "widget": {"name": "frames_number"}, "link": 329}, {"localized_name": "frame_rate", "name": "frame_rate", "type": "INT", "widget": {"name": "frame_rate"}, "link": 354}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "Latent", "name": "Latent", "type": "LATENT", "links": [300]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.68", "Node name for S&R": "LTXVEmptyLatentAudio", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [97, 25, 1]}, {"id": 123, "type": "SamplerCustomAdvanced", "pos": [-388, 3520], "size": [213.125, 120], "flags": {}, "order": 31, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 260}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 261}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 262}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 263}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 323}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "links": [272]}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.60", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 114, "type": "LTXVConditioning", "pos": [-1134, 4140], "size": [270, 86.66666666666667], "flags": {}, "order": 27, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 292}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 293}, {"localized_name": "frame_rate", "name": "frame_rate", "type": "FLOAT", "widget": {"name": "frame_rate"}, "link": 355}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [313]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [314]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "LTXVConditioning", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [25]}, {"id": 119, "type": "CLIPTextEncode", "pos": [-1164, 3880], "size": [400, 200], "flags": {}, "order": 14, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 294}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [293]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["blurry, low quality, still frame, frames, watermark, overlay, titles, has blurbox, has subtitles"], "color": "#323", "bgcolor": "#535"}, {"id": 116, "type": "LTXVConcatAVLatent", "pos": [-520, 4700], "size": [187.5, 60], "flags": {}, "order": 29, "mode": 0, "inputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "link": 324}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "link": 300}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [322, 323]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVConcatAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 122, "type": "LTXVSeparateAVLatent", "pos": [-394, 3800], "size": [240, 46], "flags": {}, "order": 30, "mode": 0, "inputs": [{"localized_name": "av_latent", "name": "av_latent", "type": "LATENT", "link": 272}], "outputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "links": [270]}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "links": [266]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVSeparateAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 124, "type": "CLIPTextEncode", "pos": [-1174.999849798713, 3514.000055195033], "size": [410, 320], "flags": {}, "order": 32, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 295}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 345}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [292]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 98, "type": "KSamplerSelect", "pos": [410, 3980], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "links": [277]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["gradient_estimation"]}, {"id": 95, "type": "LTXVScheduler", "pos": [-700, 3980], "size": [270, 170], "flags": {}, "order": 17, "mode": 0, "inputs": [{"localized_name": "latent", "name": "latent", "shape": 7, "type": "LATENT", "link": 322}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "max_shift", "name": "max_shift", "type": "FLOAT", "widget": {"name": "max_shift"}, "link": null}, {"localized_name": "base_shift", "name": "base_shift", "type": "FLOAT", "widget": {"name": "base_shift"}, "link": null}, {"localized_name": "stretch", "name": "stretch", "type": "BOOLEAN", "widget": {"name": "stretch"}, "link": null}, {"localized_name": "terminal", "name": "terminal", "type": "FLOAT", "widget": {"name": "terminal"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "links": [263]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "LTXVScheduler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [20, 2.05, 0.95, true, 0.1]}, {"id": 126, "type": "RandomNoise", "pos": [-698, 3520], "size": [270, 82], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "links": [260]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "RandomNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize"]}, {"id": 107, "type": "SamplerCustomAdvanced", "pos": [710, 3570], "size": [212.38333740234376, 106], "flags": {}, "order": 21, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 347}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 276}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 277}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 278}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 279}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "links": []}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "links": [336]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 143, "type": "RandomNoise", "pos": [410, 3570], "size": [270, 82], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "links": [347]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "RandomNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "fixed"]}, {"id": 139, "type": "LTXVAudioVAEDecode", "pos": [1130, 3840], "size": [240, 46], "flags": {}, "order": 35, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 338}, {"label": "Audio VAE", "localized_name": "audio_vae", "name": "audio_vae", "type": "VAE", "link": 384}], "outputs": [{"localized_name": "Audio", "name": "Audio", "type": "AUDIO", "links": [339]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVAudioVAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 106, "type": "CreateVideo", "pos": [1420, 3760], "size": [270, 78], "flags": {}, "order": 20, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 352}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 339}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 356}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [304]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "CreateVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [25]}, {"id": 134, "type": "LoraLoaderModelOnly", "pos": [-1650, 3760], "size": [420, 82], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 325}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 388}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [326, 327]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "ltx-2-19b-ic-lora-canny-control.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Canny-Control/resolve/main/ltx-2-19b-ic-lora-canny-control.safetensors", "directory": "loras"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-ic-lora-canny-control.safetensors", 1], "color": "#322", "bgcolor": "#533"}, {"id": 138, "type": "LTXVSeparateAVLatent", "pos": [730, 3730], "size": [193.2916015625, 46], "flags": {}, "order": 34, "mode": 0, "inputs": [{"localized_name": "av_latent", "name": "av_latent", "type": "LATENT", "link": 336}], "outputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "links": [337, 351]}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "links": [338]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVSeparateAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 144, "type": "VAEDecodeTiled", "pos": [1120, 3640], "size": [270, 150], "flags": {}, "order": 36, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 351}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 353}, {"localized_name": "tile_size", "name": "tile_size", "type": "INT", "widget": {"name": "tile_size"}, "link": null}, {"localized_name": "overlap", "name": "overlap", "type": "INT", "widget": {"name": "overlap"}, "link": null}, {"localized_name": "temporal_size", "name": "temporal_size", "type": "INT", "widget": {"name": "temporal_size"}, "link": null}, {"localized_name": "temporal_overlap", "name": "temporal_overlap", "type": "INT", "widget": {"name": "temporal_overlap"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [352]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "VAEDecodeTiled", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [512, 64, 4096, 8]}, {"id": 113, "type": "VAEDecode", "pos": [1130, 3530], "size": [240, 50], "flags": {}, "order": 26, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 337}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 291}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 110, "type": "GetImageSize", "pos": [-1630, 4450], "size": [260, 80], "flags": {}, "order": 23, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 349}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [296]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [297]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": [329, 330]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "GetImageSize", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 145, "type": "PrimitiveInt", "pos": [-1630, 4620], "size": [270, 82], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "INT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "INT", "name": "INT", "type": "INT", "links": [354]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "PrimitiveInt", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [24, "fixed"]}, {"id": 148, "type": "PrimitiveFloat", "pos": [-1630, 4750], "size": [270, 58], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [355, 356]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "PrimitiveFloat", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [24]}, {"id": 115, "type": "EmptyLTXVLatentVideo", "pos": [-1100, 4610], "size": [270, 146.66666666666669], "flags": {}, "order": 28, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 296}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 297}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": 330}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [360]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.60", "Node name for S&R": "EmptyLTXVLatentVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [768, 512, 97, 1]}, {"id": 149, "type": "LTXVImgToVideoInplace", "pos": [-1090, 4400], "size": [270, 152], "flags": {}, "order": 37, "mode": 0, "inputs": [{"localized_name": "vae", "name": "vae", "type": "VAE", "link": 359}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 364}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 360}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": 370}, {"localized_name": "bypass", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": 363}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [357]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVImgToVideoInplace", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1, false]}, {"id": 118, "type": "Reroute", "pos": [-230, 4210], "size": [75, 26], "flags": {}, "order": 13, "mode": 0, "inputs": [{"name": "", "type": "*", "link": 303}], "outputs": [{"name": "", "type": "VAE", "links": [289, 291, 367]}], "properties": {"showOutputText": false, "horizontal": false}}, {"id": 151, "type": "LTXVImgToVideoInplace", "pos": [-20, 4070], "size": [270, 182], "flags": {}, "order": 38, "mode": 0, "inputs": [{"localized_name": "vae", "name": "vae", "type": "VAE", "link": 367}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 379}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 366}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": 371}, {"localized_name": "bypass", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": 368}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [365]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVImgToVideoInplace", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1, false]}, {"id": 104, "type": "LTXVCropGuides", "pos": [-10, 3840], "size": [240, 66], "flags": {}, "order": 19, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 310}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 312}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 270}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [281]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [282]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "slot_index": 2, "links": [287]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.68", "Node name for S&R": "LTXVCropGuides", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 112, "type": "LTXVLatentUpsampler", "pos": [-10, 3960], "size": [260, 66], "flags": {}, "order": 25, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 287}, {"localized_name": "upscale_model", "name": "upscale_model", "type": "LATENT_UPSCALE_MODEL", "link": 288}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 289}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [366]}], "title": "spatial", "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVLatentUpsampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 132, "type": "LTXVAddGuide", "pos": [-600, 4420], "size": [270, 209.16666666666669], "flags": {}, "order": 33, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 313}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 314}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 328}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 357}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 348}, {"localized_name": "frame_idx", "name": "frame_idx", "type": "INT", "widget": {"name": "frame_idx"}, "link": null}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [309, 310]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [311, 312]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [324]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "LTXVAddGuide", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, 1]}, {"id": 103, "type": "CheckpointLoaderSimple", "pos": [-1650, 3590], "size": [420, 98], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 385}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [325]}, {"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": []}, {"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [303, 328, 353, 359]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CheckpointLoaderSimple", "models": [{"name": "ltx-2-19b-dev-fp8.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", "directory": "checkpoints"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-dev-fp8.safetensors"]}, {"id": 97, "type": "LTXAVTextEncoderLoader", "pos": [-1650, 4040], "size": [420, 106], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "text_encoder", "name": "text_encoder", "type": "COMBO", "widget": {"name": "text_encoder"}, "link": 389}, {"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 387}, {"localized_name": "device", "name": "device", "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [294, 295]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXAVTextEncoderLoader", "models": [{"name": "ltx-2-19b-dev-fp8.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", "directory": "checkpoints"}, {"name": "gemma_3_12B_it_fp4_mixed.safetensors", "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["gemma_3_12B_it_fp4_mixed.safetensors", "ltx-2-19b-dev-fp8.safetensors", "default"]}, {"id": 105, "type": "LoraLoaderModelOnly", "pos": [-70, 3570], "size": [390, 82], "flags": {}, "order": 15, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 327}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 390}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [280]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "ltx-2-19b-distilled-lora-384.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-lora-384.safetensors", "directory": "loras"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-distilled-lora-384.safetensors", 1]}, {"id": 100, "type": "LatentUpscaleModelLoader", "pos": [-70, 3700], "size": [390, 60], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": 391}], "outputs": [{"localized_name": "LATENT_UPSCALE_MODEL", "name": "LATENT_UPSCALE_MODEL", "type": "LATENT_UPSCALE_MODEL", "links": [288]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LatentUpscaleModelLoader", "models": [{"name": "ltx-2-spatial-upscaler-x2-1.0.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-spatial-upscaler-x2-1.0.safetensors", "directory": "latent_upscale_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-spatial-upscaler-x2-1.0.safetensors"]}, {"id": 154, "type": "MarkdownNote", "pos": [-1660, 4870], "size": [350, 170], "flags": {"collapsed": false}, "order": 10, "mode": 0, "inputs": [], "outputs": [], "title": "Frame Rate Note", "properties": {}, "widgets_values": ["Please make sure the frame rate value is the same in both boxes"], "color": "#222", "bgcolor": "#000"}, {"id": 155, "type": "LTXVAudioVAELoader", "pos": [-1640, 3910], "size": [400, 58], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 386}], "outputs": [{"localized_name": "Audio VAE", "name": "Audio VAE", "type": "VAE", "links": [383, 384]}], "properties": {"cnr_id": "comfy-core", "ver": "0.14.1", "Node name for S&R": "LTXVAudioVAELoader"}, "widgets_values": ["ltx-2-19b-dev-fp8.safetensors"]}], "groups": [{"id": 1, "title": "Model", "bounding": [-1660, 3440, 440, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Basic Sampling", "bounding": [-700, 3440, 570, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Prompt", "bounding": [-1180, 3440, 440, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 5, "title": "Latent", "bounding": [-1180, 4290, 1050, 680], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 9, "title": "Upscale Sampling(2x)", "bounding": [-100, 3440, 1090, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 6, "title": "Sampler", "bounding": [350, 3480, 620, 750], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 7, "title": "Model", "bounding": [-90, 3480, 430, 310], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 11, "title": "Frame rate", "bounding": [-1640, 4550, 290, 271.6], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 326, "origin_id": 134, "origin_slot": 0, "target_id": 93, "target_slot": 0, "type": "MODEL"}, {"id": 309, "origin_id": 132, "origin_slot": 0, "target_id": 93, "target_slot": 1, "type": "CONDITIONING"}, {"id": 311, "origin_id": 132, "origin_slot": 1, "target_id": 93, "target_slot": 2, "type": "CONDITIONING"}, {"id": 266, "origin_id": 122, "origin_slot": 1, "target_id": 101, "target_slot": 1, "type": "LATENT"}, {"id": 280, "origin_id": 105, "origin_slot": 0, "target_id": 108, "target_slot": 0, "type": "MODEL"}, {"id": 281, "origin_id": 104, "origin_slot": 0, "target_id": 108, "target_slot": 1, "type": "CONDITIONING"}, {"id": 282, "origin_id": 104, "origin_slot": 1, "target_id": 108, "target_slot": 2, "type": "CONDITIONING"}, {"id": 329, "origin_id": 110, "origin_slot": 2, "target_id": 111, "target_slot": 1, "type": "INT"}, {"id": 260, "origin_id": 126, "origin_slot": 0, "target_id": 123, "target_slot": 0, "type": "NOISE"}, {"id": 261, "origin_id": 93, "origin_slot": 0, "target_id": 123, "target_slot": 1, "type": "GUIDER"}, {"id": 262, "origin_id": 94, "origin_slot": 0, "target_id": 123, "target_slot": 2, "type": "SAMPLER"}, {"id": 263, "origin_id": 95, "origin_slot": 0, "target_id": 123, "target_slot": 3, "type": "SIGMAS"}, {"id": 323, "origin_id": 116, "origin_slot": 0, "target_id": 123, "target_slot": 4, "type": "LATENT"}, {"id": 296, "origin_id": 110, "origin_slot": 0, "target_id": 115, "target_slot": 0, "type": "INT"}, {"id": 297, "origin_id": 110, "origin_slot": 1, "target_id": 115, "target_slot": 1, "type": "INT"}, {"id": 330, "origin_id": 110, "origin_slot": 2, "target_id": 115, "target_slot": 2, "type": "INT"}, {"id": 325, "origin_id": 103, "origin_slot": 0, "target_id": 134, "target_slot": 0, "type": "MODEL"}, {"id": 292, "origin_id": 124, "origin_slot": 0, "target_id": 114, "target_slot": 0, "type": "CONDITIONING"}, {"id": 293, "origin_id": 119, "origin_slot": 0, "target_id": 114, "target_slot": 1, "type": "CONDITIONING"}, {"id": 294, "origin_id": 97, "origin_slot": 0, "target_id": 119, "target_slot": 0, "type": "CLIP"}, {"id": 324, "origin_id": 132, "origin_slot": 2, "target_id": 116, "target_slot": 0, "type": "LATENT"}, {"id": 300, "origin_id": 111, "origin_slot": 0, "target_id": 116, "target_slot": 1, "type": "LATENT"}, {"id": 313, "origin_id": 114, "origin_slot": 0, "target_id": 132, "target_slot": 0, "type": "CONDITIONING"}, {"id": 314, "origin_id": 114, "origin_slot": 1, "target_id": 132, "target_slot": 1, "type": "CONDITIONING"}, {"id": 328, "origin_id": 103, "origin_slot": 2, "target_id": 132, "target_slot": 2, "type": "VAE"}, {"id": 272, "origin_id": 123, "origin_slot": 0, "target_id": 122, "target_slot": 0, "type": "LATENT"}, {"id": 336, "origin_id": 107, "origin_slot": 1, "target_id": 138, "target_slot": 0, "type": "LATENT"}, {"id": 339, "origin_id": 139, "origin_slot": 0, "target_id": 106, "target_slot": 1, "type": "AUDIO"}, {"id": 295, "origin_id": 97, "origin_slot": 0, "target_id": 124, "target_slot": 0, "type": "CLIP"}, {"id": 303, "origin_id": 103, "origin_slot": 2, "target_id": 118, "target_slot": 0, "type": "VAE"}, {"id": 338, "origin_id": 138, "origin_slot": 1, "target_id": 139, "target_slot": 0, "type": "LATENT"}, {"id": 337, "origin_id": 138, "origin_slot": 0, "target_id": 113, "target_slot": 0, "type": "LATENT"}, {"id": 291, "origin_id": 118, "origin_slot": 0, "target_id": 113, "target_slot": 1, "type": "VAE"}, {"id": 276, "origin_id": 108, "origin_slot": 0, "target_id": 107, "target_slot": 1, "type": "GUIDER"}, {"id": 277, "origin_id": 98, "origin_slot": 0, "target_id": 107, "target_slot": 2, "type": "SAMPLER"}, {"id": 278, "origin_id": 99, "origin_slot": 0, "target_id": 107, "target_slot": 3, "type": "SIGMAS"}, {"id": 279, "origin_id": 101, "origin_slot": 0, "target_id": 107, "target_slot": 4, "type": "LATENT"}, {"id": 327, "origin_id": 134, "origin_slot": 0, "target_id": 105, "target_slot": 0, "type": "MODEL"}, {"id": 310, "origin_id": 132, "origin_slot": 0, "target_id": 104, "target_slot": 0, "type": "CONDITIONING"}, {"id": 312, "origin_id": 132, "origin_slot": 1, "target_id": 104, "target_slot": 1, "type": "CONDITIONING"}, {"id": 270, "origin_id": 122, "origin_slot": 0, "target_id": 104, "target_slot": 2, "type": "LATENT"}, {"id": 287, "origin_id": 104, "origin_slot": 2, "target_id": 112, "target_slot": 0, "type": "LATENT"}, {"id": 288, "origin_id": 100, "origin_slot": 0, "target_id": 112, "target_slot": 1, "type": "LATENT_UPSCALE_MODEL"}, {"id": 289, "origin_id": 118, "origin_slot": 0, "target_id": 112, "target_slot": 2, "type": "VAE"}, {"id": 322, "origin_id": 116, "origin_slot": 0, "target_id": 95, "target_slot": 0, "type": "LATENT"}, {"id": 304, "origin_id": 106, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 345, "origin_id": -10, "origin_slot": 0, "target_id": 124, "target_slot": 1, "type": "STRING"}, {"id": 347, "origin_id": 143, "origin_slot": 0, "target_id": 107, "target_slot": 0, "type": "NOISE"}, {"id": 348, "origin_id": -10, "origin_slot": 1, "target_id": 132, "target_slot": 4, "type": "IMAGE"}, {"id": 349, "origin_id": -10, "origin_slot": 1, "target_id": 110, "target_slot": 0, "type": "IMAGE"}, {"id": 351, "origin_id": 138, "origin_slot": 0, "target_id": 144, "target_slot": 0, "type": "LATENT"}, {"id": 352, "origin_id": 144, "origin_slot": 0, "target_id": 106, "target_slot": 0, "type": "IMAGE"}, {"id": 353, "origin_id": 103, "origin_slot": 2, "target_id": 144, "target_slot": 1, "type": "VAE"}, {"id": 354, "origin_id": 145, "origin_slot": 0, "target_id": 111, "target_slot": 2, "type": "INT"}, {"id": 355, "origin_id": 148, "origin_slot": 0, "target_id": 114, "target_slot": 2, "type": "FLOAT"}, {"id": 356, "origin_id": 148, "origin_slot": 0, "target_id": 106, "target_slot": 2, "type": "FLOAT"}, {"id": 357, "origin_id": 149, "origin_slot": 0, "target_id": 132, "target_slot": 3, "type": "LATENT"}, {"id": 359, "origin_id": 103, "origin_slot": 2, "target_id": 149, "target_slot": 0, "type": "VAE"}, {"id": 360, "origin_id": 115, "origin_slot": 0, "target_id": 149, "target_slot": 2, "type": "LATENT"}, {"id": 363, "origin_id": -10, "origin_slot": 3, "target_id": 149, "target_slot": 4, "type": "BOOLEAN"}, {"id": 364, "origin_id": -10, "origin_slot": 4, "target_id": 149, "target_slot": 1, "type": "IMAGE"}, {"id": 365, "origin_id": 151, "origin_slot": 0, "target_id": 101, "target_slot": 0, "type": "LATENT"}, {"id": 366, "origin_id": 112, "origin_slot": 0, "target_id": 151, "target_slot": 2, "type": "LATENT"}, {"id": 367, "origin_id": 118, "origin_slot": 0, "target_id": 151, "target_slot": 0, "type": "VAE"}, {"id": 368, "origin_id": -10, "origin_slot": 3, "target_id": 151, "target_slot": 4, "type": "BOOLEAN"}, {"id": 370, "origin_id": -10, "origin_slot": 2, "target_id": 149, "target_slot": 3, "type": "FLOAT"}, {"id": 371, "origin_id": -10, "origin_slot": 2, "target_id": 151, "target_slot": 3, "type": "FLOAT"}, {"id": 379, "origin_id": -10, "origin_slot": 4, "target_id": 151, "target_slot": 1, "type": "IMAGE"}, {"id": 383, "origin_id": 155, "origin_slot": 0, "target_id": 111, "target_slot": 0, "type": "VAE"}, {"id": 384, "origin_id": 155, "origin_slot": 0, "target_id": 139, "target_slot": 1, "type": "VAE"}, {"id": 385, "origin_id": -10, "origin_slot": 5, "target_id": 103, "target_slot": 0, "type": "COMBO"}, {"id": 386, "origin_id": -10, "origin_slot": 5, "target_id": 155, "target_slot": 0, "type": "COMBO"}, {"id": 387, "origin_id": -10, "origin_slot": 5, "target_id": 97, "target_slot": 1, "type": "COMBO"}, {"id": 388, "origin_id": -10, "origin_slot": 6, "target_id": 134, "target_slot": 1, "type": "COMBO"}, {"id": 389, "origin_id": -10, "origin_slot": 7, "target_id": 97, "target_slot": 0, "type": "COMBO"}, {"id": 390, "origin_id": -10, "origin_slot": 8, "target_id": 105, "target_slot": 1, "type": "COMBO"}, {"id": 391, "origin_id": -10, "origin_slot": 9, "target_id": 100, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Canny to video"}]}, "config": {}, "extra": {"workflowRendererVersion": "LG", "ds": {"scale": 0.7537190265006444, "offset": [-330.27244430536007, -3324.725077010053]}}, "version": 0.4} +{ + "id": "02f6166f-32f8-4673-b861-76be1464cba5", + "revision": 0, + "last_node_id": 155, + "last_link_id": 391, + "nodes": [ + { + "id": 1, + "type": "884e1862-7567-4e72-bd2a-fd4fdfd06320", + "pos": [ + 1519.643633934233, + 3717.5350173634242 + ], + "size": [ + 400, + 500 + ], + "flags": { + "collapsed": false + }, + "order": 0, + "mode": 0, + "inputs": [ + { + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "label": "canny_images", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "label": "image_strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "label": "disable_first_frame", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": null + }, + { + "label": "first_frame", + "name": "image_1", + "type": "IMAGE", + "link": null + }, + { + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": null + }, + { + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": null + }, + { + "label": "distlled_lora", + "name": "lora_name_1", + "type": "COMBO", + "widget": { + "name": "lora_name_1" + }, + "link": null + }, + { + "label": "upscale_model", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "strength" + ], + [ + "143", + "noise_seed" + ], + [ + "126", + "control_after_generate" + ], + [ + "-1", + "bypass" + ], + [ + "-1", + "ckpt_name" + ], + [ + "-1", + "lora_name" + ], + [ + "-1", + "text_encoder" + ], + [ + "-1", + "lora_name_1" + ], + [ + "-1", + "model_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.7.0", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "", + 1, + null, + null, + false, + "ltx-2-19b-dev-fp8.safetensors", + "ltx-2-19b-ic-lora-canny-control.safetensors", + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2-19b-distilled-lora-384.safetensors", + "ltx-2-spatial-upscaler-x2-1.0.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "884e1862-7567-4e72-bd2a-fd4fdfd06320", + "version": 1, + "state": { + "lastGroupId": 11, + "lastNodeId": 155, + "lastLinkId": 391, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Canny to Video (LTX 2.0)", + "inputNode": { + "id": -10, + "bounding": [ + -2180, + 4070, + 146.8515625, + 240 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1750, + 4090, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "0f1d2f96-933a-4a7b-8f1a-7b49fc4ade09", + "name": "text", + "type": "STRING", + "linkIds": [ + 345 + ], + "pos": [ + -2053.1484375, + 4090 + ] + }, + { + "id": "35a07084-3ecf-482a-a330-b40278770ca3", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 348, + 349 + ], + "label": "canny_images", + "pos": [ + -2053.1484375, + 4110 + ] + }, + { + "id": "59430efe-1090-4e36-8afe-b21ce7f4268b", + "name": "strength", + "type": "FLOAT", + "linkIds": [ + 370, + 371 + ], + "label": "image_strength", + "pos": [ + -2053.1484375, + 4130 + ] + }, + { + "id": "6145a9b9-68ed-4956-89f7-7a5ebdd5c99e", + "name": "bypass", + "type": "BOOLEAN", + "linkIds": [ + 363, + 368 + ], + "label": "disable_first_frame", + "pos": [ + -2053.1484375, + 4150 + ] + }, + { + "id": "bea20802-d654-4287-a8ef-0f834314bcf9", + "name": "image_1", + "type": "IMAGE", + "linkIds": [ + 364, + 379 + ], + "label": "first_frame", + "pos": [ + -2053.1484375, + 4170 + ] + }, + { + "id": "4e2f26b5-9ad6-49a6-8e90-0ed24fc6a423", + "name": "ckpt_name", + "type": "COMBO", + "linkIds": [ + 385, + 386, + 387 + ], + "pos": [ + -2053.1484375, + 4190 + ] + }, + { + "id": "81fdfcf3-92ca-4f8d-b13d-d22758231530", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 388 + ], + "pos": [ + -2053.1484375, + 4210 + ] + }, + { + "id": "3fa7991e-4419-44a7-9377-1b6125fef355", + "name": "text_encoder", + "type": "COMBO", + "linkIds": [ + 389 + ], + "pos": [ + -2053.1484375, + 4230 + ] + }, + { + "id": "b9277d33-2f18-47bb-95ab-666799e8730f", + "name": "lora_name_1", + "type": "COMBO", + "linkIds": [ + 390 + ], + "label": "distlled_lora", + "pos": [ + -2053.1484375, + 4250 + ] + }, + { + "id": "80b2e9cf-e1a7-462f-ae0d-ffb4ba668a65", + "name": "model_name", + "type": "COMBO", + "linkIds": [ + 391 + ], + "label": "upscale_model", + "pos": [ + -2053.1484375, + 4270 + ] + } + ], + "outputs": [ + { + "id": "4e837941-de2d-4df8-8f94-686e24036897", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 304 + ], + "localized_name": "VIDEO", + "pos": [ + 1770, + 4110 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 93, + "type": "CFGGuider", + "pos": [ + -698, + 3670 + ], + "size": [ + 270, + 106.66666666666667 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 326 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 309 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 311 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 261 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 94, + "type": "KSamplerSelect", + "pos": [ + -698, + 3840 + ], + "size": [ + 270, + 68.88020833333334 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 262 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 99, + "type": "ManualSigmas", + "pos": [ + 410, + 3850 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 278 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "0.909375, 0.725, 0.421875, 0.0" + ] + }, + { + "id": 101, + "type": "LTXVConcatAVLatent", + "pos": [ + 410, + 4100 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 365 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 266 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 279 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 108, + "type": "CFGGuider", + "pos": [ + 410, + 3700 + ], + "size": [ + 270, + 98 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 280 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 281 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 282 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 276 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.71", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 111, + "type": "LTXVEmptyLatentAudio", + "pos": [ + -1100, + 4810 + ], + "size": [ + 270, + 120 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 383 + }, + { + "localized_name": "frames_number", + "name": "frames_number", + "type": "INT", + "widget": { + "name": "frames_number" + }, + "link": 329 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "INT", + "widget": { + "name": "frame_rate" + }, + "link": 354 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "Latent", + "name": "Latent", + "type": "LATENT", + "links": [ + 300 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVEmptyLatentAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 97, + 25, + 1 + ] + }, + { + "id": 123, + "type": "SamplerCustomAdvanced", + "pos": [ + -388, + 3520 + ], + "size": [ + 213.125, + 120 + ], + "flags": {}, + "order": 31, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 260 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 261 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 262 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 263 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 323 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 272 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 114, + "type": "LTXVConditioning", + "pos": [ + -1134, + 4140 + ], + "size": [ + 270, + 86.66666666666667 + ], + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 292 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 293 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "FLOAT", + "widget": { + "name": "frame_rate" + }, + "link": 355 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 313 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 314 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "LTXVConditioning", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 119, + "type": "CLIPTextEncode", + "pos": [ + -1164, + 3880 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 294 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 293 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "blurry, low quality, still frame, frames, watermark, overlay, titles, has blurbox, has subtitles" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 116, + "type": "LTXVConcatAVLatent", + "pos": [ + -520, + 4700 + ], + "size": [ + 187.5, + 60 + ], + "flags": {}, + "order": 29, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 324 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 300 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 322, + 323 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 122, + "type": "LTXVSeparateAVLatent", + "pos": [ + -394, + 3800 + ], + "size": [ + 240, + 46 + ], + "flags": {}, + "order": 30, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 272 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 270 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 266 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 124, + "type": "CLIPTextEncode", + "pos": [ + -1174.999849798713, + 3514.000055195033 + ], + "size": [ + 410, + 320 + ], + "flags": {}, + "order": 32, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 295 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 345 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 292 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 98, + "type": "KSamplerSelect", + "pos": [ + 410, + 3980 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 277 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "gradient_estimation" + ] + }, + { + "id": 95, + "type": "LTXVScheduler", + "pos": [ + -700, + 3980 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "latent", + "name": "latent", + "shape": 7, + "type": "LATENT", + "link": 322 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "max_shift", + "name": "max_shift", + "type": "FLOAT", + "widget": { + "name": "max_shift" + }, + "link": null + }, + { + "localized_name": "base_shift", + "name": "base_shift", + "type": "FLOAT", + "widget": { + "name": "base_shift" + }, + "link": null + }, + { + "localized_name": "stretch", + "name": "stretch", + "type": "BOOLEAN", + "widget": { + "name": "stretch" + }, + "link": null + }, + { + "localized_name": "terminal", + "name": "terminal", + "type": "FLOAT", + "widget": { + "name": "terminal" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 263 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "LTXVScheduler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 20, + 2.05, + 0.95, + true, + 0.1 + ] + }, + { + "id": 126, + "type": "RandomNoise", + "pos": [ + -698, + 3520 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 260 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize" + ] + }, + { + "id": 107, + "type": "SamplerCustomAdvanced", + "pos": [ + 710, + 3570 + ], + "size": [ + 212.38333740234376, + 106 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 347 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 276 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 277 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 278 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 279 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [ + 336 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 143, + "type": "RandomNoise", + "pos": [ + 410, + 3570 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 347 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "fixed" + ] + }, + { + "id": 139, + "type": "LTXVAudioVAEDecode", + "pos": [ + 1130, + 3840 + ], + "size": [ + 240, + 46 + ], + "flags": {}, + "order": 35, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 338 + }, + { + "label": "Audio VAE", + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 384 + } + ], + "outputs": [ + { + "localized_name": "Audio", + "name": "Audio", + "type": "AUDIO", + "links": [ + 339 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVAudioVAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 106, + "type": "CreateVideo", + "pos": [ + 1420, + 3760 + ], + "size": [ + 270, + 78 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 352 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 339 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 356 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 304 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CreateVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 134, + "type": "LoraLoaderModelOnly", + "pos": [ + -1650, + 3760 + ], + "size": [ + 420, + 82 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 325 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 388 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 326, + 327 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "ltx-2-19b-ic-lora-canny-control.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Canny-Control/resolve/main/ltx-2-19b-ic-lora-canny-control.safetensors", + "directory": "loras" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-19b-ic-lora-canny-control.safetensors", + 1 + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 138, + "type": "LTXVSeparateAVLatent", + "pos": [ + 730, + 3730 + ], + "size": [ + 193.2916015625, + 46 + ], + "flags": {}, + "order": 34, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 336 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 337, + 351 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 338 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 144, + "type": "VAEDecodeTiled", + "pos": [ + 1120, + 3640 + ], + "size": [ + 270, + 150 + ], + "flags": {}, + "order": 36, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 351 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 353 + }, + { + "localized_name": "tile_size", + "name": "tile_size", + "type": "INT", + "widget": { + "name": "tile_size" + }, + "link": null + }, + { + "localized_name": "overlap", + "name": "overlap", + "type": "INT", + "widget": { + "name": "overlap" + }, + "link": null + }, + { + "localized_name": "temporal_size", + "name": "temporal_size", + "type": "INT", + "widget": { + "name": "temporal_size" + }, + "link": null + }, + { + "localized_name": "temporal_overlap", + "name": "temporal_overlap", + "type": "INT", + "widget": { + "name": "temporal_overlap" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 352 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "VAEDecodeTiled", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 512, + 64, + 4096, + 8 + ] + }, + { + "id": 113, + "type": "VAEDecode", + "pos": [ + 1130, + 3530 + ], + "size": [ + 240, + 50 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 337 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 291 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 110, + "type": "GetImageSize", + "pos": [ + -1630, + 4450 + ], + "size": [ + 260, + 80 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 349 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 296 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 297 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": [ + 329, + 330 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 145, + "type": "PrimitiveInt", + "pos": [ + -1630, + 4620 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 354 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24, + "fixed" + ] + }, + { + "id": 148, + "type": "PrimitiveFloat", + "pos": [ + -1630, + 4750 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 355, + 356 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 115, + "type": "EmptyLTXVLatentVideo", + "pos": [ + -1100, + 4610 + ], + "size": [ + 270, + 146.66666666666669 + ], + "flags": {}, + "order": 28, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 296 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 297 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 330 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 360 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "EmptyLTXVLatentVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 512, + 97, + 1 + ] + }, + { + "id": 149, + "type": "LTXVImgToVideoInplace", + "pos": [ + -1090, + 4400 + ], + "size": [ + 270, + 152 + ], + "flags": {}, + "order": 37, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 359 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 364 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 360 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": 370 + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 363 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 357 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 118, + "type": "Reroute", + "pos": [ + -230, + 4210 + ], + "size": [ + 75, + 26 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 303 + } + ], + "outputs": [ + { + "name": "", + "type": "VAE", + "links": [ + 289, + 291, + 367 + ] + } + ], + "properties": { + "showOutputText": false, + "horizontal": false + } + }, + { + "id": 151, + "type": "LTXVImgToVideoInplace", + "pos": [ + -20, + 4070 + ], + "size": [ + 270, + 182 + ], + "flags": {}, + "order": 38, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 367 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 379 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 366 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": 371 + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 368 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 365 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 104, + "type": "LTXVCropGuides", + "pos": [ + -10, + 3840 + ], + "size": [ + 240, + 66 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 310 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 312 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 270 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 281 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 282 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "slot_index": 2, + "links": [ + 287 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVCropGuides", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 112, + "type": "LTXVLatentUpsampler", + "pos": [ + -10, + 3960 + ], + "size": [ + 260, + 66 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 287 + }, + { + "localized_name": "upscale_model", + "name": "upscale_model", + "type": "LATENT_UPSCALE_MODEL", + "link": 288 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 289 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 366 + ] + } + ], + "title": "spatial", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVLatentUpsampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 132, + "type": "LTXVAddGuide", + "pos": [ + -600, + 4420 + ], + "size": [ + 270, + 209.16666666666669 + ], + "flags": {}, + "order": 33, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 313 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 314 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 328 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 357 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 348 + }, + { + "localized_name": "frame_idx", + "name": "frame_idx", + "type": "INT", + "widget": { + "name": "frame_idx" + }, + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 309, + 310 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 311, + 312 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 324 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "LTXVAddGuide", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + 1 + ] + }, + { + "id": 103, + "type": "CheckpointLoaderSimple", + "pos": [ + -1650, + 3590 + ], + "size": [ + 420, + 98 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 385 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 325 + ] + }, + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 303, + 328, + 353, + 359 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CheckpointLoaderSimple", + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-19b-dev-fp8.safetensors" + ] + }, + { + "id": 97, + "type": "LTXAVTextEncoderLoader", + "pos": [ + -1650, + 4040 + ], + "size": [ + 420, + 106 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "text_encoder", + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": 389 + }, + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 387 + }, + { + "localized_name": "device", + "name": "device", + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 294, + 295 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXAVTextEncoderLoader", + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + }, + { + "name": "gemma_3_12B_it_fp4_mixed.safetensors", + "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2-19b-dev-fp8.safetensors", + "default" + ] + }, + { + "id": 105, + "type": "LoraLoaderModelOnly", + "pos": [ + -70, + 3570 + ], + "size": [ + 390, + 82 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 327 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 390 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 280 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "ltx-2-19b-distilled-lora-384.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-lora-384.safetensors", + "directory": "loras" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-19b-distilled-lora-384.safetensors", + 1 + ] + }, + { + "id": 100, + "type": "LatentUpscaleModelLoader", + "pos": [ + -70, + 3700 + ], + "size": [ + 390, + 60 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "model_name", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": 391 + } + ], + "outputs": [ + { + "localized_name": "LATENT_UPSCALE_MODEL", + "name": "LATENT_UPSCALE_MODEL", + "type": "LATENT_UPSCALE_MODEL", + "links": [ + 288 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LatentUpscaleModelLoader", + "models": [ + { + "name": "ltx-2-spatial-upscaler-x2-1.0.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-spatial-upscaler-x2-1.0.safetensors", + "directory": "latent_upscale_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-spatial-upscaler-x2-1.0.safetensors" + ] + }, + { + "id": 154, + "type": "MarkdownNote", + "pos": [ + -1660, + 4870 + ], + "size": [ + 350, + 170 + ], + "flags": { + "collapsed": false + }, + "order": 10, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Frame Rate Note", + "properties": {}, + "widgets_values": [ + "Please make sure the frame rate value is the same in both boxes" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 155, + "type": "LTXVAudioVAELoader", + "pos": [ + -1640, + 3910 + ], + "size": [ + 400, + 58 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 386 + } + ], + "outputs": [ + { + "localized_name": "Audio VAE", + "name": "Audio VAE", + "type": "VAE", + "links": [ + 383, + 384 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "LTXVAudioVAELoader" + }, + "widgets_values": [ + "ltx-2-19b-dev-fp8.safetensors" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -1660, + 3440, + 440, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Basic Sampling", + "bounding": [ + -700, + 3440, + 570, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + -1180, + 3440, + 440, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "Latent", + "bounding": [ + -1180, + 4290, + 1050, + 680 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 9, + "title": "Upscale Sampling(2x)", + "bounding": [ + -100, + 3440, + 1090, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Sampler", + "bounding": [ + 350, + 3480, + 620, + 750 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Model", + "bounding": [ + -90, + 3480, + 430, + 310 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 11, + "title": "Frame rate", + "bounding": [ + -1640, + 4550, + 290, + 271.6 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 326, + "origin_id": 134, + "origin_slot": 0, + "target_id": 93, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 309, + "origin_id": 132, + "origin_slot": 0, + "target_id": 93, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 311, + "origin_id": 132, + "origin_slot": 1, + "target_id": 93, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 266, + "origin_id": 122, + "origin_slot": 1, + "target_id": 101, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 280, + "origin_id": 105, + "origin_slot": 0, + "target_id": 108, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 281, + "origin_id": 104, + "origin_slot": 0, + "target_id": 108, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 282, + "origin_id": 104, + "origin_slot": 1, + "target_id": 108, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 329, + "origin_id": 110, + "origin_slot": 2, + "target_id": 111, + "target_slot": 1, + "type": "INT" + }, + { + "id": 260, + "origin_id": 126, + "origin_slot": 0, + "target_id": 123, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 261, + "origin_id": 93, + "origin_slot": 0, + "target_id": 123, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 262, + "origin_id": 94, + "origin_slot": 0, + "target_id": 123, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 263, + "origin_id": 95, + "origin_slot": 0, + "target_id": 123, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 323, + "origin_id": 116, + "origin_slot": 0, + "target_id": 123, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 296, + "origin_id": 110, + "origin_slot": 0, + "target_id": 115, + "target_slot": 0, + "type": "INT" + }, + { + "id": 297, + "origin_id": 110, + "origin_slot": 1, + "target_id": 115, + "target_slot": 1, + "type": "INT" + }, + { + "id": 330, + "origin_id": 110, + "origin_slot": 2, + "target_id": 115, + "target_slot": 2, + "type": "INT" + }, + { + "id": 325, + "origin_id": 103, + "origin_slot": 0, + "target_id": 134, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 292, + "origin_id": 124, + "origin_slot": 0, + "target_id": 114, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 293, + "origin_id": 119, + "origin_slot": 0, + "target_id": 114, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 294, + "origin_id": 97, + "origin_slot": 0, + "target_id": 119, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 324, + "origin_id": 132, + "origin_slot": 2, + "target_id": 116, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 300, + "origin_id": 111, + "origin_slot": 0, + "target_id": 116, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 313, + "origin_id": 114, + "origin_slot": 0, + "target_id": 132, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 314, + "origin_id": 114, + "origin_slot": 1, + "target_id": 132, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 328, + "origin_id": 103, + "origin_slot": 2, + "target_id": 132, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 272, + "origin_id": 123, + "origin_slot": 0, + "target_id": 122, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 336, + "origin_id": 107, + "origin_slot": 1, + "target_id": 138, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 339, + "origin_id": 139, + "origin_slot": 0, + "target_id": 106, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 295, + "origin_id": 97, + "origin_slot": 0, + "target_id": 124, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 303, + "origin_id": 103, + "origin_slot": 2, + "target_id": 118, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 338, + "origin_id": 138, + "origin_slot": 1, + "target_id": 139, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 337, + "origin_id": 138, + "origin_slot": 0, + "target_id": 113, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 291, + "origin_id": 118, + "origin_slot": 0, + "target_id": 113, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 276, + "origin_id": 108, + "origin_slot": 0, + "target_id": 107, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 277, + "origin_id": 98, + "origin_slot": 0, + "target_id": 107, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 278, + "origin_id": 99, + "origin_slot": 0, + "target_id": 107, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 279, + "origin_id": 101, + "origin_slot": 0, + "target_id": 107, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 327, + "origin_id": 134, + "origin_slot": 0, + "target_id": 105, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 310, + "origin_id": 132, + "origin_slot": 0, + "target_id": 104, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 312, + "origin_id": 132, + "origin_slot": 1, + "target_id": 104, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 270, + "origin_id": 122, + "origin_slot": 0, + "target_id": 104, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 287, + "origin_id": 104, + "origin_slot": 2, + "target_id": 112, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 288, + "origin_id": 100, + "origin_slot": 0, + "target_id": 112, + "target_slot": 1, + "type": "LATENT_UPSCALE_MODEL" + }, + { + "id": 289, + "origin_id": 118, + "origin_slot": 0, + "target_id": 112, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 322, + "origin_id": 116, + "origin_slot": 0, + "target_id": 95, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 304, + "origin_id": 106, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 345, + "origin_id": -10, + "origin_slot": 0, + "target_id": 124, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 347, + "origin_id": 143, + "origin_slot": 0, + "target_id": 107, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 348, + "origin_id": -10, + "origin_slot": 1, + "target_id": 132, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 349, + "origin_id": -10, + "origin_slot": 1, + "target_id": 110, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 351, + "origin_id": 138, + "origin_slot": 0, + "target_id": 144, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 352, + "origin_id": 144, + "origin_slot": 0, + "target_id": 106, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 353, + "origin_id": 103, + "origin_slot": 2, + "target_id": 144, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 354, + "origin_id": 145, + "origin_slot": 0, + "target_id": 111, + "target_slot": 2, + "type": "INT" + }, + { + "id": 355, + "origin_id": 148, + "origin_slot": 0, + "target_id": 114, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 356, + "origin_id": 148, + "origin_slot": 0, + "target_id": 106, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 357, + "origin_id": 149, + "origin_slot": 0, + "target_id": 132, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 359, + "origin_id": 103, + "origin_slot": 2, + "target_id": 149, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 360, + "origin_id": 115, + "origin_slot": 0, + "target_id": 149, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 363, + "origin_id": -10, + "origin_slot": 3, + "target_id": 149, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 364, + "origin_id": -10, + "origin_slot": 4, + "target_id": 149, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 365, + "origin_id": 151, + "origin_slot": 0, + "target_id": 101, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 366, + "origin_id": 112, + "origin_slot": 0, + "target_id": 151, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 367, + "origin_id": 118, + "origin_slot": 0, + "target_id": 151, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 368, + "origin_id": -10, + "origin_slot": 3, + "target_id": 151, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 370, + "origin_id": -10, + "origin_slot": 2, + "target_id": 149, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 371, + "origin_id": -10, + "origin_slot": 2, + "target_id": 151, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 379, + "origin_id": -10, + "origin_slot": 4, + "target_id": 151, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 383, + "origin_id": 155, + "origin_slot": 0, + "target_id": 111, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 384, + "origin_id": 155, + "origin_slot": 0, + "target_id": 139, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 385, + "origin_id": -10, + "origin_slot": 5, + "target_id": 103, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 386, + "origin_id": -10, + "origin_slot": 5, + "target_id": 155, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 387, + "origin_id": -10, + "origin_slot": 5, + "target_id": 97, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 388, + "origin_id": -10, + "origin_slot": 6, + "target_id": 134, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 389, + "origin_id": -10, + "origin_slot": 7, + "target_id": 97, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 390, + "origin_id": -10, + "origin_slot": 8, + "target_id": 105, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 391, + "origin_id": -10, + "origin_slot": 9, + "target_id": 100, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video generation and editing/Canny to video" + } + ] + }, + "config": {}, + "extra": { + "workflowRendererVersion": "LG", + "ds": { + "scale": 0.7537190265006444, + "offset": [ + -330.27244430536007, + -3324.725077010053 + ] + } + }, + "version": 0.4 +} diff --git a/blueprints/Chromatic Aberration.json b/blueprints/Chromatic Aberration.json index 5513cc665..ae8037b1b 100644 --- a/blueprints/Chromatic Aberration.json +++ b/blueprints/Chromatic Aberration.json @@ -1 +1,384 @@ -{"revision": 0, "last_node_id": 19, "last_link_id": 0, "nodes": [{"id": 19, "type": "2c5ef154-2bde-496d-bc8b-9dcf42f2913f", "pos": [3710, -2070], "size": [260, 82], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "title": "Chromatic Aberration", "properties": {"proxyWidgets": [["17", "choice"], ["18", "value"]]}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "2c5ef154-2bde-496d-bc8b-9dcf42f2913f", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 18, "lastLinkId": 23, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Chromatic Aberration", "inputNode": {"id": -10, "bounding": [3270, -2050, 120, 60]}, "outputNode": {"id": -20, "bounding": [4260, -2050, 120, 60]}, "inputs": [{"id": "3b33ac46-93a6-4b1c-896a-ed6fbd24e59c", "name": "images.image0", "type": "IMAGE", "linkIds": [20], "localized_name": "images.image0", "label": "image", "pos": [3370, -2030]}], "outputs": [{"id": "abe7cd79-a87b-4bd0-8923-d79a57d81a6e", "name": "IMAGE0", "type": "IMAGE", "linkIds": [23], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [4280, -2030]}], "widgets": [], "nodes": [{"id": 16, "type": "GLSLShader", "pos": [3810, -2320], "size": [390, 212], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 20}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 22}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": 21}, {"label": "u_int1", "localized_name": "ints.u_int1", "name": "ints.u_int1", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [23]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform int u_int0; // Mode\nuniform float u_float0; // Amount (0 to 100)\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int MODE_LINEAR = 0;\nconst int MODE_RADIAL = 1;\nconst int MODE_BARREL = 2;\nconst int MODE_SWIRL = 3;\nconst int MODE_DIAGONAL = 4;\n\nconst float AMOUNT_SCALE = 0.0005;\nconst float RADIAL_MULT = 4.0;\nconst float BARREL_MULT = 8.0;\nconst float INV_SQRT2 = 0.70710678118;\n\nvoid main() {\n vec2 uv = v_texCoord;\n vec4 original = texture(u_image0, uv);\n\n float amount = u_float0 * AMOUNT_SCALE;\n\n if (amount < 0.000001) {\n fragColor = original;\n return;\n }\n\n // Aspect-corrected coordinates for circular effects\n float aspect = u_resolution.x / u_resolution.y;\n vec2 centered = uv - 0.5;\n vec2 corrected = vec2(centered.x * aspect, centered.y);\n float r = length(corrected);\n vec2 dir = r > 0.0001 ? corrected / r : vec2(0.0);\n vec2 offset = vec2(0.0);\n\n if (u_int0 == MODE_LINEAR) {\n // Horizontal shift (no aspect correction needed)\n offset = vec2(amount, 0.0);\n }\n else if (u_int0 == MODE_RADIAL) {\n // Outward from center, stronger at edges\n offset = dir * r * amount * RADIAL_MULT;\n offset.x /= aspect; // Convert back to UV space\n }\n else if (u_int0 == MODE_BARREL) {\n // Lens distortion simulation (r² falloff)\n offset = dir * r * r * amount * BARREL_MULT;\n offset.x /= aspect; // Convert back to UV space\n }\n else if (u_int0 == MODE_SWIRL) {\n // Perpendicular to radial (rotational aberration)\n vec2 perp = vec2(-dir.y, dir.x);\n offset = perp * r * amount * RADIAL_MULT;\n offset.x /= aspect; // Convert back to UV space\n }\n else if (u_int0 == MODE_DIAGONAL) {\n // 45° offset (no aspect correction needed)\n offset = vec2(amount, amount) * INV_SQRT2;\n }\n \n float red = texture(u_image0, uv + offset).r;\n float green = original.g;\n float blue = texture(u_image0, uv - offset).b;\n \n fragColor = vec4(red, green, blue, original.a);\n}", "from_input"]}, {"id": 18, "type": "PrimitiveFloat", "pos": [3810, -2430], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "amount", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [22]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "step": 1}, "widgets_values": [30]}, {"id": 17, "type": "CustomCombo", "pos": [3520, -2320], "size": [270, 222], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "mode", "localized_name": "choice", "name": "choice", "type": "COMBO", "widget": {"name": "choice"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": null}, {"localized_name": "INDEX", "name": "INDEX", "type": "INT", "links": [21]}], "properties": {"Node name for S&R": "CustomCombo"}, "widgets_values": ["Linear", 0, "Linear", "Radial", "Barrel", "Swirl", "Diagonal", ""]}], "groups": [], "links": [{"id": 22, "origin_id": 18, "origin_slot": 0, "target_id": 16, "target_slot": 2, "type": "FLOAT"}, {"id": 21, "origin_id": 17, "origin_slot": 1, "target_id": 16, "target_slot": 4, "type": "INT"}, {"id": 20, "origin_id": -10, "origin_slot": 0, "target_id": 16, "target_slot": 0, "type": "IMAGE"}, {"id": 23, "origin_id": 16, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}} +{ + "revision": 0, + "last_node_id": 19, + "last_link_id": 0, + "nodes": [ + { + "id": 19, + "type": "2c5ef154-2bde-496d-bc8b-9dcf42f2913f", + "pos": [ + 3710, + -2070 + ], + "size": [ + 260, + 82 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "title": "Chromatic Aberration", + "properties": { + "proxyWidgets": [ + [ + "17", + "choice" + ], + [ + "18", + "value" + ] + ] + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "2c5ef154-2bde-496d-bc8b-9dcf42f2913f", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 18, + "lastLinkId": 23, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Chromatic Aberration", + "inputNode": { + "id": -10, + "bounding": [ + 3270, + -2050, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4260, + -2050, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "3b33ac46-93a6-4b1c-896a-ed6fbd24e59c", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 20 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 3370, + -2030 + ] + } + ], + "outputs": [ + { + "id": "abe7cd79-a87b-4bd0-8923-d79a57d81a6e", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 23 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 4280, + -2030 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 16, + "type": "GLSLShader", + "pos": [ + 3810, + -2320 + ], + "size": [ + 390, + 212 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 20 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 22 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": 21 + }, + { + "label": "u_int1", + "localized_name": "ints.u_int1", + "name": "ints.u_int1", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 23 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform int u_int0; // Mode\nuniform float u_float0; // Amount (0 to 100)\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int MODE_LINEAR = 0;\nconst int MODE_RADIAL = 1;\nconst int MODE_BARREL = 2;\nconst int MODE_SWIRL = 3;\nconst int MODE_DIAGONAL = 4;\n\nconst float AMOUNT_SCALE = 0.0005;\nconst float RADIAL_MULT = 4.0;\nconst float BARREL_MULT = 8.0;\nconst float INV_SQRT2 = 0.70710678118;\n\nvoid main() {\n vec2 uv = v_texCoord;\n vec4 original = texture(u_image0, uv);\n\n float amount = u_float0 * AMOUNT_SCALE;\n\n if (amount < 0.000001) {\n fragColor = original;\n return;\n }\n\n // Aspect-corrected coordinates for circular effects\n float aspect = u_resolution.x / u_resolution.y;\n vec2 centered = uv - 0.5;\n vec2 corrected = vec2(centered.x * aspect, centered.y);\n float r = length(corrected);\n vec2 dir = r > 0.0001 ? corrected / r : vec2(0.0);\n vec2 offset = vec2(0.0);\n\n if (u_int0 == MODE_LINEAR) {\n // Horizontal shift (no aspect correction needed)\n offset = vec2(amount, 0.0);\n }\n else if (u_int0 == MODE_RADIAL) {\n // Outward from center, stronger at edges\n offset = dir * r * amount * RADIAL_MULT;\n offset.x /= aspect; // Convert back to UV space\n }\n else if (u_int0 == MODE_BARREL) {\n // Lens distortion simulation (r² falloff)\n offset = dir * r * r * amount * BARREL_MULT;\n offset.x /= aspect; // Convert back to UV space\n }\n else if (u_int0 == MODE_SWIRL) {\n // Perpendicular to radial (rotational aberration)\n vec2 perp = vec2(-dir.y, dir.x);\n offset = perp * r * amount * RADIAL_MULT;\n offset.x /= aspect; // Convert back to UV space\n }\n else if (u_int0 == MODE_DIAGONAL) {\n // 45° offset (no aspect correction needed)\n offset = vec2(amount, amount) * INV_SQRT2;\n }\n \n float red = texture(u_image0, uv + offset).r;\n float green = original.g;\n float blue = texture(u_image0, uv - offset).b;\n \n fragColor = vec4(red, green, blue, original.a);\n}", + "from_input" + ] + }, + { + "id": 18, + "type": "PrimitiveFloat", + "pos": [ + 3810, + -2430 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "amount", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 22 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "step": 1 + }, + "widgets_values": [ + 30 + ] + }, + { + "id": 17, + "type": "CustomCombo", + "pos": [ + 3520, + -2320 + ], + "size": [ + 270, + 222 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "mode", + "localized_name": "choice", + "name": "choice", + "type": "COMBO", + "widget": { + "name": "choice" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": null + }, + { + "localized_name": "INDEX", + "name": "INDEX", + "type": "INT", + "links": [ + 21 + ] + } + ], + "properties": { + "Node name for S&R": "CustomCombo" + }, + "widgets_values": [ + "Linear", + 0, + "Linear", + "Radial", + "Barrel", + "Swirl", + "Diagonal", + "" + ] + } + ], + "groups": [], + "links": [ + { + "id": 22, + "origin_id": 18, + "origin_slot": 0, + "target_id": 16, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 21, + "origin_id": 17, + "origin_slot": 1, + "target_id": 16, + "target_slot": 4, + "type": "INT" + }, + { + "id": 20, + "origin_id": -10, + "origin_slot": 0, + "target_id": 16, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 23, + "origin_id": 16, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} diff --git a/blueprints/Color Adjustment.json b/blueprints/Color Adjustment.json index 47f3df783..622bf28af 100644 --- a/blueprints/Color Adjustment.json +++ b/blueprints/Color Adjustment.json @@ -1 +1,603 @@ -{"revision": 0, "last_node_id": 14, "last_link_id": 0, "nodes": [{"id": 14, "type": "36677b92-5dd8-47a5-9380-4da982c1894f", "pos": [3610, -2630], "size": [270, 150], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["4", "value"], ["5", "value"], ["7", "value"], ["6", "value"]]}, "widgets_values": [], "title": "Color Adjustment"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "36677b92-5dd8-47a5-9380-4da982c1894f", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 16, "lastLinkId": 36, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Color Adjustment", "inputNode": {"id": -10, "bounding": [3110, -3560, 120, 60]}, "outputNode": {"id": -20, "bounding": [4070, -3560, 120, 60]}, "inputs": [{"id": "0431d493-5f28-4430-bd00-84733997fc08", "name": "images.image0", "type": "IMAGE", "linkIds": [29], "localized_name": "images.image0", "label": "image", "pos": [3210, -3540]}], "outputs": [{"id": "bee8ea06-a114-4612-8937-939f2c927bdb", "name": "IMAGE0", "type": "IMAGE", "linkIds": [28], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [4090, -3540]}], "widgets": [], "nodes": [{"id": 15, "type": "GLSLShader", "pos": [3590, -3940], "size": [420, 252], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 29}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 34}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 30}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": 31}, {"label": "u_float3", "localized_name": "floats.u_float3", "name": "floats.u_float3", "shape": 7, "type": "FLOAT", "link": 33}, {"label": "u_float4", "localized_name": "floats.u_float4", "name": "floats.u_float4", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [28]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // temperature (-100 to 100)\nuniform float u_float1; // tint (-100 to 100)\nuniform float u_float2; // vibrance (-100 to 100)\nuniform float u_float3; // saturation (-100 to 100)\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst float INPUT_SCALE = 0.01;\nconst float TEMP_TINT_PRIMARY = 0.3;\nconst float TEMP_TINT_SECONDARY = 0.15;\nconst float VIBRANCE_BOOST = 2.0;\nconst float SATURATION_BOOST = 2.0;\nconst float SKIN_PROTECTION = 0.5;\nconst float EPSILON = 0.001;\nconst vec3 LUMA_WEIGHTS = vec3(0.299, 0.587, 0.114);\n\nvoid main() {\n vec4 tex = texture(u_image0, v_texCoord);\n vec3 color = tex.rgb;\n \n // Scale inputs: -100/100 \u2192 -1/1\n float temperature = u_float0 * INPUT_SCALE;\n float tint = u_float1 * INPUT_SCALE;\n float vibrance = u_float2 * INPUT_SCALE;\n float saturation = u_float3 * INPUT_SCALE;\n \n // Temperature (warm/cool): positive = warm, negative = cool\n color.r += temperature * TEMP_TINT_PRIMARY;\n color.b -= temperature * TEMP_TINT_PRIMARY;\n \n // Tint (green/magenta): positive = green, negative = magenta\n color.g += tint * TEMP_TINT_PRIMARY;\n color.r -= tint * TEMP_TINT_SECONDARY;\n color.b -= tint * TEMP_TINT_SECONDARY;\n \n // Single clamp after temperature/tint\n color = clamp(color, 0.0, 1.0);\n \n // Vibrance with skin protection\n if (vibrance != 0.0) {\n float maxC = max(color.r, max(color.g, color.b));\n float minC = min(color.r, min(color.g, color.b));\n float sat = maxC - minC;\n float gray = dot(color, LUMA_WEIGHTS);\n \n if (vibrance < 0.0) {\n // Desaturate: -100 \u2192 gray\n color = mix(vec3(gray), color, 1.0 + vibrance);\n } else {\n // Boost less saturated colors more\n float vibranceAmt = vibrance * (1.0 - sat);\n \n // Branchless skin tone protection\n float isWarmTone = step(color.b, color.g) * step(color.g, color.r);\n float warmth = (color.r - color.b) / max(maxC, EPSILON);\n float skinTone = isWarmTone * warmth * sat * (1.0 - sat);\n vibranceAmt *= (1.0 - skinTone * SKIN_PROTECTION);\n \n color = mix(vec3(gray), color, 1.0 + vibranceAmt * VIBRANCE_BOOST);\n }\n }\n \n // Saturation\n if (saturation != 0.0) {\n float gray = dot(color, LUMA_WEIGHTS);\n float satMix = saturation < 0.0\n ? 1.0 + saturation // -100 \u2192 gray\n : 1.0 + saturation * SATURATION_BOOST; // +100 \u2192 3x boost\n color = mix(vec3(gray), color, satMix);\n }\n \n fragColor = vec4(clamp(color, 0.0, 1.0), tex.a);\n}", "from_input"]}, {"id": 6, "type": "PrimitiveFloat", "pos": [3290, -3610], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "vibrance", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [26, 31]}], "title": "Vibrance", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [128, 128, 128]}, {"offset": 1, "color": [255, 0, 0]}]}, "widgets_values": [0]}, {"id": 7, "type": "PrimitiveFloat", "pos": [3290, -3720], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "saturation", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [33]}], "title": "Saturation", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [128, 128, 128]}, {"offset": 1, "color": [255, 0, 0]}]}, "widgets_values": [0]}, {"id": 5, "type": "PrimitiveFloat", "pos": [3290, -3830], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "tint", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [30]}], "title": "Tint", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 255, 0]}, {"offset": 0.5, "color": [255, 255, 255]}, {"offset": 1, "color": [255, 0, 255]}]}, "widgets_values": [0]}, {"id": 4, "type": "PrimitiveFloat", "pos": [3290, -3940], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "temperature", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [34]}], "title": "Temperature", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [68, 136, 255]}, {"offset": 0.5, "color": [255, 255, 255]}, {"offset": 1, "color": [255, 136, 0]}]}, "widgets_values": [0]}], "groups": [], "links": [{"id": 34, "origin_id": 4, "origin_slot": 0, "target_id": 15, "target_slot": 2, "type": "FLOAT"}, {"id": 30, "origin_id": 5, "origin_slot": 0, "target_id": 15, "target_slot": 3, "type": "FLOAT"}, {"id": 31, "origin_id": 6, "origin_slot": 0, "target_id": 15, "target_slot": 4, "type": "FLOAT"}, {"id": 33, "origin_id": 7, "origin_slot": 0, "target_id": 15, "target_slot": 5, "type": "FLOAT"}, {"id": 29, "origin_id": -10, "origin_slot": 0, "target_id": 15, "target_slot": 0, "type": "IMAGE"}, {"id": 28, "origin_id": 15, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}} +{ + "revision": 0, + "last_node_id": 14, + "last_link_id": 0, + "nodes": [ + { + "id": 14, + "type": "36677b92-5dd8-47a5-9380-4da982c1894f", + "pos": [ + 3610, + -2630 + ], + "size": [ + 270, + 150 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "4", + "value" + ], + [ + "5", + "value" + ], + [ + "7", + "value" + ], + [ + "6", + "value" + ] + ] + }, + "widgets_values": [], + "title": "Color Adjustment" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "36677b92-5dd8-47a5-9380-4da982c1894f", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 16, + "lastLinkId": 36, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Color Adjustment", + "inputNode": { + "id": -10, + "bounding": [ + 3110, + -3560, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4070, + -3560, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "0431d493-5f28-4430-bd00-84733997fc08", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 29 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 3210, + -3540 + ] + } + ], + "outputs": [ + { + "id": "bee8ea06-a114-4612-8937-939f2c927bdb", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 28 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 4090, + -3540 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 15, + "type": "GLSLShader", + "pos": [ + 3590, + -3940 + ], + "size": [ + 420, + 252 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 29 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 34 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 30 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": 31 + }, + { + "label": "u_float3", + "localized_name": "floats.u_float3", + "name": "floats.u_float3", + "shape": 7, + "type": "FLOAT", + "link": 33 + }, + { + "label": "u_float4", + "localized_name": "floats.u_float4", + "name": "floats.u_float4", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 28 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // temperature (-100 to 100)\nuniform float u_float1; // tint (-100 to 100)\nuniform float u_float2; // vibrance (-100 to 100)\nuniform float u_float3; // saturation (-100 to 100)\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst float INPUT_SCALE = 0.01;\nconst float TEMP_TINT_PRIMARY = 0.3;\nconst float TEMP_TINT_SECONDARY = 0.15;\nconst float VIBRANCE_BOOST = 2.0;\nconst float SATURATION_BOOST = 2.0;\nconst float SKIN_PROTECTION = 0.5;\nconst float EPSILON = 0.001;\nconst vec3 LUMA_WEIGHTS = vec3(0.299, 0.587, 0.114);\n\nvoid main() {\n vec4 tex = texture(u_image0, v_texCoord);\n vec3 color = tex.rgb;\n \n // Scale inputs: -100/100 \u2192 -1/1\n float temperature = u_float0 * INPUT_SCALE;\n float tint = u_float1 * INPUT_SCALE;\n float vibrance = u_float2 * INPUT_SCALE;\n float saturation = u_float3 * INPUT_SCALE;\n \n // Temperature (warm/cool): positive = warm, negative = cool\n color.r += temperature * TEMP_TINT_PRIMARY;\n color.b -= temperature * TEMP_TINT_PRIMARY;\n \n // Tint (green/magenta): positive = green, negative = magenta\n color.g += tint * TEMP_TINT_PRIMARY;\n color.r -= tint * TEMP_TINT_SECONDARY;\n color.b -= tint * TEMP_TINT_SECONDARY;\n \n // Single clamp after temperature/tint\n color = clamp(color, 0.0, 1.0);\n \n // Vibrance with skin protection\n if (vibrance != 0.0) {\n float maxC = max(color.r, max(color.g, color.b));\n float minC = min(color.r, min(color.g, color.b));\n float sat = maxC - minC;\n float gray = dot(color, LUMA_WEIGHTS);\n \n if (vibrance < 0.0) {\n // Desaturate: -100 \u2192 gray\n color = mix(vec3(gray), color, 1.0 + vibrance);\n } else {\n // Boost less saturated colors more\n float vibranceAmt = vibrance * (1.0 - sat);\n \n // Branchless skin tone protection\n float isWarmTone = step(color.b, color.g) * step(color.g, color.r);\n float warmth = (color.r - color.b) / max(maxC, EPSILON);\n float skinTone = isWarmTone * warmth * sat * (1.0 - sat);\n vibranceAmt *= (1.0 - skinTone * SKIN_PROTECTION);\n \n color = mix(vec3(gray), color, 1.0 + vibranceAmt * VIBRANCE_BOOST);\n }\n }\n \n // Saturation\n if (saturation != 0.0) {\n float gray = dot(color, LUMA_WEIGHTS);\n float satMix = saturation < 0.0\n ? 1.0 + saturation // -100 \u2192 gray\n : 1.0 + saturation * SATURATION_BOOST; // +100 \u2192 3x boost\n color = mix(vec3(gray), color, satMix);\n }\n \n fragColor = vec4(clamp(color, 0.0, 1.0), tex.a);\n}", + "from_input" + ] + }, + { + "id": 6, + "type": "PrimitiveFloat", + "pos": [ + 3290, + -3610 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "vibrance", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 26, + 31 + ] + } + ], + "title": "Vibrance", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 7, + "type": "PrimitiveFloat", + "pos": [ + 3290, + -3720 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "saturation", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 33 + ] + } + ], + "title": "Saturation", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 5, + "type": "PrimitiveFloat", + "pos": [ + 3290, + -3830 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "tint", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 30 + ] + } + ], + "title": "Tint", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 255, + 0 + ] + }, + { + "offset": 0.5, + "color": [ + 255, + 255, + 255 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 4, + "type": "PrimitiveFloat", + "pos": [ + 3290, + -3940 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "temperature", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 34 + ] + } + ], + "title": "Temperature", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 68, + 136, + 255 + ] + }, + { + "offset": 0.5, + "color": [ + 255, + 255, + 255 + ] + }, + { + "offset": 1, + "color": [ + 255, + 136, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + } + ], + "groups": [], + "links": [ + { + "id": 34, + "origin_id": 4, + "origin_slot": 0, + "target_id": 15, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 30, + "origin_id": 5, + "origin_slot": 0, + "target_id": 15, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 31, + "origin_id": 6, + "origin_slot": 0, + "target_id": 15, + "target_slot": 4, + "type": "FLOAT" + }, + { + "id": 33, + "origin_id": 7, + "origin_slot": 0, + "target_id": 15, + "target_slot": 5, + "type": "FLOAT" + }, + { + "id": 29, + "origin_id": -10, + "origin_slot": 0, + "target_id": 15, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 28, + "origin_id": 15, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} diff --git a/blueprints/Color Balance.json b/blueprints/Color Balance.json index fe272d5dc..21d6319ed 100644 --- a/blueprints/Color Balance.json +++ b/blueprints/Color Balance.json @@ -1 +1,1136 @@ -{"revision": 0, "last_node_id": 20, "last_link_id": 0, "nodes": [{"id": 20, "type": "243b9e93-7303-4500-8c70-58acb712f5bc", "pos": [3610, -2630], "size": [270, 420], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["4", "value"], ["5", "value"], ["6", "value"], ["7", "value"], ["8", "value"], ["9", "value"], ["10", "value"], ["11", "value"], ["12", "value"], ["13", "value"]]}, "widgets_values": [], "title": "Color Balance"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "243b9e93-7303-4500-8c70-58acb712f5bc", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 15, "lastLinkId": 39, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Color Balance", "inputNode": {"id": -10, "bounding": [2660, -4500, 120, 60]}, "outputNode": {"id": -20, "bounding": [4270, -4500, 120, 60]}, "inputs": [{"id": "d24c0b6d-00bd-4e95-be80-8114e8376ec0", "name": "images.image0", "type": "IMAGE", "linkIds": [29], "localized_name": "images.image0", "label": "image", "pos": [2760, -4480]}], "outputs": [{"id": "92723f62-996e-496d-ad4f-81a38be4ad64", "name": "IMAGE0", "type": "IMAGE", "linkIds": [28], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [4290, -4480]}], "widgets": [], "nodes": [{"id": 4, "type": "PrimitiveFloat", "pos": [3060, -4500], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "shadows red", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [30]}], "title": "Shadows Red", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 255, 255]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [255, 0, 0]}]}, "widgets_values": [0]}, {"id": 5, "type": "PrimitiveFloat", "pos": [3060, -4390], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "shadows green", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [31]}], "title": "Shadows Green", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [255, 0, 255]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [0, 255, 0]}]}, "widgets_values": [0]}, {"id": 6, "type": "PrimitiveFloat", "pos": [3060, -4280], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "shadows blue", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [32]}], "title": "Shadows Blue", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [255, 255, 0]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [0, 0, 255]}]}, "widgets_values": [0]}, {"id": 7, "type": "PrimitiveFloat", "pos": [3060, -4170], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "midtones red", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [33]}], "title": "Midtones Red", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 255, 255]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [255, 0, 0]}]}, "widgets_values": [0]}, {"id": 8, "type": "PrimitiveFloat", "pos": [3060, -4060], "size": [270, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "midtones green", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [34]}], "title": "Midtones Green", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [255, 0, 255]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [0, 255, 0]}]}, "widgets_values": [0]}, {"id": 9, "type": "PrimitiveFloat", "pos": [3060, -3950], "size": [270, 58], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "midtones blue", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [35]}], "title": "Midtones Blue", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [255, 255, 0]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [0, 0, 255]}]}, "widgets_values": [0]}, {"id": 10, "type": "PrimitiveFloat", "pos": [3060, -3840], "size": [270, 58], "flags": {}, "order": 6, "mode": 0, "inputs": [{"label": "highlights red", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [36]}], "title": "Highlights Red", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 255, 255]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [255, 0, 0]}]}, "widgets_values": [0]}, {"id": 11, "type": "PrimitiveFloat", "pos": [3060, -3730], "size": [270, 58], "flags": {}, "order": 7, "mode": 0, "inputs": [{"label": "highlights green", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [37]}], "title": "Highlights Green", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [255, 0, 255]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [0, 255, 0]}]}, "widgets_values": [0]}, {"id": 12, "type": "PrimitiveFloat", "pos": [3060, -3620], "size": [270, 58], "flags": {}, "order": 8, "mode": 0, "inputs": [{"label": "highlights blue", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [38]}], "title": "Highlights Blue", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": -100, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [255, 255, 0]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [0, 0, 255]}]}, "widgets_values": [0]}, {"id": 13, "type": "PrimitiveBoolean", "pos": [3060, -3510], "size": [270, 58], "flags": {}, "order": 9, "mode": 0, "inputs": [{"label": "preserve luminosity", "localized_name": "value", "name": "value", "type": "BOOLEAN", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "BOOLEAN", "name": "BOOLEAN", "type": "BOOLEAN", "links": [39]}], "title": "Preserve Luminosity", "properties": {"Node name for S&R": "PrimitiveBoolean"}, "widgets_values": [true]}, {"id": 15, "type": "GLSLShader", "pos": [3590, -4500], "size": [420, 500], "flags": {}, "order": 10, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 29}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 30}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 31}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": 32}, {"label": "u_float3", "localized_name": "floats.u_float3", "name": "floats.u_float3", "shape": 7, "type": "FLOAT", "link": 33}, {"label": "u_float4", "localized_name": "floats.u_float4", "name": "floats.u_float4", "shape": 7, "type": "FLOAT", "link": 34}, {"label": "u_float5", "localized_name": "floats.u_float5", "name": "floats.u_float5", "shape": 7, "type": "FLOAT", "link": 35}, {"label": "u_float6", "localized_name": "floats.u_float6", "name": "floats.u_float6", "shape": 7, "type": "FLOAT", "link": 36}, {"label": "u_float7", "localized_name": "floats.u_float7", "name": "floats.u_float7", "shape": 7, "type": "FLOAT", "link": 37}, {"label": "u_float8", "localized_name": "floats.u_float8", "name": "floats.u_float8", "shape": 7, "type": "FLOAT", "link": 38}, {"label": "u_bool0", "localized_name": "bools.u_bool0", "name": "bools.u_bool0", "shape": 7, "type": "BOOLEAN", "link": 39}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [28]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // shadows red (-100 to 100)\nuniform float u_float1; // shadows green (-100 to 100)\nuniform float u_float2; // shadows blue (-100 to 100)\nuniform float u_float3; // midtones red (-100 to 100)\nuniform float u_float4; // midtones green (-100 to 100)\nuniform float u_float5; // midtones blue (-100 to 100)\nuniform float u_float6; // highlights red (-100 to 100)\nuniform float u_float7; // highlights green (-100 to 100)\nuniform float u_float8; // highlights blue (-100 to 100)\nuniform bool u_bool0; // preserve luminosity\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nvec3 rgb2hsl(vec3 c) {\n float maxC = max(c.r, max(c.g, c.b));\n float minC = min(c.r, min(c.g, c.b));\n float l = (maxC + minC) * 0.5;\n if (maxC == minC) return vec3(0.0, 0.0, l);\n float d = maxC - minC;\n float s = l > 0.5 ? d / (2.0 - maxC - minC) : d / (maxC + minC);\n float h;\n if (maxC == c.r) {\n h = (c.g - c.b) / d + (c.g < c.b ? 6.0 : 0.0);\n } else if (maxC == c.g) {\n h = (c.b - c.r) / d + 2.0;\n } else {\n h = (c.r - c.g) / d + 4.0;\n }\n h /= 6.0;\n return vec3(h, s, l);\n}\n\nfloat hue2rgb(float p, float q, float t) {\n if (t < 0.0) t += 1.0;\n if (t > 1.0) t -= 1.0;\n if (t < 1.0 / 6.0) return p + (q - p) * 6.0 * t;\n if (t < 1.0 / 2.0) return q;\n if (t < 2.0 / 3.0) return p + (q - p) * (2.0 / 3.0 - t) * 6.0;\n return p;\n}\n\nvec3 hsl2rgb(vec3 hsl) {\n float h = hsl.x, s = hsl.y, l = hsl.z;\n if (s == 0.0) return vec3(l);\n float q = l < 0.5 ? l * (1.0 + s) : l + s - l * s;\n float p = 2.0 * l - q;\n return vec3(\n hue2rgb(p, q, h + 1.0 / 3.0),\n hue2rgb(p, q, h),\n hue2rgb(p, q, h - 1.0 / 3.0)\n );\n}\n\nvoid main() {\n vec4 tex = texture(u_image0, v_texCoord);\n vec3 color = tex.rgb;\n\n // Build shadows/midtones/highlights vectors (scale -100..100 to -1..1)\n vec3 shadows = vec3(u_float0, u_float1, u_float2) * 0.01;\n vec3 midtones = vec3(u_float3, u_float4, u_float5) * 0.01;\n vec3 highlights = vec3(u_float6, u_float7, u_float8) * 0.01;\n\n // GIMP: HSL lightness for weight calculation\n float maxC = max(color.r, max(color.g, color.b));\n float minC = min(color.r, min(color.g, color.b));\n float lightness = (maxC + minC) * 0.5;\n\n // GIMP weight curves: linear ramps with constants a=0.25, b=0.333, scale=0.7\n const float a = 0.25;\n const float b = 0.333;\n const float scale = 0.7;\n\n float sw = clamp((lightness - b) / -a + 0.5, 0.0, 1.0) * scale;\n float mw = clamp((lightness - b) / a + 0.5, 0.0, 1.0) *\n clamp((lightness + b - 1.0) / -a + 0.5, 0.0, 1.0) * scale;\n float hw = clamp((lightness + b - 1.0) / a + 0.5, 0.0, 1.0) * scale;\n\n color += sw * shadows + mw * midtones + hw * highlights;\n\n if (u_bool0) {\n vec3 hsl = rgb2hsl(clamp(color, 0.0, 1.0));\n hsl.z = lightness;\n color = hsl2rgb(hsl);\n }\n\n fragColor = vec4(clamp(color, 0.0, 1.0), tex.a);\n}", "from_input"]}], "groups": [], "links": [{"id": 29, "origin_id": -10, "origin_slot": 0, "target_id": 15, "target_slot": 0, "type": "IMAGE"}, {"id": 28, "origin_id": 15, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 30, "origin_id": 4, "origin_slot": 0, "target_id": 15, "target_slot": 2, "type": "FLOAT"}, {"id": 31, "origin_id": 5, "origin_slot": 0, "target_id": 15, "target_slot": 3, "type": "FLOAT"}, {"id": 32, "origin_id": 6, "origin_slot": 0, "target_id": 15, "target_slot": 4, "type": "FLOAT"}, {"id": 33, "origin_id": 7, "origin_slot": 0, "target_id": 15, "target_slot": 5, "type": "FLOAT"}, {"id": 34, "origin_id": 8, "origin_slot": 0, "target_id": 15, "target_slot": 6, "type": "FLOAT"}, {"id": 35, "origin_id": 9, "origin_slot": 0, "target_id": 15, "target_slot": 7, "type": "FLOAT"}, {"id": 36, "origin_id": 10, "origin_slot": 0, "target_id": 15, "target_slot": 8, "type": "FLOAT"}, {"id": 37, "origin_id": 11, "origin_slot": 0, "target_id": 15, "target_slot": 9, "type": "FLOAT"}, {"id": 38, "origin_id": 12, "origin_slot": 0, "target_id": 15, "target_slot": 10, "type": "FLOAT"}, {"id": 39, "origin_id": 13, "origin_slot": 0, "target_id": 15, "target_slot": 11, "type": "BOOLEAN"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}} \ No newline at end of file +{ + "revision": 0, + "last_node_id": 20, + "last_link_id": 0, + "nodes": [ + { + "id": 20, + "type": "243b9e93-7303-4500-8c70-58acb712f5bc", + "pos": [ + 3610, + -2630 + ], + "size": [ + 270, + 420 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "4", + "value" + ], + [ + "5", + "value" + ], + [ + "6", + "value" + ], + [ + "7", + "value" + ], + [ + "8", + "value" + ], + [ + "9", + "value" + ], + [ + "10", + "value" + ], + [ + "11", + "value" + ], + [ + "12", + "value" + ], + [ + "13", + "value" + ] + ] + }, + "widgets_values": [], + "title": "Color Balance" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "243b9e93-7303-4500-8c70-58acb712f5bc", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 15, + "lastLinkId": 39, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Color Balance", + "inputNode": { + "id": -10, + "bounding": [ + 2660, + -4500, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4270, + -4500, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "d24c0b6d-00bd-4e95-be80-8114e8376ec0", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 29 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 2760, + -4480 + ] + } + ], + "outputs": [ + { + "id": "92723f62-996e-496d-ad4f-81a38be4ad64", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 28 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 4290, + -4480 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 4, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -4500 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "shadows red", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 30 + ] + } + ], + "title": "Shadows Red", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 255, + 255 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 5, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -4390 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "shadows green", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 31 + ] + } + ], + "title": "Shadows Green", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 255, + 0, + 255 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 0, + 255, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 6, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -4280 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "shadows blue", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 32 + ] + } + ], + "title": "Shadows Blue", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 255, + 255, + 0 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 0, + 0, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 7, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -4170 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "midtones red", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 33 + ] + } + ], + "title": "Midtones Red", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 255, + 255 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 8, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -4060 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "midtones green", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 34 + ] + } + ], + "title": "Midtones Green", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 255, + 0, + 255 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 0, + 255, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 9, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -3950 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "midtones blue", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 35 + ] + } + ], + "title": "Midtones Blue", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 255, + 255, + 0 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 0, + 0, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 10, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -3840 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "label": "highlights red", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 36 + ] + } + ], + "title": "Highlights Red", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 255, + 255 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 11, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -3730 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "label": "highlights green", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 37 + ] + } + ], + "title": "Highlights Green", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 255, + 0, + 255 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 0, + 255, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 12, + "type": "PrimitiveFloat", + "pos": [ + 3060, + -3620 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "label": "highlights blue", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 38 + ] + } + ], + "title": "Highlights Blue", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": -100, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 255, + 255, + 0 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 0, + 0, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 13, + "type": "PrimitiveBoolean", + "pos": [ + 3060, + -3510 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "label": "preserve luminosity", + "localized_name": "value", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "BOOLEAN", + "name": "BOOLEAN", + "type": "BOOLEAN", + "links": [ + 39 + ] + } + ], + "title": "Preserve Luminosity", + "properties": { + "Node name for S&R": "PrimitiveBoolean" + }, + "widgets_values": [ + true + ] + }, + { + "id": 15, + "type": "GLSLShader", + "pos": [ + 3590, + -4500 + ], + "size": [ + 420, + 500 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 29 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 30 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 31 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": 32 + }, + { + "label": "u_float3", + "localized_name": "floats.u_float3", + "name": "floats.u_float3", + "shape": 7, + "type": "FLOAT", + "link": 33 + }, + { + "label": "u_float4", + "localized_name": "floats.u_float4", + "name": "floats.u_float4", + "shape": 7, + "type": "FLOAT", + "link": 34 + }, + { + "label": "u_float5", + "localized_name": "floats.u_float5", + "name": "floats.u_float5", + "shape": 7, + "type": "FLOAT", + "link": 35 + }, + { + "label": "u_float6", + "localized_name": "floats.u_float6", + "name": "floats.u_float6", + "shape": 7, + "type": "FLOAT", + "link": 36 + }, + { + "label": "u_float7", + "localized_name": "floats.u_float7", + "name": "floats.u_float7", + "shape": 7, + "type": "FLOAT", + "link": 37 + }, + { + "label": "u_float8", + "localized_name": "floats.u_float8", + "name": "floats.u_float8", + "shape": 7, + "type": "FLOAT", + "link": 38 + }, + { + "label": "u_bool0", + "localized_name": "bools.u_bool0", + "name": "bools.u_bool0", + "shape": 7, + "type": "BOOLEAN", + "link": 39 + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 28 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // shadows red (-100 to 100)\nuniform float u_float1; // shadows green (-100 to 100)\nuniform float u_float2; // shadows blue (-100 to 100)\nuniform float u_float3; // midtones red (-100 to 100)\nuniform float u_float4; // midtones green (-100 to 100)\nuniform float u_float5; // midtones blue (-100 to 100)\nuniform float u_float6; // highlights red (-100 to 100)\nuniform float u_float7; // highlights green (-100 to 100)\nuniform float u_float8; // highlights blue (-100 to 100)\nuniform bool u_bool0; // preserve luminosity\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nvec3 rgb2hsl(vec3 c) {\n float maxC = max(c.r, max(c.g, c.b));\n float minC = min(c.r, min(c.g, c.b));\n float l = (maxC + minC) * 0.5;\n if (maxC == minC) return vec3(0.0, 0.0, l);\n float d = maxC - minC;\n float s = l > 0.5 ? d / (2.0 - maxC - minC) : d / (maxC + minC);\n float h;\n if (maxC == c.r) {\n h = (c.g - c.b) / d + (c.g < c.b ? 6.0 : 0.0);\n } else if (maxC == c.g) {\n h = (c.b - c.r) / d + 2.0;\n } else {\n h = (c.r - c.g) / d + 4.0;\n }\n h /= 6.0;\n return vec3(h, s, l);\n}\n\nfloat hue2rgb(float p, float q, float t) {\n if (t < 0.0) t += 1.0;\n if (t > 1.0) t -= 1.0;\n if (t < 1.0 / 6.0) return p + (q - p) * 6.0 * t;\n if (t < 1.0 / 2.0) return q;\n if (t < 2.0 / 3.0) return p + (q - p) * (2.0 / 3.0 - t) * 6.0;\n return p;\n}\n\nvec3 hsl2rgb(vec3 hsl) {\n float h = hsl.x, s = hsl.y, l = hsl.z;\n if (s == 0.0) return vec3(l);\n float q = l < 0.5 ? l * (1.0 + s) : l + s - l * s;\n float p = 2.0 * l - q;\n return vec3(\n hue2rgb(p, q, h + 1.0 / 3.0),\n hue2rgb(p, q, h),\n hue2rgb(p, q, h - 1.0 / 3.0)\n );\n}\n\nvoid main() {\n vec4 tex = texture(u_image0, v_texCoord);\n vec3 color = tex.rgb;\n\n // Build shadows/midtones/highlights vectors (scale -100..100 to -1..1)\n vec3 shadows = vec3(u_float0, u_float1, u_float2) * 0.01;\n vec3 midtones = vec3(u_float3, u_float4, u_float5) * 0.01;\n vec3 highlights = vec3(u_float6, u_float7, u_float8) * 0.01;\n\n // GIMP: HSL lightness for weight calculation\n float maxC = max(color.r, max(color.g, color.b));\n float minC = min(color.r, min(color.g, color.b));\n float lightness = (maxC + minC) * 0.5;\n\n // GIMP weight curves: linear ramps with constants a=0.25, b=0.333, scale=0.7\n const float a = 0.25;\n const float b = 0.333;\n const float scale = 0.7;\n\n float sw = clamp((lightness - b) / -a + 0.5, 0.0, 1.0) * scale;\n float mw = clamp((lightness - b) / a + 0.5, 0.0, 1.0) *\n clamp((lightness + b - 1.0) / -a + 0.5, 0.0, 1.0) * scale;\n float hw = clamp((lightness + b - 1.0) / a + 0.5, 0.0, 1.0) * scale;\n\n color += sw * shadows + mw * midtones + hw * highlights;\n\n if (u_bool0) {\n vec3 hsl = rgb2hsl(clamp(color, 0.0, 1.0));\n hsl.z = lightness;\n color = hsl2rgb(hsl);\n }\n\n fragColor = vec4(clamp(color, 0.0, 1.0), tex.a);\n}", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 29, + "origin_id": -10, + "origin_slot": 0, + "target_id": 15, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 28, + "origin_id": 15, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 30, + "origin_id": 4, + "origin_slot": 0, + "target_id": 15, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 31, + "origin_id": 5, + "origin_slot": 0, + "target_id": 15, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 32, + "origin_id": 6, + "origin_slot": 0, + "target_id": 15, + "target_slot": 4, + "type": "FLOAT" + }, + { + "id": 33, + "origin_id": 7, + "origin_slot": 0, + "target_id": 15, + "target_slot": 5, + "type": "FLOAT" + }, + { + "id": 34, + "origin_id": 8, + "origin_slot": 0, + "target_id": 15, + "target_slot": 6, + "type": "FLOAT" + }, + { + "id": 35, + "origin_id": 9, + "origin_slot": 0, + "target_id": 15, + "target_slot": 7, + "type": "FLOAT" + }, + { + "id": 36, + "origin_id": 10, + "origin_slot": 0, + "target_id": 15, + "target_slot": 8, + "type": "FLOAT" + }, + { + "id": 37, + "origin_id": 11, + "origin_slot": 0, + "target_id": 15, + "target_slot": 9, + "type": "FLOAT" + }, + { + "id": 38, + "origin_id": 12, + "origin_slot": 0, + "target_id": 15, + "target_slot": 10, + "type": "FLOAT" + }, + { + "id": 39, + "origin_id": 13, + "origin_slot": 0, + "target_id": 15, + "target_slot": 11, + "type": "BOOLEAN" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} \ No newline at end of file diff --git a/blueprints/Color Curves.json b/blueprints/Color Curves.json index 933c53978..1461cf396 100644 --- a/blueprints/Color Curves.json +++ b/blueprints/Color Curves.json @@ -1 +1,615 @@ -{"revision": 0,"last_node_id": 10,"last_link_id": 0,"nodes": [{"id": 10,"type": "d5c462c8-1372-4af8-84f2-547c83470d04","pos": [3610,-2630],"size": [270,420],"flags": {},"order": 0,"mode": 0,"inputs": [{"label": "image","localized_name": "images.image0","name": "images.image0","type": "IMAGE","link": null}],"outputs": [{"label": "IMAGE","localized_name": "IMAGE0","name": "IMAGE0","type": "IMAGE","links": []}],"properties": {"proxyWidgets": [["4","curve"],["5","curve"],["6","curve"],["7","curve"]]},"widgets_values": [],"title": "Color Curves"}],"links": [],"version": 0.4,"definitions": {"subgraphs": [{"id": "d5c462c8-1372-4af8-84f2-547c83470d04","version": 1,"state": {"lastGroupId": 0,"lastNodeId": 8,"lastLinkId": 33,"lastRerouteId": 0},"revision": 0,"config": {},"name": "Color Curves","inputNode": {"id": -10,"bounding": [2660,-4500,120,60]},"outputNode": {"id": -20,"bounding": [4270,-4500,120,60]},"inputs": [{"id": "abc345b7-f55e-4f32-a11d-3aa4c2b0936b","name": "images.image0","type": "IMAGE","linkIds": [29],"localized_name": "images.image0","label": "image","pos": [2760,-4480]}],"outputs": [{"id": "eb0ec079-46da-4408-8263-9ef85569d33d","name": "IMAGE0","type": "IMAGE","linkIds": [28],"localized_name": "IMAGE0","label": "IMAGE","pos": [4290,-4480]}],"widgets": [],"nodes": [{"id": 4,"type": "CurveEditor","pos": [3060,-4500],"size": [270,200],"flags": {},"order": 0,"mode": 0,"inputs": [{"label": "curve","localized_name": "curve","name": "curve","type": "CURVE","widget": {"name": "curve"},"link": null},{"label": "histogram","localized_name": "histogram","name": "histogram","type": "HISTOGRAM","shape": 7,"link": null}],"outputs": [{"localized_name": "CURVE","name": "CURVE","type": "CURVE","links": [30]}],"title": "RGB Master","properties": {"Node name for S&R": "CurveEditor"},"widgets_values": []},{"id": 5,"type": "CurveEditor","pos": [3060,-4250],"size": [270,200],"flags": {},"order": 1,"mode": 0,"inputs": [{"label": "curve","localized_name": "curve","name": "curve","type": "CURVE","widget": {"name": "curve"},"link": null},{"label": "histogram","localized_name": "histogram","name": "histogram","type": "HISTOGRAM","shape": 7,"link": null}],"outputs": [{"localized_name": "CURVE","name": "CURVE","type": "CURVE","links": [31]}],"title": "Red","properties": {"Node name for S&R": "CurveEditor"},"widgets_values": []},{"id": 6,"type": "CurveEditor","pos": [3060,-4000],"size": [270,200],"flags": {},"order": 2,"mode": 0,"inputs": [{"label": "curve","localized_name": "curve","name": "curve","type": "CURVE","widget": {"name": "curve"},"link": null},{"label": "histogram","localized_name": "histogram","name": "histogram","type": "HISTOGRAM","shape": 7,"link": null}],"outputs": [{"localized_name": "CURVE","name": "CURVE","type": "CURVE","links": [32]}],"title": "Green","properties": {"Node name for S&R": "CurveEditor"},"widgets_values": []},{"id": 7,"type": "CurveEditor","pos": [3060,-3750],"size": [270,200],"flags": {},"order": 3,"mode": 0,"inputs": [{"label": "curve","localized_name": "curve","name": "curve","type": "CURVE","widget": {"name": "curve"},"link": null},{"label": "histogram","localized_name": "histogram","name": "histogram","type": "HISTOGRAM","shape": 7,"link": null}],"outputs": [{"localized_name": "CURVE","name": "CURVE","type": "CURVE","links": [33]}],"title": "Blue","properties": {"Node name for S&R": "CurveEditor"},"widgets_values": []},{"id": 8,"type": "GLSLShader","pos": [3590,-4500],"size": [420,500],"flags": {},"order": 4,"mode": 0,"inputs": [{"label": "image0","localized_name": "images.image0","name": "images.image0","type": "IMAGE","link": 29},{"label": "image1","localized_name": "images.image1","name": "images.image1","shape": 7,"type": "IMAGE","link": null},{"label": "u_curve0","localized_name": "curves.u_curve0","name": "curves.u_curve0","shape": 7,"type": "CURVE","link": 30},{"label": "u_curve1","localized_name": "curves.u_curve1","name": "curves.u_curve1","shape": 7,"type": "CURVE","link": 31},{"label": "u_curve2","localized_name": "curves.u_curve2","name": "curves.u_curve2","shape": 7,"type": "CURVE","link": 32},{"label": "u_curve3","localized_name": "curves.u_curve3","name": "curves.u_curve3","shape": 7,"type": "CURVE","link": 33},{"localized_name": "fragment_shader","name": "fragment_shader","type": "STRING","widget": {"name": "fragment_shader"},"link": null},{"localized_name": "size_mode","name": "size_mode","type": "COMFY_DYNAMICCOMBO_V3","widget": {"name": "size_mode"},"link": null}],"outputs": [{"localized_name": "IMAGE0","name": "IMAGE0","type": "IMAGE","links": [28]},{"localized_name": "IMAGE1","name": "IMAGE1","type": "IMAGE","links": null},{"localized_name": "IMAGE2","name": "IMAGE2","type": "IMAGE","links": null},{"localized_name": "IMAGE3","name": "IMAGE3","type": "IMAGE","links": null}],"properties": {"Node name for S&R": "GLSLShader"},"widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform sampler2D u_curve0; // RGB master curve (256x1 LUT)\nuniform sampler2D u_curve1; // Red channel curve\nuniform sampler2D u_curve2; // Green channel curve\nuniform sampler2D u_curve3; // Blue channel curve\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\n// GIMP-compatible curve lookup with manual linear interpolation.\n// Matches gimp_curve_map_value_inline() from gimpcurve-map.c:\n// index = value * (n_samples - 1)\n// f = fract(index)\n// result = (1-f) * samples[floor] + f * samples[ceil]\n//\n// Uses texelFetch (NEAREST) to avoid GPU half-texel offset issues\n// that occur with texture() + GL_LINEAR on small 256x1 LUTs.\nfloat applyCurve(sampler2D curve, float value) {\n value = clamp(value, 0.0, 1.0);\n\n float pos = value * 255.0;\n int lo = int(floor(pos));\n int hi = min(lo + 1, 255);\n float f = pos - float(lo);\n\n float a = texelFetch(curve, ivec2(lo, 0), 0).r;\n float b = texelFetch(curve, ivec2(hi, 0), 0).r;\n\n return a + f * (b - a);\n}\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n\n // GIMP order: per-channel curves first, then RGB master curve.\n // See gimp_curve_map_pixels() default case in gimpcurve-map.c:\n // dest = colors_curve( channel_curve( src ) )\n float tmp_r = applyCurve(u_curve1, color.r);\n float tmp_g = applyCurve(u_curve2, color.g);\n float tmp_b = applyCurve(u_curve3, color.b);\n color.r = applyCurve(u_curve0, tmp_r);\n color.g = applyCurve(u_curve0, tmp_g);\n color.b = applyCurve(u_curve0, tmp_b);\n\n fragColor0 = vec4(color.rgb, color.a);\n}\n","from_input"]}],"groups": [],"links": [{"id": 29,"origin_id": -10,"origin_slot": 0,"target_id": 8,"target_slot": 0,"type": "IMAGE"},{"id": 28,"origin_id": 8,"origin_slot": 0,"target_id": -20,"target_slot": 0,"type": "IMAGE"},{"id": 30,"origin_id": 4,"origin_slot": 0,"target_id": 8,"target_slot": 2,"type": "CURVE"},{"id": 31,"origin_id": 5,"origin_slot": 0,"target_id": 8,"target_slot": 3,"type": "CURVE"},{"id": 32,"origin_id": 6,"origin_slot": 0,"target_id": 8,"target_slot": 4,"type": "CURVE"},{"id": 33,"origin_id": 7,"origin_slot": 0,"target_id": 8,"target_slot": 5,"type": "CURVE"}],"extra": {"workflowRendererVersion": "LG"},"category": "Image Tools/Color adjust"}]}} \ No newline at end of file +{ + "revision": 0, + "last_node_id": 10, + "last_link_id": 0, + "nodes": [ + { + "id": 10, + "type": "d5c462c8-1372-4af8-84f2-547c83470d04", + "pos": [ + 3610, + -2630 + ], + "size": [ + 270, + 420 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "4", + "curve" + ], + [ + "5", + "curve" + ], + [ + "6", + "curve" + ], + [ + "7", + "curve" + ] + ] + }, + "widgets_values": [], + "title": "Color Curves" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "d5c462c8-1372-4af8-84f2-547c83470d04", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 9, + "lastLinkId": 38, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Color Curves", + "inputNode": { + "id": -10, + "bounding": [ + 2660, + -4500, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4270, + -4500, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "abc345b7-f55e-4f32-a11d-3aa4c2b0936b", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 29, + 34 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 2760, + -4480 + ] + } + ], + "outputs": [ + { + "id": "eb0ec079-46da-4408-8263-9ef85569d33d", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 28 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 4290, + -4480 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 4, + "type": "CurveEditor", + "pos": [ + 3060, + -4500 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "curve", + "localized_name": "curve", + "name": "curve", + "type": "CURVE", + "widget": { + "name": "curve" + }, + "link": null + }, + { + "label": "histogram", + "localized_name": "histogram", + "name": "histogram", + "type": "HISTOGRAM", + "shape": 7, + "link": 35 + } + ], + "outputs": [ + { + "localized_name": "CURVE", + "name": "CURVE", + "type": "CURVE", + "links": [ + 30 + ] + } + ], + "title": "RGB Master", + "properties": { + "Node name for S&R": "CurveEditor" + }, + "widgets_values": [] + }, + { + "id": 5, + "type": "CurveEditor", + "pos": [ + 3060, + -4250 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "curve", + "localized_name": "curve", + "name": "curve", + "type": "CURVE", + "widget": { + "name": "curve" + }, + "link": null + }, + { + "label": "histogram", + "localized_name": "histogram", + "name": "histogram", + "type": "HISTOGRAM", + "shape": 7, + "link": 36 + } + ], + "outputs": [ + { + "localized_name": "CURVE", + "name": "CURVE", + "type": "CURVE", + "links": [ + 31 + ] + } + ], + "title": "Red", + "properties": { + "Node name for S&R": "CurveEditor" + }, + "widgets_values": [] + }, + { + "id": 6, + "type": "CurveEditor", + "pos": [ + 3060, + -4000 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "curve", + "localized_name": "curve", + "name": "curve", + "type": "CURVE", + "widget": { + "name": "curve" + }, + "link": null + }, + { + "label": "histogram", + "localized_name": "histogram", + "name": "histogram", + "type": "HISTOGRAM", + "shape": 7, + "link": 37 + } + ], + "outputs": [ + { + "localized_name": "CURVE", + "name": "CURVE", + "type": "CURVE", + "links": [ + 32 + ] + } + ], + "title": "Green", + "properties": { + "Node name for S&R": "CurveEditor" + }, + "widgets_values": [] + }, + { + "id": 7, + "type": "CurveEditor", + "pos": [ + 3060, + -3750 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "curve", + "localized_name": "curve", + "name": "curve", + "type": "CURVE", + "widget": { + "name": "curve" + }, + "link": null + }, + { + "label": "histogram", + "localized_name": "histogram", + "name": "histogram", + "type": "HISTOGRAM", + "shape": 7, + "link": 38 + } + ], + "outputs": [ + { + "localized_name": "CURVE", + "name": "CURVE", + "type": "CURVE", + "links": [ + 33 + ] + } + ], + "title": "Blue", + "properties": { + "Node name for S&R": "CurveEditor" + }, + "widgets_values": [] + }, + { + "id": 8, + "type": "GLSLShader", + "pos": [ + 3590, + -4500 + ], + "size": [ + 420, + 500 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 29 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_curve0", + "localized_name": "curves.u_curve0", + "name": "curves.u_curve0", + "shape": 7, + "type": "CURVE", + "link": 30 + }, + { + "label": "u_curve1", + "localized_name": "curves.u_curve1", + "name": "curves.u_curve1", + "shape": 7, + "type": "CURVE", + "link": 31 + }, + { + "label": "u_curve2", + "localized_name": "curves.u_curve2", + "name": "curves.u_curve2", + "shape": 7, + "type": "CURVE", + "link": 32 + }, + { + "label": "u_curve3", + "localized_name": "curves.u_curve3", + "name": "curves.u_curve3", + "shape": 7, + "type": "CURVE", + "link": 33 + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 28 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform sampler2D u_curve0; // RGB master curve (256x1 LUT)\nuniform sampler2D u_curve1; // Red channel curve\nuniform sampler2D u_curve2; // Green channel curve\nuniform sampler2D u_curve3; // Blue channel curve\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\n// GIMP-compatible curve lookup with manual linear interpolation.\n// Matches gimp_curve_map_value_inline() from gimpcurve-map.c:\n// index = value * (n_samples - 1)\n// f = fract(index)\n// result = (1-f) * samples[floor] + f * samples[ceil]\n//\n// Uses texelFetch (NEAREST) to avoid GPU half-texel offset issues\n// that occur with texture() + GL_LINEAR on small 256x1 LUTs.\nfloat applyCurve(sampler2D curve, float value) {\n value = clamp(value, 0.0, 1.0);\n\n float pos = value * 255.0;\n int lo = int(floor(pos));\n int hi = min(lo + 1, 255);\n float f = pos - float(lo);\n\n float a = texelFetch(curve, ivec2(lo, 0), 0).r;\n float b = texelFetch(curve, ivec2(hi, 0), 0).r;\n\n return a + f * (b - a);\n}\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n\n // GIMP order: per-channel curves first, then RGB master curve.\n // See gimp_curve_map_pixels() default case in gimpcurve-map.c:\n // dest = colors_curve( channel_curve( src ) )\n float tmp_r = applyCurve(u_curve1, color.r);\n float tmp_g = applyCurve(u_curve2, color.g);\n float tmp_b = applyCurve(u_curve3, color.b);\n color.r = applyCurve(u_curve0, tmp_r);\n color.g = applyCurve(u_curve0, tmp_g);\n color.b = applyCurve(u_curve0, tmp_b);\n\n fragColor0 = vec4(color.rgb, color.a);\n}\n", + "from_input" + ] + }, + { + "id": 9, + "type": "ImageHistogram", + "pos": [ + 2800, + -4300 + ], + "size": [ + 210, + 150 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 34 + } + ], + "outputs": [ + { + "localized_name": "HISTOGRAM", + "name": "rgb", + "type": "HISTOGRAM", + "links": [ + 35 + ] + }, + { + "localized_name": "HISTOGRAM", + "name": "luminance", + "type": "HISTOGRAM", + "links": [] + }, + { + "localized_name": "HISTOGRAM", + "name": "red", + "type": "HISTOGRAM", + "links": [ + 36 + ] + }, + { + "localized_name": "HISTOGRAM", + "name": "green", + "type": "HISTOGRAM", + "links": [ + 37 + ] + }, + { + "localized_name": "HISTOGRAM", + "name": "blue", + "type": "HISTOGRAM", + "links": [ + 38 + ] + } + ], + "properties": { + "Node name for S&R": "ImageHistogram" + }, + "widgets_values": [] + } + ], + "groups": [], + "links": [ + { + "id": 29, + "origin_id": -10, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 28, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 30, + "origin_id": 4, + "origin_slot": 0, + "target_id": 8, + "target_slot": 2, + "type": "CURVE" + }, + { + "id": 31, + "origin_id": 5, + "origin_slot": 0, + "target_id": 8, + "target_slot": 3, + "type": "CURVE" + }, + { + "id": 32, + "origin_id": 6, + "origin_slot": 0, + "target_id": 8, + "target_slot": 4, + "type": "CURVE" + }, + { + "id": 33, + "origin_id": 7, + "origin_slot": 0, + "target_id": 8, + "target_slot": 5, + "type": "CURVE" + }, + { + "id": 34, + "origin_id": -10, + "origin_slot": 0, + "target_id": 9, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 35, + "origin_id": 9, + "origin_slot": 0, + "target_id": 4, + "target_slot": 1, + "type": "HISTOGRAM" + }, + { + "id": 36, + "origin_id": 9, + "origin_slot": 2, + "target_id": 5, + "target_slot": 1, + "type": "HISTOGRAM" + }, + { + "id": 37, + "origin_id": 9, + "origin_slot": 3, + "target_id": 6, + "target_slot": 1, + "type": "HISTOGRAM" + }, + { + "id": 38, + "origin_id": 9, + "origin_slot": 4, + "target_id": 7, + "target_slot": 1, + "type": "HISTOGRAM" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} \ No newline at end of file diff --git a/blueprints/Crop Images 2x2.json b/blueprints/Crop Images 2x2.json new file mode 100644 index 000000000..2aa42cfc3 --- /dev/null +++ b/blueprints/Crop Images 2x2.json @@ -0,0 +1,1620 @@ +{ + "revision": 0, + "last_node_id": 139, + "last_link_id": 0, + "nodes": [ + { + "id": 135, + "type": "3b5ed000-6ab3-4458-91f7-8d6d366b0b40", + "pos": [ + -2479.9999801712506, + 2019.9999372732784 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "top_left", + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + }, + { + "label": "bottom_left", + "localized_name": "IMAGE_1", + "name": "IMAGE_1", + "type": "IMAGE", + "links": [] + }, + { + "label": "top_right", + "localized_name": "IMAGE_2", + "name": "IMAGE_2", + "type": "IMAGE", + "links": [] + }, + { + "label": "bottom_right", + "localized_name": "IMAGE_3", + "name": "IMAGE_3", + "type": "IMAGE", + "links": [] + }, + { + "label": "images", + "name": "IMAGE_4", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [], + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1" + }, + "widgets_values": [], + "title": "Crop Images 2x2" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "3b5ed000-6ab3-4458-91f7-8d6d366b0b40", + "version": 1, + "state": { + "lastGroupId": 3, + "lastNodeId": 142, + "lastLinkId": 245, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Crop Images 2x2", + "inputNode": { + "id": -10, + "bounding": [ + -10, + 1570, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 2919.9998608196274, + 1435, + 120, + 140 + ] + }, + "inputs": [ + { + "id": "741854dd-bfb1-4700-ba8c-3b9dea59d021", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 2, + 11, + 13, + 30, + 32 + ], + "localized_name": "image", + "pos": [ + 90, + 1590 + ] + } + ], + "outputs": [ + { + "id": "0eaca6d4-679a-433e-9703-bfa6dceacb18", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 41 + ], + "localized_name": "IMAGE", + "label": "top_left", + "pos": [ + 2939.9998608196274, + 1455 + ] + }, + { + "id": "fff5a1ad-3a74-4c87-938c-ee0fff55f840", + "name": "IMAGE_1", + "type": "IMAGE", + "linkIds": [ + 42 + ], + "localized_name": "IMAGE_1", + "label": "bottom_left", + "pos": [ + 2939.9998608196274, + 1475 + ] + }, + { + "id": "08f40978-fb25-4d98-b716-b61e43b16043", + "name": "IMAGE_2", + "type": "IMAGE", + "linkIds": [ + 43 + ], + "localized_name": "IMAGE_2", + "label": "top_right", + "pos": [ + 2939.9998608196274, + 1495 + ] + }, + { + "id": "17b9416f-3369-43c1-b62f-3e31fc2a7e32", + "name": "IMAGE_3", + "type": "IMAGE", + "linkIds": [ + 44 + ], + "localized_name": "IMAGE_3", + "label": "bottom_right", + "pos": [ + 2939.9998608196274, + 1515 + ] + }, + { + "id": "430e2f3b-c617-4549-9daf-3ebf5be423a3", + "name": "IMAGE_4", + "type": "IMAGE", + "linkIds": [ + 240 + ], + "label": "images", + "pos": [ + 2939.9998608196274, + 1535 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 7, + "type": "ComfyMathExpression", + "pos": [ + 740, + 1390 + ], + "size": [ + 370, + 190 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 3 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 4 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 7, + 14, + 28, + 40, + 242 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, int(a/b))" + ] + }, + { + "id": 8, + "type": "GetImageSize", + "pos": [ + 390, + 1450 + ], + "size": [ + 230, + 120 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 2 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 3, + 241 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 5, + 245 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": null + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "GetImageSize" + } + }, + { + "id": 9, + "type": "PrimitiveInt", + "pos": [ + 390, + 1650 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 4, + 6 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveInt" + }, + "widgets_values": [ + 2, + "fixed" + ] + }, + { + "id": 10, + "type": "ImageCropV2", + "pos": [ + 1710, + 430 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 11 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 9 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 41, + 236 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 12, + "type": "PrimitiveBoundingBox", + "pos": [ + 1370, + 570 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": null + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": null + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 7 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 8 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 9 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 0, + 0, + 512, + 512 + ] + }, + { + "id": 13, + "type": "ComfyMathExpression", + "pos": [ + 750, + 1650 + ], + "size": [ + 370, + 190 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 5 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 6 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 8, + 23, + 27, + 39, + 246 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, int(a/b))" + ] + }, + { + "id": 138, + "type": "ComfyMathExpression", + "pos": [ + 1170, + 1210 + ], + "size": [ + 420, + 190 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 241 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 242 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 243, + 244 + ] + } + ], + "title": "Math Expression (Right Width)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, a - b)" + ] + }, + { + "id": 139, + "type": "ComfyMathExpression", + "pos": [ + 1170, + 1860 + ], + "size": [ + 420, + 190 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 245 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 246 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 247, + 248 + ] + } + ], + "title": "Math Expression (Bottom Height)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, a - b)" + ] + }, + { + "id": 15, + "type": "ImageCropV2", + "pos": [ + 1740, + 1600 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 13 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 12 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 42, + 238 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 16, + "type": "PrimitiveBoundingBox", + "pos": [ + 1350, + 1780 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": null + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 23 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 14 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 247 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 12 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 0, + 0, + 512, + 512 + ] + }, + { + "id": 25, + "type": "PrimitiveBoundingBox", + "pos": [ + 1350, + 1200 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 28 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": null + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 243 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 27 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 29 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 26, + "type": "ImageCropV2", + "pos": [ + 1720, + 1050 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 30 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 29 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 43, + 237 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 30, + "type": "ImageCropV2", + "pos": [ + 1740, + 2130 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 32 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 35 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 44, + 239 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 32, + "type": "PrimitiveBoundingBox", + "pos": [ + 1370, + 2280 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 40 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 39 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 244 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 248 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 35 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 137, + "type": "BatchImagesNode", + "pos": [ + 2520, + 1540 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 236 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "type": "IMAGE", + "link": 237 + }, + { + "label": "image2", + "localized_name": "images.image2", + "name": "images.image2", + "shape": 7, + "type": "IMAGE", + "link": 238 + }, + { + "label": "image3", + "localized_name": "images.image3", + "name": "images.image3", + "shape": 7, + "type": "IMAGE", + "link": 239 + }, + { + "label": "image4", + "localized_name": "images.image4", + "name": "images.image4", + "shape": 7, + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 240 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "BatchImagesNode" + } + } + ], + "groups": [ + { + "id": 1, + "title": "Crop Images 2x2", + "bounding": [ + 380, + 360, + 1710, + 2270 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 3, + "origin_id": 8, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "INT" + }, + { + "id": 4, + "origin_id": 9, + "origin_slot": 0, + "target_id": 7, + "target_slot": 1, + "type": "INT" + }, + { + "id": 9, + "origin_id": 12, + "origin_slot": 0, + "target_id": 10, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 7, + "origin_id": 7, + "origin_slot": 1, + "target_id": 12, + "target_slot": 2, + "type": "INT" + }, + { + "id": 8, + "origin_id": 13, + "origin_slot": 1, + "target_id": 12, + "target_slot": 3, + "type": "INT" + }, + { + "id": 5, + "origin_id": 8, + "origin_slot": 1, + "target_id": 13, + "target_slot": 0, + "type": "INT" + }, + { + "id": 6, + "origin_id": 9, + "origin_slot": 0, + "target_id": 13, + "target_slot": 1, + "type": "INT" + }, + { + "id": 12, + "origin_id": 16, + "origin_slot": 0, + "target_id": 15, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 23, + "origin_id": 13, + "origin_slot": 1, + "target_id": 16, + "target_slot": 1, + "type": "INT" + }, + { + "id": 14, + "origin_id": 7, + "origin_slot": 1, + "target_id": 16, + "target_slot": 2, + "type": "INT" + }, + { + "id": 247, + "origin_id": 139, + "origin_slot": 1, + "target_id": 16, + "target_slot": 3, + "type": "INT" + }, + { + "id": 28, + "origin_id": 7, + "origin_slot": 1, + "target_id": 25, + "target_slot": 0, + "type": "INT" + }, + { + "id": 243, + "origin_id": 138, + "origin_slot": 1, + "target_id": 25, + "target_slot": 2, + "type": "INT" + }, + { + "id": 27, + "origin_id": 13, + "origin_slot": 1, + "target_id": 25, + "target_slot": 3, + "type": "INT" + }, + { + "id": 29, + "origin_id": 25, + "origin_slot": 0, + "target_id": 26, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 35, + "origin_id": 32, + "origin_slot": 0, + "target_id": 30, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 40, + "origin_id": 7, + "origin_slot": 1, + "target_id": 32, + "target_slot": 0, + "type": "INT" + }, + { + "id": 39, + "origin_id": 13, + "origin_slot": 1, + "target_id": 32, + "target_slot": 1, + "type": "INT" + }, + { + "id": 244, + "origin_id": 138, + "origin_slot": 1, + "target_id": 32, + "target_slot": 2, + "type": "INT" + }, + { + "id": 248, + "origin_id": 139, + "origin_slot": 1, + "target_id": 32, + "target_slot": 3, + "type": "INT" + }, + { + "id": 241, + "origin_id": 8, + "origin_slot": 0, + "target_id": 138, + "target_slot": 0, + "type": "INT" + }, + { + "id": 242, + "origin_id": 7, + "origin_slot": 1, + "target_id": 138, + "target_slot": 1, + "type": "INT" + }, + { + "id": 245, + "origin_id": 8, + "origin_slot": 1, + "target_id": 139, + "target_slot": 0, + "type": "INT" + }, + { + "id": 246, + "origin_id": 13, + "origin_slot": 1, + "target_id": 139, + "target_slot": 1, + "type": "INT" + }, + { + "id": 2, + "origin_id": -10, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 11, + "origin_id": -10, + "origin_slot": 0, + "target_id": 10, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 13, + "origin_id": -10, + "origin_slot": 0, + "target_id": 15, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 30, + "origin_id": -10, + "origin_slot": 0, + "target_id": 26, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 32, + "origin_id": -10, + "origin_slot": 0, + "target_id": 30, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 41, + "origin_id": 10, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 42, + "origin_id": 15, + "origin_slot": 0, + "target_id": -20, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 43, + "origin_id": 26, + "origin_slot": 0, + "target_id": -20, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 44, + "origin_id": 30, + "origin_slot": 0, + "target_id": -20, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 236, + "origin_id": 10, + "origin_slot": 0, + "target_id": 137, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 237, + "origin_id": 26, + "origin_slot": 0, + "target_id": 137, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 238, + "origin_id": 15, + "origin_slot": 0, + "target_id": 137, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 239, + "origin_id": 30, + "origin_slot": 0, + "target_id": 137, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 240, + "origin_id": 137, + "origin_slot": 0, + "target_id": -20, + "target_slot": 4, + "type": "IMAGE" + } + ], + "extra": {}, + "category": "Image Tools/Crop" + } + ] + }, + "extra": { + "ue_links": [], + "links_added_by_ue": [] + } +} \ No newline at end of file diff --git a/blueprints/Crop Images 3x3.json b/blueprints/Crop Images 3x3.json new file mode 100644 index 000000000..3a3615ac8 --- /dev/null +++ b/blueprints/Crop Images 3x3.json @@ -0,0 +1,2957 @@ +{ + "revision": 0, + "last_node_id": 141, + "last_link_id": 0, + "nodes": [ + { + "id": 134, + "type": "7fd47bca-ff89-476c-a98d-ca6f7cf756fe", + "pos": [ + -2620, + 1620 + ], + "size": [ + 230, + 290 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "top_left", + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + }, + { + "label": "top_center", + "name": "IMAGE_1", + "type": "IMAGE", + "links": [] + }, + { + "label": "top_right", + "name": "IMAGE_2", + "type": "IMAGE", + "links": [] + }, + { + "label": "middle_left", + "name": "IMAGE_3", + "type": "IMAGE", + "links": [] + }, + { + "label": "middle_center", + "name": "IMAGE_4", + "type": "IMAGE", + "links": [] + }, + { + "label": "middle_right", + "name": "IMAGE_5", + "type": "IMAGE", + "links": [] + }, + { + "label": "bottom_left", + "name": "IMAGE_6", + "type": "IMAGE", + "links": [] + }, + { + "label": "bottom_center", + "name": "IMAGE_7", + "type": "IMAGE", + "links": [] + }, + { + "label": "bottom_right", + "name": "IMAGE_8", + "type": "IMAGE", + "links": [] + }, + { + "label": "images", + "name": "IMAGE_9", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [], + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1" + }, + "widgets_values": [], + "title": "Crop Images 3x3" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "7fd47bca-ff89-476c-a98d-ca6f7cf756fe", + "version": 1, + "state": { + "lastGroupId": 3, + "lastNodeId": 142, + "lastLinkId": 245, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Crop Images 3x3", + "inputNode": { + "id": -10, + "bounding": [ + -710, + 5440, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 3430, + 5270, + 121.720703125, + 240 + ] + }, + "inputs": [ + { + "id": "e54e8e8b-6ce6-4f80-a38f-87a77d990efc", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 74, + 75, + 82, + 91, + 94, + 117, + 129, + 137, + 148, + 157 + ], + "localized_name": "image", + "pos": [ + -610, + 5460 + ] + } + ], + "outputs": [ + { + "id": "3dd8abe2-a7da-4052-a556-9ae157ff3cf4", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 101 + ], + "localized_name": "IMAGE", + "label": "top_left", + "pos": [ + 3450, + 5290 + ] + }, + { + "id": "aa220733-759b-474e-9d29-634a3a23c5da", + "name": "IMAGE_1", + "type": "IMAGE", + "linkIds": [ + 192 + ], + "label": "top_center", + "pos": [ + 3450, + 5310 + ] + }, + { + "id": "f1911df1-d50c-4bf8-9623-5e581d2a8902", + "name": "IMAGE_2", + "type": "IMAGE", + "linkIds": [ + 193 + ], + "label": "top_right", + "pos": [ + 3450, + 5330 + ] + }, + { + "id": "71ebb807-e7e9-438f-990d-511e0745d10d", + "name": "IMAGE_3", + "type": "IMAGE", + "linkIds": [ + 194 + ], + "label": "middle_left", + "pos": [ + 3450, + 5350 + ] + }, + { + "id": "4fb9c99c-3340-4de5-ba2d-51a653aab0b3", + "name": "IMAGE_4", + "type": "IMAGE", + "linkIds": [ + 195 + ], + "label": "middle_center", + "pos": [ + 3450, + 5370 + ] + }, + { + "id": "398643e8-e349-4d59-9c68-6403b7a2772d", + "name": "IMAGE_5", + "type": "IMAGE", + "linkIds": [ + 196 + ], + "label": "middle_right", + "pos": [ + 3450, + 5390 + ] + }, + { + "id": "5b11949c-f4cc-4525-86ae-690e30d3dada", + "name": "IMAGE_6", + "type": "IMAGE", + "linkIds": [ + 197 + ], + "label": "bottom_left", + "pos": [ + 3450, + 5410 + ] + }, + { + "id": "82c69fd9-de36-4c8f-8311-a9e49159640b", + "name": "IMAGE_7", + "type": "IMAGE", + "linkIds": [ + 198 + ], + "label": "bottom_center", + "pos": [ + 3450, + 5430 + ] + }, + { + "id": "aef678db-20aa-47d4-be8a-978065f078c6", + "name": "IMAGE_8", + "type": "IMAGE", + "linkIds": [ + 199 + ], + "label": "bottom_right", + "pos": [ + 3450, + 5450 + ] + }, + { + "id": "77574277-edde-439c-8720-7daa849f4f27", + "name": "IMAGE_9", + "type": "IMAGE", + "linkIds": [ + 226 + ], + "label": "images", + "pos": [ + 3450, + 5470 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 50, + "type": "ComfyMathExpression", + "pos": [ + 770, + 5310 + ], + "size": [ + 370, + 190 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 73 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 108 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 77, + 85, + 89, + 97, + 99, + 127, + 142, + 146, + 152, + 300 + ] + } + ], + "title": "Math Expression （Width）", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, int(a/b))" + ] + }, + { + "id": 51, + "type": "GetImageSize", + "pos": [ + 440, + 5390 + ], + "size": [ + 230, + 120 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 74 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 73, + 300 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 79, + 305 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": null + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "GetImageSize" + } + }, + { + "id": 52, + "type": "PrimitiveInt", + "pos": [ + 440, + 5590 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 80, + 108 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveInt" + }, + "widgets_values": [ + 3, + "fixed" + ] + }, + { + "id": 53, + "type": "ImageCropV2", + "pos": [ + 2080, + 3020 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 75 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 76 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 101, + 227 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 54, + "type": "PrimitiveBoundingBox", + "pos": [ + 1740, + 3160 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": null + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": null + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 77 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 78 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 76 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 0, + 0, + 512, + 512 + ] + }, + { + "id": 55, + "type": "ComfyMathExpression", + "pos": [ + 780, + 5570 + ], + "size": [ + 370, + 190 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 79 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 80 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 78, + 84, + 86, + 88, + 90, + 98, + 100, + 121, + 123, + 126, + 161 + ] + } + ], + "title": "Math Expression(Height)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, int(a/b))" + ] + }, + { + "id": 57, + "type": "ImageCropV2", + "pos": [ + 2080, + 4700 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 82 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 83 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 194, + 230 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 58, + "type": "PrimitiveBoundingBox", + "pos": [ + 1740, + 4830 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": null + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 84 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 85 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 86 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 83 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 0, + 0, + 512, + 512 + ] + }, + { + "id": 60, + "type": "PrimitiveBoundingBox", + "pos": [ + 1740, + 3700 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 88 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": null + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 89 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 90 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 92 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 61, + "type": "ImageCropV2", + "pos": [ + 2100, + 3570 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 91 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 92 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 192, + 228 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 63, + "type": "ImageCropV2", + "pos": [ + 2080, + 5310 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 94 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 95 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 195, + 231 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 65, + "type": "PrimitiveBoundingBox", + "pos": [ + 1750, + 5330 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 97 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 98 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 99 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 100 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 95 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 71, + "type": "ComfyMathExpression", + "pos": [ + 780, + 6090 + ], + "size": [ + 400, + 190 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 126 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 136, + 147, + 156, + 306 + ] + } + ], + "title": "Math Expression(height)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "2 * a" + ] + }, + { + "id": 75, + "type": "ImageCropV2", + "pos": [ + 2100, + 5900 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 117 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 118 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 196, + 232 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 77, + "type": "PrimitiveBoundingBox", + "pos": [ + 1750, + 5970 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 128 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 121 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 302 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 123 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 118 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 78, + "type": "ComfyMathExpression", + "pos": [ + 780, + 5820 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 127 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 128, + 132, + 163, + 301 + ] + } + ], + "title": "Math Expression(width)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "2 * a" + ] + }, + { + "id": 140, + "type": "ComfyMathExpression", + "pos": [ + 1240, + 5640 + ], + "size": [ + 420, + 190 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 300 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 301 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 302, + 303, + 304 + ] + } + ], + "title": "Math Expression (Right Width)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, a - b)" + ] + }, + { + "id": 141, + "type": "ComfyMathExpression", + "pos": [ + 1230, + 6340 + ], + "size": [ + 420, + 190 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 305 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 306 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 307, + 308, + 309 + ] + } + ], + "title": "Math Expression (Bottom Height)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "max(1, a - b)" + ] + }, + { + "id": 79, + "type": "ImageCropV2", + "pos": [ + 2120, + 7580 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 129 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 130 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 199, + 235 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 81, + "type": "PrimitiveBoundingBox", + "pos": [ + 1720, + 7620 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 132 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 136 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 303 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 307 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 130 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 82, + "type": "ImageCropV2", + "pos": [ + 2120, + 7040 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 137 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 138 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 198, + 234 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 84, + "type": "PrimitiveBoundingBox", + "pos": [ + 1720, + 7080 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 146 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 147 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 142 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 308 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 138 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 85, + "type": "ImageCropV2", + "pos": [ + 2110, + 6480 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 148 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 149 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 197, + 233 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 86, + "type": "PrimitiveBoundingBox", + "pos": [ + 1670, + 6570 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": null + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": 156 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 152 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 309 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 149 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 0, + 0, + 512, + 512 + ] + }, + { + "id": 88, + "type": "ImageCropV2", + "pos": [ + 2060, + 4140 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 157 + }, + { + "localized_name": "crop_region", + "name": "crop_region", + "type": "BOUNDING_BOX", + "widget": { + "name": "crop_region" + }, + "link": 158 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 193, + 229 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ImageCropV2" + }, + "widgets_values": [ + { + "x": 0, + "y": 0, + "width": 512, + "height": 512 + }, + 0, + 0, + 512, + 512 + ] + }, + { + "id": 89, + "type": "PrimitiveBoundingBox", + "pos": [ + 1720, + 4150 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": 163 + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": null + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 304 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 161 + } + ], + "outputs": [ + { + "localized_name": "BOUNDING_BOX", + "name": "BOUNDING_BOX", + "type": "BOUNDING_BOX", + "links": [ + 158 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "PrimitiveBoundingBox" + }, + "widgets_values": [ + 6, + 0, + 512, + 512 + ] + }, + { + "id": 136, + "type": "BatchImagesNode", + "pos": [ + 3170, + 5640 + ], + "size": [ + 230, + 290 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 227 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "type": "IMAGE", + "link": 228 + }, + { + "label": "image2", + "localized_name": "images.image2", + "name": "images.image2", + "shape": 7, + "type": "IMAGE", + "link": 229 + }, + { + "label": "image3", + "localized_name": "images.image3", + "name": "images.image3", + "shape": 7, + "type": "IMAGE", + "link": 230 + }, + { + "label": "image4", + "localized_name": "images.image4", + "name": "images.image4", + "shape": 7, + "type": "IMAGE", + "link": 231 + }, + { + "label": "image5", + "localized_name": "images.image5", + "name": "images.image5", + "shape": 7, + "type": "IMAGE", + "link": 232 + }, + { + "label": "image6", + "localized_name": "images.image6", + "name": "images.image6", + "shape": 7, + "type": "IMAGE", + "link": 233 + }, + { + "label": "image7", + "localized_name": "images.image7", + "name": "images.image7", + "shape": 7, + "type": "IMAGE", + "link": 234 + }, + { + "label": "image8", + "localized_name": "images.image8", + "name": "images.image8", + "shape": 7, + "type": "IMAGE", + "link": 235 + }, + { + "label": "image9", + "localized_name": "images.image9", + "name": "images.image9", + "shape": 7, + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 226 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "BatchImagesNode" + } + } + ], + "groups": [ + { + "id": 3, + "title": "Crop Images 3x3", + "bounding": [ + 100, + 2700, + 2640, + 5480 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 73, + "origin_id": 51, + "origin_slot": 0, + "target_id": 50, + "target_slot": 0, + "type": "INT" + }, + { + "id": 108, + "origin_id": 52, + "origin_slot": 0, + "target_id": 50, + "target_slot": 1, + "type": "INT" + }, + { + "id": 76, + "origin_id": 54, + "origin_slot": 0, + "target_id": 53, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 77, + "origin_id": 50, + "origin_slot": 1, + "target_id": 54, + "target_slot": 2, + "type": "INT" + }, + { + "id": 78, + "origin_id": 55, + "origin_slot": 1, + "target_id": 54, + "target_slot": 3, + "type": "INT" + }, + { + "id": 79, + "origin_id": 51, + "origin_slot": 1, + "target_id": 55, + "target_slot": 0, + "type": "INT" + }, + { + "id": 80, + "origin_id": 52, + "origin_slot": 0, + "target_id": 55, + "target_slot": 1, + "type": "INT" + }, + { + "id": 83, + "origin_id": 58, + "origin_slot": 0, + "target_id": 57, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 84, + "origin_id": 55, + "origin_slot": 1, + "target_id": 58, + "target_slot": 1, + "type": "INT" + }, + { + "id": 85, + "origin_id": 50, + "origin_slot": 1, + "target_id": 58, + "target_slot": 2, + "type": "INT" + }, + { + "id": 86, + "origin_id": 55, + "origin_slot": 1, + "target_id": 58, + "target_slot": 3, + "type": "INT" + }, + { + "id": 88, + "origin_id": 50, + "origin_slot": 1, + "target_id": 60, + "target_slot": 0, + "type": "INT" + }, + { + "id": 89, + "origin_id": 50, + "origin_slot": 1, + "target_id": 60, + "target_slot": 2, + "type": "INT" + }, + { + "id": 90, + "origin_id": 55, + "origin_slot": 1, + "target_id": 60, + "target_slot": 3, + "type": "INT" + }, + { + "id": 92, + "origin_id": 60, + "origin_slot": 0, + "target_id": 61, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 95, + "origin_id": 65, + "origin_slot": 0, + "target_id": 63, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 97, + "origin_id": 50, + "origin_slot": 1, + "target_id": 65, + "target_slot": 0, + "type": "INT" + }, + { + "id": 98, + "origin_id": 55, + "origin_slot": 1, + "target_id": 65, + "target_slot": 1, + "type": "INT" + }, + { + "id": 99, + "origin_id": 50, + "origin_slot": 1, + "target_id": 65, + "target_slot": 2, + "type": "INT" + }, + { + "id": 100, + "origin_id": 55, + "origin_slot": 1, + "target_id": 65, + "target_slot": 3, + "type": "INT" + }, + { + "id": 126, + "origin_id": 55, + "origin_slot": 1, + "target_id": 71, + "target_slot": 0, + "type": "INT" + }, + { + "id": 118, + "origin_id": 77, + "origin_slot": 0, + "target_id": 75, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 128, + "origin_id": 78, + "origin_slot": 1, + "target_id": 77, + "target_slot": 0, + "type": "INT" + }, + { + "id": 121, + "origin_id": 55, + "origin_slot": 1, + "target_id": 77, + "target_slot": 1, + "type": "INT" + }, + { + "id": 302, + "origin_id": 140, + "origin_slot": 1, + "target_id": 77, + "target_slot": 2, + "type": "INT" + }, + { + "id": 123, + "origin_id": 55, + "origin_slot": 1, + "target_id": 77, + "target_slot": 3, + "type": "INT" + }, + { + "id": 127, + "origin_id": 50, + "origin_slot": 1, + "target_id": 78, + "target_slot": 0, + "type": "INT" + }, + { + "id": 130, + "origin_id": 81, + "origin_slot": 0, + "target_id": 79, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 132, + "origin_id": 78, + "origin_slot": 1, + "target_id": 81, + "target_slot": 0, + "type": "INT" + }, + { + "id": 136, + "origin_id": 71, + "origin_slot": 1, + "target_id": 81, + "target_slot": 1, + "type": "INT" + }, + { + "id": 303, + "origin_id": 140, + "origin_slot": 1, + "target_id": 81, + "target_slot": 2, + "type": "INT" + }, + { + "id": 307, + "origin_id": 141, + "origin_slot": 1, + "target_id": 81, + "target_slot": 3, + "type": "INT" + }, + { + "id": 138, + "origin_id": 84, + "origin_slot": 0, + "target_id": 82, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 146, + "origin_id": 50, + "origin_slot": 1, + "target_id": 84, + "target_slot": 0, + "type": "INT" + }, + { + "id": 147, + "origin_id": 71, + "origin_slot": 1, + "target_id": 84, + "target_slot": 1, + "type": "INT" + }, + { + "id": 142, + "origin_id": 50, + "origin_slot": 1, + "target_id": 84, + "target_slot": 2, + "type": "INT" + }, + { + "id": 308, + "origin_id": 141, + "origin_slot": 1, + "target_id": 84, + "target_slot": 3, + "type": "INT" + }, + { + "id": 149, + "origin_id": 86, + "origin_slot": 0, + "target_id": 85, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 156, + "origin_id": 71, + "origin_slot": 1, + "target_id": 86, + "target_slot": 1, + "type": "INT" + }, + { + "id": 152, + "origin_id": 50, + "origin_slot": 1, + "target_id": 86, + "target_slot": 2, + "type": "INT" + }, + { + "id": 309, + "origin_id": 141, + "origin_slot": 1, + "target_id": 86, + "target_slot": 3, + "type": "INT" + }, + { + "id": 158, + "origin_id": 89, + "origin_slot": 0, + "target_id": 88, + "target_slot": 1, + "type": "BOUNDING_BOX" + }, + { + "id": 163, + "origin_id": 78, + "origin_slot": 1, + "target_id": 89, + "target_slot": 0, + "type": "INT" + }, + { + "id": 304, + "origin_id": 140, + "origin_slot": 1, + "target_id": 89, + "target_slot": 2, + "type": "INT" + }, + { + "id": 161, + "origin_id": 55, + "origin_slot": 1, + "target_id": 89, + "target_slot": 3, + "type": "INT" + }, + { + "id": 300, + "origin_id": 51, + "origin_slot": 0, + "target_id": 140, + "target_slot": 0, + "type": "INT" + }, + { + "id": 301, + "origin_id": 78, + "origin_slot": 1, + "target_id": 140, + "target_slot": 1, + "type": "INT" + }, + { + "id": 305, + "origin_id": 51, + "origin_slot": 1, + "target_id": 141, + "target_slot": 0, + "type": "INT" + }, + { + "id": 306, + "origin_id": 71, + "origin_slot": 1, + "target_id": 141, + "target_slot": 1, + "type": "INT" + }, + { + "id": 74, + "origin_id": -10, + "origin_slot": 0, + "target_id": 51, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 75, + "origin_id": -10, + "origin_slot": 0, + "target_id": 53, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 82, + "origin_id": -10, + "origin_slot": 0, + "target_id": 57, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 91, + "origin_id": -10, + "origin_slot": 0, + "target_id": 61, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 94, + "origin_id": -10, + "origin_slot": 0, + "target_id": 63, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 117, + "origin_id": -10, + "origin_slot": 0, + "target_id": 75, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 129, + "origin_id": -10, + "origin_slot": 0, + "target_id": 79, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 137, + "origin_id": -10, + "origin_slot": 0, + "target_id": 82, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 148, + "origin_id": -10, + "origin_slot": 0, + "target_id": 85, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 157, + "origin_id": -10, + "origin_slot": 0, + "target_id": 88, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 101, + "origin_id": 53, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 192, + "origin_id": 61, + "origin_slot": 0, + "target_id": -20, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 193, + "origin_id": 88, + "origin_slot": 0, + "target_id": -20, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 194, + "origin_id": 57, + "origin_slot": 0, + "target_id": -20, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 195, + "origin_id": 63, + "origin_slot": 0, + "target_id": -20, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 196, + "origin_id": 75, + "origin_slot": 0, + "target_id": -20, + "target_slot": 5, + "type": "IMAGE" + }, + { + "id": 197, + "origin_id": 85, + "origin_slot": 0, + "target_id": -20, + "target_slot": 6, + "type": "IMAGE" + }, + { + "id": 198, + "origin_id": 82, + "origin_slot": 0, + "target_id": -20, + "target_slot": 7, + "type": "IMAGE" + }, + { + "id": 199, + "origin_id": 79, + "origin_slot": 0, + "target_id": -20, + "target_slot": 8, + "type": "IMAGE" + }, + { + "id": 226, + "origin_id": 136, + "origin_slot": 0, + "target_id": -20, + "target_slot": 9, + "type": "IMAGE" + }, + { + "id": 227, + "origin_id": 53, + "origin_slot": 0, + "target_id": 136, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 228, + "origin_id": 61, + "origin_slot": 0, + "target_id": 136, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 229, + "origin_id": 88, + "origin_slot": 0, + "target_id": 136, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 230, + "origin_id": 57, + "origin_slot": 0, + "target_id": 136, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 231, + "origin_id": 63, + "origin_slot": 0, + "target_id": 136, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 232, + "origin_id": 75, + "origin_slot": 0, + "target_id": 136, + "target_slot": 5, + "type": "IMAGE" + }, + { + "id": 233, + "origin_id": 85, + "origin_slot": 0, + "target_id": 136, + "target_slot": 6, + "type": "IMAGE" + }, + { + "id": 234, + "origin_id": 82, + "origin_slot": 0, + "target_id": 136, + "target_slot": 7, + "type": "IMAGE" + }, + { + "id": 235, + "origin_id": 79, + "origin_slot": 0, + "target_id": 136, + "target_slot": 8, + "type": "IMAGE" + } + ], + "extra": {}, + "category": "Image Tools/Crop" + } + ] + }, + "extra": { + "ue_links": [], + "links_added_by_ue": [] + } +} \ No newline at end of file diff --git a/blueprints/Depth to Image (Z-Image-Turbo).json b/blueprints/Depth to Image (Z-Image-Turbo).json index baffc4fc9..4f69a8149 100644 --- a/blueprints/Depth to Image (Z-Image-Turbo).json +++ b/blueprints/Depth to Image (Z-Image-Turbo).json @@ -1 +1,2485 @@ -{"id": "e046dd74-e2a7-4f31-a75b-5e11a8c72d4e", "revision": 0, "last_node_id": 76, "last_link_id": 259, "nodes": [{"id": 13, "type": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", "pos": [400, 3630], "size": [400, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "control image", "name": "image", "type": "IMAGE", "link": null}, {"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}, {"name": "name", "type": "COMBO", "widget": {"name": "name"}, "link": null}, {"label": "lotus_model", "name": "unet_name_1", "type": "COMBO", "widget": {"name": "unet_name_1"}, "link": null}, {"label": "sd15_vae", "name": "vae_name_1", "type": "COMBO", "widget": {"name": "vae_name_1"}, "link": null}], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": null}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"], ["-1", "name"], ["-1", "unet_name_1"], ["-1", "vae_name_1"], ["7", "control_after_generate"], ["7", "seed"]], "cnr_id": "comfy-core", "ver": "0.11.0"}, "widgets_values": ["", "z_image_turbo_bf16.safetensors", "qwen_3_4b.safetensors", "ae.safetensors", "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", "lotus-depth-d-v1-1.safetensors", "vae-ft-mse-840000-ema-pruned.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", "version": 1, "state": {"lastGroupId": 3, "lastNodeId": 76, "lastLinkId": 259, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Depth to Image (Z-Image-Turbo)", "inputNode": {"id": -10, "bounding": [27.60368520069494, 4936.043696127976, 120, 200]}, "outputNode": {"id": -20, "bounding": [1598.6038576146689, 4936.043696127976, 120, 60]}, "inputs": [{"id": "29ca271b-8f63-4e7b-a4b8-c9b4192ada0b", "name": "image", "type": "IMAGE", "linkIds": [25], "label": "control image", "pos": [127.60368520069494, 4956.043696127976]}, {"id": "b6549f90-39ee-4b79-9e00-af4d9df969fe", "name": "text", "type": "STRING", "linkIds": [16], "label": "prompt", "pos": [127.60368520069494, 4976.043696127976]}, {"id": "add4a703-1185-4848-9494-b27dd37ff434", "name": "unet_name", "type": "COMBO", "linkIds": [252], "pos": [127.60368520069494, 4996.043696127976]}, {"id": "03233f9e-df65-4e05-b5c5-34d83129e85e", "name": "clip_name", "type": "COMBO", "linkIds": [253], "pos": [127.60368520069494, 5016.043696127976]}, {"id": "0c643ffb-326d-40ca-8a89-ebc585cf5015", "name": "vae_name", "type": "COMBO", "linkIds": [254], "pos": [127.60368520069494, 5036.043696127976]}, {"id": "409cdebe-632b-410f-a66c-711c2a1527e1", "name": "name", "type": "COMBO", "linkIds": [255], "pos": [127.60368520069494, 5056.043696127976]}, {"id": "80e6915f-5d59-4d6b-a197-d8c565ad2922", "name": "unet_name_1", "type": "COMBO", "linkIds": [258], "label": "lotus_model", "pos": [127.60368520069494, 5076.043696127976]}, {"id": "4207ec84-4409-4816-8444-76062bf6310c", "name": "vae_name_1", "type": "COMBO", "linkIds": [259], "label": "sd15_vae", "pos": [127.60368520069494, 5096.043696127976]}], "outputs": [{"id": "47f9a22d-6619-4917-9447-a7d5d08dceb5", "name": "IMAGE", "type": "IMAGE", "linkIds": [18], "pos": [1618.6038576146689, 4956.043696127976]}], "widgets": [], "nodes": [{"id": 1, "type": "CLIPLoader", "pos": [228.60381716506714, 4700.188262345759], "size": [269.9479166666667, 106], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 253}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [14]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_3_4b.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_3_4b.safetensors", "lumina2", "default"]}, {"id": 2, "type": "UNETLoader", "pos": [228.60381716506714, 4550.188402733727], "size": [269.9479166666667, 82], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 252}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [9]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "UNETLoader", "models": [{"name": "z_image_turbo_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["z_image_turbo_bf16.safetensors", "default"]}, {"id": 3, "type": "VAELoader", "pos": [228.60381716506714, 4880.188283008492], "size": [269.9479166666667, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 254}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [2, 11]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "VAELoader", "models": [{"name": "ae.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ae.safetensors"]}, {"id": 4, "type": "ModelPatchLoader", "pos": [228.60381716506714, 5010.1883654774], "size": [269.9479166666667, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "name", "name": "name", "type": "COMBO", "widget": {"name": "name"}, "link": 255}], "outputs": [{"localized_name": "MODEL_PATCH", "name": "MODEL_PATCH", "type": "MODEL_PATCH", "links": [10]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "ModelPatchLoader", "models": [{"name": "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", "url": "https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union/resolve/main/Z-Image-Turbo-Fun-Controlnet-Union.safetensors", "directory": "model_patches"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["Z-Image-Turbo-Fun-Controlnet-Union.safetensors"]}, {"id": 6, "type": "ModelSamplingAuraFlow", "pos": [998.6041081931173, 4490.1880693746825], "size": [289.97395833333337, 58], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 3}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [4]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "ModelSamplingAuraFlow", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 7, "type": "KSampler", "pos": [998.6041081931173, 4600.188363442829], "size": [300, 262], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 4}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 5}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 6}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 7}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [1]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize", 9, 1, "res_multistep", "simple", 1]}, {"id": 8, "type": "ConditioningZeroOut", "pos": [748.2706508086186, 5044.854997097082], "size": [204.134765625, 26], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 8}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [6]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "ConditioningZeroOut", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 10, "type": "EmptySD3LatentImage", "pos": [1028.2702326451792, 5334.855683329977], "size": [259.9479166666667, 106], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 12}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 13}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [7]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "EmptySD3LatentImage", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1024, 1024, 1]}, {"id": 5, "type": "VAEDecode", "pos": [1338.604012131086, 4500.188453282262], "size": [200, 46], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 1}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 2}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [18]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 9, "type": "QwenImageDiffsynthControlnet", "pos": [608.2704996459613, 5204.85528564724], "size": [289.97395833333337, 138], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 9}, {"localized_name": "model_patch", "name": "model_patch", "type": "MODEL_PATCH", "link": 10}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 11}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 248}, {"localized_name": "mask", "name": "mask", "shape": 7, "type": "MASK", "link": null}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [3]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.76", "Node name for S&R": "QwenImageDiffsynthControlnet", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 11, "type": "GetImageSize", "pos": [530, 5440], "size": [140, 66], "flags": {"collapsed": false}, "order": 10, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 247}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [12]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [13]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": null}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.76", "Node name for S&R": "GetImageSize", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 12, "type": "CLIPTextEncode", "pos": [548.2706278500244, 4544.854827124228], "size": [400, 420], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 14}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 16}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [5, 8]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 14, "type": "ImageScaleToTotalPixels", "pos": [90, 5180], "size": [270, 106], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 25}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "megapixels", "name": "megapixels", "type": "FLOAT", "widget": {"name": "megapixels"}, "link": null}, {"localized_name": "resolution_steps", "name": "resolution_steps", "type": "INT", "widget": {"name": "resolution_steps"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [248, 250]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "ImageScaleToTotalPixels"}, "widgets_values": ["lanczos", 1, 1]}, {"id": 15, "type": "PreviewImage", "pos": [90, 5530], "size": [380, 260], "flags": {}, "order": 13, "mode": 4, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 251}], "outputs": [], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "PreviewImage"}, "widgets_values": []}, {"id": 76, "type": "458bdf3c-4b58-421c-af50-c9c663a4d74c", "pos": [90, 5340], "size": [400, 150], "flags": {}, "order": 14, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 250}, {"label": "depth_intensity", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 258}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 259}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [247, 251]}], "properties": {"proxyWidgets": [["-1", "sigma"], ["-1", "unet_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": [999.0000000000002, "lotus-depth-d-v1-1.safetensors", "vae-ft-mse-840000-ema-pruned.safetensors"]}], "groups": [{"id": 1, "title": "Prompt", "bounding": [530, 4470, 440, 630], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Models", "bounding": [210, 4470, 300, 640], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Apple ControlNet", "bounding": [530, 5120, 440, 260], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 1, "origin_id": 7, "origin_slot": 0, "target_id": 5, "target_slot": 0, "type": "LATENT"}, {"id": 2, "origin_id": 3, "origin_slot": 0, "target_id": 5, "target_slot": 1, "type": "VAE"}, {"id": 3, "origin_id": 9, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "MODEL"}, {"id": 4, "origin_id": 6, "origin_slot": 0, "target_id": 7, "target_slot": 0, "type": "MODEL"}, {"id": 5, "origin_id": 12, "origin_slot": 0, "target_id": 7, "target_slot": 1, "type": "CONDITIONING"}, {"id": 6, "origin_id": 8, "origin_slot": 0, "target_id": 7, "target_slot": 2, "type": "CONDITIONING"}, {"id": 7, "origin_id": 10, "origin_slot": 0, "target_id": 7, "target_slot": 3, "type": "LATENT"}, {"id": 8, "origin_id": 12, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "CONDITIONING"}, {"id": 9, "origin_id": 2, "origin_slot": 0, "target_id": 9, "target_slot": 0, "type": "MODEL"}, {"id": 10, "origin_id": 4, "origin_slot": 0, "target_id": 9, "target_slot": 1, "type": "MODEL_PATCH"}, {"id": 11, "origin_id": 3, "origin_slot": 0, "target_id": 9, "target_slot": 2, "type": "VAE"}, {"id": 12, "origin_id": 11, "origin_slot": 0, "target_id": 10, "target_slot": 0, "type": "INT"}, {"id": 13, "origin_id": 11, "origin_slot": 1, "target_id": 10, "target_slot": 1, "type": "INT"}, {"id": 14, "origin_id": 1, "origin_slot": 0, "target_id": 12, "target_slot": 0, "type": "CLIP"}, {"id": 16, "origin_id": -10, "origin_slot": 1, "target_id": 12, "target_slot": 1, "type": "STRING"}, {"id": 18, "origin_id": 5, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 25, "origin_id": -10, "origin_slot": 0, "target_id": 14, "target_slot": 0, "type": "IMAGE"}, {"id": 247, "origin_id": 76, "origin_slot": 0, "target_id": 11, "target_slot": 0, "type": "IMAGE"}, {"id": 248, "origin_id": 14, "origin_slot": 0, "target_id": 9, "target_slot": 3, "type": "IMAGE"}, {"id": 250, "origin_id": 14, "origin_slot": 0, "target_id": 76, "target_slot": 0, "type": "IMAGE"}, {"id": 251, "origin_id": 76, "origin_slot": 0, "target_id": 15, "target_slot": 0, "type": "IMAGE"}, {"id": 252, "origin_id": -10, "origin_slot": 2, "target_id": 2, "target_slot": 0, "type": "COMBO"}, {"id": 253, "origin_id": -10, "origin_slot": 3, "target_id": 1, "target_slot": 0, "type": "COMBO"}, {"id": 254, "origin_id": -10, "origin_slot": 4, "target_id": 3, "target_slot": 0, "type": "COMBO"}, {"id": 255, "origin_id": -10, "origin_slot": 5, "target_id": 4, "target_slot": 0, "type": "COMBO"}, {"id": 258, "origin_id": -10, "origin_slot": 6, "target_id": 76, "target_slot": 2, "type": "COMBO"}, {"id": 259, "origin_id": -10, "origin_slot": 7, "target_id": 76, "target_slot": 3, "type": "COMBO"}], "extra": {"ds": {"scale": 1.3889423076923078, "offset": [22.056074766355096, -3503.3333333333335]}, "frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true}, "category": "Image generation and editing/Depth to image"}, {"id": "458bdf3c-4b58-421c-af50-c9c663a4d74c", "version": 1, "state": {"lastGroupId": 3, "lastNodeId": 76, "lastLinkId": 259, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image to Depth Map (Lotus)", "inputNode": {"id": -10, "bounding": [-60, -172.61268043518066, 126.625, 120]}, "outputNode": {"id": -20, "bounding": [1650, -172.61268043518066, 120, 60]}, "inputs": [{"id": "3bdd30c3-4ec9-485a-814b-e7d39fb6b5cc", "name": "pixels", "type": "IMAGE", "linkIds": [37], "localized_name": "pixels", "pos": [46.625, -152.61268043518066]}, {"id": "f9a1017c-f4b9-43b4-94c2-41c088b3a492", "name": "sigma", "type": "FLOAT", "linkIds": [243], "label": "depth_intensity", "pos": [46.625, -132.61268043518066]}, {"id": "d721b249-fd2a-441b-9a78-2805f04e2644", "name": "unet_name", "type": "COMBO", "linkIds": [256], "pos": [46.625, -112.61268043518066]}, {"id": "0430e2ea-f8b5-4191-9b72-b7d62176f97c", "name": "vae_name", "type": "COMBO", "linkIds": [257], "pos": [46.625, -92.61268043518066]}], "outputs": [{"id": "2ec278bd-0b66-4b30-9c5b-994d5f638214", "name": "IMAGE", "type": "IMAGE", "linkIds": [242], "localized_name": "IMAGE", "pos": [1670, -152.61268043518066]}], "widgets": [], "nodes": [{"id": 8, "type": "VAEDecode", "pos": [1380.0000135211146, -240.0000135211144], "size": [210, 60], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 232}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 240}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [35]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAEDecode", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 10, "type": "UNETLoader", "pos": [135.34178335388546, -290.1947851765315], "size": [305.9244791666667, 97.7734375], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 256}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [31, 241]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "UNETLoader", "models": [{"name": "lotus-depth-d-v1-1.safetensors", "url": "https://huggingface.co/Comfy-Org/lotus/resolve/main/lotus-depth-d-v1-1.safetensors", "directory": "diffusion_models"}], "widget_ue_connectable": {}}, "widgets_values": ["lotus-depth-d-v1-1.safetensors", "default"]}, {"id": 14, "type": "VAELoader", "pos": [134.53144605616137, -165.18194011768782], "size": [305.9244791666667, 68.88020833333334], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 257}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [38, 240]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAELoader", "models": [{"name": "vae-ft-mse-840000-ema-pruned.safetensors", "url": "https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors", "directory": "vae"}], "widget_ue_connectable": {}}, "widgets_values": ["vae-ft-mse-840000-ema-pruned.safetensors"]}, {"id": 16, "type": "SamplerCustomAdvanced", "pos": [990.6585475753939, -319.91444852782104], "size": [355.1953125, 325.98958333333337], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 237}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 27}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 33}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 194}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 201}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "slot_index": 0, "links": [232]}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "slot_index": 1, "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "SamplerCustomAdvanced", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 18, "type": "DisableNoise", "pos": [730.4769792883567, -320.00005408445816], "size": [210, 40], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "slot_index": 0, "links": [237]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "DisableNoise", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 19, "type": "BasicGuider", "pos": [730.2630921572128, -251.22541185314978], "size": [210, 60], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 241}, {"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 238}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "slot_index": 0, "links": [27]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "BasicGuider", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 20, "type": "BasicScheduler", "pos": [488.64457755981744, -147.67201223931278], "size": [210, 122.21354166666667], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 31}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "slot_index": 0, "links": [66]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "BasicScheduler", "widget_ue_connectable": {}}, "widgets_values": ["normal", 1, 1]}, {"id": 21, "type": "KSamplerSelect", "pos": [730.2630921572128, -161.22540847287118], "size": [210, 68.88020833333334], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "slot_index": 0, "links": [33]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "KSamplerSelect", "widget_ue_connectable": {}}, "widgets_values": ["euler"]}, {"id": 22, "type": "ImageInvert", "pos": [1373.3333333333335, -318.33333333333337], "size": [210, 40], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 35}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [242]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "ImageInvert", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 23, "type": "VAEEncode", "pos": [730.2630921572128, 38.774608428522015], "size": [210, 60], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 37}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 38}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [201]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAEEncode", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 28, "type": "SetFirstSigma", "pos": [730.2630921572128, -61.225357768691524], "size": [210, 66.66666666666667], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 66}, {"localized_name": "sigma", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": 243}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "slot_index": 0, "links": [194]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "SetFirstSigma", "widget_ue_connectable": {}}, "widgets_values": [999.0000000000002]}, {"id": 68, "type": "LotusConditioning", "pos": [489.99998478874613, -229.99996619721344], "size": [210, 40], "flags": {}, "order": 4, "mode": 0, "inputs": [], "outputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "slot_index": 0, "links": [238]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "LotusConditioning", "widget_ue_connectable": {}}, "widgets_values": []}], "groups": [{"id": 2, "title": "Models", "bounding": [123.33333333333334, -351.6666666666667, 323.4014831310574, 263.55972005884377], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 232, "origin_id": 16, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 240, "origin_id": 14, "origin_slot": 0, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 237, "origin_id": 18, "origin_slot": 0, "target_id": 16, "target_slot": 0, "type": "NOISE"}, {"id": 27, "origin_id": 19, "origin_slot": 0, "target_id": 16, "target_slot": 1, "type": "GUIDER"}, {"id": 33, "origin_id": 21, "origin_slot": 0, "target_id": 16, "target_slot": 2, "type": "SAMPLER"}, {"id": 194, "origin_id": 28, "origin_slot": 0, "target_id": 16, "target_slot": 3, "type": "SIGMAS"}, {"id": 201, "origin_id": 23, "origin_slot": 0, "target_id": 16, "target_slot": 4, "type": "LATENT"}, {"id": 241, "origin_id": 10, "origin_slot": 0, "target_id": 19, "target_slot": 0, "type": "MODEL"}, {"id": 238, "origin_id": 68, "origin_slot": 0, "target_id": 19, "target_slot": 1, "type": "CONDITIONING"}, {"id": 31, "origin_id": 10, "origin_slot": 0, "target_id": 20, "target_slot": 0, "type": "MODEL"}, {"id": 35, "origin_id": 8, "origin_slot": 0, "target_id": 22, "target_slot": 0, "type": "IMAGE"}, {"id": 38, "origin_id": 14, "origin_slot": 0, "target_id": 23, "target_slot": 1, "type": "VAE"}, {"id": 66, "origin_id": 20, "origin_slot": 0, "target_id": 28, "target_slot": 0, "type": "SIGMAS"}, {"id": 37, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 242, "origin_id": 22, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 243, "origin_id": -10, "origin_slot": 1, "target_id": 28, "target_slot": 1, "type": "FLOAT"}, {"id": 256, "origin_id": -10, "origin_slot": 2, "target_id": 10, "target_slot": 0, "type": "COMBO"}, {"id": 257, "origin_id": -10, "origin_slot": 3, "target_id": 14, "target_slot": 0, "type": "COMBO"}], "extra": {"ds": {"scale": 1.2354281696404266, "offset": [-114.15605447786857, -754.3368938705543]}, "workflowRendererVersion": "LG"}}]}, "config": {}, "extra": {"ds": {"scale": 0.7886233956111374, "offset": [741.6589462093539, -3278.0806447095165]}, "frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true}, "version": 0.4} +{ + "id": "e046dd74-e2a7-4f31-a75b-5e11a8c72d4e", + "revision": 0, + "last_node_id": 76, + "last_link_id": 259, + "nodes": [ + { + "id": 13, + "type": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", + "pos": [ + 400, + 3630 + ], + "size": [ + 400, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "control image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "name": "name", + "type": "COMBO", + "widget": { + "name": "name" + }, + "link": null + }, + { + "label": "lotus_model", + "name": "unet_name_1", + "type": "COMBO", + "widget": { + "name": "unet_name_1" + }, + "link": null + }, + { + "label": "sd15_vae", + "name": "vae_name_1", + "type": "COMBO", + "widget": { + "name": "vae_name_1" + }, + "link": null + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ], + [ + "-1", + "name" + ], + [ + "-1", + "unet_name_1" + ], + [ + "-1", + "vae_name_1" + ], + [ + "7", + "control_after_generate" + ], + [ + "7", + "seed" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.11.0" + }, + "widgets_values": [ + "", + "z_image_turbo_bf16.safetensors", + "qwen_3_4b.safetensors", + "ae.safetensors", + "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", + "lotus-depth-d-v1-1.safetensors", + "vae-ft-mse-840000-ema-pruned.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", + "version": 1, + "state": { + "lastGroupId": 3, + "lastNodeId": 76, + "lastLinkId": 259, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Depth to Image (Z-Image-Turbo)", + "inputNode": { + "id": -10, + "bounding": [ + 27.60368520069494, + 4936.043696127976, + 120, + 200 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1598.6038576146689, + 4936.043696127976, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "29ca271b-8f63-4e7b-a4b8-c9b4192ada0b", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 25 + ], + "label": "control image", + "pos": [ + 127.60368520069494, + 4956.043696127976 + ] + }, + { + "id": "b6549f90-39ee-4b79-9e00-af4d9df969fe", + "name": "text", + "type": "STRING", + "linkIds": [ + 16 + ], + "label": "prompt", + "pos": [ + 127.60368520069494, + 4976.043696127976 + ] + }, + { + "id": "add4a703-1185-4848-9494-b27dd37ff434", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 252 + ], + "pos": [ + 127.60368520069494, + 4996.043696127976 + ] + }, + { + "id": "03233f9e-df65-4e05-b5c5-34d83129e85e", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 253 + ], + "pos": [ + 127.60368520069494, + 5016.043696127976 + ] + }, + { + "id": "0c643ffb-326d-40ca-8a89-ebc585cf5015", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 254 + ], + "pos": [ + 127.60368520069494, + 5036.043696127976 + ] + }, + { + "id": "409cdebe-632b-410f-a66c-711c2a1527e1", + "name": "name", + "type": "COMBO", + "linkIds": [ + 255 + ], + "pos": [ + 127.60368520069494, + 5056.043696127976 + ] + }, + { + "id": "80e6915f-5d59-4d6b-a197-d8c565ad2922", + "name": "unet_name_1", + "type": "COMBO", + "linkIds": [ + 258 + ], + "label": "lotus_model", + "pos": [ + 127.60368520069494, + 5076.043696127976 + ] + }, + { + "id": "4207ec84-4409-4816-8444-76062bf6310c", + "name": "vae_name_1", + "type": "COMBO", + "linkIds": [ + 259 + ], + "label": "sd15_vae", + "pos": [ + 127.60368520069494, + 5096.043696127976 + ] + } + ], + "outputs": [ + { + "id": "47f9a22d-6619-4917-9447-a7d5d08dceb5", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 18 + ], + "pos": [ + 1618.6038576146689, + 4956.043696127976 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 1, + "type": "CLIPLoader", + "pos": [ + 228.60381716506714, + 4700.188262345759 + ], + "size": [ + 269.9479166666667, + 106 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 253 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 14 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_3_4b.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_3_4b.safetensors", + "lumina2", + "default" + ] + }, + { + "id": 2, + "type": "UNETLoader", + "pos": [ + 228.60381716506714, + 4550.188402733727 + ], + "size": [ + 269.9479166666667, + 82 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 252 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 9 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "z_image_turbo_bf16.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "z_image_turbo_bf16.safetensors", + "default" + ] + }, + { + "id": 3, + "type": "VAELoader", + "pos": [ + 228.60381716506714, + 4880.188283008492 + ], + "size": [ + 269.9479166666667, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 254 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 2, + 11 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 4, + "type": "ModelPatchLoader", + "pos": [ + 228.60381716506714, + 5010.1883654774 + ], + "size": [ + 269.9479166666667, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "name", + "name": "name", + "type": "COMBO", + "widget": { + "name": "name" + }, + "link": 255 + } + ], + "outputs": [ + { + "localized_name": "MODEL_PATCH", + "name": "MODEL_PATCH", + "type": "MODEL_PATCH", + "links": [ + 10 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "ModelPatchLoader", + "models": [ + { + "name": "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", + "url": "https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union/resolve/main/Z-Image-Turbo-Fun-Controlnet-Union.safetensors", + "directory": "model_patches" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "Z-Image-Turbo-Fun-Controlnet-Union.safetensors" + ] + }, + { + "id": 6, + "type": "ModelSamplingAuraFlow", + "pos": [ + 998.6041081931173, + 4490.1880693746825 + ], + "size": [ + 289.97395833333337, + 58 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 3 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 4 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 7, + "type": "KSampler", + "pos": [ + 998.6041081931173, + 4600.188363442829 + ], + "size": [ + 300, + 262 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 4 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 5 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 6 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 7 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 1 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize", + 9, + 1, + "res_multistep", + "simple", + 1 + ] + }, + { + "id": 8, + "type": "ConditioningZeroOut", + "pos": [ + 748.2706508086186, + 5044.854997097082 + ], + "size": [ + 204.134765625, + 26 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 8 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 6 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "ConditioningZeroOut", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 10, + "type": "EmptySD3LatentImage", + "pos": [ + 1028.2702326451792, + 5334.855683329977 + ], + "size": [ + 259.9479166666667, + 106 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 12 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 13 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 7 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "EmptySD3LatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 5, + "type": "VAEDecode", + "pos": [ + 1338.604012131086, + 4500.188453282262 + ], + "size": [ + 200, + 46 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 1 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 2 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 18 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 9, + "type": "QwenImageDiffsynthControlnet", + "pos": [ + 608.2704996459613, + 5204.85528564724 + ], + "size": [ + 289.97395833333337, + 138 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 9 + }, + { + "localized_name": "model_patch", + "name": "model_patch", + "type": "MODEL_PATCH", + "link": 10 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 11 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 248 + }, + { + "localized_name": "mask", + "name": "mask", + "shape": 7, + "type": "MASK", + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 3 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.76", + "Node name for S&R": "QwenImageDiffsynthControlnet", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 11, + "type": "GetImageSize", + "pos": [ + 530, + 5440 + ], + "size": [ + 140, + 66 + ], + "flags": { + "collapsed": false + }, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 247 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 12 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 13 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.76", + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 12, + "type": "CLIPTextEncode", + "pos": [ + 548.2706278500244, + 4544.854827124228 + ], + "size": [ + 400, + 420 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 14 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 16 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 5, + 8 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 14, + "type": "ImageScaleToTotalPixels", + "pos": [ + 90, + 5180 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 25 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "megapixels", + "name": "megapixels", + "type": "FLOAT", + "widget": { + "name": "megapixels" + }, + "link": null + }, + { + "localized_name": "resolution_steps", + "name": "resolution_steps", + "type": "INT", + "widget": { + "name": "resolution_steps" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 248, + 250 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.0", + "Node name for S&R": "ImageScaleToTotalPixels" + }, + "widgets_values": [ + "lanczos", + 1, + 1 + ] + }, + { + "id": 15, + "type": "PreviewImage", + "pos": [ + 90, + 5530 + ], + "size": [ + 380, + 260 + ], + "flags": {}, + "order": 13, + "mode": 4, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 251 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.0", + "Node name for S&R": "PreviewImage" + }, + "widgets_values": [] + }, + { + "id": 76, + "type": "458bdf3c-4b58-421c-af50-c9c663a4d74c", + "pos": [ + 90, + 5340 + ], + "size": [ + 400, + 150 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 250 + }, + { + "label": "depth_intensity", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 258 + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 259 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 247, + 251 + ] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "sigma" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.14.1" + }, + "widgets_values": [ + 999.0000000000002, + "lotus-depth-d-v1-1.safetensors", + "vae-ft-mse-840000-ema-pruned.safetensors" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Prompt", + "bounding": [ + 530, + 4470, + 440, + 630 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Models", + "bounding": [ + 210, + 4470, + 300, + 640 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Apple ControlNet", + "bounding": [ + 530, + 5120, + 440, + 260 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 1, + "origin_id": 7, + "origin_slot": 0, + "target_id": 5, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 2, + "origin_id": 3, + "origin_slot": 0, + "target_id": 5, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 3, + "origin_id": 9, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 4, + "origin_id": 6, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 5, + "origin_id": 12, + "origin_slot": 0, + "target_id": 7, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 6, + "origin_id": 8, + "origin_slot": 0, + "target_id": 7, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 7, + "origin_id": 10, + "origin_slot": 0, + "target_id": 7, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 8, + "origin_id": 12, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 9, + "origin_id": 2, + "origin_slot": 0, + "target_id": 9, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 10, + "origin_id": 4, + "origin_slot": 0, + "target_id": 9, + "target_slot": 1, + "type": "MODEL_PATCH" + }, + { + "id": 11, + "origin_id": 3, + "origin_slot": 0, + "target_id": 9, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 12, + "origin_id": 11, + "origin_slot": 0, + "target_id": 10, + "target_slot": 0, + "type": "INT" + }, + { + "id": 13, + "origin_id": 11, + "origin_slot": 1, + "target_id": 10, + "target_slot": 1, + "type": "INT" + }, + { + "id": 14, + "origin_id": 1, + "origin_slot": 0, + "target_id": 12, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 16, + "origin_id": -10, + "origin_slot": 1, + "target_id": 12, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 18, + "origin_id": 5, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 25, + "origin_id": -10, + "origin_slot": 0, + "target_id": 14, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 247, + "origin_id": 76, + "origin_slot": 0, + "target_id": 11, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 248, + "origin_id": 14, + "origin_slot": 0, + "target_id": 9, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 250, + "origin_id": 14, + "origin_slot": 0, + "target_id": 76, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 251, + "origin_id": 76, + "origin_slot": 0, + "target_id": 15, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 252, + "origin_id": -10, + "origin_slot": 2, + "target_id": 2, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 253, + "origin_id": -10, + "origin_slot": 3, + "target_id": 1, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 254, + "origin_id": -10, + "origin_slot": 4, + "target_id": 3, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 255, + "origin_id": -10, + "origin_slot": 5, + "target_id": 4, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 258, + "origin_id": -10, + "origin_slot": 6, + "target_id": 76, + "target_slot": 2, + "type": "COMBO" + }, + { + "id": 259, + "origin_id": -10, + "origin_slot": 7, + "target_id": 76, + "target_slot": 3, + "type": "COMBO" + } + ], + "extra": { + "ds": { + "scale": 1.3889423076923078, + "offset": [ + 22.056074766355096, + -3503.3333333333335 + ] + }, + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "category": "Image generation and editing/Depth to image" + }, + { + "id": "458bdf3c-4b58-421c-af50-c9c663a4d74c", + "version": 1, + "state": { + "lastGroupId": 3, + "lastNodeId": 76, + "lastLinkId": 259, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image to Depth Map (Lotus)", + "inputNode": { + "id": -10, + "bounding": [ + -60, + -172.61268043518066, + 126.625, + 120 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1650, + -172.61268043518066, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "3bdd30c3-4ec9-485a-814b-e7d39fb6b5cc", + "name": "pixels", + "type": "IMAGE", + "linkIds": [ + 37 + ], + "localized_name": "pixels", + "pos": [ + 46.625, + -152.61268043518066 + ] + }, + { + "id": "f9a1017c-f4b9-43b4-94c2-41c088b3a492", + "name": "sigma", + "type": "FLOAT", + "linkIds": [ + 243 + ], + "label": "depth_intensity", + "pos": [ + 46.625, + -132.61268043518066 + ] + }, + { + "id": "d721b249-fd2a-441b-9a78-2805f04e2644", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 256 + ], + "pos": [ + 46.625, + -112.61268043518066 + ] + }, + { + "id": "0430e2ea-f8b5-4191-9b72-b7d62176f97c", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 257 + ], + "pos": [ + 46.625, + -92.61268043518066 + ] + } + ], + "outputs": [ + { + "id": "2ec278bd-0b66-4b30-9c5b-994d5f638214", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 242 + ], + "localized_name": "IMAGE", + "pos": [ + 1670, + -152.61268043518066 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 1380.0000135211146, + -240.0000135211144 + ], + "size": [ + 210, + 60 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 232 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 240 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 35 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAEDecode", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 10, + "type": "UNETLoader", + "pos": [ + 135.34178335388546, + -290.1947851765315 + ], + "size": [ + 305.9244791666667, + 97.7734375 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 256 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 31, + 241 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "lotus-depth-d-v1-1.safetensors", + "url": "https://huggingface.co/Comfy-Org/lotus/resolve/main/lotus-depth-d-v1-1.safetensors", + "directory": "diffusion_models" + } + ], + "widget_ue_connectable": {} + }, + "widgets_values": [ + "lotus-depth-d-v1-1.safetensors", + "default" + ] + }, + { + "id": 14, + "type": "VAELoader", + "pos": [ + 134.53144605616137, + -165.18194011768782 + ], + "size": [ + 305.9244791666667, + 68.88020833333334 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 257 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 38, + 240 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "vae-ft-mse-840000-ema-pruned.safetensors", + "url": "https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors", + "directory": "vae" + } + ], + "widget_ue_connectable": {} + }, + "widgets_values": [ + "vae-ft-mse-840000-ema-pruned.safetensors" + ] + }, + { + "id": 16, + "type": "SamplerCustomAdvanced", + "pos": [ + 990.6585475753939, + -319.91444852782104 + ], + "size": [ + 355.1953125, + 325.98958333333337 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 237 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 27 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 33 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 194 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 201 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "slot_index": 0, + "links": [ + 232 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "slot_index": 1, + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "SamplerCustomAdvanced", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 18, + "type": "DisableNoise", + "pos": [ + 730.4769792883567, + -320.00005408445816 + ], + "size": [ + 210, + 40 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "slot_index": 0, + "links": [ + 237 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "DisableNoise", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 19, + "type": "BasicGuider", + "pos": [ + 730.2630921572128, + -251.22541185314978 + ], + "size": [ + 210, + 60 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 241 + }, + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 238 + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "slot_index": 0, + "links": [ + 27 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "BasicGuider", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 20, + "type": "BasicScheduler", + "pos": [ + 488.64457755981744, + -147.67201223931278 + ], + "size": [ + 210, + 122.21354166666667 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 31 + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "slot_index": 0, + "links": [ + 66 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "BasicScheduler", + "widget_ue_connectable": {} + }, + "widgets_values": [ + "normal", + 1, + 1 + ] + }, + { + "id": 21, + "type": "KSamplerSelect", + "pos": [ + 730.2630921572128, + -161.22540847287118 + ], + "size": [ + 210, + 68.88020833333334 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "slot_index": 0, + "links": [ + 33 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "KSamplerSelect", + "widget_ue_connectable": {} + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 22, + "type": "ImageInvert", + "pos": [ + 1373.3333333333335, + -318.33333333333337 + ], + "size": [ + 210, + 40 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 35 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 242 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "ImageInvert", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 23, + "type": "VAEEncode", + "pos": [ + 730.2630921572128, + 38.774608428522015 + ], + "size": [ + 210, + 60 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 37 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 38 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 201 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAEEncode", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 28, + "type": "SetFirstSigma", + "pos": [ + 730.2630921572128, + -61.225357768691524 + ], + "size": [ + 210, + 66.66666666666667 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 66 + }, + { + "localized_name": "sigma", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": 243 + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "slot_index": 0, + "links": [ + 194 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "SetFirstSigma", + "widget_ue_connectable": {} + }, + "widgets_values": [ + 999.0000000000002 + ] + }, + { + "id": 68, + "type": "LotusConditioning", + "pos": [ + 489.99998478874613, + -229.99996619721344 + ], + "size": [ + 210, + 40 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 238 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "LotusConditioning", + "widget_ue_connectable": {} + }, + "widgets_values": [] + } + ], + "groups": [ + { + "id": 2, + "title": "Models", + "bounding": [ + 123.33333333333334, + -351.6666666666667, + 323.4014831310574, + 263.55972005884377 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 232, + "origin_id": 16, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 240, + "origin_id": 14, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 237, + "origin_id": 18, + "origin_slot": 0, + "target_id": 16, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 27, + "origin_id": 19, + "origin_slot": 0, + "target_id": 16, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 33, + "origin_id": 21, + "origin_slot": 0, + "target_id": 16, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 194, + "origin_id": 28, + "origin_slot": 0, + "target_id": 16, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 201, + "origin_id": 23, + "origin_slot": 0, + "target_id": 16, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 241, + "origin_id": 10, + "origin_slot": 0, + "target_id": 19, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 238, + "origin_id": 68, + "origin_slot": 0, + "target_id": 19, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 31, + "origin_id": 10, + "origin_slot": 0, + "target_id": 20, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 35, + "origin_id": 8, + "origin_slot": 0, + "target_id": 22, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 38, + "origin_id": 14, + "origin_slot": 0, + "target_id": 23, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 66, + "origin_id": 20, + "origin_slot": 0, + "target_id": 28, + "target_slot": 0, + "type": "SIGMAS" + }, + { + "id": 37, + "origin_id": -10, + "origin_slot": 0, + "target_id": 23, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 242, + "origin_id": 22, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 243, + "origin_id": -10, + "origin_slot": 1, + "target_id": 28, + "target_slot": 1, + "type": "FLOAT" + }, + { + "id": 256, + "origin_id": -10, + "origin_slot": 2, + "target_id": 10, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 257, + "origin_id": -10, + "origin_slot": 3, + "target_id": 14, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "ds": { + "scale": 1.2354281696404266, + "offset": [ + -114.15605447786857, + -754.3368938705543 + ] + }, + "workflowRendererVersion": "LG" + } + } + ] + }, + "config": {}, + "extra": { + "ds": { + "scale": 0.7886233956111374, + "offset": [ + 741.6589462093539, + -3278.0806447095165 + ] + }, + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "version": 0.4 +} \ No newline at end of file diff --git a/blueprints/Depth to Video (ltx 2.0).json b/blueprints/Depth to Video (ltx 2.0).json index 9656b6253..f15212520 100644 --- a/blueprints/Depth to Video (ltx 2.0).json +++ b/blueprints/Depth to Video (ltx 2.0).json @@ -1 +1,5211 @@ -{"id": "ec176c82-4db5-4ab9-b5a0-8aa8e5684a81", "revision": 0, "last_node_id": 191, "last_link_id": 433, "nodes": [{"id": 143, "type": "68857357-cbc2-4c3a-a786-c3a58d43f9b1", "pos": [289.99998661973035, 3960.0002084505168], "size": [400, 500], "flags": {"collapsed": false}, "order": 0, "mode": 0, "inputs": [{"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"label": "image_strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}, {"label": "disable_first_frame", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": null}, {"label": "depth reference video", "name": "video", "type": "VIDEO", "link": null}, {"label": "first frame", "name": "image_2", "type": "IMAGE", "link": null}, {"label": "width", "name": "resize_type.width", "type": "INT", "widget": {"name": "resize_type.width"}, "link": null}, {"label": "height", "name": "resize_type.height", "type": "INT", "widget": {"name": "resize_type.height"}, "link": null}, {"name": "length", "type": "INT", "widget": {"name": "length"}, "link": null}, {"name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": null}, {"name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"name": "text_encoder", "type": "COMBO", "widget": {"name": "text_encoder"}, "link": null}, {"label": "distill_lora", "name": "lora_name_1", "type": "COMBO", "widget": {"name": "lora_name_1"}, "link": null}, {"name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": null}, {"label": "lotus_depth_model", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"label": "sd15_vae", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "bypass"], ["-1", "strength"], ["-1", "resize_type.width"], ["-1", "resize_type.height"], ["-1", "length"], ["126", "noise_seed"], ["143", "control_after_generate"], ["-1", "ckpt_name"], ["-1", "lora_name"], ["-1", "text_encoder"], ["-1", "lora_name_1"], ["-1", "model_name"], ["-1", "unet_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.7.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", false, 1, 1280, 720, 121, null, null, "ltx-2-19b-dev-fp8.safetensors", "ltx-2-19b-ic-lora-depth-control.safetensors", "gemma_3_12B_it_fp4_mixed.safetensors", "ltx-2-19b-distilled-lora-384.safetensors", "ltx-2-spatial-upscaler-x2-1.0.safetensors", "lotus-depth-d-v1-1.safetensors", "vae-ft-mse-840000-ema-pruned.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "68857357-cbc2-4c3a-a786-c3a58d43f9b1", "version": 1, "state": {"lastGroupId": 16, "lastNodeId": 191, "lastLinkId": 433, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Depth to Video (LTX 2.0)", "inputNode": {"id": -10, "bounding": [-2730, 4020, 165.30859375, 340]}, "outputNode": {"id": -20, "bounding": [1750, 4090, 120, 60]}, "inputs": [{"id": "0f1d2f96-933a-4a7b-8f1a-7b49fc4ade09", "name": "text", "type": "STRING", "linkIds": [345], "label": "prompt", "pos": [-2584.69140625, 4040]}, {"id": "59430efe-1090-4e36-8afe-b21ce7f4268b", "name": "strength", "type": "FLOAT", "linkIds": [370, 371], "label": "image_strength", "pos": [-2584.69140625, 4060]}, {"id": "6145a9b9-68ed-4956-89f7-7a5ebdd5c99e", "name": "bypass", "type": "BOOLEAN", "linkIds": [363, 368], "label": "disable_first_frame", "pos": [-2584.69140625, 4080]}, {"id": "de434962-832a-485c-a016-869b3f2176ca", "name": "video", "type": "VIDEO", "linkIds": [419], "label": "depth reference video", "pos": [-2584.69140625, 4100]}, {"id": "a1189d3d-bbff-4933-875d-cffa58dd4cb0", "name": "image_2", "type": "IMAGE", "linkIds": [410], "label": "first frame", "pos": [-2584.69140625, 4120]}, {"id": "577dae4c-447b-4c84-9973-56381fdbc6a9", "name": "resize_type.width", "type": "INT", "linkIds": [420], "label": "width", "pos": [-2584.69140625, 4140]}, {"id": "fb30c570-128c-46b8-a140-054aff294edc", "name": "resize_type.height", "type": "INT", "linkIds": [421], "label": "height", "pos": [-2584.69140625, 4160]}, {"id": "33d5f598-00ae-4e2d-8eb2-2da23ae5ba46", "name": "length", "type": "INT", "linkIds": [422], "pos": [-2584.69140625, 4180]}, {"id": "68cc58b0-2013-4c3a-81ff-3d1e86232d76", "name": "ckpt_name", "type": "COMBO", "linkIds": [425, 433], "pos": [-2584.69140625, 4200]}, {"id": "0c65a06b-e12a-4298-8d81-69e57a123188", "name": "lora_name", "type": "COMBO", "linkIds": [426], "pos": [-2584.69140625, 4220]}, {"id": "eba96545-b8c6-4fba-b086-ddeeb4a9130d", "name": "text_encoder", "type": "COMBO", "linkIds": [427], "pos": [-2584.69140625, 4240]}, {"id": "848f9d82-3fde-4b95-b226-4b0db7082112", "name": "lora_name_1", "type": "COMBO", "linkIds": [429], "label": "distill_lora", "pos": [-2584.69140625, 4260]}, {"id": "32ace7dd-4da8-416b-b1e3-00652b3e6838", "name": "model_name", "type": "COMBO", "linkIds": [430], "pos": [-2584.69140625, 4280]}, {"id": "d6ad1978-71b6-425b-be13-c8f1e1d798d9", "name": "unet_name", "type": "COMBO", "linkIds": [431], "label": "lotus_depth_model", "pos": [-2584.69140625, 4300]}, {"id": "b0545a5d-65e8-4baa-a7be-d5f3d2b8b6e3", "name": "vae_name", "type": "COMBO", "linkIds": [432], "label": "sd15_vae", "pos": [-2584.69140625, 4320]}], "outputs": [{"id": "4e837941-de2d-4df8-8f94-686e24036897", "name": "VIDEO", "type": "VIDEO", "linkIds": [304], "localized_name": "VIDEO", "pos": [1770, 4110]}], "widgets": [], "nodes": [{"id": 93, "type": "CFGGuider", "pos": [-697.9999467324425, 3670.0001318308678], "size": [270, 106.66666666666667], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 326}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 309}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 311}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "links": [261]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "CFGGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 94, "type": "KSamplerSelect", "pos": [-697.9999467324425, 3840.0000630985346], "size": [270, 68.88020833333334], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "links": [262]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["euler"]}, {"id": 99, "type": "ManualSigmas", "pos": [409.9999946478922, 3850.0001667604133], "size": [270, 70], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "sigmas", "name": "sigmas", "type": "STRING", "widget": {"name": "sigmas"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "links": [278]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "ManualSigmas", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["0.909375, 0.725, 0.421875, 0.0"]}, {"id": 101, "type": "LTXVConcatAVLatent", "pos": [409.9999946478922, 4100.000194929402], "size": [270, 110], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "link": 365}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "link": 266}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [279]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVConcatAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 108, "type": "CFGGuider", "pos": [409.9999946478922, 3700.00007661965], "size": [270, 106.66666666666667], "flags": {}, "order": 19, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 280}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 281}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 282}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "links": [276]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.71", "Node name for S&R": "CFGGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 111, "type": "LTXVEmptyLatentAudio", "pos": [-1100.000003380279, 4810.000230985708], "size": [270, 120], "flags": {}, "order": 21, "mode": 0, "inputs": [{"localized_name": "audio_vae", "name": "audio_vae", "type": "VAE", "link": 285}, {"localized_name": "frames_number", "name": "frames_number", "type": "INT", "widget": {"name": "frames_number"}, "link": 329}, {"localized_name": "frame_rate", "name": "frame_rate", "type": "INT", "widget": {"name": "frame_rate"}, "link": 354}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "Latent", "name": "Latent", "type": "LATENT", "links": [300]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.68", "Node name for S&R": "LTXVEmptyLatentAudio", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [97, 25, 1]}, {"id": 123, "type": "SamplerCustomAdvanced", "pos": [-387.99998321128277, 3520.0000416901034], "size": [213.125, 120], "flags": {}, "order": 30, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 260}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 261}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 262}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 263}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 323}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "links": [272]}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.60", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 114, "type": "LTXVConditioning", "pos": [-1134.000099492868, 4140.000243380063], "size": [270, 86.66666666666667], "flags": {}, "order": 24, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 292}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 293}, {"localized_name": "frame_rate", "name": "frame_rate", "type": "FLOAT", "widget": {"name": "frame_rate"}, "link": 355}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [313]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [314]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "LTXVConditioning", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [25]}, {"id": 119, "type": "CLIPTextEncode", "pos": [-1164.0000442816504, 3880.0001115491955], "size": [400, 200], "flags": {}, "order": 28, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 294}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [293]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["blurry, low quality, still frame, frames, watermark, overlay, titles, has blurbox, has subtitles"], "color": "#323", "bgcolor": "#535"}, {"id": 116, "type": "LTXVConcatAVLatent", "pos": [-519.9999874648, 4700.000189295605], "size": [187.5, 60], "flags": {}, "order": 26, "mode": 0, "inputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "link": 324}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "link": 300}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [322, 323]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVConcatAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 122, "type": "LTXVSeparateAVLatent", "pos": [-393.9999813239605, 3800.0000146478747], "size": [240, 60], "flags": {}, "order": 29, "mode": 0, "inputs": [{"localized_name": "av_latent", "name": "av_latent", "type": "LATENT", "link": 272}], "outputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "links": [270]}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "links": [266]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVSeparateAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 124, "type": "CLIPTextEncode", "pos": [-1174.9999569014471, 3514.0002724504593], "size": [410, 320], "flags": {}, "order": 31, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 295}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 345}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [292]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 98, "type": "KSamplerSelect", "pos": [409.9999946478922, 3980.00004957742], "size": [270, 68.88020833333334], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "links": [277]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["gradient_estimation"]}, {"id": 95, "type": "LTXVScheduler", "pos": [-699.9999766197394, 3980.00004957742], "size": [270, 170], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "latent", "name": "latent", "shape": 7, "type": "LATENT", "link": 322}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "max_shift", "name": "max_shift", "type": "FLOAT", "widget": {"name": "max_shift"}, "link": null}, {"localized_name": "base_shift", "name": "base_shift", "type": "FLOAT", "widget": {"name": "base_shift"}, "link": null}, {"localized_name": "stretch", "name": "stretch", "type": "BOOLEAN", "widget": {"name": "stretch"}, "link": null}, {"localized_name": "terminal", "name": "terminal", "type": "FLOAT", "widget": {"name": "terminal"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "links": [263]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "LTXVScheduler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [20, 2.05, 0.95, true, 0.1]}, {"id": 126, "type": "RandomNoise", "pos": [-697.9999467324425, 3520.0000416901034], "size": [270, 82], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "links": [260]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "RandomNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "fixed"]}, {"id": 107, "type": "SamplerCustomAdvanced", "pos": [709.9999918309934, 3570.000193802643], "size": [212.3828125, 120], "flags": {}, "order": 18, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 347}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 276}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 277}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 278}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 279}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "links": []}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "links": [336]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 143, "type": "RandomNoise", "pos": [409.9999946478922, 3570.000193802643], "size": [270, 82], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "links": [347]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "RandomNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize"]}, {"id": 139, "type": "LTXVAudioVAEDecode", "pos": [1129.9999512676497, 3840.0000630985346], "size": [240, 60], "flags": {}, "order": 35, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 338}, {"label": "Audio VAE", "localized_name": "audio_vae", "name": "audio_vae", "type": "VAE", "link": 340}], "outputs": [{"localized_name": "Audio", "name": "Audio", "type": "AUDIO", "links": [339]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVAudioVAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 134, "type": "LoraLoaderModelOnly", "pos": [-1650.0000287323687, 3760.0003323940673], "size": [420, 95.546875], "flags": {}, "order": 33, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 325}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 426}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [326, 327]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "ltx-2-19b-ic-lora-depth-control.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Depth-Control/resolve/main/ltx-2-19b-ic-lora-depth-control.safetensors", "directory": "loras"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-ic-lora-depth-control.safetensors", 1], "color": "#322", "bgcolor": "#533"}, {"id": 138, "type": "LTXVSeparateAVLatent", "pos": [730.0000160563236, 3730.0000214084316], "size": [193.2916015625, 60], "flags": {}, "order": 34, "mode": 0, "inputs": [{"localized_name": "av_latent", "name": "av_latent", "type": "LATENT", "link": 336}], "outputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "links": [337, 351]}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "links": [338]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVSeparateAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 144, "type": "VAEDecodeTiled", "pos": [1119.9999391549845, 3640.000187042085], "size": [270, 150], "flags": {}, "order": 36, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 351}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 353}, {"localized_name": "tile_size", "name": "tile_size", "type": "INT", "widget": {"name": "tile_size"}, "link": null}, {"localized_name": "overlap", "name": "overlap", "type": "INT", "widget": {"name": "overlap"}, "link": null}, {"localized_name": "temporal_size", "name": "temporal_size", "type": "INT", "widget": {"name": "temporal_size"}, "link": null}, {"localized_name": "temporal_overlap", "name": "temporal_overlap", "type": "INT", "widget": {"name": "temporal_overlap"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [352]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "VAEDecodeTiled", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [512, 64, 4096, 8]}, {"id": 113, "type": "VAEDecode", "pos": [1129.9999512676497, 3530.000145351982], "size": [240, 60], "flags": {}, "order": 23, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 337}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 291}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 145, "type": "PrimitiveInt", "pos": [-1630.0000045070383, 4620.0000923942835], "size": [270, 82], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "INT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "INT", "name": "INT", "type": "INT", "links": [354]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "PrimitiveInt", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [24, "fixed"]}, {"id": 148, "type": "PrimitiveFloat", "pos": [-1630.0000045070383, 4749.99997521129], "size": [270, 66.66666666666667], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [355, 356]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "PrimitiveFloat", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [24]}, {"id": 115, "type": "EmptyLTXVLatentVideo", "pos": [-1100.000003380279, 4609.999988732406], "size": [270, 146.66666666666669], "flags": {}, "order": 25, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 296}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 297}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": 330}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [360]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.60", "Node name for S&R": "EmptyLTXVLatentVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [768, 512, 97, 1]}, {"id": 149, "type": "LTXVImgToVideoInplace", "pos": [-1089.9999912676137, 4400.000009014077], "size": [270, 151.9921875], "flags": {}, "order": 37, "mode": 0, "inputs": [{"localized_name": "vae", "name": "vae", "type": "VAE", "link": 359}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 417}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 360}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": 370}, {"localized_name": "bypass", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": 363}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [357]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVImgToVideoInplace", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1, false]}, {"id": 118, "type": "Reroute", "pos": [-229.99999095071237, 4210.000236619506], "size": [75, 26], "flags": {}, "order": 27, "mode": 0, "inputs": [{"name": "", "type": "*", "link": 303}], "outputs": [{"name": "", "type": "VAE", "links": [289, 291, 367]}], "properties": {"showOutputText": false, "horizontal": false}}, {"id": 151, "type": "LTXVImgToVideoInplace", "pos": [-19.999999788732577, 4070.0002501406198], "size": [270, 181.9921875], "flags": {}, "order": 38, "mode": 0, "inputs": [{"localized_name": "vae", "name": "vae", "type": "VAE", "link": 367}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 410}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 366}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": 371}, {"localized_name": "bypass", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": 368}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [365]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVImgToVideoInplace", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1, false]}, {"id": 104, "type": "LTXVCropGuides", "pos": [-9.999999119719098, 3840.0000630985346], "size": [240, 80], "flags": {}, "order": 15, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 310}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 312}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 270}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [281]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [282]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "slot_index": 2, "links": [287]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.68", "Node name for S&R": "LTXVCropGuides", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 112, "type": "LTXVLatentUpsampler", "pos": [-9.999999119719098, 3960.0002084505168], "size": [260, 80], "flags": {}, "order": 22, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 287}, {"localized_name": "upscale_model", "name": "upscale_model", "type": "LATENT_UPSCALE_MODEL", "link": 288}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 289}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [366]}], "title": "spatial", "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVLatentUpsampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 132, "type": "LTXVAddGuide", "pos": [-599.9999928169079, 4420.000216337834], "size": [270, 209.16666666666669], "flags": {}, "order": 32, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 313}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 314}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 328}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 357}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 418}, {"localized_name": "frame_idx", "name": "frame_idx", "type": "INT", "widget": {"name": "frame_idx"}, "link": null}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [309, 310]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [311, 312]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [324]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "LTXVAddGuide", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, 1]}, {"id": 96, "type": "LTXVAudioVAELoader", "pos": [-1650.0000287323687, 3910.000056337978], "size": [420, 68.88020833333334], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 377}], "outputs": [{"localized_name": "Audio VAE", "name": "Audio VAE", "type": "VAE", "links": [285, 340]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.68", "Node name for S&R": "LTXVAudioVAELoader", "models": [{"name": "ltx-2-19b-dev-fp8.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", "directory": "checkpoints"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-dev-fp8.safetensors"]}, {"id": 103, "type": "CheckpointLoaderSimple", "pos": [-1650.0000287323687, 3590.0000349295465], "size": [420, 108.88020833333334], "flags": {}, "order": 14, "mode": 0, "inputs": [{"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 425}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [325]}, {"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": []}, {"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [303, 328, 353, 359]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CheckpointLoaderSimple", "models": [{"name": "ltx-2-19b-dev-fp8.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", "directory": "checkpoints"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-dev-fp8.safetensors"]}, {"id": 105, "type": "LoraLoaderModelOnly", "pos": [-69.99999741197416, 3570.000193802643], "size": [390, 95.546875], "flags": {}, "order": 16, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 327}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 429}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [280]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "ltx-2-19b-distilled-lora-384.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-lora-384.safetensors", "directory": "loras"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-distilled-lora-384.safetensors", 1]}, {"id": 100, "type": "LatentUpscaleModelLoader", "pos": [-69.99999741197416, 3700.00007661965], "size": [390, 68.88020833333334], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": 430}], "outputs": [{"localized_name": "LATENT_UPSCALE_MODEL", "name": "LATENT_UPSCALE_MODEL", "type": "LATENT_UPSCALE_MODEL", "links": [288]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LatentUpscaleModelLoader", "models": [{"name": "ltx-2-spatial-upscaler-x2-1.0.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-spatial-upscaler-x2-1.0.safetensors", "directory": "latent_upscale_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-spatial-upscaler-x2-1.0.safetensors"]}, {"id": 110, "type": "GetImageSize", "pos": [-1630.0000045070383, 4450.000161126616], "size": [260, 80], "flags": {}, "order": 20, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 416}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [296]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [297]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": [329, 330]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "GetImageSize", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 106, "type": "CreateVideo", "pos": [1419.9999363380857, 3760.0003323940673], "size": [270, 86.66666666666667], "flags": {}, "order": 17, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 352}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 339}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 356}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [304]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "CreateVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [25]}, {"id": 187, "type": "ImageFromBatch", "pos": [-2310.000095774562, 3689.999972957771], "size": [260, 93.33333333333334], "flags": {}, "order": 39, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 412}, {"localized_name": "batch_index", "name": "batch_index", "type": "INT", "widget": {"name": "batch_index"}, "link": null}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": 422}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [415]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "ImageFromBatch", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, 121]}, {"id": 191, "type": "ResizeImageMaskNode", "pos": [-2320.0000163380137, 3850.0001667604133], "size": [284.375, 154], "flags": {}, "order": 43, "mode": 0, "inputs": [{"localized_name": "input", "name": "input", "type": "IMAGE,MASK", "link": 415}, {"localized_name": "resize_type", "name": "resize_type", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "resize_type"}, "link": null}, {"localized_name": "width", "name": "resize_type.width", "type": "INT", "widget": {"name": "resize_type.width"}, "link": 420}, {"localized_name": "height", "name": "resize_type.height", "type": "INT", "widget": {"name": "resize_type.height"}, "link": 421}, {"localized_name": "crop", "name": "resize_type.crop", "type": "COMBO", "widget": {"name": "resize_type.crop"}, "link": null}, {"localized_name": "scale_method", "name": "scale_method", "type": "COMBO", "widget": {"name": "scale_method"}, "link": null}], "outputs": [{"localized_name": "resized", "name": "resized", "type": "IMAGE", "links": [413]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "ResizeImageMaskNode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["scale dimensions", 1280, 720, "center", "lanczos"]}, {"id": 188, "type": "GetVideoComponents", "pos": [-2320.0000163380137, 3520.0000416901034], "size": [280, 80], "flags": {"collapsed": false}, "order": 40, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": 419}], "outputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "links": [412]}, {"localized_name": "audio", "name": "audio", "type": "AUDIO", "links": []}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "GetVideoComponents", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 189, "type": "ImageScaleBy", "pos": [-1990.0000743661303, 3670.0001318308678], "size": [280, 125.546875], "flags": {}, "order": 41, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 413}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "scale_by", "name": "scale_by", "type": "FLOAT", "widget": {"name": "scale_by"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [414]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "ImageScaleBy", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["lanczos", 0.5]}, {"id": 154, "type": "MarkdownNote", "pos": [-1659.9999492958204, 4870.000120563272], "size": [350, 170], "flags": {"collapsed": false}, "order": 7, "mode": 0, "inputs": [], "outputs": [], "title": "Frame Rate Note", "properties": {}, "widgets_values": ["Please make sure the frame rate value is the same in both boxes"], "color": "#222", "bgcolor": "#000"}, {"id": 190, "type": "38b60539-50a7-42f9-a5fe-bdeca26272e2", "pos": [-1999.9999949295823, 3910.000056337978], "size": [310, 106], "flags": {}, "order": 42, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 414}, {"label": "depth_intensity", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 431}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 432}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [416, 417, 418]}], "properties": {"proxyWidgets": [["-1", "sigma"], ["-1", "unet_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [999.0000000000002, "lotus-depth-d-v1-1.safetensors", "vae-ft-mse-840000-ema-pruned.safetensors"], "color": "#322", "bgcolor": "#533"}, {"id": 97, "type": "LTXAVTextEncoderLoader", "pos": [-1650.0000287323687, 4040.0003053518376], "size": [420, 124.44010416666667], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "text_encoder", "name": "text_encoder", "type": "COMBO", "widget": {"name": "text_encoder"}, "link": 427}, {"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 433}, {"localized_name": "device", "name": "device", "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [294, 295]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXAVTextEncoderLoader", "models": [{"name": "ltx-2-19b-dev-fp8.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", "directory": "checkpoints"}, {"name": "gemma_3_12B_it_fp4_mixed.safetensors", "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["gemma_3_12B_it_fp4_mixed.safetensors", "ltx-2-19b-dev-fp8.safetensors", "default"]}], "groups": [{"id": 1, "title": "Model", "bounding": [-1660, 3440, 440, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Basic Sampling", "bounding": [-700, 3440, 570, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Prompt", "bounding": [-1180, 3440, 440, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 5, "title": "Latent", "bounding": [-1180, 4290, 1050, 680], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 9, "title": "Upscale Sampling(2x)", "bounding": [-100, 3440, 1090, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 6, "title": "Sampler", "bounding": [350, 3480, 620, 750], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 7, "title": "Model", "bounding": [-90, 3480, 430, 310], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 11, "title": "Frame rate", "bounding": [-1640, 4550, 290, 271.6], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 16, "title": "Video Preprocess", "bounding": [-2330, 3450, 650, 567.6], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 15, "title": "video length", "bounding": [-2320, 3620, 290, 180], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 326, "origin_id": 134, "origin_slot": 0, "target_id": 93, "target_slot": 0, "type": "MODEL"}, {"id": 309, "origin_id": 132, "origin_slot": 0, "target_id": 93, "target_slot": 1, "type": "CONDITIONING"}, {"id": 311, "origin_id": 132, "origin_slot": 1, "target_id": 93, "target_slot": 2, "type": "CONDITIONING"}, {"id": 266, "origin_id": 122, "origin_slot": 1, "target_id": 101, "target_slot": 1, "type": "LATENT"}, {"id": 280, "origin_id": 105, "origin_slot": 0, "target_id": 108, "target_slot": 0, "type": "MODEL"}, {"id": 281, "origin_id": 104, "origin_slot": 0, "target_id": 108, "target_slot": 1, "type": "CONDITIONING"}, {"id": 282, "origin_id": 104, "origin_slot": 1, "target_id": 108, "target_slot": 2, "type": "CONDITIONING"}, {"id": 285, "origin_id": 96, "origin_slot": 0, "target_id": 111, "target_slot": 0, "type": "VAE"}, {"id": 329, "origin_id": 110, "origin_slot": 2, "target_id": 111, "target_slot": 1, "type": "INT"}, {"id": 260, "origin_id": 126, "origin_slot": 0, "target_id": 123, "target_slot": 0, "type": "NOISE"}, {"id": 261, "origin_id": 93, "origin_slot": 0, "target_id": 123, "target_slot": 1, "type": "GUIDER"}, {"id": 262, "origin_id": 94, "origin_slot": 0, "target_id": 123, "target_slot": 2, "type": "SAMPLER"}, {"id": 263, "origin_id": 95, "origin_slot": 0, "target_id": 123, "target_slot": 3, "type": "SIGMAS"}, {"id": 323, "origin_id": 116, "origin_slot": 0, "target_id": 123, "target_slot": 4, "type": "LATENT"}, {"id": 296, "origin_id": 110, "origin_slot": 0, "target_id": 115, "target_slot": 0, "type": "INT"}, {"id": 297, "origin_id": 110, "origin_slot": 1, "target_id": 115, "target_slot": 1, "type": "INT"}, {"id": 330, "origin_id": 110, "origin_slot": 2, "target_id": 115, "target_slot": 2, "type": "INT"}, {"id": 325, "origin_id": 103, "origin_slot": 0, "target_id": 134, "target_slot": 0, "type": "MODEL"}, {"id": 292, "origin_id": 124, "origin_slot": 0, "target_id": 114, "target_slot": 0, "type": "CONDITIONING"}, {"id": 293, "origin_id": 119, "origin_slot": 0, "target_id": 114, "target_slot": 1, "type": "CONDITIONING"}, {"id": 294, "origin_id": 97, "origin_slot": 0, "target_id": 119, "target_slot": 0, "type": "CLIP"}, {"id": 324, "origin_id": 132, "origin_slot": 2, "target_id": 116, "target_slot": 0, "type": "LATENT"}, {"id": 300, "origin_id": 111, "origin_slot": 0, "target_id": 116, "target_slot": 1, "type": "LATENT"}, {"id": 313, "origin_id": 114, "origin_slot": 0, "target_id": 132, "target_slot": 0, "type": "CONDITIONING"}, {"id": 314, "origin_id": 114, "origin_slot": 1, "target_id": 132, "target_slot": 1, "type": "CONDITIONING"}, {"id": 328, "origin_id": 103, "origin_slot": 2, "target_id": 132, "target_slot": 2, "type": "VAE"}, {"id": 272, "origin_id": 123, "origin_slot": 0, "target_id": 122, "target_slot": 0, "type": "LATENT"}, {"id": 336, "origin_id": 107, "origin_slot": 1, "target_id": 138, "target_slot": 0, "type": "LATENT"}, {"id": 339, "origin_id": 139, "origin_slot": 0, "target_id": 106, "target_slot": 1, "type": "AUDIO"}, {"id": 295, "origin_id": 97, "origin_slot": 0, "target_id": 124, "target_slot": 0, "type": "CLIP"}, {"id": 303, "origin_id": 103, "origin_slot": 2, "target_id": 118, "target_slot": 0, "type": "VAE"}, {"id": 338, "origin_id": 138, "origin_slot": 1, "target_id": 139, "target_slot": 0, "type": "LATENT"}, {"id": 340, "origin_id": 96, "origin_slot": 0, "target_id": 139, "target_slot": 1, "type": "VAE"}, {"id": 337, "origin_id": 138, "origin_slot": 0, "target_id": 113, "target_slot": 0, "type": "LATENT"}, {"id": 291, "origin_id": 118, "origin_slot": 0, "target_id": 113, "target_slot": 1, "type": "VAE"}, {"id": 276, "origin_id": 108, "origin_slot": 0, "target_id": 107, "target_slot": 1, "type": "GUIDER"}, {"id": 277, "origin_id": 98, "origin_slot": 0, "target_id": 107, "target_slot": 2, "type": "SAMPLER"}, {"id": 278, "origin_id": 99, "origin_slot": 0, "target_id": 107, "target_slot": 3, "type": "SIGMAS"}, {"id": 279, "origin_id": 101, "origin_slot": 0, "target_id": 107, "target_slot": 4, "type": "LATENT"}, {"id": 327, "origin_id": 134, "origin_slot": 0, "target_id": 105, "target_slot": 0, "type": "MODEL"}, {"id": 310, "origin_id": 132, "origin_slot": 0, "target_id": 104, "target_slot": 0, "type": "CONDITIONING"}, {"id": 312, "origin_id": 132, "origin_slot": 1, "target_id": 104, "target_slot": 1, "type": "CONDITIONING"}, {"id": 270, "origin_id": 122, "origin_slot": 0, "target_id": 104, "target_slot": 2, "type": "LATENT"}, {"id": 287, "origin_id": 104, "origin_slot": 2, "target_id": 112, "target_slot": 0, "type": "LATENT"}, {"id": 288, "origin_id": 100, "origin_slot": 0, "target_id": 112, "target_slot": 1, "type": "LATENT_UPSCALE_MODEL"}, {"id": 289, "origin_id": 118, "origin_slot": 0, "target_id": 112, "target_slot": 2, "type": "VAE"}, {"id": 322, "origin_id": 116, "origin_slot": 0, "target_id": 95, "target_slot": 0, "type": "LATENT"}, {"id": 304, "origin_id": 106, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 345, "origin_id": -10, "origin_slot": 0, "target_id": 124, "target_slot": 1, "type": "STRING"}, {"id": 347, "origin_id": 143, "origin_slot": 0, "target_id": 107, "target_slot": 0, "type": "NOISE"}, {"id": 351, "origin_id": 138, "origin_slot": 0, "target_id": 144, "target_slot": 0, "type": "LATENT"}, {"id": 352, "origin_id": 144, "origin_slot": 0, "target_id": 106, "target_slot": 0, "type": "IMAGE"}, {"id": 353, "origin_id": 103, "origin_slot": 2, "target_id": 144, "target_slot": 1, "type": "VAE"}, {"id": 354, "origin_id": 145, "origin_slot": 0, "target_id": 111, "target_slot": 2, "type": "INT"}, {"id": 355, "origin_id": 148, "origin_slot": 0, "target_id": 114, "target_slot": 2, "type": "FLOAT"}, {"id": 356, "origin_id": 148, "origin_slot": 0, "target_id": 106, "target_slot": 2, "type": "FLOAT"}, {"id": 357, "origin_id": 149, "origin_slot": 0, "target_id": 132, "target_slot": 3, "type": "LATENT"}, {"id": 359, "origin_id": 103, "origin_slot": 2, "target_id": 149, "target_slot": 0, "type": "VAE"}, {"id": 360, "origin_id": 115, "origin_slot": 0, "target_id": 149, "target_slot": 2, "type": "LATENT"}, {"id": 363, "origin_id": -10, "origin_slot": 2, "target_id": 149, "target_slot": 4, "type": "BOOLEAN"}, {"id": 365, "origin_id": 151, "origin_slot": 0, "target_id": 101, "target_slot": 0, "type": "LATENT"}, {"id": 366, "origin_id": 112, "origin_slot": 0, "target_id": 151, "target_slot": 2, "type": "LATENT"}, {"id": 367, "origin_id": 118, "origin_slot": 0, "target_id": 151, "target_slot": 0, "type": "VAE"}, {"id": 368, "origin_id": -10, "origin_slot": 2, "target_id": 151, "target_slot": 4, "type": "BOOLEAN"}, {"id": 370, "origin_id": -10, "origin_slot": 1, "target_id": 149, "target_slot": 3, "type": "FLOAT"}, {"id": 371, "origin_id": -10, "origin_slot": 1, "target_id": 151, "target_slot": 3, "type": "FLOAT"}, {"id": 377, "origin_id": -10, "origin_slot": 6, "target_id": 96, "target_slot": 0, "type": "COMBO"}, {"id": 410, "origin_id": -10, "origin_slot": 4, "target_id": 151, "target_slot": 1, "type": "IMAGE"}, {"id": 412, "origin_id": 188, "origin_slot": 0, "target_id": 187, "target_slot": 0, "type": "IMAGE"}, {"id": 413, "origin_id": 191, "origin_slot": 0, "target_id": 189, "target_slot": 0, "type": "IMAGE"}, {"id": 414, "origin_id": 189, "origin_slot": 0, "target_id": 190, "target_slot": 0, "type": "IMAGE"}, {"id": 415, "origin_id": 187, "origin_slot": 0, "target_id": 191, "target_slot": 0, "type": "IMAGE"}, {"id": 416, "origin_id": 190, "origin_slot": 0, "target_id": 110, "target_slot": 0, "type": "IMAGE"}, {"id": 417, "origin_id": 190, "origin_slot": 0, "target_id": 149, "target_slot": 1, "type": "IMAGE"}, {"id": 418, "origin_id": 190, "origin_slot": 0, "target_id": 132, "target_slot": 4, "type": "IMAGE"}, {"id": 419, "origin_id": -10, "origin_slot": 3, "target_id": 188, "target_slot": 0, "type": "VIDEO"}, {"id": 420, "origin_id": -10, "origin_slot": 5, "target_id": 191, "target_slot": 2, "type": "INT"}, {"id": 421, "origin_id": -10, "origin_slot": 6, "target_id": 191, "target_slot": 3, "type": "INT"}, {"id": 422, "origin_id": -10, "origin_slot": 7, "target_id": 187, "target_slot": 2, "type": "INT"}, {"id": 425, "origin_id": -10, "origin_slot": 8, "target_id": 103, "target_slot": 0, "type": "COMBO"}, {"id": 426, "origin_id": -10, "origin_slot": 9, "target_id": 134, "target_slot": 1, "type": "COMBO"}, {"id": 427, "origin_id": -10, "origin_slot": 10, "target_id": 97, "target_slot": 0, "type": "COMBO"}, {"id": 429, "origin_id": -10, "origin_slot": 11, "target_id": 105, "target_slot": 1, "type": "COMBO"}, {"id": 430, "origin_id": -10, "origin_slot": 12, "target_id": 100, "target_slot": 0, "type": "COMBO"}, {"id": 431, "origin_id": -10, "origin_slot": 13, "target_id": 190, "target_slot": 2, "type": "COMBO"}, {"id": 432, "origin_id": -10, "origin_slot": 14, "target_id": 190, "target_slot": 3, "type": "COMBO"}, {"id": 433, "origin_id": -10, "origin_slot": 8, "target_id": 97, "target_slot": 1, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Depth to video"}, {"id": "38b60539-50a7-42f9-a5fe-bdeca26272e2", "version": 1, "state": {"lastGroupId": 16, "lastNodeId": 191, "lastLinkId": 433, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image to Depth Map (Lotus)", "inputNode": {"id": -10, "bounding": [-60, -172.61268043518066, 126.625, 120]}, "outputNode": {"id": -20, "bounding": [1650, -172.61268043518066, 120, 60]}, "inputs": [{"id": "3bdd30c3-4ec9-485a-814b-e7d39fb6b5cc", "name": "pixels", "type": "IMAGE", "linkIds": [37], "localized_name": "pixels", "pos": [46.625, -152.61268043518066]}, {"id": "f9a1017c-f4b9-43b4-94c2-41c088b3a492", "name": "sigma", "type": "FLOAT", "linkIds": [243], "label": "depth_intensity", "pos": [46.625, -132.61268043518066]}, {"id": "374bfecc-34bb-47f9-82b6-cbe9383f8756", "name": "unet_name", "type": "COMBO", "linkIds": [423], "pos": [46.625, -112.61268043518066]}, {"id": "bb8707a1-46c3-44be-a15a-0adc908d871d", "name": "vae_name", "type": "COMBO", "linkIds": [424], "pos": [46.625, -92.61268043518066]}], "outputs": [{"id": "2ec278bd-0b66-4b30-9c5b-994d5f638214", "name": "IMAGE", "type": "IMAGE", "linkIds": [242], "localized_name": "IMAGE", "pos": [1670, -152.61268043518066]}], "widgets": [], "nodes": [{"id": 8, "type": "VAEDecode", "pos": [1380, -240], "size": [210, 46], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 232}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 240}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [35]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 10, "type": "UNETLoader", "pos": [135.34181213378906, -290.1947937011719], "size": [305.93701171875, 82], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 423}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [31, 241]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "UNETLoader", "models": [{"name": "lotus-depth-d-v1-1.safetensors", "url": "https://huggingface.co/Comfy-Org/lotus/resolve/main/lotus-depth-d-v1-1.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["lotus-depth-d-v1-1.safetensors", "default"]}, {"id": 14, "type": "VAELoader", "pos": [134.531494140625, -165.18197631835938], "size": [305.93701171875, 58], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 424}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [38, 240]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAELoader", "models": [{"name": "vae-ft-mse-840000-ema-pruned.safetensors", "url": "https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["vae-ft-mse-840000-ema-pruned.safetensors"]}, {"id": 16, "type": "SamplerCustomAdvanced", "pos": [990.6585693359375, -319.9144287109375], "size": [355.20001220703125, 326], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 237}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 27}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 33}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 194}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 201}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "slot_index": 0, "links": [232]}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "slot_index": 1, "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 18, "type": "DisableNoise", "pos": [730.47705078125, -320], "size": [210, 26], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "slot_index": 0, "links": [237]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "DisableNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 19, "type": "BasicGuider", "pos": [730.2631225585938, -251.22537231445312], "size": [210, 46], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 241}, {"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 238}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "slot_index": 0, "links": [27]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "BasicGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 20, "type": "BasicScheduler", "pos": [488.64459228515625, -147.67201232910156], "size": [210, 106], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 31}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "slot_index": 0, "links": [66]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "BasicScheduler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["normal", 1, 1]}, {"id": 21, "type": "KSamplerSelect", "pos": [730.2631225585938, -161.22537231445312], "size": [210, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "slot_index": 0, "links": [33]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["euler"]}, {"id": 22, "type": "ImageInvert", "pos": [1380, -310], "size": [210, 26], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 35}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [242]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "ImageInvert", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 23, "type": "VAEEncode", "pos": [730.2631225585938, 38.77463912963867], "size": [210, 46], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 37}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 38}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [201]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAEEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 28, "type": "SetFirstSigma", "pos": [730.2631225585938, -61.22536087036133], "size": [210, 58], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 66}, {"localized_name": "sigma", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": 243}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "slot_index": 0, "links": [194]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "SetFirstSigma", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": [999.0000000000002]}, {"id": 68, "type": "LotusConditioning", "pos": [490, -230], "size": [210, 26], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "slot_index": 0, "links": [238]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "LotusConditioning", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}], "groups": [{"id": 1, "title": "Load Models", "bounding": [120, -370, 335, 281.6000061035156], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 232, "origin_id": 16, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 240, "origin_id": 14, "origin_slot": 0, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 237, "origin_id": 18, "origin_slot": 0, "target_id": 16, "target_slot": 0, "type": "NOISE"}, {"id": 27, "origin_id": 19, "origin_slot": 0, "target_id": 16, "target_slot": 1, "type": "GUIDER"}, {"id": 33, "origin_id": 21, "origin_slot": 0, "target_id": 16, "target_slot": 2, "type": "SAMPLER"}, {"id": 194, "origin_id": 28, "origin_slot": 0, "target_id": 16, "target_slot": 3, "type": "SIGMAS"}, {"id": 201, "origin_id": 23, "origin_slot": 0, "target_id": 16, "target_slot": 4, "type": "LATENT"}, {"id": 241, "origin_id": 10, "origin_slot": 0, "target_id": 19, "target_slot": 0, "type": "MODEL"}, {"id": 238, "origin_id": 68, "origin_slot": 0, "target_id": 19, "target_slot": 1, "type": "CONDITIONING"}, {"id": 31, "origin_id": 10, "origin_slot": 0, "target_id": 20, "target_slot": 0, "type": "MODEL"}, {"id": 35, "origin_id": 8, "origin_slot": 0, "target_id": 22, "target_slot": 0, "type": "IMAGE"}, {"id": 38, "origin_id": 14, "origin_slot": 0, "target_id": 23, "target_slot": 1, "type": "VAE"}, {"id": 66, "origin_id": 20, "origin_slot": 0, "target_id": 28, "target_slot": 0, "type": "SIGMAS"}, {"id": 37, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 242, "origin_id": 22, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 243, "origin_id": -10, "origin_slot": 1, "target_id": 28, "target_slot": 1, "type": "FLOAT"}, {"id": 423, "origin_id": -10, "origin_slot": 2, "target_id": 10, "target_slot": 0, "type": "COMBO"}, {"id": 424, "origin_id": -10, "origin_slot": 3, "target_id": 14, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}}]}, "config": {}, "extra": {"ds": {"scale": 1.313181818181818, "offset": [271.9196871428176, -3845.0123774536323]}, "workflowRendererVersion": "LG"}, "version": 0.4} +{ + "id": "ec176c82-4db5-4ab9-b5a0-8aa8e5684a81", + "revision": 0, + "last_node_id": 191, + "last_link_id": 433, + "nodes": [ + { + "id": 143, + "type": "68857357-cbc2-4c3a-a786-c3a58d43f9b1", + "pos": [ + 289.99998661973035, + 3960.0002084505168 + ], + "size": [ + 400, + 500 + ], + "flags": { + "collapsed": false + }, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "label": "image_strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "label": "disable_first_frame", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": null + }, + { + "label": "depth reference video", + "name": "video", + "type": "VIDEO", + "link": null + }, + { + "label": "first frame", + "name": "image_2", + "type": "IMAGE", + "link": null + }, + { + "label": "width", + "name": "resize_type.width", + "type": "INT", + "widget": { + "name": "resize_type.width" + }, + "link": null + }, + { + "label": "height", + "name": "resize_type.height", + "type": "INT", + "widget": { + "name": "resize_type.height" + }, + "link": null + }, + { + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": null + }, + { + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": null + }, + { + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": null + }, + { + "label": "distill_lora", + "name": "lora_name_1", + "type": "COMBO", + "widget": { + "name": "lora_name_1" + }, + "link": null + }, + { + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": null + }, + { + "label": "lotus_depth_model", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "label": "sd15_vae", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "bypass" + ], + [ + "-1", + "strength" + ], + [ + "-1", + "resize_type.width" + ], + [ + "-1", + "resize_type.height" + ], + [ + "-1", + "length" + ], + [ + "126", + "noise_seed" + ], + [ + "143", + "control_after_generate" + ], + [ + "-1", + "ckpt_name" + ], + [ + "-1", + "lora_name" + ], + [ + "-1", + "text_encoder" + ], + [ + "-1", + "lora_name_1" + ], + [ + "-1", + "model_name" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.7.0", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "", + false, + 1, + 1280, + 720, + 121, + null, + null, + "ltx-2-19b-dev-fp8.safetensors", + "ltx-2-19b-ic-lora-depth-control.safetensors", + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2-19b-distilled-lora-384.safetensors", + "ltx-2-spatial-upscaler-x2-1.0.safetensors", + "lotus-depth-d-v1-1.safetensors", + "vae-ft-mse-840000-ema-pruned.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "68857357-cbc2-4c3a-a786-c3a58d43f9b1", + "version": 1, + "state": { + "lastGroupId": 16, + "lastNodeId": 191, + "lastLinkId": 433, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Depth to Video (LTX 2.0)", + "inputNode": { + "id": -10, + "bounding": [ + -2730, + 4020, + 165.30859375, + 340 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1750, + 4090, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "0f1d2f96-933a-4a7b-8f1a-7b49fc4ade09", + "name": "text", + "type": "STRING", + "linkIds": [ + 345 + ], + "label": "prompt", + "pos": [ + -2584.69140625, + 4040 + ] + }, + { + "id": "59430efe-1090-4e36-8afe-b21ce7f4268b", + "name": "strength", + "type": "FLOAT", + "linkIds": [ + 370, + 371 + ], + "label": "image_strength", + "pos": [ + -2584.69140625, + 4060 + ] + }, + { + "id": "6145a9b9-68ed-4956-89f7-7a5ebdd5c99e", + "name": "bypass", + "type": "BOOLEAN", + "linkIds": [ + 363, + 368 + ], + "label": "disable_first_frame", + "pos": [ + -2584.69140625, + 4080 + ] + }, + { + "id": "de434962-832a-485c-a016-869b3f2176ca", + "name": "video", + "type": "VIDEO", + "linkIds": [ + 419 + ], + "label": "depth reference video", + "pos": [ + -2584.69140625, + 4100 + ] + }, + { + "id": "a1189d3d-bbff-4933-875d-cffa58dd4cb0", + "name": "image_2", + "type": "IMAGE", + "linkIds": [ + 410 + ], + "label": "first frame", + "pos": [ + -2584.69140625, + 4120 + ] + }, + { + "id": "577dae4c-447b-4c84-9973-56381fdbc6a9", + "name": "resize_type.width", + "type": "INT", + "linkIds": [ + 420 + ], + "label": "width", + "pos": [ + -2584.69140625, + 4140 + ] + }, + { + "id": "fb30c570-128c-46b8-a140-054aff294edc", + "name": "resize_type.height", + "type": "INT", + "linkIds": [ + 421 + ], + "label": "height", + "pos": [ + -2584.69140625, + 4160 + ] + }, + { + "id": "33d5f598-00ae-4e2d-8eb2-2da23ae5ba46", + "name": "length", + "type": "INT", + "linkIds": [ + 422 + ], + "pos": [ + -2584.69140625, + 4180 + ] + }, + { + "id": "68cc58b0-2013-4c3a-81ff-3d1e86232d76", + "name": "ckpt_name", + "type": "COMBO", + "linkIds": [ + 425, + 433 + ], + "pos": [ + -2584.69140625, + 4200 + ] + }, + { + "id": "0c65a06b-e12a-4298-8d81-69e57a123188", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 426 + ], + "pos": [ + -2584.69140625, + 4220 + ] + }, + { + "id": "eba96545-b8c6-4fba-b086-ddeeb4a9130d", + "name": "text_encoder", + "type": "COMBO", + "linkIds": [ + 427 + ], + "pos": [ + -2584.69140625, + 4240 + ] + }, + { + "id": "848f9d82-3fde-4b95-b226-4b0db7082112", + "name": "lora_name_1", + "type": "COMBO", + "linkIds": [ + 429 + ], + "label": "distill_lora", + "pos": [ + -2584.69140625, + 4260 + ] + }, + { + "id": "32ace7dd-4da8-416b-b1e3-00652b3e6838", + "name": "model_name", + "type": "COMBO", + "linkIds": [ + 430 + ], + "pos": [ + -2584.69140625, + 4280 + ] + }, + { + "id": "d6ad1978-71b6-425b-be13-c8f1e1d798d9", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 431 + ], + "label": "lotus_depth_model", + "pos": [ + -2584.69140625, + 4300 + ] + }, + { + "id": "b0545a5d-65e8-4baa-a7be-d5f3d2b8b6e3", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 432 + ], + "label": "sd15_vae", + "pos": [ + -2584.69140625, + 4320 + ] + } + ], + "outputs": [ + { + "id": "4e837941-de2d-4df8-8f94-686e24036897", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 304 + ], + "localized_name": "VIDEO", + "pos": [ + 1770, + 4110 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 93, + "type": "CFGGuider", + "pos": [ + -697.9999467324425, + 3670.0001318308678 + ], + "size": [ + 270, + 106.66666666666667 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 326 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 309 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 311 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 261 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 94, + "type": "KSamplerSelect", + "pos": [ + -697.9999467324425, + 3840.0000630985346 + ], + "size": [ + 270, + 68.88020833333334 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 262 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 99, + "type": "ManualSigmas", + "pos": [ + 409.9999946478922, + 3850.0001667604133 + ], + "size": [ + 270, + 70 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 278 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "0.909375, 0.725, 0.421875, 0.0" + ] + }, + { + "id": 101, + "type": "LTXVConcatAVLatent", + "pos": [ + 409.9999946478922, + 4100.000194929402 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 365 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 266 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 279 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 108, + "type": "CFGGuider", + "pos": [ + 409.9999946478922, + 3700.00007661965 + ], + "size": [ + 270, + 106.66666666666667 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 280 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 281 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 282 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 276 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.71", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 111, + "type": "LTXVEmptyLatentAudio", + "pos": [ + -1100.000003380279, + 4810.000230985708 + ], + "size": [ + 270, + 120 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 285 + }, + { + "localized_name": "frames_number", + "name": "frames_number", + "type": "INT", + "widget": { + "name": "frames_number" + }, + "link": 329 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "INT", + "widget": { + "name": "frame_rate" + }, + "link": 354 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "Latent", + "name": "Latent", + "type": "LATENT", + "links": [ + 300 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVEmptyLatentAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 97, + 25, + 1 + ] + }, + { + "id": 123, + "type": "SamplerCustomAdvanced", + "pos": [ + -387.99998321128277, + 3520.0000416901034 + ], + "size": [ + 213.125, + 120 + ], + "flags": {}, + "order": 30, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 260 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 261 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 262 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 263 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 323 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 272 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 114, + "type": "LTXVConditioning", + "pos": [ + -1134.000099492868, + 4140.000243380063 + ], + "size": [ + 270, + 86.66666666666667 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 292 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 293 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "FLOAT", + "widget": { + "name": "frame_rate" + }, + "link": 355 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 313 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 314 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "LTXVConditioning", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 119, + "type": "CLIPTextEncode", + "pos": [ + -1164.0000442816504, + 3880.0001115491955 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 28, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 294 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 293 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "blurry, low quality, still frame, frames, watermark, overlay, titles, has blurbox, has subtitles" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 116, + "type": "LTXVConcatAVLatent", + "pos": [ + -519.9999874648, + 4700.000189295605 + ], + "size": [ + 187.5, + 60 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 324 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 300 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 322, + 323 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 122, + "type": "LTXVSeparateAVLatent", + "pos": [ + -393.9999813239605, + 3800.0000146478747 + ], + "size": [ + 240, + 60 + ], + "flags": {}, + "order": 29, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 272 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 270 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 266 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 124, + "type": "CLIPTextEncode", + "pos": [ + -1174.9999569014471, + 3514.0002724504593 + ], + "size": [ + 410, + 320 + ], + "flags": {}, + "order": 31, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 295 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 345 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 292 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 98, + "type": "KSamplerSelect", + "pos": [ + 409.9999946478922, + 3980.00004957742 + ], + "size": [ + 270, + 68.88020833333334 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 277 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "gradient_estimation" + ] + }, + { + "id": 95, + "type": "LTXVScheduler", + "pos": [ + -699.9999766197394, + 3980.00004957742 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "latent", + "name": "latent", + "shape": 7, + "type": "LATENT", + "link": 322 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "max_shift", + "name": "max_shift", + "type": "FLOAT", + "widget": { + "name": "max_shift" + }, + "link": null + }, + { + "localized_name": "base_shift", + "name": "base_shift", + "type": "FLOAT", + "widget": { + "name": "base_shift" + }, + "link": null + }, + { + "localized_name": "stretch", + "name": "stretch", + "type": "BOOLEAN", + "widget": { + "name": "stretch" + }, + "link": null + }, + { + "localized_name": "terminal", + "name": "terminal", + "type": "FLOAT", + "widget": { + "name": "terminal" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 263 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "LTXVScheduler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 20, + 2.05, + 0.95, + true, + 0.1 + ] + }, + { + "id": 126, + "type": "RandomNoise", + "pos": [ + -697.9999467324425, + 3520.0000416901034 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 260 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "fixed" + ] + }, + { + "id": 107, + "type": "SamplerCustomAdvanced", + "pos": [ + 709.9999918309934, + 3570.000193802643 + ], + "size": [ + 212.3828125, + 120 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 347 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 276 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 277 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 278 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 279 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [ + 336 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 143, + "type": "RandomNoise", + "pos": [ + 409.9999946478922, + 3570.000193802643 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 347 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize" + ] + }, + { + "id": 139, + "type": "LTXVAudioVAEDecode", + "pos": [ + 1129.9999512676497, + 3840.0000630985346 + ], + "size": [ + 240, + 60 + ], + "flags": {}, + "order": 35, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 338 + }, + { + "label": "Audio VAE", + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 340 + } + ], + "outputs": [ + { + "localized_name": "Audio", + "name": "Audio", + "type": "AUDIO", + "links": [ + 339 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVAudioVAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 134, + "type": "LoraLoaderModelOnly", + "pos": [ + -1650.0000287323687, + 3760.0003323940673 + ], + "size": [ + 420, + 95.546875 + ], + "flags": {}, + "order": 33, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 325 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 426 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 326, + 327 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "ltx-2-19b-ic-lora-depth-control.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Depth-Control/resolve/main/ltx-2-19b-ic-lora-depth-control.safetensors", + "directory": "loras" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-19b-ic-lora-depth-control.safetensors", + 1 + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 138, + "type": "LTXVSeparateAVLatent", + "pos": [ + 730.0000160563236, + 3730.0000214084316 + ], + "size": [ + 193.2916015625, + 60 + ], + "flags": {}, + "order": 34, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 336 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 337, + 351 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 338 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 144, + "type": "VAEDecodeTiled", + "pos": [ + 1119.9999391549845, + 3640.000187042085 + ], + "size": [ + 270, + 150 + ], + "flags": {}, + "order": 36, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 351 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 353 + }, + { + "localized_name": "tile_size", + "name": "tile_size", + "type": "INT", + "widget": { + "name": "tile_size" + }, + "link": null + }, + { + "localized_name": "overlap", + "name": "overlap", + "type": "INT", + "widget": { + "name": "overlap" + }, + "link": null + }, + { + "localized_name": "temporal_size", + "name": "temporal_size", + "type": "INT", + "widget": { + "name": "temporal_size" + }, + "link": null + }, + { + "localized_name": "temporal_overlap", + "name": "temporal_overlap", + "type": "INT", + "widget": { + "name": "temporal_overlap" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 352 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "VAEDecodeTiled", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 512, + 64, + 4096, + 8 + ] + }, + { + "id": 113, + "type": "VAEDecode", + "pos": [ + 1129.9999512676497, + 3530.000145351982 + ], + "size": [ + 240, + 60 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 337 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 291 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 145, + "type": "PrimitiveInt", + "pos": [ + -1630.0000045070383, + 4620.0000923942835 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 354 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24, + "fixed" + ] + }, + { + "id": 148, + "type": "PrimitiveFloat", + "pos": [ + -1630.0000045070383, + 4749.99997521129 + ], + "size": [ + 270, + 66.66666666666667 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 355, + 356 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 115, + "type": "EmptyLTXVLatentVideo", + "pos": [ + -1100.000003380279, + 4609.999988732406 + ], + "size": [ + 270, + 146.66666666666669 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 296 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 297 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 330 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 360 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "EmptyLTXVLatentVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 512, + 97, + 1 + ] + }, + { + "id": 149, + "type": "LTXVImgToVideoInplace", + "pos": [ + -1089.9999912676137, + 4400.000009014077 + ], + "size": [ + 270, + 151.9921875 + ], + "flags": {}, + "order": 37, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 359 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 417 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 360 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": 370 + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 363 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 357 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 118, + "type": "Reroute", + "pos": [ + -229.99999095071237, + 4210.000236619506 + ], + "size": [ + 75, + 26 + ], + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 303 + } + ], + "outputs": [ + { + "name": "", + "type": "VAE", + "links": [ + 289, + 291, + 367 + ] + } + ], + "properties": { + "showOutputText": false, + "horizontal": false + } + }, + { + "id": 151, + "type": "LTXVImgToVideoInplace", + "pos": [ + -19.999999788732577, + 4070.0002501406198 + ], + "size": [ + 270, + 181.9921875 + ], + "flags": {}, + "order": 38, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 367 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 410 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 366 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": 371 + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 368 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 365 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 104, + "type": "LTXVCropGuides", + "pos": [ + -9.999999119719098, + 3840.0000630985346 + ], + "size": [ + 240, + 80 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 310 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 312 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 270 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 281 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 282 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "slot_index": 2, + "links": [ + 287 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVCropGuides", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 112, + "type": "LTXVLatentUpsampler", + "pos": [ + -9.999999119719098, + 3960.0002084505168 + ], + "size": [ + 260, + 80 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 287 + }, + { + "localized_name": "upscale_model", + "name": "upscale_model", + "type": "LATENT_UPSCALE_MODEL", + "link": 288 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 289 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 366 + ] + } + ], + "title": "spatial", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVLatentUpsampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 132, + "type": "LTXVAddGuide", + "pos": [ + -599.9999928169079, + 4420.000216337834 + ], + "size": [ + 270, + 209.16666666666669 + ], + "flags": {}, + "order": 32, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 313 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 314 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 328 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 357 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 418 + }, + { + "localized_name": "frame_idx", + "name": "frame_idx", + "type": "INT", + "widget": { + "name": "frame_idx" + }, + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 309, + 310 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 311, + 312 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 324 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "LTXVAddGuide", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + 1 + ] + }, + { + "id": 96, + "type": "LTXVAudioVAELoader", + "pos": [ + -1650.0000287323687, + 3910.000056337978 + ], + "size": [ + 420, + 68.88020833333334 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 377 + } + ], + "outputs": [ + { + "localized_name": "Audio VAE", + "name": "Audio VAE", + "type": "VAE", + "links": [ + 285, + 340 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVAudioVAELoader", + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-19b-dev-fp8.safetensors" + ] + }, + { + "id": 103, + "type": "CheckpointLoaderSimple", + "pos": [ + -1650.0000287323687, + 3590.0000349295465 + ], + "size": [ + 420, + 108.88020833333334 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 425 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 325 + ] + }, + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 303, + 328, + 353, + 359 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CheckpointLoaderSimple", + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-19b-dev-fp8.safetensors" + ] + }, + { + "id": 105, + "type": "LoraLoaderModelOnly", + "pos": [ + -69.99999741197416, + 3570.000193802643 + ], + "size": [ + 390, + 95.546875 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 327 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 429 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 280 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "ltx-2-19b-distilled-lora-384.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-lora-384.safetensors", + "directory": "loras" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-19b-distilled-lora-384.safetensors", + 1 + ] + }, + { + "id": 100, + "type": "LatentUpscaleModelLoader", + "pos": [ + -69.99999741197416, + 3700.00007661965 + ], + "size": [ + 390, + 68.88020833333334 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "model_name", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": 430 + } + ], + "outputs": [ + { + "localized_name": "LATENT_UPSCALE_MODEL", + "name": "LATENT_UPSCALE_MODEL", + "type": "LATENT_UPSCALE_MODEL", + "links": [ + 288 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LatentUpscaleModelLoader", + "models": [ + { + "name": "ltx-2-spatial-upscaler-x2-1.0.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-spatial-upscaler-x2-1.0.safetensors", + "directory": "latent_upscale_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ltx-2-spatial-upscaler-x2-1.0.safetensors" + ] + }, + { + "id": 110, + "type": "GetImageSize", + "pos": [ + -1630.0000045070383, + 4450.000161126616 + ], + "size": [ + 260, + 80 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 416 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 296 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 297 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": [ + 329, + 330 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 106, + "type": "CreateVideo", + "pos": [ + 1419.9999363380857, + 3760.0003323940673 + ], + "size": [ + 270, + 86.66666666666667 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 352 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 339 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 356 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 304 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CreateVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 187, + "type": "ImageFromBatch", + "pos": [ + -2310.000095774562, + 3689.999972957771 + ], + "size": [ + 260, + 93.33333333333334 + ], + "flags": {}, + "order": 39, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 412 + }, + { + "localized_name": "batch_index", + "name": "batch_index", + "type": "INT", + "widget": { + "name": "batch_index" + }, + "link": null + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 422 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 415 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "ImageFromBatch", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + 121 + ] + }, + { + "id": 191, + "type": "ResizeImageMaskNode", + "pos": [ + -2320.0000163380137, + 3850.0001667604133 + ], + "size": [ + 284.375, + 154 + ], + "flags": {}, + "order": 43, + "mode": 0, + "inputs": [ + { + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": 415 + }, + { + "localized_name": "resize_type", + "name": "resize_type", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "resize_type" + }, + "link": null + }, + { + "localized_name": "width", + "name": "resize_type.width", + "type": "INT", + "widget": { + "name": "resize_type.width" + }, + "link": 420 + }, + { + "localized_name": "height", + "name": "resize_type.height", + "type": "INT", + "widget": { + "name": "resize_type.height" + }, + "link": 421 + }, + { + "localized_name": "crop", + "name": "resize_type.crop", + "type": "COMBO", + "widget": { + "name": "resize_type.crop" + }, + "link": null + }, + { + "localized_name": "scale_method", + "name": "scale_method", + "type": "COMBO", + "widget": { + "name": "scale_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "resized", + "name": "resized", + "type": "IMAGE", + "links": [ + 413 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "ResizeImageMaskNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "scale dimensions", + 1280, + 720, + "center", + "lanczos" + ] + }, + { + "id": 188, + "type": "GetVideoComponents", + "pos": [ + -2320.0000163380137, + 3520.0000416901034 + ], + "size": [ + 280, + 80 + ], + "flags": { + "collapsed": false + }, + "order": 40, + "mode": 0, + "inputs": [ + { + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": 419 + } + ], + "outputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "links": [ + 412 + ] + }, + { + "localized_name": "audio", + "name": "audio", + "type": "AUDIO", + "links": [] + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "GetVideoComponents", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 189, + "type": "ImageScaleBy", + "pos": [ + -1990.0000743661303, + 3670.0001318308678 + ], + "size": [ + 280, + 125.546875 + ], + "flags": {}, + "order": 41, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 413 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "scale_by", + "name": "scale_by", + "type": "FLOAT", + "widget": { + "name": "scale_by" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 414 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ImageScaleBy", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "lanczos", + 0.5 + ] + }, + { + "id": 154, + "type": "MarkdownNote", + "pos": [ + -1659.9999492958204, + 4870.000120563272 + ], + "size": [ + 350, + 170 + ], + "flags": { + "collapsed": false + }, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Frame Rate Note", + "properties": {}, + "widgets_values": [ + "Please make sure the frame rate value is the same in both boxes" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 190, + "type": "38b60539-50a7-42f9-a5fe-bdeca26272e2", + "pos": [ + -1999.9999949295823, + 3910.000056337978 + ], + "size": [ + 310, + 106 + ], + "flags": {}, + "order": 42, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 414 + }, + { + "label": "depth_intensity", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 431 + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 432 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 416, + 417, + 418 + ] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "sigma" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.5.1", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 999.0000000000002, + "lotus-depth-d-v1-1.safetensors", + "vae-ft-mse-840000-ema-pruned.safetensors" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 97, + "type": "LTXAVTextEncoderLoader", + "pos": [ + -1650.0000287323687, + 4040.0003053518376 + ], + "size": [ + 420, + 124.44010416666667 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "text_encoder", + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": 427 + }, + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 433 + }, + { + "localized_name": "device", + "name": "device", + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 294, + 295 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXAVTextEncoderLoader", + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + }, + { + "name": "gemma_3_12B_it_fp4_mixed.safetensors", + "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2-19b-dev-fp8.safetensors", + "default" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -1660, + 3440, + 440, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Basic Sampling", + "bounding": [ + -700, + 3440, + 570, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + -1180, + 3440, + 440, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "Latent", + "bounding": [ + -1180, + 4290, + 1050, + 680 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 9, + "title": "Upscale Sampling(2x)", + "bounding": [ + -100, + 3440, + 1090, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Sampler", + "bounding": [ + 350, + 3480, + 620, + 750 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Model", + "bounding": [ + -90, + 3480, + 430, + 310 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 11, + "title": "Frame rate", + "bounding": [ + -1640, + 4550, + 290, + 271.6 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 16, + "title": "Video Preprocess", + "bounding": [ + -2330, + 3450, + 650, + 567.6 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 15, + "title": "video length", + "bounding": [ + -2320, + 3620, + 290, + 180 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 326, + "origin_id": 134, + "origin_slot": 0, + "target_id": 93, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 309, + "origin_id": 132, + "origin_slot": 0, + "target_id": 93, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 311, + "origin_id": 132, + "origin_slot": 1, + "target_id": 93, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 266, + "origin_id": 122, + "origin_slot": 1, + "target_id": 101, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 280, + "origin_id": 105, + "origin_slot": 0, + "target_id": 108, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 281, + "origin_id": 104, + "origin_slot": 0, + "target_id": 108, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 282, + "origin_id": 104, + "origin_slot": 1, + "target_id": 108, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 285, + "origin_id": 96, + "origin_slot": 0, + "target_id": 111, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 329, + "origin_id": 110, + "origin_slot": 2, + "target_id": 111, + "target_slot": 1, + "type": "INT" + }, + { + "id": 260, + "origin_id": 126, + "origin_slot": 0, + "target_id": 123, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 261, + "origin_id": 93, + "origin_slot": 0, + "target_id": 123, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 262, + "origin_id": 94, + "origin_slot": 0, + "target_id": 123, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 263, + "origin_id": 95, + "origin_slot": 0, + "target_id": 123, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 323, + "origin_id": 116, + "origin_slot": 0, + "target_id": 123, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 296, + "origin_id": 110, + "origin_slot": 0, + "target_id": 115, + "target_slot": 0, + "type": "INT" + }, + { + "id": 297, + "origin_id": 110, + "origin_slot": 1, + "target_id": 115, + "target_slot": 1, + "type": "INT" + }, + { + "id": 330, + "origin_id": 110, + "origin_slot": 2, + "target_id": 115, + "target_slot": 2, + "type": "INT" + }, + { + "id": 325, + "origin_id": 103, + "origin_slot": 0, + "target_id": 134, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 292, + "origin_id": 124, + "origin_slot": 0, + "target_id": 114, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 293, + "origin_id": 119, + "origin_slot": 0, + "target_id": 114, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 294, + "origin_id": 97, + "origin_slot": 0, + "target_id": 119, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 324, + "origin_id": 132, + "origin_slot": 2, + "target_id": 116, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 300, + "origin_id": 111, + "origin_slot": 0, + "target_id": 116, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 313, + "origin_id": 114, + "origin_slot": 0, + "target_id": 132, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 314, + "origin_id": 114, + "origin_slot": 1, + "target_id": 132, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 328, + "origin_id": 103, + "origin_slot": 2, + "target_id": 132, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 272, + "origin_id": 123, + "origin_slot": 0, + "target_id": 122, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 336, + "origin_id": 107, + "origin_slot": 1, + "target_id": 138, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 339, + "origin_id": 139, + "origin_slot": 0, + "target_id": 106, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 295, + "origin_id": 97, + "origin_slot": 0, + "target_id": 124, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 303, + "origin_id": 103, + "origin_slot": 2, + "target_id": 118, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 338, + "origin_id": 138, + "origin_slot": 1, + "target_id": 139, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 340, + "origin_id": 96, + "origin_slot": 0, + "target_id": 139, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 337, + "origin_id": 138, + "origin_slot": 0, + "target_id": 113, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 291, + "origin_id": 118, + "origin_slot": 0, + "target_id": 113, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 276, + "origin_id": 108, + "origin_slot": 0, + "target_id": 107, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 277, + "origin_id": 98, + "origin_slot": 0, + "target_id": 107, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 278, + "origin_id": 99, + "origin_slot": 0, + "target_id": 107, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 279, + "origin_id": 101, + "origin_slot": 0, + "target_id": 107, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 327, + "origin_id": 134, + "origin_slot": 0, + "target_id": 105, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 310, + "origin_id": 132, + "origin_slot": 0, + "target_id": 104, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 312, + "origin_id": 132, + "origin_slot": 1, + "target_id": 104, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 270, + "origin_id": 122, + "origin_slot": 0, + "target_id": 104, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 287, + "origin_id": 104, + "origin_slot": 2, + "target_id": 112, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 288, + "origin_id": 100, + "origin_slot": 0, + "target_id": 112, + "target_slot": 1, + "type": "LATENT_UPSCALE_MODEL" + }, + { + "id": 289, + "origin_id": 118, + "origin_slot": 0, + "target_id": 112, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 322, + "origin_id": 116, + "origin_slot": 0, + "target_id": 95, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 304, + "origin_id": 106, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 345, + "origin_id": -10, + "origin_slot": 0, + "target_id": 124, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 347, + "origin_id": 143, + "origin_slot": 0, + "target_id": 107, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 351, + "origin_id": 138, + "origin_slot": 0, + "target_id": 144, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 352, + "origin_id": 144, + "origin_slot": 0, + "target_id": 106, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 353, + "origin_id": 103, + "origin_slot": 2, + "target_id": 144, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 354, + "origin_id": 145, + "origin_slot": 0, + "target_id": 111, + "target_slot": 2, + "type": "INT" + }, + { + "id": 355, + "origin_id": 148, + "origin_slot": 0, + "target_id": 114, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 356, + "origin_id": 148, + "origin_slot": 0, + "target_id": 106, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 357, + "origin_id": 149, + "origin_slot": 0, + "target_id": 132, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 359, + "origin_id": 103, + "origin_slot": 2, + "target_id": 149, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 360, + "origin_id": 115, + "origin_slot": 0, + "target_id": 149, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 363, + "origin_id": -10, + "origin_slot": 2, + "target_id": 149, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 365, + "origin_id": 151, + "origin_slot": 0, + "target_id": 101, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 366, + "origin_id": 112, + "origin_slot": 0, + "target_id": 151, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 367, + "origin_id": 118, + "origin_slot": 0, + "target_id": 151, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 368, + "origin_id": -10, + "origin_slot": 2, + "target_id": 151, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 370, + "origin_id": -10, + "origin_slot": 1, + "target_id": 149, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 371, + "origin_id": -10, + "origin_slot": 1, + "target_id": 151, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 377, + "origin_id": -10, + "origin_slot": 6, + "target_id": 96, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 410, + "origin_id": -10, + "origin_slot": 4, + "target_id": 151, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 412, + "origin_id": 188, + "origin_slot": 0, + "target_id": 187, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 413, + "origin_id": 191, + "origin_slot": 0, + "target_id": 189, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 414, + "origin_id": 189, + "origin_slot": 0, + "target_id": 190, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 415, + "origin_id": 187, + "origin_slot": 0, + "target_id": 191, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 416, + "origin_id": 190, + "origin_slot": 0, + "target_id": 110, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 417, + "origin_id": 190, + "origin_slot": 0, + "target_id": 149, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 418, + "origin_id": 190, + "origin_slot": 0, + "target_id": 132, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 419, + "origin_id": -10, + "origin_slot": 3, + "target_id": 188, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 420, + "origin_id": -10, + "origin_slot": 5, + "target_id": 191, + "target_slot": 2, + "type": "INT" + }, + { + "id": 421, + "origin_id": -10, + "origin_slot": 6, + "target_id": 191, + "target_slot": 3, + "type": "INT" + }, + { + "id": 422, + "origin_id": -10, + "origin_slot": 7, + "target_id": 187, + "target_slot": 2, + "type": "INT" + }, + { + "id": 425, + "origin_id": -10, + "origin_slot": 8, + "target_id": 103, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 426, + "origin_id": -10, + "origin_slot": 9, + "target_id": 134, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 427, + "origin_id": -10, + "origin_slot": 10, + "target_id": 97, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 429, + "origin_id": -10, + "origin_slot": 11, + "target_id": 105, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 430, + "origin_id": -10, + "origin_slot": 12, + "target_id": 100, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 431, + "origin_id": -10, + "origin_slot": 13, + "target_id": 190, + "target_slot": 2, + "type": "COMBO" + }, + { + "id": 432, + "origin_id": -10, + "origin_slot": 14, + "target_id": 190, + "target_slot": 3, + "type": "COMBO" + }, + { + "id": 433, + "origin_id": -10, + "origin_slot": 8, + "target_id": 97, + "target_slot": 1, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video generation and editing/Depth to video" + }, + { + "id": "38b60539-50a7-42f9-a5fe-bdeca26272e2", + "version": 1, + "state": { + "lastGroupId": 16, + "lastNodeId": 191, + "lastLinkId": 433, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image to Depth Map (Lotus)", + "inputNode": { + "id": -10, + "bounding": [ + -60, + -172.61268043518066, + 126.625, + 120 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1650, + -172.61268043518066, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "3bdd30c3-4ec9-485a-814b-e7d39fb6b5cc", + "name": "pixels", + "type": "IMAGE", + "linkIds": [ + 37 + ], + "localized_name": "pixels", + "pos": [ + 46.625, + -152.61268043518066 + ] + }, + { + "id": "f9a1017c-f4b9-43b4-94c2-41c088b3a492", + "name": "sigma", + "type": "FLOAT", + "linkIds": [ + 243 + ], + "label": "depth_intensity", + "pos": [ + 46.625, + -132.61268043518066 + ] + }, + { + "id": "374bfecc-34bb-47f9-82b6-cbe9383f8756", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 423 + ], + "pos": [ + 46.625, + -112.61268043518066 + ] + }, + { + "id": "bb8707a1-46c3-44be-a15a-0adc908d871d", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 424 + ], + "pos": [ + 46.625, + -92.61268043518066 + ] + } + ], + "outputs": [ + { + "id": "2ec278bd-0b66-4b30-9c5b-994d5f638214", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 242 + ], + "localized_name": "IMAGE", + "pos": [ + 1670, + -152.61268043518066 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 1380, + -240 + ], + "size": [ + 210, + 46 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 232 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 240 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 35 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 10, + "type": "UNETLoader", + "pos": [ + 135.34181213378906, + -290.1947937011719 + ], + "size": [ + 305.93701171875, + 82 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 423 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 31, + 241 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "lotus-depth-d-v1-1.safetensors", + "url": "https://huggingface.co/Comfy-Org/lotus/resolve/main/lotus-depth-d-v1-1.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "lotus-depth-d-v1-1.safetensors", + "default" + ] + }, + { + "id": 14, + "type": "VAELoader", + "pos": [ + 134.531494140625, + -165.18197631835938 + ], + "size": [ + 305.93701171875, + 58 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 424 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 38, + 240 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "vae-ft-mse-840000-ema-pruned.safetensors", + "url": "https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "vae-ft-mse-840000-ema-pruned.safetensors" + ] + }, + { + "id": 16, + "type": "SamplerCustomAdvanced", + "pos": [ + 990.6585693359375, + -319.9144287109375 + ], + "size": [ + 355.20001220703125, + 326 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 237 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 27 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 33 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 194 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 201 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "slot_index": 0, + "links": [ + 232 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "slot_index": 1, + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 18, + "type": "DisableNoise", + "pos": [ + 730.47705078125, + -320 + ], + "size": [ + 210, + 26 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "slot_index": 0, + "links": [ + 237 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "DisableNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 19, + "type": "BasicGuider", + "pos": [ + 730.2631225585938, + -251.22537231445312 + ], + "size": [ + 210, + 46 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 241 + }, + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 238 + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "slot_index": 0, + "links": [ + 27 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "BasicGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 20, + "type": "BasicScheduler", + "pos": [ + 488.64459228515625, + -147.67201232910156 + ], + "size": [ + 210, + 106 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 31 + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "slot_index": 0, + "links": [ + 66 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "BasicScheduler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "normal", + 1, + 1 + ] + }, + { + "id": 21, + "type": "KSamplerSelect", + "pos": [ + 730.2631225585938, + -161.22537231445312 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "slot_index": 0, + "links": [ + 33 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 22, + "type": "ImageInvert", + "pos": [ + 1380, + -310 + ], + "size": [ + 210, + 26 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 35 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 242 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "ImageInvert", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 23, + "type": "VAEEncode", + "pos": [ + 730.2631225585938, + 38.77463912963867 + ], + "size": [ + 210, + 46 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 37 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 38 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 201 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAEEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 28, + "type": "SetFirstSigma", + "pos": [ + 730.2631225585938, + -61.22536087036133 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 66 + }, + { + "localized_name": "sigma", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": 243 + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "slot_index": 0, + "links": [ + 194 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "SetFirstSigma", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + 999.0000000000002 + ] + }, + { + "id": 68, + "type": "LotusConditioning", + "pos": [ + 490, + -230 + ], + "size": [ + 210, + 26 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 238 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "LotusConditioning", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + } + ], + "groups": [ + { + "id": 1, + "title": "Load Models", + "bounding": [ + 120, + -370, + 335, + 281.6000061035156 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 232, + "origin_id": 16, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 240, + "origin_id": 14, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 237, + "origin_id": 18, + "origin_slot": 0, + "target_id": 16, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 27, + "origin_id": 19, + "origin_slot": 0, + "target_id": 16, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 33, + "origin_id": 21, + "origin_slot": 0, + "target_id": 16, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 194, + "origin_id": 28, + "origin_slot": 0, + "target_id": 16, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 201, + "origin_id": 23, + "origin_slot": 0, + "target_id": 16, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 241, + "origin_id": 10, + "origin_slot": 0, + "target_id": 19, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 238, + "origin_id": 68, + "origin_slot": 0, + "target_id": 19, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 31, + "origin_id": 10, + "origin_slot": 0, + "target_id": 20, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 35, + "origin_id": 8, + "origin_slot": 0, + "target_id": 22, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 38, + "origin_id": 14, + "origin_slot": 0, + "target_id": 23, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 66, + "origin_id": 20, + "origin_slot": 0, + "target_id": 28, + "target_slot": 0, + "type": "SIGMAS" + }, + { + "id": 37, + "origin_id": -10, + "origin_slot": 0, + "target_id": 23, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 242, + "origin_id": 22, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 243, + "origin_id": -10, + "origin_slot": 1, + "target_id": 28, + "target_slot": 1, + "type": "FLOAT" + }, + { + "id": 423, + "origin_id": -10, + "origin_slot": 2, + "target_id": 10, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 424, + "origin_id": -10, + "origin_slot": 3, + "target_id": 14, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + } + } + ] + }, + "config": {}, + "extra": { + "ds": { + "scale": 1.313181818181818, + "offset": [ + 271.9196871428176, + -3845.0123774536323 + ] + }, + "workflowRendererVersion": "LG" + }, + "version": 0.4 +} \ No newline at end of file diff --git a/blueprints/Edge-Preserving Blur.json b/blueprints/Edge-Preserving Blur.json index 4f2416e9b..18012beb1 100644 --- a/blueprints/Edge-Preserving Blur.json +++ b/blueprints/Edge-Preserving Blur.json @@ -1 +1,458 @@ -{"revision": 0, "last_node_id": 136, "last_link_id": 0, "nodes": [{"id": 136, "type": "c6dc0f88-416b-4db1-bed1-442d793de5ad", "pos": [669.0822222222221, 835.5507407407408], "size": [210, 106], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["130", "value"], ["131", "value"], ["133", "value"]]}, "widgets_values": [], "title": "Edge-Preserving Blur"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "c6dc0f88-416b-4db1-bed1-442d793de5ad", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 138, "lastLinkId": 109, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Edge-Preserving Blur", "inputNode": {"id": -10, "bounding": [1750, -620, 120, 60]}, "outputNode": {"id": -20, "bounding": [2700, -620, 120, 60]}, "inputs": [{"id": "06a6d0ad-25d7-4784-8c72-7fc8e7110a22", "name": "images.image0", "type": "IMAGE", "linkIds": [106], "localized_name": "images.image0", "label": "image", "pos": [1850, -600]}], "outputs": [{"id": "3ae9f5d7-be63-4c9f-9893-6f848defa377", "name": "IMAGE0", "type": "IMAGE", "linkIds": [99], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [2720, -600]}], "widgets": [], "nodes": [{"id": 128, "type": "GLSLShader", "pos": [2220, -860], "size": [420, 252], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 106}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 100}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 101}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": 107}, {"label": "u_int1", "localized_name": "ints.u_int1", "name": "ints.u_int1", "shape": 7, "type": "INT", "link": 103}, {"label": "u_int2", "localized_name": "ints.u_int2", "name": "ints.u_int2", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [99]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // Blur radius (0–20, default ~5)\nuniform float u_float1; // Edge threshold (0–100, default ~30)\nuniform int u_int0; // Step size (0/1 = every pixel, 2+ = skip pixels)\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int MAX_RADIUS = 20;\nconst float EPSILON = 0.0001;\n\n// Perceptual luminance\nfloat getLuminance(vec3 rgb) {\n return dot(rgb, vec3(0.299, 0.587, 0.114));\n}\n\nvec4 bilateralFilter(vec2 uv, vec2 texelSize, int radius,\n float sigmaSpatial, float sigmaColor)\n{\n vec4 center = texture(u_image0, uv);\n vec3 centerRGB = center.rgb;\n\n float invSpatial2 = -0.5 / (sigmaSpatial * sigmaSpatial);\n float invColor2 = -0.5 / (sigmaColor * sigmaColor + EPSILON);\n\n vec3 sumRGB = vec3(0.0);\n float sumWeight = 0.0;\n\n int step = max(u_int0, 1);\n float radius2 = float(radius * radius);\n\n for (int dy = -MAX_RADIUS; dy <= MAX_RADIUS; dy++) {\n if (dy < -radius || dy > radius) continue;\n if (abs(dy) % step != 0) continue;\n\n for (int dx = -MAX_RADIUS; dx <= MAX_RADIUS; dx++) {\n if (dx < -radius || dx > radius) continue;\n if (abs(dx) % step != 0) continue;\n\n vec2 offset = vec2(float(dx), float(dy));\n float dist2 = dot(offset, offset);\n if (dist2 > radius2) continue;\n\n vec3 sampleRGB = texture(u_image0, uv + offset * texelSize).rgb;\n\n // Spatial Gaussian\n float spatialWeight = exp(dist2 * invSpatial2);\n\n // Perceptual color distance (weighted RGB)\n vec3 diff = sampleRGB - centerRGB;\n float colorDist = dot(diff * diff, vec3(0.299, 0.587, 0.114));\n float colorWeight = exp(colorDist * invColor2);\n\n float w = spatialWeight * colorWeight;\n sumRGB += sampleRGB * w;\n sumWeight += w;\n }\n }\n\n vec3 resultRGB = sumRGB / max(sumWeight, EPSILON);\n return vec4(resultRGB, center.a); // preserve center alpha\n}\n\nvoid main() {\n vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));\n\n float radiusF = clamp(u_float0, 0.0, float(MAX_RADIUS));\n int radius = int(radiusF + 0.5);\n\n if (radius == 0) {\n fragColor = texture(u_image0, v_texCoord);\n return;\n }\n\n // Edge threshold → color sigma\n // Squared curve for better low-end control\n float t = clamp(u_float1, 0.0, 100.0) / 100.0;\n t *= t;\n float sigmaColor = mix(0.01, 0.5, t);\n\n // Spatial sigma tied to radius\n float sigmaSpatial = max(radiusF * 0.75, 0.5);\n\n fragColor = bilateralFilter(\n v_texCoord,\n texelSize,\n radius,\n sigmaSpatial,\n sigmaColor\n );\n}", "from_input"]}, {"id": 130, "type": "PrimitiveFloat", "pos": [1930, -860], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "blur_radius", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [100]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 20, "step": 0.5, "precision": 1}, "widgets_values": [20]}, {"id": 131, "type": "PrimitiveFloat", "pos": [1930, -760], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "edge_threshold", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [101]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "step": 1}, "widgets_values": [50]}, {"id": 133, "type": "PrimitiveInt", "pos": [1930, -660], "size": [270, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "step_size", "localized_name": "value", "name": "value", "type": "INT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "INT", "name": "INT", "type": "INT", "links": [103, 107]}], "properties": {"Node name for S&R": "PrimitiveInt", "min": 0}, "widgets_values": [1, "fixed"]}], "groups": [], "links": [{"id": 100, "origin_id": 130, "origin_slot": 0, "target_id": 128, "target_slot": 2, "type": "FLOAT"}, {"id": 101, "origin_id": 131, "origin_slot": 0, "target_id": 128, "target_slot": 3, "type": "FLOAT"}, {"id": 107, "origin_id": 133, "origin_slot": 0, "target_id": 128, "target_slot": 5, "type": "INT"}, {"id": 103, "origin_id": 133, "origin_slot": 0, "target_id": 128, "target_slot": 6, "type": "INT"}, {"id": 106, "origin_id": -10, "origin_slot": 0, "target_id": 128, "target_slot": 0, "type": "IMAGE"}, {"id": 99, "origin_id": 128, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Blur"}]}, "extra": {}} +{ + "revision": 0, + "last_node_id": 136, + "last_link_id": 0, + "nodes": [ + { + "id": 136, + "type": "c6dc0f88-416b-4db1-bed1-442d793de5ad", + "pos": [ + 669.0822222222221, + 835.5507407407408 + ], + "size": [ + 210, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "130", + "value" + ], + [ + "131", + "value" + ], + [ + "133", + "value" + ] + ] + }, + "widgets_values": [], + "title": "Edge-Preserving Blur" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "c6dc0f88-416b-4db1-bed1-442d793de5ad", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 138, + "lastLinkId": 109, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Edge-Preserving Blur", + "inputNode": { + "id": -10, + "bounding": [ + 1750, + -620, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 2700, + -620, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "06a6d0ad-25d7-4784-8c72-7fc8e7110a22", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 106 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 1850, + -600 + ] + } + ], + "outputs": [ + { + "id": "3ae9f5d7-be63-4c9f-9893-6f848defa377", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 99 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 2720, + -600 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 128, + "type": "GLSLShader", + "pos": [ + 2220, + -860 + ], + "size": [ + 420, + 252 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 106 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 100 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 101 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": 107 + }, + { + "label": "u_int1", + "localized_name": "ints.u_int1", + "name": "ints.u_int1", + "shape": 7, + "type": "INT", + "link": 103 + }, + { + "label": "u_int2", + "localized_name": "ints.u_int2", + "name": "ints.u_int2", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 99 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // Blur radius (0–20, default ~5)\nuniform float u_float1; // Edge threshold (0–100, default ~30)\nuniform int u_int0; // Step size (0/1 = every pixel, 2+ = skip pixels)\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int MAX_RADIUS = 20;\nconst float EPSILON = 0.0001;\n\n// Perceptual luminance\nfloat getLuminance(vec3 rgb) {\n return dot(rgb, vec3(0.299, 0.587, 0.114));\n}\n\nvec4 bilateralFilter(vec2 uv, vec2 texelSize, int radius,\n float sigmaSpatial, float sigmaColor)\n{\n vec4 center = texture(u_image0, uv);\n vec3 centerRGB = center.rgb;\n\n float invSpatial2 = -0.5 / (sigmaSpatial * sigmaSpatial);\n float invColor2 = -0.5 / (sigmaColor * sigmaColor + EPSILON);\n\n vec3 sumRGB = vec3(0.0);\n float sumWeight = 0.0;\n\n int step = max(u_int0, 1);\n float radius2 = float(radius * radius);\n\n for (int dy = -MAX_RADIUS; dy <= MAX_RADIUS; dy++) {\n if (dy < -radius || dy > radius) continue;\n if (abs(dy) % step != 0) continue;\n\n for (int dx = -MAX_RADIUS; dx <= MAX_RADIUS; dx++) {\n if (dx < -radius || dx > radius) continue;\n if (abs(dx) % step != 0) continue;\n\n vec2 offset = vec2(float(dx), float(dy));\n float dist2 = dot(offset, offset);\n if (dist2 > radius2) continue;\n\n vec3 sampleRGB = texture(u_image0, uv + offset * texelSize).rgb;\n\n // Spatial Gaussian\n float spatialWeight = exp(dist2 * invSpatial2);\n\n // Perceptual color distance (weighted RGB)\n vec3 diff = sampleRGB - centerRGB;\n float colorDist = dot(diff * diff, vec3(0.299, 0.587, 0.114));\n float colorWeight = exp(colorDist * invColor2);\n\n float w = spatialWeight * colorWeight;\n sumRGB += sampleRGB * w;\n sumWeight += w;\n }\n }\n\n vec3 resultRGB = sumRGB / max(sumWeight, EPSILON);\n return vec4(resultRGB, center.a); // preserve center alpha\n}\n\nvoid main() {\n vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));\n\n float radiusF = clamp(u_float0, 0.0, float(MAX_RADIUS));\n int radius = int(radiusF + 0.5);\n\n if (radius == 0) {\n fragColor = texture(u_image0, v_texCoord);\n return;\n }\n\n // Edge threshold → color sigma\n // Squared curve for better low-end control\n float t = clamp(u_float1, 0.0, 100.0) / 100.0;\n t *= t;\n float sigmaColor = mix(0.01, 0.5, t);\n\n // Spatial sigma tied to radius\n float sigmaSpatial = max(radiusF * 0.75, 0.5);\n\n fragColor = bilateralFilter(\n v_texCoord,\n texelSize,\n radius,\n sigmaSpatial,\n sigmaColor\n );\n}", + "from_input" + ] + }, + { + "id": 130, + "type": "PrimitiveFloat", + "pos": [ + 1930, + -860 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "blur_radius", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 100 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 20, + "step": 0.5, + "precision": 1 + }, + "widgets_values": [ + 20 + ] + }, + { + "id": 131, + "type": "PrimitiveFloat", + "pos": [ + 1930, + -760 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "edge_threshold", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 101 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "step": 1 + }, + "widgets_values": [ + 50 + ] + }, + { + "id": 133, + "type": "PrimitiveInt", + "pos": [ + 1930, + -660 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "step_size", + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 103, + 107 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveInt", + "min": 0 + }, + "widgets_values": [ + 1, + "fixed" + ] + } + ], + "groups": [], + "links": [ + { + "id": 100, + "origin_id": 130, + "origin_slot": 0, + "target_id": 128, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 101, + "origin_id": 131, + "origin_slot": 0, + "target_id": 128, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 107, + "origin_id": 133, + "origin_slot": 0, + "target_id": 128, + "target_slot": 5, + "type": "INT" + }, + { + "id": 103, + "origin_id": 133, + "origin_slot": 0, + "target_id": 128, + "target_slot": 6, + "type": "INT" + }, + { + "id": 106, + "origin_id": -10, + "origin_slot": 0, + "target_id": 128, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 99, + "origin_id": 128, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Blur" + } + ] + }, + "extra": {} +} diff --git a/blueprints/Film Grain.json b/blueprints/Film Grain.json index b7ebe2a36..a680b3ece 100644 --- a/blueprints/Film Grain.json +++ b/blueprints/Film Grain.json @@ -1 +1,587 @@ -{"revision": 0, "last_node_id": 22, "last_link_id": 0, "nodes": [{"id": 22, "type": "3324cf54-bcff-405f-a4bf-c5122c72fe56", "pos": [4800, -1180], "size": [250, 154], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "title": "Film Grain", "properties": {"proxyWidgets": [["17", "value"], ["18", "value"], ["19", "value"], ["20", "value"], ["21", "choice"]]}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "3324cf54-bcff-405f-a4bf-c5122c72fe56", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 21, "lastLinkId": 30, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Film Grain", "inputNode": {"id": -10, "bounding": [4096.671470760602, -948.2184031393472, 120, 60]}, "outputNode": {"id": -20, "bounding": [4900, -948.2184031393472, 120, 60]}, "inputs": [{"id": "062968ea-da25-47e7-a180-d913c267f148", "name": "images.image0", "type": "IMAGE", "linkIds": [22], "localized_name": "images.image0", "label": "image", "pos": [4196.671470760602, -928.2184031393472]}], "outputs": [{"id": "43247d06-a39f-4733-9828-c39400fe02a4", "name": "IMAGE0", "type": "IMAGE", "linkIds": [23], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [4920, -928.2184031393472]}], "widgets": [], "nodes": [{"id": 15, "type": "GLSLShader", "pos": [4510, -1180], "size": [330, 272], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 22}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 26}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 27}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": 28}, {"label": "u_float3", "localized_name": "floats.u_float3", "name": "floats.u_float3", "shape": 7, "type": "FLOAT", "link": 29}, {"label": "u_float4", "localized_name": "floats.u_float4", "name": "floats.u_float4", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": 30}, {"label": "u_int1", "localized_name": "ints.u_int1", "name": "ints.u_int1", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [23]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // grain amount [0.0 – 1.0] typical: 0.2–0.8\nuniform float u_float1; // grain size [0.3 – 3.0] lower = finer grain\nuniform float u_float2; // color amount [0.0 – 1.0] 0 = monochrome, 1 = RGB grain\nuniform float u_float3; // luminance bias [0.0 – 1.0] 0 = uniform, 1 = shadows only\nuniform int u_int0; // noise mode [0 or 1] 0 = smooth, 1 = grainy\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\n// High-quality integer hash (pcg-like)\nuint pcg(uint v) {\n uint state = v * 747796405u + 2891336453u;\n uint word = ((state >> ((state >> 28u) + 4u)) ^ state) * 277803737u;\n return (word >> 22u) ^ word;\n}\n\n// 2D -> 1D hash input\nuint hash2d(uvec2 p) {\n return pcg(p.x + pcg(p.y));\n}\n\n// Hash to float [0, 1]\nfloat hashf(uvec2 p) {\n return float(hash2d(p)) / float(0xffffffffu);\n}\n\n// Hash to float with offset (for RGB channels)\nfloat hashf(uvec2 p, uint offset) {\n return float(pcg(hash2d(p) + offset)) / float(0xffffffffu);\n}\n\n// Convert uniform [0,1] to roughly Gaussian distribution\n// Using simple approximation: average of multiple samples\nfloat toGaussian(uvec2 p) {\n float sum = hashf(p, 0u) + hashf(p, 1u) + hashf(p, 2u) + hashf(p, 3u);\n return (sum - 2.0) * 0.7; // Centered, scaled\n}\n\nfloat toGaussian(uvec2 p, uint offset) {\n float sum = hashf(p, offset) + hashf(p, offset + 1u) \n + hashf(p, offset + 2u) + hashf(p, offset + 3u);\n return (sum - 2.0) * 0.7;\n}\n\n// Smooth noise with better interpolation\nfloat smoothNoise(vec2 p) {\n vec2 i = floor(p);\n vec2 f = fract(p);\n \n // Quintic interpolation (less banding than cubic)\n f = f * f * f * (f * (f * 6.0 - 15.0) + 10.0);\n \n uvec2 ui = uvec2(i);\n float a = toGaussian(ui);\n float b = toGaussian(ui + uvec2(1u, 0u));\n float c = toGaussian(ui + uvec2(0u, 1u));\n float d = toGaussian(ui + uvec2(1u, 1u));\n \n return mix(mix(a, b, f.x), mix(c, d, f.x), f.y);\n}\n\nfloat smoothNoise(vec2 p, uint offset) {\n vec2 i = floor(p);\n vec2 f = fract(p);\n \n f = f * f * f * (f * (f * 6.0 - 15.0) + 10.0);\n \n uvec2 ui = uvec2(i);\n float a = toGaussian(ui, offset);\n float b = toGaussian(ui + uvec2(1u, 0u), offset);\n float c = toGaussian(ui + uvec2(0u, 1u), offset);\n float d = toGaussian(ui + uvec2(1u, 1u), offset);\n \n return mix(mix(a, b, f.x), mix(c, d, f.x), f.y);\n}\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n \n // Luminance (Rec.709)\n float luma = dot(color.rgb, vec3(0.2126, 0.7152, 0.0722));\n \n // Grain UV (resolution-independent)\n vec2 grainUV = v_texCoord * u_resolution / max(u_float1, 0.01);\n uvec2 grainPixel = uvec2(grainUV);\n \n float g;\n vec3 grainRGB;\n \n if (u_int0 == 1) {\n // Grainy mode: pure hash noise (no interpolation = no banding)\n g = toGaussian(grainPixel);\n grainRGB = vec3(\n toGaussian(grainPixel, 100u),\n toGaussian(grainPixel, 200u),\n toGaussian(grainPixel, 300u)\n );\n } else {\n // Smooth mode: interpolated with quintic curve\n g = smoothNoise(grainUV);\n grainRGB = vec3(\n smoothNoise(grainUV, 100u),\n smoothNoise(grainUV, 200u),\n smoothNoise(grainUV, 300u)\n );\n }\n \n // Luminance weighting (less grain in highlights)\n float lumWeight = mix(1.0, 1.0 - luma, clamp(u_float3, 0.0, 1.0));\n \n // Strength\n float strength = u_float0 * 0.15;\n \n // Color vs monochrome grain\n vec3 grainColor = mix(vec3(g), grainRGB, clamp(u_float2, 0.0, 1.0));\n \n color.rgb += grainColor * strength * lumWeight;\n fragColor0 = vec4(clamp(color.rgb, 0.0, 1.0), color.a);\n}\n", "from_input"]}, {"id": 21, "type": "CustomCombo", "pos": [4280, -780], "size": [210, 153.8888931274414], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "grain_mode", "localized_name": "choice", "name": "choice", "type": "COMBO", "widget": {"name": "choice"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": null}, {"localized_name": "INDEX", "name": "INDEX", "type": "INT", "links": [30]}], "properties": {"Node name for S&R": "CustomCombo"}, "widgets_values": ["Smooth", 0, "Smooth", "Grainy", ""]}, {"id": 17, "type": "PrimitiveFloat", "pos": [4276.671470760602, -1180.3256994061358], "size": [210, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "grain_amount", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [26]}], "title": "Grain amount", "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 1, "step": 0.05, "precision": 2}, "widgets_values": [0.25]}, {"id": 18, "type": "PrimitiveFloat", "pos": [4280, -1080], "size": [210, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "grain_size", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [27]}], "title": "Grain size", "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0.05, "max": 3, "precision": 2, "step": 0.05}, "widgets_values": [0.1]}, {"id": 19, "type": "PrimitiveFloat", "pos": [4280, -980], "size": [210, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "color_amount", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [28]}], "title": "Color amount", "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 1, "precision": 2, "step": 0.05}, "widgets_values": [0]}, {"id": 20, "type": "PrimitiveFloat", "pos": [4280, -880], "size": [210, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "shadow_focus", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [29]}], "title": "Luminance bias", "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 1, "precision": 2, "step": 0.05}, "widgets_values": [0]}], "groups": [], "links": [{"id": 26, "origin_id": 17, "origin_slot": 0, "target_id": 15, "target_slot": 2, "type": "FLOAT"}, {"id": 27, "origin_id": 18, "origin_slot": 0, "target_id": 15, "target_slot": 3, "type": "FLOAT"}, {"id": 28, "origin_id": 19, "origin_slot": 0, "target_id": 15, "target_slot": 4, "type": "FLOAT"}, {"id": 29, "origin_id": 20, "origin_slot": 0, "target_id": 15, "target_slot": 5, "type": "FLOAT"}, {"id": 30, "origin_id": 21, "origin_slot": 1, "target_id": 15, "target_slot": 7, "type": "INT"}, {"id": 22, "origin_id": -10, "origin_slot": 0, "target_id": 15, "target_slot": 0, "type": "IMAGE"}, {"id": 23, "origin_id": 15, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}} +{ + "revision": 0, + "last_node_id": 22, + "last_link_id": 0, + "nodes": [ + { + "id": 22, + "type": "3324cf54-bcff-405f-a4bf-c5122c72fe56", + "pos": [ + 4800, + -1180 + ], + "size": [ + 250, + 154 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "title": "Film Grain", + "properties": { + "proxyWidgets": [ + [ + "17", + "value" + ], + [ + "18", + "value" + ], + [ + "19", + "value" + ], + [ + "20", + "value" + ], + [ + "21", + "choice" + ] + ] + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "3324cf54-bcff-405f-a4bf-c5122c72fe56", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 21, + "lastLinkId": 30, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Film Grain", + "inputNode": { + "id": -10, + "bounding": [ + 4096.671470760602, + -948.2184031393472, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4900, + -948.2184031393472, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "062968ea-da25-47e7-a180-d913c267f148", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 22 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 4196.671470760602, + -928.2184031393472 + ] + } + ], + "outputs": [ + { + "id": "43247d06-a39f-4733-9828-c39400fe02a4", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 23 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 4920, + -928.2184031393472 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 15, + "type": "GLSLShader", + "pos": [ + 4510, + -1180 + ], + "size": [ + 330, + 272 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 22 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 26 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 27 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": 28 + }, + { + "label": "u_float3", + "localized_name": "floats.u_float3", + "name": "floats.u_float3", + "shape": 7, + "type": "FLOAT", + "link": 29 + }, + { + "label": "u_float4", + "localized_name": "floats.u_float4", + "name": "floats.u_float4", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": 30 + }, + { + "label": "u_int1", + "localized_name": "ints.u_int1", + "name": "ints.u_int1", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 23 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // grain amount [0.0 – 1.0] typical: 0.2–0.8\nuniform float u_float1; // grain size [0.3 – 3.0] lower = finer grain\nuniform float u_float2; // color amount [0.0 – 1.0] 0 = monochrome, 1 = RGB grain\nuniform float u_float3; // luminance bias [0.0 – 1.0] 0 = uniform, 1 = shadows only\nuniform int u_int0; // noise mode [0 or 1] 0 = smooth, 1 = grainy\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\n// High-quality integer hash (pcg-like)\nuint pcg(uint v) {\n uint state = v * 747796405u + 2891336453u;\n uint word = ((state >> ((state >> 28u) + 4u)) ^ state) * 277803737u;\n return (word >> 22u) ^ word;\n}\n\n// 2D -> 1D hash input\nuint hash2d(uvec2 p) {\n return pcg(p.x + pcg(p.y));\n}\n\n// Hash to float [0, 1]\nfloat hashf(uvec2 p) {\n return float(hash2d(p)) / float(0xffffffffu);\n}\n\n// Hash to float with offset (for RGB channels)\nfloat hashf(uvec2 p, uint offset) {\n return float(pcg(hash2d(p) + offset)) / float(0xffffffffu);\n}\n\n// Convert uniform [0,1] to roughly Gaussian distribution\n// Using simple approximation: average of multiple samples\nfloat toGaussian(uvec2 p) {\n float sum = hashf(p, 0u) + hashf(p, 1u) + hashf(p, 2u) + hashf(p, 3u);\n return (sum - 2.0) * 0.7; // Centered, scaled\n}\n\nfloat toGaussian(uvec2 p, uint offset) {\n float sum = hashf(p, offset) + hashf(p, offset + 1u) \n + hashf(p, offset + 2u) + hashf(p, offset + 3u);\n return (sum - 2.0) * 0.7;\n}\n\n// Smooth noise with better interpolation\nfloat smoothNoise(vec2 p) {\n vec2 i = floor(p);\n vec2 f = fract(p);\n \n // Quintic interpolation (less banding than cubic)\n f = f * f * f * (f * (f * 6.0 - 15.0) + 10.0);\n \n uvec2 ui = uvec2(i);\n float a = toGaussian(ui);\n float b = toGaussian(ui + uvec2(1u, 0u));\n float c = toGaussian(ui + uvec2(0u, 1u));\n float d = toGaussian(ui + uvec2(1u, 1u));\n \n return mix(mix(a, b, f.x), mix(c, d, f.x), f.y);\n}\n\nfloat smoothNoise(vec2 p, uint offset) {\n vec2 i = floor(p);\n vec2 f = fract(p);\n \n f = f * f * f * (f * (f * 6.0 - 15.0) + 10.0);\n \n uvec2 ui = uvec2(i);\n float a = toGaussian(ui, offset);\n float b = toGaussian(ui + uvec2(1u, 0u), offset);\n float c = toGaussian(ui + uvec2(0u, 1u), offset);\n float d = toGaussian(ui + uvec2(1u, 1u), offset);\n \n return mix(mix(a, b, f.x), mix(c, d, f.x), f.y);\n}\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n \n // Luminance (Rec.709)\n float luma = dot(color.rgb, vec3(0.2126, 0.7152, 0.0722));\n \n // Grain UV (resolution-independent)\n vec2 grainUV = v_texCoord * u_resolution / max(u_float1, 0.01);\n uvec2 grainPixel = uvec2(grainUV);\n \n float g;\n vec3 grainRGB;\n \n if (u_int0 == 1) {\n // Grainy mode: pure hash noise (no interpolation = no banding)\n g = toGaussian(grainPixel);\n grainRGB = vec3(\n toGaussian(grainPixel, 100u),\n toGaussian(grainPixel, 200u),\n toGaussian(grainPixel, 300u)\n );\n } else {\n // Smooth mode: interpolated with quintic curve\n g = smoothNoise(grainUV);\n grainRGB = vec3(\n smoothNoise(grainUV, 100u),\n smoothNoise(grainUV, 200u),\n smoothNoise(grainUV, 300u)\n );\n }\n \n // Luminance weighting (less grain in highlights)\n float lumWeight = mix(1.0, 1.0 - luma, clamp(u_float3, 0.0, 1.0));\n \n // Strength\n float strength = u_float0 * 0.15;\n \n // Color vs monochrome grain\n vec3 grainColor = mix(vec3(g), grainRGB, clamp(u_float2, 0.0, 1.0));\n \n color.rgb += grainColor * strength * lumWeight;\n fragColor0 = vec4(clamp(color.rgb, 0.0, 1.0), color.a);\n}\n", + "from_input" + ] + }, + { + "id": 21, + "type": "CustomCombo", + "pos": [ + 4280, + -780 + ], + "size": [ + 210, + 153.8888931274414 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "grain_mode", + "localized_name": "choice", + "name": "choice", + "type": "COMBO", + "widget": { + "name": "choice" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": null + }, + { + "localized_name": "INDEX", + "name": "INDEX", + "type": "INT", + "links": [ + 30 + ] + } + ], + "properties": { + "Node name for S&R": "CustomCombo" + }, + "widgets_values": [ + "Smooth", + 0, + "Smooth", + "Grainy", + "" + ] + }, + { + "id": 17, + "type": "PrimitiveFloat", + "pos": [ + 4276.671470760602, + -1180.3256994061358 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "grain_amount", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 26 + ] + } + ], + "title": "Grain amount", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 1, + "step": 0.05, + "precision": 2 + }, + "widgets_values": [ + 0.25 + ] + }, + { + "id": 18, + "type": "PrimitiveFloat", + "pos": [ + 4280, + -1080 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "grain_size", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 27 + ] + } + ], + "title": "Grain size", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0.05, + "max": 3, + "precision": 2, + "step": 0.05 + }, + "widgets_values": [ + 0.1 + ] + }, + { + "id": 19, + "type": "PrimitiveFloat", + "pos": [ + 4280, + -980 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "color_amount", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 28 + ] + } + ], + "title": "Color amount", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 1, + "precision": 2, + "step": 0.05 + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 20, + "type": "PrimitiveFloat", + "pos": [ + 4280, + -880 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "shadow_focus", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 29 + ] + } + ], + "title": "Luminance bias", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 1, + "precision": 2, + "step": 0.05 + }, + "widgets_values": [ + 0 + ] + } + ], + "groups": [], + "links": [ + { + "id": 26, + "origin_id": 17, + "origin_slot": 0, + "target_id": 15, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 27, + "origin_id": 18, + "origin_slot": 0, + "target_id": 15, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 28, + "origin_id": 19, + "origin_slot": 0, + "target_id": 15, + "target_slot": 4, + "type": "FLOAT" + }, + { + "id": 29, + "origin_id": 20, + "origin_slot": 0, + "target_id": 15, + "target_slot": 5, + "type": "FLOAT" + }, + { + "id": 30, + "origin_id": 21, + "origin_slot": 1, + "target_id": 15, + "target_slot": 7, + "type": "INT" + }, + { + "id": 22, + "origin_id": -10, + "origin_slot": 0, + "target_id": 15, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 23, + "origin_id": 15, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} diff --git a/blueprints/First-Last-Frame to Video (LTX-2.3).json b/blueprints/First-Last-Frame to Video (LTX-2.3).json new file mode 100644 index 000000000..8ec9ed61a --- /dev/null +++ b/blueprints/First-Last-Frame to Video (LTX-2.3).json @@ -0,0 +1,3360 @@ +{ + "revision": 0, + "last_node_id": 228, + "last_link_id": 0, + "nodes": [ + { + "id": 228, + "type": "a5982aee-8136-4819-86a0-cf9d9e510ad6", + "pos": [ + 1490, + 4730 + ], + "size": [ + 274.8169921875, + 276 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "first_frame", + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": null + }, + { + "label": "last_frame", + "localized_name": "input_1", + "name": "input_1", + "type": "IMAGE,MASK", + "link": null + }, + { + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "label": "width", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + }, + { + "label": "height", + "name": "value_1", + "type": "INT", + "widget": { + "name": "value_1" + }, + "link": null + }, + { + "label": "duration", + "name": "value_2", + "type": "INT", + "widget": { + "name": "value_2" + }, + "link": null + }, + { + "label": "fps", + "name": "value_3", + "type": "INT", + "widget": { + "name": "value_3" + }, + "link": null + }, + { + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + }, + { + "label": "ckpt_name", + "name": "ckpt_name_1", + "type": "COMBO", + "widget": { + "name": "ckpt_name_1" + }, + "link": null + }, + { + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "222", + "text" + ], + [ + "215", + "value" + ], + [ + "216", + "value" + ], + [ + "198", + "value" + ], + [ + "205", + "value" + ], + [ + "196", + "noise_seed" + ], + [ + "224", + "ckpt_name" + ], + [ + "225", + "text_encoder" + ] + ], + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1" + }, + "widgets_values": [], + "title": "First-Last-Frame to Video (LTX-2.3)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "a5982aee-8136-4819-86a0-cf9d9e510ad6", + "version": 1, + "state": { + "lastGroupId": 22, + "lastNodeId": 228, + "lastLinkId": 276, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "First-Last-Frame to Video (LTX-2.3)", + "inputNode": { + "id": -10, + "bounding": [ + 270, + 3100, + 120, + 240 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 3620, + 3120, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "6fe179c4-d96f-4383-b202-844f6de4922e", + "name": "input", + "type": "IMAGE,MASK", + "linkIds": [ + 251 + ], + "localized_name": "input", + "label": "first_frame", + "pos": [ + 370, + 3120 + ] + }, + { + "id": "e80df1ae-5f39-4f86-91bd-0467635e2f2d", + "name": "input_1", + "type": "IMAGE,MASK", + "linkIds": [ + 253 + ], + "localized_name": "input_1", + "label": "last_frame", + "pos": [ + 370, + 3140 + ] + }, + { + "id": "433148fa-bf73-4ab1-81d9-09e2e38ed861", + "name": "text", + "type": "STRING", + "linkIds": [ + 265 + ], + "pos": [ + 370, + 3160 + ] + }, + { + "id": "36915bc8-a6ed-4d48-8619-e0e8723228e9", + "name": "value", + "type": "INT", + "linkIds": [ + 266 + ], + "label": "width", + "pos": [ + 370, + 3180 + ] + }, + { + "id": "425a36b8-91ab-41b7-81e9-496eba064ec8", + "name": "value_1", + "type": "INT", + "linkIds": [ + 267 + ], + "label": "height", + "pos": [ + 370, + 3200 + ] + }, + { + "id": "0c9e003b-bd07-4b7d-aa6d-789e138ed161", + "name": "value_2", + "type": "INT", + "linkIds": [ + 268 + ], + "label": "duration", + "pos": [ + 370, + 3220 + ] + }, + { + "id": "581b52ff-21c5-4774-ac2a-8f69a7e09e2e", + "name": "value_3", + "type": "INT", + "linkIds": [ + 269 + ], + "label": "fps", + "pos": [ + 370, + 3240 + ] + }, + { + "id": "d03cc171-45da-4658-99aa-77252bbcf522", + "name": "noise_seed", + "type": "INT", + "linkIds": [ + 270 + ], + "pos": [ + 370, + 3260 + ] + }, + { + "id": "e68e61c8-905e-43ac-8c76-65ac52270a08", + "name": "ckpt_name_1", + "type": "COMBO", + "linkIds": [ + 272, + 275, + 276 + ], + "label": "ckpt_name", + "pos": [ + 370, + 3280 + ] + }, + { + "id": "5d065f3b-891b-499f-950b-c2df0be24536", + "name": "text_encoder", + "type": "COMBO", + "linkIds": [ + 273 + ], + "pos": [ + 370, + 3300 + ] + } + ], + "outputs": [ + { + "id": "0c8c2dc0-c67c-4bc2-9e57-6aa00db2e3a9", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 252 + ], + "localized_name": "VIDEO", + "pos": [ + 3640, + 3140 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 195, + "type": "LTXVPreprocess", + "pos": [ + 1480, + 3780 + ], + "size": [ + 230, + 110 + ], + "flags": { + "collapsed": false + }, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 203 + }, + { + "localized_name": "img_compression", + "name": "img_compression", + "type": "INT", + "widget": { + "name": "img_compression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "output_image", + "name": "output_image", + "type": "IMAGE", + "links": [ + 229 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVPreprocess", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 196, + "type": "RandomNoise", + "pos": [ + 1990, + 2320 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": 270 + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 246 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": { + "noise_seed": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 315253765879496, + "randomize" + ] + }, + { + "id": 197, + "type": "LTXVEmptyLatentAudio", + "pos": [ + 2090, + 3820 + ], + "size": [ + 280, + 170 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 205 + }, + { + "localized_name": "frames_number", + "name": "frames_number", + "type": "INT", + "widget": { + "name": "frames_number" + }, + "link": 262 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "INT", + "widget": { + "name": "frame_rate" + }, + "link": 207 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "Latent", + "name": "Latent", + "type": "LATENT", + "links": [ + 245 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVEmptyLatentAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 97, + 25, + 1 + ] + }, + { + "id": 198, + "type": "PrimitiveInt", + "pos": [ + 760, + 3650 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 268 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 260 + ] + } + ], + "title": "Duration", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 5, + "fixed" + ] + }, + { + "id": 199, + "type": "LTXVPreprocess", + "pos": [ + 1480, + 3340 + ], + "size": [ + 230, + 110 + ], + "flags": { + "collapsed": false + }, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 210 + }, + { + "localized_name": "img_compression", + "name": "img_compression", + "type": "INT", + "widget": { + "name": "img_compression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "output_image", + "name": "output_image", + "type": "IMAGE", + "links": [ + 240 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVPreprocess", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 200, + "type": "LTXVCropGuides", + "pos": [ + 2820, + 2450 + ], + "size": [ + 280, + 120 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 213 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 214 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 215 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 211 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.5.2" + }, + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "LTXVCropGuides", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 201, + "type": "EmptyLTXVLatentVideo", + "pos": [ + 2090, + 3580 + ], + "size": [ + 280, + 200 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 218 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 219 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 263 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 239 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "EmptyLTXVLatentVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 512, + 97, + 1 + ] + }, + { + "id": 202, + "type": "LTXVConditioning", + "pos": [ + 2090, + 3400 + ], + "size": [ + 280, + 130 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 221 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 222 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "FLOAT", + "widget": { + "name": "frame_rate" + }, + "link": 223 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 236 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 237 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "LTXVConditioning", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 203, + "type": "GetImageSize", + "pos": [ + 1480, + 3500 + ], + "size": [ + 230, + 130 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 224 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 218 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 219 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 204, + "type": "LTXVAddGuide", + "pos": [ + 2750, + 3700 + ], + "size": [ + 280, + 240 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 225 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 226 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 227 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 228 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 229 + }, + { + "localized_name": "frame_idx", + "name": "frame_idx", + "type": "INT", + "widget": { + "name": "frame_idx" + }, + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 213, + 242 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 214, + 243 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 244 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "LTXVAddGuide", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + -1, + 0.7 + ] + }, + { + "id": 205, + "type": "PrimitiveInt", + "pos": [ + 760, + 3800 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 269 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 207, + 235, + 261 + ] + } + ], + "title": "Frame Rate(int)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25, + "fixed" + ] + }, + { + "id": 206, + "type": "LTXVAddGuide", + "pos": [ + 2750, + 3430 + ], + "size": [ + 280, + 240 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 236 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 237 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 238 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 239 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 240 + }, + { + "localized_name": "frame_idx", + "name": "frame_idx", + "type": "INT", + "widget": { + "name": "frame_idx" + }, + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 225 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 226 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 228 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "LTXVAddGuide", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + 0.7 + ] + }, + { + "id": 207, + "type": "CFGGuider", + "pos": [ + 1990, + 2500 + ], + "size": [ + 280, + 160 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 241 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 242 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 243 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 247 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 208, + "type": "SamplerEulerAncestral", + "pos": [ + 1990, + 2720 + ], + "size": [ + 280, + 120 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "eta", + "name": "eta", + "type": "FLOAT", + "widget": { + "name": "eta" + }, + "link": null + }, + { + "localized_name": "s_noise", + "name": "s_noise", + "type": "FLOAT", + "widget": { + "name": "s_noise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 248 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "SamplerEulerAncestral", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + 1 + ] + }, + { + "id": 209, + "type": "ManualSigmas", + "pos": [ + 1990, + 2910 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 249 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "1., 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0" + ] + }, + { + "id": 210, + "type": "LTXVConcatAVLatent", + "pos": [ + 1990, + 3090 + ], + "size": [ + 280, + 100 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 244 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 245 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 250 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 211, + "type": "SamplerCustomAdvanced", + "pos": [ + 2460, + 2330 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 246 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 247 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 248 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 249 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 250 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [ + 204 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 212, + "type": "ComfyMathExpression", + "pos": [ + 760, + 3970 + ], + "size": [ + 230, + 170 + ], + "flags": { + "collapsed": true + }, + "order": 17, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 235 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 223, + 234 + ] + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.17.0", + "Node name for S&R": "ComfyMathExpression", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "a" + ] + }, + { + "id": 213, + "type": "ResizeImageMaskNode", + "pos": [ + 1130, + 3340 + ], + "size": [ + 280, + 160 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": 251 + }, + { + "localized_name": "resize_type", + "name": "resize_type", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "resize_type" + }, + "link": null + }, + { + "localized_name": "width", + "name": "resize_type.width", + "type": "INT", + "widget": { + "name": "resize_type.width" + }, + "link": 208 + }, + { + "localized_name": "height", + "name": "resize_type.height", + "type": "INT", + "widget": { + "name": "resize_type.height" + }, + "link": 209 + }, + { + "localized_name": "crop", + "name": "resize_type.crop", + "type": "COMBO", + "widget": { + "name": "resize_type.crop" + }, + "link": null + }, + { + "localized_name": "scale_method", + "name": "scale_method", + "type": "COMBO", + "widget": { + "name": "scale_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "resized", + "name": "resized", + "type": "*", + "links": [ + 210, + 224 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": { + "resize_type.width": true, + "resize_type.height": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "ResizeImageMaskNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "scale dimensions", + 640, + 360, + "center", + "nearest-exact" + ] + }, + { + "id": 214, + "type": "ResizeImageMaskNode", + "pos": [ + 1130, + 3780 + ], + "size": [ + 280, + 160 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": 253 + }, + { + "localized_name": "resize_type", + "name": "resize_type", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "resize_type" + }, + "link": null + }, + { + "localized_name": "width", + "name": "resize_type.width", + "type": "INT", + "widget": { + "name": "resize_type.width" + }, + "link": 201 + }, + { + "localized_name": "height", + "name": "resize_type.height", + "type": "INT", + "widget": { + "name": "resize_type.height" + }, + "link": 202 + }, + { + "localized_name": "crop", + "name": "resize_type.crop", + "type": "COMBO", + "widget": { + "name": "resize_type.crop" + }, + "link": null + }, + { + "localized_name": "scale_method", + "name": "scale_method", + "type": "COMBO", + "widget": { + "name": "scale_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "resized", + "name": "resized", + "type": "*", + "links": [ + 203 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": { + "resize_type.width": true, + "resize_type.height": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "ResizeImageMaskNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "scale dimensions", + 640, + 360, + "center", + "nearest-exact" + ] + }, + { + "id": 215, + "type": "PrimitiveInt", + "pos": [ + 760, + 3340 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 266 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 201, + 208 + ] + } + ], + "title": "Width", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1280, + "fixed" + ] + }, + { + "id": 216, + "type": "PrimitiveInt", + "pos": [ + 760, + 3490 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 267 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 202, + 209 + ] + } + ], + "title": "height", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 720, + "fixed" + ] + }, + { + "id": 217, + "type": "CLIPTextEncode", + "pos": [ + 1320, + 2870 + ], + "size": [ + 590, + 200 + ], + "flags": { + "collapsed": false + }, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 230 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 222 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts." + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 218, + "type": "CreateVideo", + "pos": [ + 3280, + 2320 + ], + "size": [ + 280, + 130 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 232 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 233 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 234 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 252 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "CreateVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 219, + "type": "VAEDecodeTiled", + "pos": [ + 2820, + 2630 + ], + "size": [ + 280, + 200 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 211 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 212 + }, + { + "localized_name": "tile_size", + "name": "tile_size", + "type": "INT", + "widget": { + "name": "tile_size" + }, + "link": null + }, + { + "localized_name": "overlap", + "name": "overlap", + "type": "INT", + "widget": { + "name": "overlap" + }, + "link": null + }, + { + "localized_name": "temporal_size", + "name": "temporal_size", + "type": "INT", + "widget": { + "name": "temporal_size" + }, + "link": null + }, + { + "localized_name": "temporal_overlap", + "name": "temporal_overlap", + "type": "INT", + "widget": { + "name": "temporal_overlap" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 232 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "VAEDecodeTiled", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 64, + 4096, + 64 + ] + }, + { + "id": 220, + "type": "LTXVAudioVAEDecode", + "pos": [ + 2820, + 2920 + ], + "size": [ + 280, + 100 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 216 + }, + { + "label": "Audio VAE", + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 217 + } + ], + "outputs": [ + { + "localized_name": "Audio", + "name": "Audio", + "type": "AUDIO", + "links": [ + 233 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVAudioVAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 221, + "type": "LTXVSeparateAVLatent", + "pos": [ + 2460, + 2580 + ], + "size": [ + 250, + 100 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 204 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 215 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 216 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 222, + "type": "CLIPTextEncode", + "pos": [ + 1310, + 2380 + ], + "size": [ + 620, + 420 + ], + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 231 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 265 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 221 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.5.2", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 223, + "type": "CheckpointLoaderSimple", + "pos": [ + 770, + 2380 + ], + "size": [ + 420, + 160 + ], + "flags": {}, + "order": 28, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 276 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 241 + ] + }, + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 212, + 227, + 238 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.5.2" + }, + "cnr_id": "comfy-core", + "ver": "0.10.0", + "Node name for S&R": "CheckpointLoaderSimple", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-distilled-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-distilled-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-distilled-fp8.safetensors" + ] + }, + { + "id": 224, + "type": "LTXVAudioVAELoader", + "pos": [ + 770, + 2660 + ], + "size": [ + 420, + 110 + ], + "flags": {}, + "order": 29, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 272 + } + ], + "outputs": [ + { + "localized_name": "Audio VAE", + "name": "Audio VAE", + "type": "VAE", + "links": [ + 205, + 217 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.5.2" + }, + "cnr_id": "comfy-core", + "ver": "0.10.0", + "Node name for S&R": "LTXVAudioVAELoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-distilled-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-distilled-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-distilled-fp8.safetensors" + ] + }, + { + "id": 225, + "type": "LTXAVTextEncoderLoader", + "pos": [ + 770, + 2890 + ], + "size": [ + 410, + 160 + ], + "flags": {}, + "order": 30, + "mode": 0, + "inputs": [ + { + "localized_name": "text_encoder", + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": 273 + }, + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 275 + }, + { + "localized_name": "device", + "name": "device", + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 230, + 231 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.5.2" + }, + "cnr_id": "comfy-core", + "ver": "0.10.0", + "Node name for S&R": "LTXAVTextEncoderLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "gemma_3_12B_it_fp4_mixed.safetensors", + "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", + "directory": "text_encoders" + }, + { + "name": "ltx-2.3-22b-distilled-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-distilled-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2.3-22b-distilled-fp8.safetensors", + "default" + ] + }, + { + "id": 226, + "type": "ComfyMathExpression", + "pos": [ + 760, + 4020 + ], + "size": [ + 400, + 200 + ], + "flags": { + "collapsed": true + }, + "order": 31, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 260 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 261 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 262, + 263 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "a * b + 1" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Conditioning", + "bounding": [ + 1850, + 3250, + 1370, + 800 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Settings", + "bounding": [ + 730, + 3250, + 290, + 800 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "FIrst Frame", + "bounding": [ + 1050, + 3250, + 770, + 400 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 4, + "title": "Last Frame", + "bounding": [ + 1050, + 3680, + 770, + 370 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "Model", + "bounding": [ + 730, + 2240, + 500, + 980 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Prompt", + "bounding": [ + 1260, + 2240, + 680, + 980 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Sampling", + "bounding": [ + 1970, + 2240, + 770, + 980 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 8, + "title": "Decoding", + "bounding": [ + 2770, + 2240, + 450, + 980 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 203, + "origin_id": 214, + "origin_slot": 0, + "target_id": 195, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 205, + "origin_id": 224, + "origin_slot": 0, + "target_id": 197, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 207, + "origin_id": 205, + "origin_slot": 0, + "target_id": 197, + "target_slot": 2, + "type": "INT" + }, + { + "id": 210, + "origin_id": 213, + "origin_slot": 0, + "target_id": 199, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 213, + "origin_id": 204, + "origin_slot": 0, + "target_id": 200, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 214, + "origin_id": 204, + "origin_slot": 1, + "target_id": 200, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 215, + "origin_id": 221, + "origin_slot": 0, + "target_id": 200, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 218, + "origin_id": 203, + "origin_slot": 0, + "target_id": 201, + "target_slot": 0, + "type": "INT" + }, + { + "id": 219, + "origin_id": 203, + "origin_slot": 1, + "target_id": 201, + "target_slot": 1, + "type": "INT" + }, + { + "id": 221, + "origin_id": 222, + "origin_slot": 0, + "target_id": 202, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 222, + "origin_id": 217, + "origin_slot": 0, + "target_id": 202, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 223, + "origin_id": 212, + "origin_slot": 0, + "target_id": 202, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 224, + "origin_id": 213, + "origin_slot": 0, + "target_id": 203, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 225, + "origin_id": 206, + "origin_slot": 0, + "target_id": 204, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 226, + "origin_id": 206, + "origin_slot": 1, + "target_id": 204, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 227, + "origin_id": 223, + "origin_slot": 2, + "target_id": 204, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 228, + "origin_id": 206, + "origin_slot": 2, + "target_id": 204, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 229, + "origin_id": 195, + "origin_slot": 0, + "target_id": 204, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 236, + "origin_id": 202, + "origin_slot": 0, + "target_id": 206, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 237, + "origin_id": 202, + "origin_slot": 1, + "target_id": 206, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 238, + "origin_id": 223, + "origin_slot": 2, + "target_id": 206, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 239, + "origin_id": 201, + "origin_slot": 0, + "target_id": 206, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 240, + "origin_id": 199, + "origin_slot": 0, + "target_id": 206, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 241, + "origin_id": 223, + "origin_slot": 0, + "target_id": 207, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 242, + "origin_id": 204, + "origin_slot": 0, + "target_id": 207, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 243, + "origin_id": 204, + "origin_slot": 1, + "target_id": 207, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 244, + "origin_id": 204, + "origin_slot": 2, + "target_id": 210, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 245, + "origin_id": 197, + "origin_slot": 0, + "target_id": 210, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 246, + "origin_id": 196, + "origin_slot": 0, + "target_id": 211, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 247, + "origin_id": 207, + "origin_slot": 0, + "target_id": 211, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 248, + "origin_id": 208, + "origin_slot": 0, + "target_id": 211, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 249, + "origin_id": 209, + "origin_slot": 0, + "target_id": 211, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 250, + "origin_id": 210, + "origin_slot": 0, + "target_id": 211, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 235, + "origin_id": 205, + "origin_slot": 0, + "target_id": 212, + "target_slot": 0, + "type": "INT" + }, + { + "id": 208, + "origin_id": 215, + "origin_slot": 0, + "target_id": 213, + "target_slot": 2, + "type": "INT" + }, + { + "id": 209, + "origin_id": 216, + "origin_slot": 0, + "target_id": 213, + "target_slot": 3, + "type": "INT" + }, + { + "id": 201, + "origin_id": 215, + "origin_slot": 0, + "target_id": 214, + "target_slot": 2, + "type": "INT" + }, + { + "id": 202, + "origin_id": 216, + "origin_slot": 0, + "target_id": 214, + "target_slot": 3, + "type": "INT" + }, + { + "id": 230, + "origin_id": 225, + "origin_slot": 0, + "target_id": 217, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 232, + "origin_id": 219, + "origin_slot": 0, + "target_id": 218, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 233, + "origin_id": 220, + "origin_slot": 0, + "target_id": 218, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 234, + "origin_id": 212, + "origin_slot": 0, + "target_id": 218, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 211, + "origin_id": 200, + "origin_slot": 2, + "target_id": 219, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 212, + "origin_id": 223, + "origin_slot": 2, + "target_id": 219, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 216, + "origin_id": 221, + "origin_slot": 1, + "target_id": 220, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 217, + "origin_id": 224, + "origin_slot": 0, + "target_id": 220, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 204, + "origin_id": 211, + "origin_slot": 1, + "target_id": 221, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 231, + "origin_id": 225, + "origin_slot": 0, + "target_id": 222, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 251, + "origin_id": -10, + "origin_slot": 0, + "target_id": 213, + "target_slot": 0, + "type": "IMAGE,MASK" + }, + { + "id": 253, + "origin_id": -10, + "origin_slot": 1, + "target_id": 214, + "target_slot": 0, + "type": "IMAGE,MASK" + }, + { + "id": 252, + "origin_id": 218, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 260, + "origin_id": 198, + "origin_slot": 0, + "target_id": 226, + "target_slot": 0, + "type": "INT" + }, + { + "id": 261, + "origin_id": 205, + "origin_slot": 0, + "target_id": 226, + "target_slot": 1, + "type": "INT" + }, + { + "id": 262, + "origin_id": 226, + "origin_slot": 1, + "target_id": 197, + "target_slot": 1, + "type": "INT" + }, + { + "id": 263, + "origin_id": 226, + "origin_slot": 1, + "target_id": 201, + "target_slot": 2, + "type": "INT" + }, + { + "id": 265, + "origin_id": -10, + "origin_slot": 2, + "target_id": 222, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 266, + "origin_id": -10, + "origin_slot": 3, + "target_id": 215, + "target_slot": 0, + "type": "INT" + }, + { + "id": 267, + "origin_id": -10, + "origin_slot": 4, + "target_id": 216, + "target_slot": 0, + "type": "INT" + }, + { + "id": 268, + "origin_id": -10, + "origin_slot": 5, + "target_id": 198, + "target_slot": 0, + "type": "INT" + }, + { + "id": 269, + "origin_id": -10, + "origin_slot": 6, + "target_id": 205, + "target_slot": 0, + "type": "INT" + }, + { + "id": 270, + "origin_id": -10, + "origin_slot": 7, + "target_id": 196, + "target_slot": 0, + "type": "INT" + }, + { + "id": 272, + "origin_id": -10, + "origin_slot": 8, + "target_id": 224, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 273, + "origin_id": -10, + "origin_slot": 9, + "target_id": 225, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 275, + "origin_id": -10, + "origin_slot": 8, + "target_id": 225, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 276, + "origin_id": -10, + "origin_slot": 8, + "target_id": 223, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": {}, + "category": "Video generation and editing/First-Last-Frame to Video" + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Glow.json b/blueprints/Glow.json index 590445c06..1dafb2d35 100644 --- a/blueprints/Glow.json +++ b/blueprints/Glow.json @@ -1 +1,582 @@ -{"revision": 0, "last_node_id": 37, "last_link_id": 0, "nodes": [{"id": 37, "type": "0a99445a-aaf8-4a7f-aec3-d7d710ae1495", "pos": [2160, -360], "size": [260, 154], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["34", "value"], ["35", "value"], ["33", "value"], ["31", "choice"], ["32", "color"]]}, "widgets_values": [], "title": "Glow"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "0a99445a-aaf8-4a7f-aec3-d7d710ae1495", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 36, "lastLinkId": 53, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Glow", "inputNode": {"id": -10, "bounding": [2110, -165, 120, 60]}, "outputNode": {"id": -20, "bounding": [3170, -165, 120, 60]}, "inputs": [{"id": "ffc7cf94-be90-4d56-a3b8-d0514d61c015", "name": "images.image0", "type": "IMAGE", "linkIds": [45], "localized_name": "images.image0", "label": "image", "pos": [2210, -145]}], "outputs": [{"id": "04986101-50be-4762-8957-8e2a5e460bbb", "name": "IMAGE0", "type": "IMAGE", "linkIds": [53], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [3190, -145]}], "widgets": [], "nodes": [{"id": 30, "type": "GLSLShader", "pos": [2590, -520], "size": [520, 272], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 45}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 51}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 50}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": 52}, {"label": "u_float3", "localized_name": "floats.u_float3", "name": "floats.u_float3", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": 46}, {"label": "u_int1", "localized_name": "ints.u_int1", "name": "ints.u_int1", "shape": 7, "type": "INT", "link": 47}, {"label": "u_int2", "localized_name": "ints.u_int2", "name": "ints.u_int2", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [53]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision mediump float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform int u_int0; // Blend mode\nuniform int u_int1; // Color tint\nuniform float u_float0; // Intensity\nuniform float u_float1; // Radius\nuniform float u_float2; // Threshold\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int BLEND_ADD = 0;\nconst int BLEND_SCREEN = 1;\nconst int BLEND_SOFT = 2;\nconst int BLEND_OVERLAY = 3;\nconst int BLEND_LIGHTEN = 4;\n\nconst float GOLDEN_ANGLE = 2.39996323;\nconst int MAX_SAMPLES = 48;\nconst vec3 LUMA = vec3(0.299, 0.587, 0.114);\n\nfloat hash(vec2 p) {\n p = fract(p * vec2(123.34, 456.21));\n p += dot(p, p + 45.32);\n return fract(p.x * p.y);\n}\n\nvec3 hexToRgb(int h) {\n return vec3(\n float((h >> 16) & 255),\n float((h >> 8) & 255),\n float(h & 255)\n ) * (1.0 / 255.0);\n}\n\nvec3 blend(vec3 base, vec3 glow, int mode) {\n if (mode == BLEND_SCREEN) {\n return 1.0 - (1.0 - base) * (1.0 - glow);\n }\n if (mode == BLEND_SOFT) {\n return mix(\n base - (1.0 - 2.0 * glow) * base * (1.0 - base),\n base + (2.0 * glow - 1.0) * (sqrt(base) - base),\n step(0.5, glow)\n );\n }\n if (mode == BLEND_OVERLAY) {\n return mix(\n 2.0 * base * glow,\n 1.0 - 2.0 * (1.0 - base) * (1.0 - glow),\n step(0.5, base)\n );\n }\n if (mode == BLEND_LIGHTEN) {\n return max(base, glow);\n }\n return base + glow;\n}\n\nvoid main() {\n vec4 original = texture(u_image0, v_texCoord);\n \n float intensity = u_float0 * 0.05;\n float radius = u_float1 * u_float1 * 0.012;\n \n if (intensity < 0.001 || radius < 0.1) {\n fragColor = original;\n return;\n }\n \n float threshold = 1.0 - u_float2 * 0.01;\n float t0 = threshold - 0.15;\n float t1 = threshold + 0.15;\n \n vec2 texelSize = 1.0 / u_resolution;\n float radius2 = radius * radius;\n \n float sampleScale = clamp(radius * 0.75, 0.35, 1.0);\n int samples = int(float(MAX_SAMPLES) * sampleScale);\n \n float noise = hash(gl_FragCoord.xy);\n float angleOffset = noise * GOLDEN_ANGLE;\n float radiusJitter = 0.85 + noise * 0.3;\n \n float ca = cos(GOLDEN_ANGLE);\n float sa = sin(GOLDEN_ANGLE);\n vec2 dir = vec2(cos(angleOffset), sin(angleOffset));\n \n vec3 glow = vec3(0.0);\n float totalWeight = 0.0;\n \n // Center tap\n float centerMask = smoothstep(t0, t1, dot(original.rgb, LUMA));\n glow += original.rgb * centerMask * 2.0;\n totalWeight += 2.0;\n \n for (int i = 1; i < MAX_SAMPLES; i++) {\n if (i >= samples) break;\n \n float fi = float(i);\n float dist = sqrt(fi / float(samples)) * radius * radiusJitter;\n \n vec2 offset = dir * dist * texelSize;\n vec3 c = texture(u_image0, v_texCoord + offset).rgb;\n float mask = smoothstep(t0, t1, dot(c, LUMA));\n \n float w = 1.0 - (dist * dist) / (radius2 * 1.5);\n w = max(w, 0.0);\n w *= w;\n \n glow += c * mask * w;\n totalWeight += w;\n \n dir = vec2(\n dir.x * ca - dir.y * sa,\n dir.x * sa + dir.y * ca\n );\n }\n \n glow *= intensity / max(totalWeight, 0.001);\n \n if (u_int1 > 0) {\n glow *= hexToRgb(u_int1);\n }\n \n vec3 result = blend(original.rgb, glow, u_int0);\n result += (noise - 0.5) * (1.0 / 255.0);\n \n fragColor = vec4(clamp(result, 0.0, 1.0), original.a);\n}", "from_input"]}, {"id": 34, "type": "PrimitiveFloat", "pos": [2290, -510], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "intensity", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [51]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "precision": 1, "step": 1}, "widgets_values": [30]}, {"id": 35, "type": "PrimitiveFloat", "pos": [2290, -410], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "radius", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [50]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "precision": 1, "step": 1}, "widgets_values": [25]}, {"id": 33, "type": "PrimitiveFloat", "pos": [2290, -310], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "threshold", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [52]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "precision": 1, "step": 1}, "widgets_values": [100]}, {"id": 32, "type": "ColorToRGBInt", "pos": [2290, -210], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "color_tint", "localized_name": "color", "name": "color", "type": "COLOR", "widget": {"name": "color"}, "link": null}], "outputs": [{"localized_name": "rgb_int", "name": "rgb_int", "type": "INT", "links": [47]}], "properties": {"Node name for S&R": "ColorToRGBInt"}, "widgets_values": ["#45edf5"]}, {"id": 31, "type": "CustomCombo", "pos": [2290, -110], "size": [270, 222], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "blend_mode", "localized_name": "choice", "name": "choice", "type": "COMBO", "widget": {"name": "choice"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": null}, {"localized_name": "INDEX", "name": "INDEX", "type": "INT", "links": [46]}], "properties": {"Node name for S&R": "CustomCombo"}, "widgets_values": ["add", 0, "add", "screen", "soft", "overlay", "lighten", ""]}], "groups": [], "links": [{"id": 51, "origin_id": 34, "origin_slot": 0, "target_id": 30, "target_slot": 2, "type": "FLOAT"}, {"id": 50, "origin_id": 35, "origin_slot": 0, "target_id": 30, "target_slot": 3, "type": "FLOAT"}, {"id": 52, "origin_id": 33, "origin_slot": 0, "target_id": 30, "target_slot": 4, "type": "FLOAT"}, {"id": 46, "origin_id": 31, "origin_slot": 1, "target_id": 30, "target_slot": 6, "type": "INT"}, {"id": 47, "origin_id": 32, "origin_slot": 0, "target_id": 30, "target_slot": 7, "type": "INT"}, {"id": 45, "origin_id": -10, "origin_slot": 0, "target_id": 30, "target_slot": 0, "type": "IMAGE"}, {"id": 53, "origin_id": 30, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}} +{ + "revision": 0, + "last_node_id": 37, + "last_link_id": 0, + "nodes": [ + { + "id": 37, + "type": "0a99445a-aaf8-4a7f-aec3-d7d710ae1495", + "pos": [ + 2160, + -360 + ], + "size": [ + 260, + 154 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "34", + "value" + ], + [ + "35", + "value" + ], + [ + "33", + "value" + ], + [ + "31", + "choice" + ], + [ + "32", + "color" + ] + ] + }, + "widgets_values": [], + "title": "Glow" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "0a99445a-aaf8-4a7f-aec3-d7d710ae1495", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 36, + "lastLinkId": 53, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Glow", + "inputNode": { + "id": -10, + "bounding": [ + 2110, + -165, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 3170, + -165, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "ffc7cf94-be90-4d56-a3b8-d0514d61c015", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 45 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 2210, + -145 + ] + } + ], + "outputs": [ + { + "id": "04986101-50be-4762-8957-8e2a5e460bbb", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 53 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 3190, + -145 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 30, + "type": "GLSLShader", + "pos": [ + 2590, + -520 + ], + "size": [ + 520, + 272 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 45 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 51 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 50 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": 52 + }, + { + "label": "u_float3", + "localized_name": "floats.u_float3", + "name": "floats.u_float3", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": 46 + }, + { + "label": "u_int1", + "localized_name": "ints.u_int1", + "name": "ints.u_int1", + "shape": 7, + "type": "INT", + "link": 47 + }, + { + "label": "u_int2", + "localized_name": "ints.u_int2", + "name": "ints.u_int2", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 53 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision mediump float;\n\nuniform sampler2D u_image0;\nuniform int u_int0; // Blend mode\nuniform int u_int1; // Color tint\nuniform float u_float0; // Intensity\nuniform float u_float1; // Radius\nuniform float u_float2; // Threshold\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int BLEND_ADD = 0;\nconst int BLEND_SCREEN = 1;\nconst int BLEND_SOFT = 2;\nconst int BLEND_OVERLAY = 3;\nconst int BLEND_LIGHTEN = 4;\n\nconst float GOLDEN_ANGLE = 2.39996323;\nconst int MAX_SAMPLES = 48;\nconst vec3 LUMA = vec3(0.299, 0.587, 0.114);\n\nfloat hash(vec2 p) {\n p = fract(p * vec2(123.34, 456.21));\n p += dot(p, p + 45.32);\n return fract(p.x * p.y);\n}\n\nvec3 hexToRgb(int h) {\n return vec3(\n float((h >> 16) & 255),\n float((h >> 8) & 255),\n float(h & 255)\n ) * (1.0 / 255.0);\n}\n\nvec3 blend(vec3 base, vec3 glow, int mode) {\n if (mode == BLEND_SCREEN) {\n return 1.0 - (1.0 - base) * (1.0 - glow);\n }\n if (mode == BLEND_SOFT) {\n return mix(\n base - (1.0 - 2.0 * glow) * base * (1.0 - base),\n base + (2.0 * glow - 1.0) * (sqrt(base) - base),\n step(0.5, glow)\n );\n }\n if (mode == BLEND_OVERLAY) {\n return mix(\n 2.0 * base * glow,\n 1.0 - 2.0 * (1.0 - base) * (1.0 - glow),\n step(0.5, base)\n );\n }\n if (mode == BLEND_LIGHTEN) {\n return max(base, glow);\n }\n return base + glow;\n}\n\nvoid main() {\n vec4 original = texture(u_image0, v_texCoord);\n \n float intensity = u_float0 * 0.05;\n float radius = u_float1 * u_float1 * 0.012;\n \n if (intensity < 0.001 || radius < 0.1) {\n fragColor = original;\n return;\n }\n \n float threshold = 1.0 - u_float2 * 0.01;\n float t0 = threshold - 0.15;\n float t1 = threshold + 0.15;\n \n vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));\n float radius2 = radius * radius;\n \n float sampleScale = clamp(radius * 0.75, 0.35, 1.0);\n int samples = int(float(MAX_SAMPLES) * sampleScale);\n \n float noise = hash(gl_FragCoord.xy);\n float angleOffset = noise * GOLDEN_ANGLE;\n float radiusJitter = 0.85 + noise * 0.3;\n \n float ca = cos(GOLDEN_ANGLE);\n float sa = sin(GOLDEN_ANGLE);\n vec2 dir = vec2(cos(angleOffset), sin(angleOffset));\n \n vec3 glow = vec3(0.0);\n float totalWeight = 0.0;\n \n // Center tap\n float centerMask = smoothstep(t0, t1, dot(original.rgb, LUMA));\n glow += original.rgb * centerMask * 2.0;\n totalWeight += 2.0;\n \n for (int i = 1; i < MAX_SAMPLES; i++) {\n if (i >= samples) break;\n \n float fi = float(i);\n float dist = sqrt(fi / float(samples)) * radius * radiusJitter;\n \n vec2 offset = dir * dist * texelSize;\n vec3 c = texture(u_image0, v_texCoord + offset).rgb;\n float mask = smoothstep(t0, t1, dot(c, LUMA));\n \n float w = 1.0 - (dist * dist) / (radius2 * 1.5);\n w = max(w, 0.0);\n w *= w;\n \n glow += c * mask * w;\n totalWeight += w;\n \n dir = vec2(\n dir.x * ca - dir.y * sa,\n dir.x * sa + dir.y * ca\n );\n }\n \n glow *= intensity / max(totalWeight, 0.001);\n \n if (u_int1 > 0) {\n glow *= hexToRgb(u_int1);\n }\n \n vec3 result = blend(original.rgb, glow, u_int0);\n result += (noise - 0.5) * (1.0 / 255.0);\n \n fragColor = vec4(clamp(result, 0.0, 1.0), original.a);\n}", + "from_input" + ] + }, + { + "id": 34, + "type": "PrimitiveFloat", + "pos": [ + 2290, + -510 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "intensity", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 51 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "precision": 1, + "step": 1 + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 35, + "type": "PrimitiveFloat", + "pos": [ + 2290, + -410 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "radius", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 50 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "precision": 1, + "step": 1 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 33, + "type": "PrimitiveFloat", + "pos": [ + 2290, + -310 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "threshold", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 52 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "precision": 1, + "step": 1 + }, + "widgets_values": [ + 100 + ] + }, + { + "id": 32, + "type": "ColorToRGBInt", + "pos": [ + 2290, + -210 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "color_tint", + "localized_name": "color", + "name": "color", + "type": "COLOR", + "widget": { + "name": "color" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "rgb_int", + "name": "rgb_int", + "type": "INT", + "links": [ + 47 + ] + } + ], + "properties": { + "Node name for S&R": "ColorToRGBInt" + }, + "widgets_values": [ + "#45edf5" + ] + }, + { + "id": 31, + "type": "CustomCombo", + "pos": [ + 2290, + -110 + ], + "size": [ + 270, + 222 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "blend_mode", + "localized_name": "choice", + "name": "choice", + "type": "COMBO", + "widget": { + "name": "choice" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": null + }, + { + "localized_name": "INDEX", + "name": "INDEX", + "type": "INT", + "links": [ + 46 + ] + } + ], + "properties": { + "Node name for S&R": "CustomCombo" + }, + "widgets_values": [ + "add", + 0, + "add", + "screen", + "soft", + "overlay", + "lighten", + "" + ] + } + ], + "groups": [], + "links": [ + { + "id": 51, + "origin_id": 34, + "origin_slot": 0, + "target_id": 30, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 50, + "origin_id": 35, + "origin_slot": 0, + "target_id": 30, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 52, + "origin_id": 33, + "origin_slot": 0, + "target_id": 30, + "target_slot": 4, + "type": "FLOAT" + }, + { + "id": 46, + "origin_id": 31, + "origin_slot": 1, + "target_id": 30, + "target_slot": 6, + "type": "INT" + }, + { + "id": 47, + "origin_id": 32, + "origin_slot": 0, + "target_id": 30, + "target_slot": 7, + "type": "INT" + }, + { + "id": 45, + "origin_id": -10, + "origin_slot": 0, + "target_id": 30, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 53, + "origin_id": 30, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} diff --git a/blueprints/Hue and Saturation.json b/blueprints/Hue and Saturation.json index 04846c51d..1a2df8937 100644 --- a/blueprints/Hue and Saturation.json +++ b/blueprints/Hue and Saturation.json @@ -1 +1,759 @@ -{"revision": 0, "last_node_id": 11, "last_link_id": 0, "nodes": [{"id": 11, "type": "c64f83e9-aa5d-4031-89f1-0704e39299fe", "pos": [870, -220], "size": [250, 178], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "title": "Hue and Saturation", "properties": {"proxyWidgets": [["2", "choice"], ["4", "value"], ["5", "value"], ["6", "value"], ["7", "value"], ["3", "choice"]]}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "c64f83e9-aa5d-4031-89f1-0704e39299fe", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 10, "lastLinkId": 11, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Hue and Saturation", "inputNode": {"id": -10, "bounding": [360, -176, 120, 60]}, "outputNode": {"id": -20, "bounding": [1410, -176, 120, 60]}, "inputs": [{"id": "a5aae7ea-b511-4045-b5da-94101e269cd7", "name": "images.image0", "type": "IMAGE", "linkIds": [10], "localized_name": "images.image0", "label": "image", "pos": [460, -156]}], "outputs": [{"id": "30b72604-69b3-4944-b253-a9099bbd73a9", "name": "IMAGE0", "type": "IMAGE", "linkIds": [8], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [1430, -156]}], "widgets": [], "nodes": [{"id": 3, "type": "CustomCombo", "pos": [540, -240], "size": [270, 150], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "color_space", "localized_name": "choice", "name": "choice", "type": "COMBO", "widget": {"name": "choice"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": null}, {"localized_name": "INDEX", "name": "INDEX", "type": "INT", "links": [2]}], "properties": {"Node name for S&R": "CustomCombo"}, "widgets_values": ["HSL", 0, "HSL", "HSB/HSV", ""]}, {"id": 2, "type": "CustomCombo", "pos": [540, -580], "size": [270, 294], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "mode", "localized_name": "choice", "name": "choice", "type": "COMBO", "widget": {"name": "choice"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": null}, {"localized_name": "INDEX", "name": "INDEX", "type": "INT", "links": [1]}], "properties": {"Node name for S&R": "CustomCombo"}, "widgets_values": ["Master", 0, "Master", "Reds", "Yellows", "Greens", "Cyans", "Blues", "Magentas", "Colorize", ""]}, {"id": 7, "type": "PrimitiveFloat", "pos": [540, 260], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "overlap", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [6]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 100, "precision": 1, "step": 1}, "widgets_values": [50]}, {"id": 6, "type": "PrimitiveFloat", "pos": [540, 160], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "brightness", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [5]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": -100, "max": 100, "precision": 1, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 0, 0]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [0]}, {"id": 5, "type": "PrimitiveFloat", "pos": [540, 60], "size": [270, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "saturation", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [4]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": -100, "max": 100, "precision": 1, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [128, 128, 128]}, {"offset": 1, "color": [255, 0, 0]}]}, "widgets_values": [0]}, {"id": 4, "type": "PrimitiveFloat", "pos": [540, -40], "size": [270, 58], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "hue", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [3]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": -180, "max": 180, "precision": 1, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [255, 0, 0]}, {"offset": 0.16666666666666666, "color": [255, 255, 0]}, {"offset": 0.3333333333333333, "color": [0, 255, 0]}, {"offset": 0.5, "color": [0, 255, 255]}, {"offset": 0.6666666666666666, "color": [0, 0, 255]}, {"offset": 0.8333333333333334, "color": [255, 0, 255]}, {"offset": 1, "color": [255, 0, 0]}]}, "widgets_values": [0]}, {"id": 1, "type": "GLSLShader", "pos": [880, -300], "size": [470, 292], "flags": {}, "order": 6, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 10}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 3}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 4}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": 5}, {"label": "u_float3", "localized_name": "floats.u_float3", "name": "floats.u_float3", "shape": 7, "type": "FLOAT", "link": 6}, {"label": "u_float4", "localized_name": "floats.u_float4", "name": "floats.u_float4", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": 1}, {"label": "u_int1", "localized_name": "ints.u_int1", "name": "ints.u_int1", "shape": 7, "type": "INT", "link": 2}, {"label": "u_int2", "localized_name": "ints.u_int2", "name": "ints.u_int2", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [8]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform int u_int0; // Mode: 0=Master, 1=Reds, 2=Yellows, 3=Greens, 4=Cyans, 5=Blues, 6=Magentas, 7=Colorize\nuniform int u_int1; // Color Space: 0=HSL, 1=HSB/HSV\nuniform float u_float0; // Hue (-180 to 180)\nuniform float u_float1; // Saturation (-100 to 100)\nuniform float u_float2; // Lightness/Brightness (-100 to 100)\nuniform float u_float3; // Overlap (0 to 100) - feathering between adjacent color ranges\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\n// Color range modes\nconst int MODE_MASTER = 0;\nconst int MODE_RED = 1;\nconst int MODE_YELLOW = 2;\nconst int MODE_GREEN = 3;\nconst int MODE_CYAN = 4;\nconst int MODE_BLUE = 5;\nconst int MODE_MAGENTA = 6;\nconst int MODE_COLORIZE = 7;\n\n// Color space modes\nconst int COLORSPACE_HSL = 0;\nconst int COLORSPACE_HSB = 1;\n\nconst float EPSILON = 0.0001;\n\n//=============================================================================\n// RGB <-> HSL Conversions\n//=============================================================================\n\nvec3 rgb2hsl(vec3 c) {\n float maxC = max(max(c.r, c.g), c.b);\n float minC = min(min(c.r, c.g), c.b);\n float delta = maxC - minC;\n\n float h = 0.0;\n float s = 0.0;\n float l = (maxC + minC) * 0.5;\n\n if (delta > EPSILON) {\n s = l < 0.5\n ? delta / (maxC + minC)\n : delta / (2.0 - maxC - minC);\n\n if (maxC == c.r) {\n h = (c.g - c.b) / delta + (c.g < c.b ? 6.0 : 0.0);\n } else if (maxC == c.g) {\n h = (c.b - c.r) / delta + 2.0;\n } else {\n h = (c.r - c.g) / delta + 4.0;\n }\n h /= 6.0;\n }\n\n return vec3(h, s, l);\n}\n\nfloat hue2rgb(float p, float q, float t) {\n t = fract(t);\n if (t < 1.0/6.0) return p + (q - p) * 6.0 * t;\n if (t < 0.5) return q;\n if (t < 2.0/3.0) return p + (q - p) * (2.0/3.0 - t) * 6.0;\n return p;\n}\n\nvec3 hsl2rgb(vec3 hsl) {\n if (hsl.y < EPSILON) return vec3(hsl.z);\n\n float q = hsl.z < 0.5\n ? hsl.z * (1.0 + hsl.y)\n : hsl.z + hsl.y - hsl.z * hsl.y;\n float p = 2.0 * hsl.z - q;\n\n return vec3(\n hue2rgb(p, q, hsl.x + 1.0/3.0),\n hue2rgb(p, q, hsl.x),\n hue2rgb(p, q, hsl.x - 1.0/3.0)\n );\n}\n\nvec3 rgb2hsb(vec3 c) {\n float maxC = max(max(c.r, c.g), c.b);\n float minC = min(min(c.r, c.g), c.b);\n float delta = maxC - minC;\n\n float h = 0.0;\n float s = (maxC > EPSILON) ? delta / maxC : 0.0;\n float b = maxC;\n\n if (delta > EPSILON) {\n if (maxC == c.r) {\n h = (c.g - c.b) / delta + (c.g < c.b ? 6.0 : 0.0);\n } else if (maxC == c.g) {\n h = (c.b - c.r) / delta + 2.0;\n } else {\n h = (c.r - c.g) / delta + 4.0;\n }\n h /= 6.0;\n }\n\n return vec3(h, s, b);\n}\n\nvec3 hsb2rgb(vec3 hsb) {\n vec3 rgb = clamp(abs(mod(hsb.x * 6.0 + vec3(0.0, 4.0, 2.0), 6.0) - 3.0) - 1.0, 0.0, 1.0);\n return hsb.z * mix(vec3(1.0), rgb, hsb.y);\n}\n\n//=============================================================================\n// Color Range Weight Calculation\n//=============================================================================\n\nfloat hueDistance(float a, float b) {\n float d = abs(a - b);\n return min(d, 1.0 - d);\n}\n\nfloat getHueWeight(float hue, float center, float overlap) {\n float baseWidth = 1.0 / 6.0;\n float feather = baseWidth * overlap;\n\n float d = hueDistance(hue, center);\n\n float inner = baseWidth * 0.5;\n float outer = inner + feather;\n\n return 1.0 - smoothstep(inner, outer, d);\n}\n\nfloat getModeWeight(float hue, int mode, float overlap) {\n if (mode == MODE_MASTER || mode == MODE_COLORIZE) return 1.0;\n\n if (mode == MODE_RED) {\n return max(\n getHueWeight(hue, 0.0, overlap),\n getHueWeight(hue, 1.0, overlap)\n );\n }\n\n float center = float(mode - 1) / 6.0;\n return getHueWeight(hue, center, overlap);\n}\n\n//=============================================================================\n// Adjustment Functions\n//=============================================================================\n\nfloat adjustLightness(float l, float amount) {\n return amount > 0.0\n ? l + (1.0 - l) * amount\n : l + l * amount;\n}\n\nfloat adjustBrightness(float b, float amount) {\n return clamp(b + amount, 0.0, 1.0);\n}\n\nfloat adjustSaturation(float s, float amount) {\n return amount > 0.0\n ? s + (1.0 - s) * amount\n : s + s * amount;\n}\n\nvec3 colorize(vec3 rgb, float hue, float sat, float light) {\n float lum = dot(rgb, vec3(0.299, 0.587, 0.114));\n float l = adjustLightness(lum, light);\n\n vec3 hsl = vec3(fract(hue), clamp(sat, 0.0, 1.0), clamp(l, 0.0, 1.0));\n return hsl2rgb(hsl);\n}\n\n//=============================================================================\n// Main\n//=============================================================================\n\nvoid main() {\n vec4 original = texture(u_image0, v_texCoord);\n\n float hueShift = u_float0 / 360.0; // -180..180 -> -0.5..0.5\n float satAmount = u_float1 / 100.0; // -100..100 -> -1..1\n float lightAmount= u_float2 / 100.0; // -100..100 -> -1..1\n float overlap = u_float3 / 100.0; // 0..100 -> 0..1\n\n vec3 result;\n\n if (u_int0 == MODE_COLORIZE) {\n result = colorize(original.rgb, hueShift, satAmount, lightAmount);\n fragColor = vec4(result, original.a);\n return;\n }\n\n vec3 hsx = (u_int1 == COLORSPACE_HSL)\n ? rgb2hsl(original.rgb)\n : rgb2hsb(original.rgb);\n\n float weight = getModeWeight(hsx.x, u_int0, overlap);\n\n if (u_int0 != MODE_MASTER && hsx.y < EPSILON) {\n weight = 0.0;\n }\n\n if (weight > EPSILON) {\n float h = fract(hsx.x + hueShift * weight);\n float s = clamp(adjustSaturation(hsx.y, satAmount * weight), 0.0, 1.0);\n float v = (u_int1 == COLORSPACE_HSL)\n ? clamp(adjustLightness(hsx.z, lightAmount * weight), 0.0, 1.0)\n : clamp(adjustBrightness(hsx.z, lightAmount * weight), 0.0, 1.0);\n\n vec3 adjusted = vec3(h, s, v);\n result = (u_int1 == COLORSPACE_HSL)\n ? hsl2rgb(adjusted)\n : hsb2rgb(adjusted);\n } else {\n result = original.rgb;\n }\n\n fragColor = vec4(result, original.a);\n}\n", "from_input"]}], "groups": [], "links": [{"id": 3, "origin_id": 4, "origin_slot": 0, "target_id": 1, "target_slot": 2, "type": "FLOAT"}, {"id": 4, "origin_id": 5, "origin_slot": 0, "target_id": 1, "target_slot": 3, "type": "FLOAT"}, {"id": 5, "origin_id": 6, "origin_slot": 0, "target_id": 1, "target_slot": 4, "type": "FLOAT"}, {"id": 6, "origin_id": 7, "origin_slot": 0, "target_id": 1, "target_slot": 5, "type": "FLOAT"}, {"id": 1, "origin_id": 2, "origin_slot": 1, "target_id": 1, "target_slot": 7, "type": "INT"}, {"id": 2, "origin_id": 3, "origin_slot": 1, "target_id": 1, "target_slot": 8, "type": "INT"}, {"id": 10, "origin_id": -10, "origin_slot": 0, "target_id": 1, "target_slot": 0, "type": "IMAGE"}, {"id": 8, "origin_id": 1, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}} +{ + "revision": 0, + "last_node_id": 11, + "last_link_id": 0, + "nodes": [ + { + "id": 11, + "type": "c64f83e9-aa5d-4031-89f1-0704e39299fe", + "pos": [ + 870, + -220 + ], + "size": [ + 250, + 178 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "title": "Hue and Saturation", + "properties": { + "proxyWidgets": [ + [ + "2", + "choice" + ], + [ + "4", + "value" + ], + [ + "5", + "value" + ], + [ + "6", + "value" + ], + [ + "7", + "value" + ], + [ + "3", + "choice" + ] + ] + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "c64f83e9-aa5d-4031-89f1-0704e39299fe", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 10, + "lastLinkId": 11, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Hue and Saturation", + "inputNode": { + "id": -10, + "bounding": [ + 360, + -176, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1410, + -176, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "a5aae7ea-b511-4045-b5da-94101e269cd7", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 10 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 460, + -156 + ] + } + ], + "outputs": [ + { + "id": "30b72604-69b3-4944-b253-a9099bbd73a9", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 8 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 1430, + -156 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 3, + "type": "CustomCombo", + "pos": [ + 540, + -240 + ], + "size": [ + 270, + 150 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "color_space", + "localized_name": "choice", + "name": "choice", + "type": "COMBO", + "widget": { + "name": "choice" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": null + }, + { + "localized_name": "INDEX", + "name": "INDEX", + "type": "INT", + "links": [ + 2 + ] + } + ], + "properties": { + "Node name for S&R": "CustomCombo" + }, + "widgets_values": [ + "HSL", + 0, + "HSL", + "HSB/HSV", + "" + ] + }, + { + "id": 2, + "type": "CustomCombo", + "pos": [ + 540, + -580 + ], + "size": [ + 270, + 294 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "mode", + "localized_name": "choice", + "name": "choice", + "type": "COMBO", + "widget": { + "name": "choice" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": null + }, + { + "localized_name": "INDEX", + "name": "INDEX", + "type": "INT", + "links": [ + 1 + ] + } + ], + "properties": { + "Node name for S&R": "CustomCombo" + }, + "widgets_values": [ + "Master", + 0, + "Master", + "Reds", + "Yellows", + "Greens", + "Cyans", + "Blues", + "Magentas", + "Colorize", + "" + ] + }, + { + "id": 7, + "type": "PrimitiveFloat", + "pos": [ + 540, + 260 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "overlap", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 6 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 100, + "precision": 1, + "step": 1 + }, + "widgets_values": [ + 50 + ] + }, + { + "id": 6, + "type": "PrimitiveFloat", + "pos": [ + 540, + 160 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "brightness", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 5 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": -100, + "max": 100, + "precision": 1, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 5, + "type": "PrimitiveFloat", + "pos": [ + 540, + 60 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "saturation", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 4 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": -100, + "max": 100, + "precision": 1, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 4, + "type": "PrimitiveFloat", + "pos": [ + 540, + -40 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "hue", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 3 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": -180, + "max": 180, + "precision": 1, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 255, + 0, + 0 + ] + }, + { + "offset": 0.16666666666666666, + "color": [ + 255, + 255, + 0 + ] + }, + { + "offset": 0.3333333333333333, + "color": [ + 0, + 255, + 0 + ] + }, + { + "offset": 0.5, + "color": [ + 0, + 255, + 255 + ] + }, + { + "offset": 0.6666666666666666, + "color": [ + 0, + 0, + 255 + ] + }, + { + "offset": 0.8333333333333334, + "color": [ + 255, + 0, + 255 + ] + }, + { + "offset": 1, + "color": [ + 255, + 0, + 0 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 1, + "type": "GLSLShader", + "pos": [ + 880, + -300 + ], + "size": [ + 470, + 292 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 10 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 3 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 4 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": 5 + }, + { + "label": "u_float3", + "localized_name": "floats.u_float3", + "name": "floats.u_float3", + "shape": 7, + "type": "FLOAT", + "link": 6 + }, + { + "label": "u_float4", + "localized_name": "floats.u_float4", + "name": "floats.u_float4", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": 1 + }, + { + "label": "u_int1", + "localized_name": "ints.u_int1", + "name": "ints.u_int1", + "shape": 7, + "type": "INT", + "link": 2 + }, + { + "label": "u_int2", + "localized_name": "ints.u_int2", + "name": "ints.u_int2", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 8 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform int u_int0; // Mode: 0=Master, 1=Reds, 2=Yellows, 3=Greens, 4=Cyans, 5=Blues, 6=Magentas, 7=Colorize\nuniform int u_int1; // Color Space: 0=HSL, 1=HSB/HSV\nuniform float u_float0; // Hue (-180 to 180)\nuniform float u_float1; // Saturation (-100 to 100)\nuniform float u_float2; // Lightness/Brightness (-100 to 100)\nuniform float u_float3; // Overlap (0 to 100) - feathering between adjacent color ranges\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\n// Color range modes\nconst int MODE_MASTER = 0;\nconst int MODE_RED = 1;\nconst int MODE_YELLOW = 2;\nconst int MODE_GREEN = 3;\nconst int MODE_CYAN = 4;\nconst int MODE_BLUE = 5;\nconst int MODE_MAGENTA = 6;\nconst int MODE_COLORIZE = 7;\n\n// Color space modes\nconst int COLORSPACE_HSL = 0;\nconst int COLORSPACE_HSB = 1;\n\nconst float EPSILON = 0.0001;\n\n//=============================================================================\n// RGB <-> HSL Conversions\n//=============================================================================\n\nvec3 rgb2hsl(vec3 c) {\n float maxC = max(max(c.r, c.g), c.b);\n float minC = min(min(c.r, c.g), c.b);\n float delta = maxC - minC;\n\n float h = 0.0;\n float s = 0.0;\n float l = (maxC + minC) * 0.5;\n\n if (delta > EPSILON) {\n s = l < 0.5\n ? delta / (maxC + minC)\n : delta / (2.0 - maxC - minC);\n\n if (maxC == c.r) {\n h = (c.g - c.b) / delta + (c.g < c.b ? 6.0 : 0.0);\n } else if (maxC == c.g) {\n h = (c.b - c.r) / delta + 2.0;\n } else {\n h = (c.r - c.g) / delta + 4.0;\n }\n h /= 6.0;\n }\n\n return vec3(h, s, l);\n}\n\nfloat hue2rgb(float p, float q, float t) {\n t = fract(t);\n if (t < 1.0/6.0) return p + (q - p) * 6.0 * t;\n if (t < 0.5) return q;\n if (t < 2.0/3.0) return p + (q - p) * (2.0/3.0 - t) * 6.0;\n return p;\n}\n\nvec3 hsl2rgb(vec3 hsl) {\n if (hsl.y < EPSILON) return vec3(hsl.z);\n\n float q = hsl.z < 0.5\n ? hsl.z * (1.0 + hsl.y)\n : hsl.z + hsl.y - hsl.z * hsl.y;\n float p = 2.0 * hsl.z - q;\n\n return vec3(\n hue2rgb(p, q, hsl.x + 1.0/3.0),\n hue2rgb(p, q, hsl.x),\n hue2rgb(p, q, hsl.x - 1.0/3.0)\n );\n}\n\nvec3 rgb2hsb(vec3 c) {\n float maxC = max(max(c.r, c.g), c.b);\n float minC = min(min(c.r, c.g), c.b);\n float delta = maxC - minC;\n\n float h = 0.0;\n float s = (maxC > EPSILON) ? delta / maxC : 0.0;\n float b = maxC;\n\n if (delta > EPSILON) {\n if (maxC == c.r) {\n h = (c.g - c.b) / delta + (c.g < c.b ? 6.0 : 0.0);\n } else if (maxC == c.g) {\n h = (c.b - c.r) / delta + 2.0;\n } else {\n h = (c.r - c.g) / delta + 4.0;\n }\n h /= 6.0;\n }\n\n return vec3(h, s, b);\n}\n\nvec3 hsb2rgb(vec3 hsb) {\n vec3 rgb = clamp(abs(mod(hsb.x * 6.0 + vec3(0.0, 4.0, 2.0), 6.0) - 3.0) - 1.0, 0.0, 1.0);\n return hsb.z * mix(vec3(1.0), rgb, hsb.y);\n}\n\n//=============================================================================\n// Color Range Weight Calculation\n//=============================================================================\n\nfloat hueDistance(float a, float b) {\n float d = abs(a - b);\n return min(d, 1.0 - d);\n}\n\nfloat getHueWeight(float hue, float center, float overlap) {\n float baseWidth = 1.0 / 6.0;\n float feather = baseWidth * overlap;\n\n float d = hueDistance(hue, center);\n\n float inner = baseWidth * 0.5;\n float outer = inner + feather;\n\n return 1.0 - smoothstep(inner, outer, d);\n}\n\nfloat getModeWeight(float hue, int mode, float overlap) {\n if (mode == MODE_MASTER || mode == MODE_COLORIZE) return 1.0;\n\n if (mode == MODE_RED) {\n return max(\n getHueWeight(hue, 0.0, overlap),\n getHueWeight(hue, 1.0, overlap)\n );\n }\n\n float center = float(mode - 1) / 6.0;\n return getHueWeight(hue, center, overlap);\n}\n\n//=============================================================================\n// Adjustment Functions\n//=============================================================================\n\nfloat adjustLightness(float l, float amount) {\n return amount > 0.0\n ? l + (1.0 - l) * amount\n : l + l * amount;\n}\n\nfloat adjustBrightness(float b, float amount) {\n return clamp(b + amount, 0.0, 1.0);\n}\n\nfloat adjustSaturation(float s, float amount) {\n return amount > 0.0\n ? s + (1.0 - s) * amount\n : s + s * amount;\n}\n\nvec3 colorize(vec3 rgb, float hue, float sat, float light) {\n float lum = dot(rgb, vec3(0.299, 0.587, 0.114));\n float l = adjustLightness(lum, light);\n\n vec3 hsl = vec3(fract(hue), clamp(sat, 0.0, 1.0), clamp(l, 0.0, 1.0));\n return hsl2rgb(hsl);\n}\n\n//=============================================================================\n// Main\n//=============================================================================\n\nvoid main() {\n vec4 original = texture(u_image0, v_texCoord);\n\n float hueShift = u_float0 / 360.0; // -180..180 -> -0.5..0.5\n float satAmount = u_float1 / 100.0; // -100..100 -> -1..1\n float lightAmount= u_float2 / 100.0; // -100..100 -> -1..1\n float overlap = u_float3 / 100.0; // 0..100 -> 0..1\n\n vec3 result;\n\n if (u_int0 == MODE_COLORIZE) {\n result = colorize(original.rgb, hueShift, satAmount, lightAmount);\n fragColor = vec4(result, original.a);\n return;\n }\n\n vec3 hsx = (u_int1 == COLORSPACE_HSL)\n ? rgb2hsl(original.rgb)\n : rgb2hsb(original.rgb);\n\n float weight = getModeWeight(hsx.x, u_int0, overlap);\n\n if (u_int0 != MODE_MASTER && hsx.y < EPSILON) {\n weight = 0.0;\n }\n\n if (weight > EPSILON) {\n float h = fract(hsx.x + hueShift * weight);\n float s = clamp(adjustSaturation(hsx.y, satAmount * weight), 0.0, 1.0);\n float v = (u_int1 == COLORSPACE_HSL)\n ? clamp(adjustLightness(hsx.z, lightAmount * weight), 0.0, 1.0)\n : clamp(adjustBrightness(hsx.z, lightAmount * weight), 0.0, 1.0);\n\n vec3 adjusted = vec3(h, s, v);\n result = (u_int1 == COLORSPACE_HSL)\n ? hsl2rgb(adjusted)\n : hsb2rgb(adjusted);\n } else {\n result = original.rgb;\n }\n\n fragColor = vec4(result, original.a);\n}\n", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 3, + "origin_id": 4, + "origin_slot": 0, + "target_id": 1, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 4, + "origin_id": 5, + "origin_slot": 0, + "target_id": 1, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 5, + "origin_id": 6, + "origin_slot": 0, + "target_id": 1, + "target_slot": 4, + "type": "FLOAT" + }, + { + "id": 6, + "origin_id": 7, + "origin_slot": 0, + "target_id": 1, + "target_slot": 5, + "type": "FLOAT" + }, + { + "id": 1, + "origin_id": 2, + "origin_slot": 1, + "target_id": 1, + "target_slot": 7, + "type": "INT" + }, + { + "id": 2, + "origin_id": 3, + "origin_slot": 1, + "target_id": 1, + "target_slot": 8, + "type": "INT" + }, + { + "id": 10, + "origin_id": -10, + "origin_slot": 0, + "target_id": 1, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 8, + "origin_id": 1, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} diff --git a/blueprints/Image Blur.json b/blueprints/Image Blur.json index 4b9e74255..3c7a784b0 100644 --- a/blueprints/Image Blur.json +++ b/blueprints/Image Blur.json @@ -1 +1,381 @@ -{"revision": 0, "last_node_id": 8, "last_link_id": 0, "nodes": [{"id": 8, "type": "198632a3-ee76-4aab-9ce7-a69c624eaff9", "pos": [4470, -1840], "size": [210, 82], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "blurred_image", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["12", "choice"], ["10", "value"]]}, "widgets_values": [], "title": "Image Blur"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "198632a3-ee76-4aab-9ce7-a69c624eaff9", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 12, "lastLinkId": 11, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Blur", "inputNode": {"id": -10, "bounding": [3540, -2445, 120, 60]}, "outputNode": {"id": -20, "bounding": [4620, -2445, 121.11666870117188, 60]}, "inputs": [{"id": "7ff2a402-6b11-45e8-a92a-7158d216520a", "name": "images.image0", "type": "IMAGE", "linkIds": [9], "localized_name": "images.image0", "label": "image", "pos": [3640, -2425]}], "outputs": [{"id": "80a8e19e-ffd9-44a5-90f2-710815a5b063", "name": "IMAGE0", "type": "IMAGE", "linkIds": [3], "localized_name": "IMAGE0", "label": "blurred_image", "pos": [4640, -2425]}], "widgets": [], "nodes": [{"id": 12, "type": "CustomCombo", "pos": [3720, -2620], "size": [270, 174], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "blur_type", "localized_name": "choice", "name": "choice", "type": "COMBO", "widget": {"name": "choice"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": null}, {"localized_name": "INDEX", "name": "INDEX", "type": "INT", "links": [11]}], "properties": {"Node name for S&R": "CustomCombo"}, "widgets_values": ["Gaussian", 0, "Gaussian", "Box", "Radial", ""]}, {"id": 10, "type": "PrimitiveFloat", "pos": [4020, -2780], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "strength", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [10]}], "properties": {"Node name for S&R": "PrimitiveFloat", "max": 100, "min": 0}, "widgets_values": [20]}, {"id": 1, "type": "GLSLShader", "pos": [4020, -2670], "size": [430, 212], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 9}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 10}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": 11}, {"label": "u_int1", "localized_name": "ints.u_int1", "name": "ints.u_int1", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [3]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": []}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": []}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": []}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\n#pragma passes 2\nprecision highp float;\n\n// Blur type constants\nconst int BLUR_GAUSSIAN = 0;\nconst int BLUR_BOX = 1;\nconst int BLUR_RADIAL = 2;\n\n// Radial blur config\nconst int RADIAL_SAMPLES = 12;\nconst float RADIAL_STRENGTH = 0.0003;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform int u_int0; // Blur type (BLUR_GAUSSIAN, BLUR_BOX, BLUR_RADIAL)\nuniform float u_float0; // Blur radius/amount\nuniform int u_pass; // Pass index (0 = horizontal, 1 = vertical)\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nvoid main() {\n vec2 texelSize = 1.0 / u_resolution;\n float radius = max(u_float0, 0.0);\n\n // Radial (angular) blur - single pass, doesn't use separable\n if (u_int0 == BLUR_RADIAL) {\n // Only execute on first pass\n if (u_pass > 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec2 center = vec2(0.5);\n vec2 dir = v_texCoord - center;\n float dist = length(dir);\n\n if (dist < 1e-4) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec4 sum = vec4(0.0);\n float totalWeight = 0.0;\n float angleStep = radius * RADIAL_STRENGTH;\n\n dir /= dist;\n\n float cosStep = cos(angleStep);\n float sinStep = sin(angleStep);\n\n float negAngle = -float(RADIAL_SAMPLES) * angleStep;\n vec2 rotDir = vec2(\n dir.x * cos(negAngle) - dir.y * sin(negAngle),\n dir.x * sin(negAngle) + dir.y * cos(negAngle)\n );\n\n for (int i = -RADIAL_SAMPLES; i <= RADIAL_SAMPLES; i++) {\n vec2 uv = center + rotDir * dist;\n float w = 1.0 - abs(float(i)) / float(RADIAL_SAMPLES);\n sum += texture(u_image0, uv) * w;\n totalWeight += w;\n\n rotDir = vec2(\n rotDir.x * cosStep - rotDir.y * sinStep,\n rotDir.x * sinStep + rotDir.y * cosStep\n );\n }\n\n fragColor0 = sum / max(totalWeight, 0.001);\n return;\n }\n\n // Separable Gaussian / Box blur\n int samples = int(ceil(radius));\n\n if (samples == 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n // Direction: pass 0 = horizontal, pass 1 = vertical\n vec2 dir = (u_pass == 0) ? vec2(1.0, 0.0) : vec2(0.0, 1.0);\n\n vec4 color = vec4(0.0);\n float totalWeight = 0.0;\n float sigma = radius / 2.0;\n\n for (int i = -samples; i <= samples; i++) {\n vec2 offset = dir * float(i) * texelSize;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float weight;\n if (u_int0 == BLUR_GAUSSIAN) {\n weight = gaussian(float(i), sigma);\n } else {\n // BLUR_BOX\n weight = 1.0;\n }\n\n color += sample_color * weight;\n totalWeight += weight;\n }\n\n fragColor0 = color / totalWeight;\n}\n", "from_input"]}], "groups": [], "links": [{"id": 10, "origin_id": 10, "origin_slot": 0, "target_id": 1, "target_slot": 2, "type": "FLOAT"}, {"id": 11, "origin_id": 12, "origin_slot": 1, "target_id": 1, "target_slot": 4, "type": "INT"}, {"id": 9, "origin_id": -10, "origin_slot": 0, "target_id": 1, "target_slot": 0, "type": "IMAGE"}, {"id": 3, "origin_id": 1, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Blur"}]}} +{ + "revision": 0, + "last_node_id": 8, + "last_link_id": 0, + "nodes": [ + { + "id": 8, + "type": "198632a3-ee76-4aab-9ce7-a69c624eaff9", + "pos": [ + 4470, + -1840 + ], + "size": [ + 210, + 82 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "blurred_image", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "12", + "choice" + ], + [ + "10", + "value" + ] + ] + }, + "widgets_values": [], + "title": "Image Blur" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "198632a3-ee76-4aab-9ce7-a69c624eaff9", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 12, + "lastLinkId": 11, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Blur", + "inputNode": { + "id": -10, + "bounding": [ + 3540, + -2445, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4620, + -2445, + 121.11666870117188, + 60 + ] + }, + "inputs": [ + { + "id": "7ff2a402-6b11-45e8-a92a-7158d216520a", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 9 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 3640, + -2425 + ] + } + ], + "outputs": [ + { + "id": "80a8e19e-ffd9-44a5-90f2-710815a5b063", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 3 + ], + "localized_name": "IMAGE0", + "label": "blurred_image", + "pos": [ + 4640, + -2425 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 12, + "type": "CustomCombo", + "pos": [ + 3720, + -2620 + ], + "size": [ + 270, + 174 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "blur_type", + "localized_name": "choice", + "name": "choice", + "type": "COMBO", + "widget": { + "name": "choice" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": null + }, + { + "localized_name": "INDEX", + "name": "INDEX", + "type": "INT", + "links": [ + 11 + ] + } + ], + "properties": { + "Node name for S&R": "CustomCombo" + }, + "widgets_values": [ + "Gaussian", + 0, + "Gaussian", + "Box", + "Radial", + "" + ] + }, + { + "id": 10, + "type": "PrimitiveFloat", + "pos": [ + 4020, + -2780 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "strength", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 10 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 100, + "min": 0 + }, + "widgets_values": [ + 20 + ] + }, + { + "id": 1, + "type": "GLSLShader", + "pos": [ + 4020, + -2670 + ], + "size": [ + 430, + 212 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 9 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 10 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": 11 + }, + { + "label": "u_int1", + "localized_name": "ints.u_int1", + "name": "ints.u_int1", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 3 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": [] + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": [] + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\n#pragma passes 2\nprecision highp float;\n\n// Blur type constants\nconst int BLUR_GAUSSIAN = 0;\nconst int BLUR_BOX = 1;\nconst int BLUR_RADIAL = 2;\n\n// Radial blur config\nconst int RADIAL_SAMPLES = 12;\nconst float RADIAL_STRENGTH = 0.0003;\n\nuniform sampler2D u_image0;\nuniform int u_int0; // Blur type (BLUR_GAUSSIAN, BLUR_BOX, BLUR_RADIAL)\nuniform float u_float0; // Blur radius/amount\nuniform int u_pass; // Pass index (0 = horizontal, 1 = vertical)\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nvoid main() {\n vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));\n float radius = max(u_float0, 0.0);\n\n // Radial (angular) blur - single pass, doesn't use separable\n if (u_int0 == BLUR_RADIAL) {\n // Only execute on first pass\n if (u_pass > 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec2 center = vec2(0.5);\n vec2 dir = v_texCoord - center;\n float dist = length(dir);\n\n if (dist < 1e-4) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec4 sum = vec4(0.0);\n float totalWeight = 0.0;\n float angleStep = radius * RADIAL_STRENGTH;\n\n dir /= dist;\n\n float cosStep = cos(angleStep);\n float sinStep = sin(angleStep);\n\n float negAngle = -float(RADIAL_SAMPLES) * angleStep;\n vec2 rotDir = vec2(\n dir.x * cos(negAngle) - dir.y * sin(negAngle),\n dir.x * sin(negAngle) + dir.y * cos(negAngle)\n );\n\n for (int i = -RADIAL_SAMPLES; i <= RADIAL_SAMPLES; i++) {\n vec2 uv = center + rotDir * dist;\n float w = 1.0 - abs(float(i)) / float(RADIAL_SAMPLES);\n sum += texture(u_image0, uv) * w;\n totalWeight += w;\n\n rotDir = vec2(\n rotDir.x * cosStep - rotDir.y * sinStep,\n rotDir.x * sinStep + rotDir.y * cosStep\n );\n }\n\n fragColor0 = sum / max(totalWeight, 0.001);\n return;\n }\n\n // Separable Gaussian / Box blur\n int samples = int(ceil(radius));\n\n if (samples == 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n // Direction: pass 0 = horizontal, pass 1 = vertical\n vec2 dir = (u_pass == 0) ? vec2(1.0, 0.0) : vec2(0.0, 1.0);\n\n vec4 color = vec4(0.0);\n float totalWeight = 0.0;\n float sigma = radius / 2.0;\n\n for (int i = -samples; i <= samples; i++) {\n vec2 offset = dir * float(i) * texelSize;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float weight;\n if (u_int0 == BLUR_GAUSSIAN) {\n weight = gaussian(float(i), sigma);\n } else {\n // BLUR_BOX\n weight = 1.0;\n }\n\n color += sample_color * weight;\n totalWeight += weight;\n }\n\n fragColor0 = color / totalWeight;\n}\n", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 10, + "origin_id": 10, + "origin_slot": 0, + "target_id": 1, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 11, + "origin_id": 12, + "origin_slot": 1, + "target_id": 1, + "target_slot": 4, + "type": "INT" + }, + { + "id": 9, + "origin_id": -10, + "origin_slot": 0, + "target_id": 1, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 3, + "origin_id": 1, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Blur" + } + ] + } +} diff --git a/blueprints/Image Captioning (gemini).json b/blueprints/Image Captioning (gemini).json index 89ebac802..98cfb8999 100644 --- a/blueprints/Image Captioning (gemini).json +++ b/blueprints/Image Captioning (gemini).json @@ -1 +1,317 @@ -{"revision": 0, "last_node_id": 231, "last_link_id": 0, "nodes": [{"id": 231, "type": "e3e78497-720e-45a2-b4fb-c7bfdb80dd11", "pos": [23.13283014087665, 1034.468391137315], "size": [280, 260], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": null}, {"name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}, {"name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": []}], "properties": {"proxyWidgets": [["-1", "prompt"], ["-1", "model"], ["1", "seed"]], "cnr_id": "comfy-core", "ver": "0.13.0"}, "widgets_values": ["Describe this image", "gemini-2.5-pro"], "title": "Image Captioning(Gemini)"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "e3e78497-720e-45a2-b4fb-c7bfdb80dd11", "version": 1, "state": {"lastGroupId": 1, "lastNodeId": 16, "lastLinkId": 16, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Captioning(Gemini)", "inputNode": {"id": -10, "bounding": [-6870, 2530, 120, 100]}, "outputNode": {"id": -20, "bounding": [-6240, 2530, 120, 60]}, "inputs": [{"id": "97cb8fa5-0514-4e05-b206-46fa6d7b5589", "name": "images", "type": "IMAGE", "linkIds": [1], "localized_name": "images", "shape": 7, "pos": [-6770, 2550]}, {"id": "d8cbd7eb-636a-4d7b-8ff6-b22f1755e26c", "name": "prompt", "type": "STRING", "linkIds": [15], "pos": [-6770, 2570]}, {"id": "b034e26a-d114-4604-aec2-32783e86aa6b", "name": "model", "type": "COMBO", "linkIds": [16], "pos": [-6770, 2590]}], "outputs": [{"id": "e12c6e80-5210-4328-a581-bc8924c53070", "name": "STRING", "type": "STRING", "linkIds": [6], "localized_name": "STRING", "pos": [-6220, 2550]}], "widgets": [], "nodes": [{"id": 1, "type": "GeminiNode", "pos": [-6690, 2360], "size": [390, 430], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "shape": 7, "type": "IMAGE", "link": 1}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "video", "name": "video", "shape": 7, "type": "VIDEO", "link": null}, {"localized_name": "files", "name": "files", "shape": 7, "type": "GEMINI_INPUT_FILES", "link": null}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": 15}, {"localized_name": "model", "name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": 16}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "system_prompt", "name": "system_prompt", "shape": 7, "type": "STRING", "widget": {"name": "system_prompt"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": [6]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "GeminiNode"}, "widgets_values": ["Describe this image", "gemini-2.5-pro", 511865409297955, "randomize", "- Role: AI Image Analysis and Description Specialist\n- Background: The user requires a prompt that enables AI to analyze images and generate detailed descriptions which can be used as drawing prompts to create similar images. This is essential for tasks like content creation, design inspiration, and artistic exploration.\n- Profile: As an AI Image Analysis and Description Specialist, you possess extensive knowledge in computer vision, image processing, and natural language generation. You are adept at interpreting visual data and translating it into descriptive text that can guide the creation of new images.\n- Skills: Proficiency in image recognition, feature extraction, descriptive language generation, and understanding of artistic elements such as composition, color, and texture.\n- Goals: To analyze the provided image, generate a comprehensive and detailed description that captures the key visual elements, and ensure this description can effectively serve as a drawing prompt for creating similar images.\n- Constrains: The description must be clear, concise, and specific enough to guide the creation of a similar image. It should avoid ambiguity and focus on the most salient features of the image. The output should only contain the drawing prompt.\n- OutputFormat: A detailed text description of the image, highlighting key visual elements such as objects, colors, composition, and any unique features.\n- Workflow:\n 1. Analyze the image to identify key visual elements including objects, colors, and composition.\n 2. Generate a detailed description that captures the essence of the image, ensuring it is specific and actionable.\n 3. Refine the description to ensure clarity and conciseness, making it suitable for use as a drawing prompt."], "color": "#432", "bgcolor": "#653"}], "groups": [], "links": [{"id": 1, "origin_id": -10, "origin_slot": 0, "target_id": 1, "target_slot": 0, "type": "IMAGE"}, {"id": 6, "origin_id": 1, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "*"}, {"id": 15, "origin_id": -10, "origin_slot": 1, "target_id": 1, "target_slot": 4, "type": "STRING"}, {"id": 16, "origin_id": -10, "origin_slot": 2, "target_id": 1, "target_slot": 5, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Text generation/Image Captioning"}]}} +{ + "revision": 0, + "last_node_id": 231, + "last_link_id": 0, + "nodes": [ + { + "id": 231, + "type": "e3e78497-720e-45a2-b4fb-c7bfdb80dd11", + "pos": [ + 23.13283014087665, + 1034.468391137315 + ], + "size": [ + 280, + 260 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": null + }, + { + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + }, + { + "name": "model", + "type": "COMBO", + "widget": { + "name": "model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "prompt" + ], + [ + "-1", + "model" + ], + [ + "1", + "seed" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.13.0" + }, + "widgets_values": [ + "Describe this image", + "gemini-2.5-pro" + ], + "title": "Image Captioning(Gemini)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "e3e78497-720e-45a2-b4fb-c7bfdb80dd11", + "version": 1, + "state": { + "lastGroupId": 1, + "lastNodeId": 16, + "lastLinkId": 16, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Captioning(Gemini)", + "inputNode": { + "id": -10, + "bounding": [ + -6870, + 2530, + 120, + 100 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + -6240, + 2530, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "97cb8fa5-0514-4e05-b206-46fa6d7b5589", + "name": "images", + "type": "IMAGE", + "linkIds": [ + 1 + ], + "localized_name": "images", + "shape": 7, + "pos": [ + -6770, + 2550 + ] + }, + { + "id": "d8cbd7eb-636a-4d7b-8ff6-b22f1755e26c", + "name": "prompt", + "type": "STRING", + "linkIds": [ + 15 + ], + "pos": [ + -6770, + 2570 + ] + }, + { + "id": "b034e26a-d114-4604-aec2-32783e86aa6b", + "name": "model", + "type": "COMBO", + "linkIds": [ + 16 + ], + "pos": [ + -6770, + 2590 + ] + } + ], + "outputs": [ + { + "id": "e12c6e80-5210-4328-a581-bc8924c53070", + "name": "STRING", + "type": "STRING", + "linkIds": [ + 6 + ], + "localized_name": "STRING", + "pos": [ + -6220, + 2550 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 1, + "type": "GeminiNode", + "pos": [ + -6690, + 2360 + ], + "size": [ + 390, + 430 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "shape": 7, + "type": "IMAGE", + "link": 1 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": null + }, + { + "localized_name": "video", + "name": "video", + "shape": 7, + "type": "VIDEO", + "link": null + }, + { + "localized_name": "files", + "name": "files", + "shape": 7, + "type": "GEMINI_INPUT_FILES", + "link": null + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": 15 + }, + { + "localized_name": "model", + "name": "model", + "type": "COMBO", + "widget": { + "name": "model" + }, + "link": 16 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "system_prompt", + "name": "system_prompt", + "shape": 7, + "type": "STRING", + "widget": { + "name": "system_prompt" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 6 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "GeminiNode" + }, + "widgets_values": [ + "Describe this image", + "gemini-2.5-pro", + 511865409297955, + "randomize", + "- Role: AI Image Analysis and Description Specialist\n- Background: The user requires a prompt that enables AI to analyze images and generate detailed descriptions which can be used as drawing prompts to create similar images. This is essential for tasks like content creation, design inspiration, and artistic exploration.\n- Profile: As an AI Image Analysis and Description Specialist, you possess extensive knowledge in computer vision, image processing, and natural language generation. You are adept at interpreting visual data and translating it into descriptive text that can guide the creation of new images.\n- Skills: Proficiency in image recognition, feature extraction, descriptive language generation, and understanding of artistic elements such as composition, color, and texture.\n- Goals: To analyze the provided image, generate a comprehensive and detailed description that captures the key visual elements, and ensure this description can effectively serve as a drawing prompt for creating similar images.\n- Constrains: The description must be clear, concise, and specific enough to guide the creation of a similar image. It should avoid ambiguity and focus on the most salient features of the image. The output should only contain the drawing prompt.\n- OutputFormat: A detailed text description of the image, highlighting key visual elements such as objects, colors, composition, and any unique features.\n- Workflow:\n 1. Analyze the image to identify key visual elements including objects, colors, and composition.\n 2. Generate a detailed description that captures the essence of the image, ensuring it is specific and actionable.\n 3. Refine the description to ensure clarity and conciseness, making it suitable for use as a drawing prompt." + ], + "color": "#432", + "bgcolor": "#653" + } + ], + "groups": [], + "links": [ + { + "id": 1, + "origin_id": -10, + "origin_slot": 0, + "target_id": 1, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 6, + "origin_id": 1, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "*" + }, + { + "id": 15, + "origin_id": -10, + "origin_slot": 1, + "target_id": 1, + "target_slot": 4, + "type": "STRING" + }, + { + "id": 16, + "origin_id": -10, + "origin_slot": 2, + "target_id": 1, + "target_slot": 5, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Text generation/Image Captioning" + } + ] + } +} diff --git a/blueprints/Image Channels.json b/blueprints/Image Channels.json index cb3488883..9c7b675b2 100644 --- a/blueprints/Image Channels.json +++ b/blueprints/Image Channels.json @@ -1 +1,322 @@ -{"revision": 0, "last_node_id": 29, "last_link_id": 0, "nodes": [{"id": 29, "type": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "pos": [1970, -230], "size": [180, 86], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": []}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": []}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": []}], "title": "Image Channels", "properties": {"proxyWidgets": []}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 28, "lastLinkId": 39, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Channels", "inputNode": {"id": -10, "bounding": [1820, -185, 120, 60]}, "outputNode": {"id": -20, "bounding": [2460, -215, 120, 120]}, "inputs": [{"id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe", "name": "images.image0", "type": "IMAGE", "linkIds": [39], "localized_name": "images.image0", "label": "image", "pos": [1920, -165]}], "outputs": [{"id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b", "name": "IMAGE0", "type": "IMAGE", "linkIds": [26], "localized_name": "IMAGE0", "label": "R", "pos": [2480, -195]}, {"id": "fb44a77e-0522-43e9-9527-82e7465b3596", "name": "IMAGE1", "type": "IMAGE", "linkIds": [27], "localized_name": "IMAGE1", "label": "G", "pos": [2480, -175]}, {"id": "81460ee6-0131-402a-874f-6bf3001fc4ff", "name": "IMAGE2", "type": "IMAGE", "linkIds": [28], "localized_name": "IMAGE2", "label": "B", "pos": [2480, -155]}, {"id": "ae690246-80d4-4951-b1d9-9306d8a77417", "name": "IMAGE3", "type": "IMAGE", "linkIds": [29], "localized_name": "IMAGE3", "label": "A", "pos": [2480, -135]}], "widgets": [], "nodes": [{"id": 23, "type": "GLSLShader", "pos": [2000, -330], "size": [400, 172], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 39}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [26]}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": [27]}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": [28]}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": [29]}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n // Output each channel as grayscale to separate render targets\n fragColor0 = vec4(vec3(color.r), 1.0); // Red channel\n fragColor1 = vec4(vec3(color.g), 1.0); // Green channel\n fragColor2 = vec4(vec3(color.b), 1.0); // Blue channel\n fragColor3 = vec4(vec3(color.a), 1.0); // Alpha channel\n}\n", "from_input"]}], "groups": [], "links": [{"id": 39, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 26, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 27, "origin_id": 23, "origin_slot": 1, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 28, "origin_id": 23, "origin_slot": 2, "target_id": -20, "target_slot": 2, "type": "IMAGE"}, {"id": 29, "origin_id": 23, "origin_slot": 3, "target_id": -20, "target_slot": 3, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}} +{ + "revision": 0, + "last_node_id": 29, + "last_link_id": 0, + "nodes": [ + { + "id": 29, + "type": "4c9d6ea4-b912-40e5-8766-6793a9758c53", + "pos": [ + 1970, + -230 + ], + "size": [ + 180, + 86 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "R", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + }, + { + "label": "G", + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": [] + }, + { + "label": "B", + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": [] + }, + { + "label": "A", + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": [] + } + ], + "title": "Image Channels", + "properties": { + "proxyWidgets": [] + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "4c9d6ea4-b912-40e5-8766-6793a9758c53", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 28, + "lastLinkId": 39, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Channels", + "inputNode": { + "id": -10, + "bounding": [ + 1820, + -185, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 2460, + -215, + 120, + 120 + ] + }, + "inputs": [ + { + "id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 39 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 1920, + -165 + ] + } + ], + "outputs": [ + { + "id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 26 + ], + "localized_name": "IMAGE0", + "label": "R", + "pos": [ + 2480, + -195 + ] + }, + { + "id": "fb44a77e-0522-43e9-9527-82e7465b3596", + "name": "IMAGE1", + "type": "IMAGE", + "linkIds": [ + 27 + ], + "localized_name": "IMAGE1", + "label": "G", + "pos": [ + 2480, + -175 + ] + }, + { + "id": "81460ee6-0131-402a-874f-6bf3001fc4ff", + "name": "IMAGE2", + "type": "IMAGE", + "linkIds": [ + 28 + ], + "localized_name": "IMAGE2", + "label": "B", + "pos": [ + 2480, + -155 + ] + }, + { + "id": "ae690246-80d4-4951-b1d9-9306d8a77417", + "name": "IMAGE3", + "type": "IMAGE", + "linkIds": [ + 29 + ], + "localized_name": "IMAGE3", + "label": "A", + "pos": [ + 2480, + -135 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 23, + "type": "GLSLShader", + "pos": [ + 2000, + -330 + ], + "size": [ + 400, + 172 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 39 + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "R", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 26 + ] + }, + { + "label": "G", + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": [ + 27 + ] + }, + { + "label": "B", + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": [ + 28 + ] + }, + { + "label": "A", + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": [ + 29 + ] + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n // Output each channel as grayscale to separate render targets\n fragColor0 = vec4(vec3(color.r), 1.0); // Red channel\n fragColor1 = vec4(vec3(color.g), 1.0); // Green channel\n fragColor2 = vec4(vec3(color.b), 1.0); // Blue channel\n fragColor3 = vec4(vec3(color.a), 1.0); // Alpha channel\n}\n", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 39, + "origin_id": -10, + "origin_slot": 0, + "target_id": 23, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 26, + "origin_id": 23, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 27, + "origin_id": 23, + "origin_slot": 1, + "target_id": -20, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 28, + "origin_id": 23, + "origin_slot": 2, + "target_id": -20, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 29, + "origin_id": 23, + "origin_slot": 3, + "target_id": -20, + "target_slot": 3, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + } +} diff --git a/blueprints/Image Edit (FireRed Image Edit 1.1).json b/blueprints/Image Edit (FireRed Image Edit 1.1).json new file mode 100644 index 000000000..c34246ce6 --- /dev/null +++ b/blueprints/Image Edit (FireRed Image Edit 1.1).json @@ -0,0 +1,2148 @@ +{ + "revision": 0, + "last_node_id": 172, + "last_link_id": 0, + "nodes": [ + { + "id": 172, + "type": "edf73971-14ee-4d39-b58e-46ce2a89d3d0", + "pos": [ + 30, + 200 + ], + "size": [ + 500, + 570 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "label": "image2 (optional)", + "name": "image2_1", + "type": "IMAGE", + "link": null + }, + { + "label": "image3 (optional)", + "name": "image3_1", + "type": "IMAGE", + "link": null + }, + { + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + }, + { + "label": "enable_turbo_mode", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "118", + "prompt" + ], + [ + "153", + "value" + ], + [ + "130", + "seed" + ], + [ + "128", + "unet_name" + ], + [ + "115", + "clip_name" + ], + [ + "116", + "vae_name" + ], + [ + "151", + "lora_name" + ], + [ + "130", + "control_after_generate" + ] + ], + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [], + "title": "Image Edit (FireRed Image Edit 1.1)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "edf73971-14ee-4d39-b58e-46ce2a89d3d0", + "version": 1, + "state": { + "lastGroupId": 8, + "lastNodeId": 174, + "lastLinkId": 376, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Edit (FireRed Image Edit 1.1)", + "inputNode": { + "id": -10, + "bounding": [ + -1670, + -1370, + 151.744140625, + 240 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1147.5, + -1215, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "1d810e30-f1fb-4d10-95f8-3c5f7db2c8b7", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 371 + ], + "localized_name": "image", + "pos": [ + -1538.255859375, + -1350 + ] + }, + { + "id": "a8decf32-2262-4cdd-9e6b-c0ca7d4cdebe", + "name": "image2_1", + "type": "IMAGE", + "linkIds": [ + 355, + 356 + ], + "label": "image2 (optional)", + "pos": [ + -1538.255859375, + -1330 + ] + }, + { + "id": "3ff7a4ed-8e3d-45d4-b1d8-40ed88a6def6", + "name": "image3_1", + "type": "IMAGE", + "linkIds": [ + 357, + 358 + ], + "label": "image3 (optional)", + "pos": [ + -1538.255859375, + -1310 + ] + }, + { + "id": "01d9e68c-c664-4584-9cde-66f60e54eb3c", + "name": "prompt", + "type": "STRING", + "linkIds": [ + 359 + ], + "pos": [ + -1538.255859375, + -1290 + ] + }, + { + "id": "97d24b10-6540-48c4-81eb-a432832f5729", + "name": "value", + "type": "BOOLEAN", + "linkIds": [ + 364 + ], + "label": "enable_turbo_mode", + "pos": [ + -1538.255859375, + -1270 + ] + }, + { + "id": "15890efb-ba15-41cd-91ef-5adad7a52167", + "name": "seed", + "type": "INT", + "linkIds": [ + 372 + ], + "pos": [ + -1538.255859375, + -1250 + ] + }, + { + "id": "43f22fe2-6836-4f75-8146-04c84fbba75d", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 373 + ], + "pos": [ + -1538.255859375, + -1230 + ] + }, + { + "id": "cd5e4502-2aca-4645-9e2e-ca8719f05bf6", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 374 + ], + "pos": [ + -1538.255859375, + -1210 + ] + }, + { + "id": "f6ae73dc-39e8-44b2-958d-705ae159ea86", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 375 + ], + "pos": [ + -1538.255859375, + -1190 + ] + }, + { + "id": "66dc179d-e6c9-4485-a2db-a47d25b44363", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 376 + ], + "pos": [ + -1538.255859375, + -1170 + ] + } + ], + "outputs": [ + { + "id": "712c5c76-8620-44e1-9c9d-0798b6cdb77a", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 292 + ], + "localized_name": "IMAGE", + "pos": [ + 1167.5, + -1195 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 120, + "type": "ModelSamplingAuraFlow", + "pos": [ + 1060, + -1760 + ], + "size": [ + 290, + 110 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 326 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 294 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3.1 + ] + }, + { + "id": 154, + "type": "ComfySwitchNode", + "pos": [ + 680, + -1690 + ], + "size": [ + 260, + 140 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 324 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 325 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 323 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 326 + ] + } + ], + "title": "Switch (Model)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "ComfySwitchNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 155, + "type": "PrimitiveInt", + "pos": [ + 190, + -1680 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 329 + ] + } + ], + "title": "Int (Steps)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 40, + "fixed" + ] + }, + { + "id": 123, + "type": "CFGNorm", + "pos": [ + 1060, + -1590 + ], + "size": [ + 290, + 110 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 294 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "patched_model", + "name": "patched_model", + "type": "MODEL", + "links": [ + 295 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CFGNorm", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 164, + "type": "ComfySwitchNode", + "pos": [ + 680, + -1250 + ], + "size": [ + 230, + 130 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 333 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 334 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 336 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 335 + ] + } + ], + "title": "Switch (CFG)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "ComfySwitchNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 156, + "type": "PrimitiveInt", + "pos": [ + 190, + -1060 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 337 + ] + } + ], + "title": "Float (Steps)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 8, + "fixed" + ] + }, + { + "id": 162, + "type": "PrimitiveFloat", + "pos": [ + 190, + -1500 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 333 + ] + } + ], + "title": "Float (CFG)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 4 + ] + }, + { + "id": 163, + "type": "PrimitiveFloat", + "pos": [ + 190, + -1230 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 334 + ] + } + ], + "title": "Float (CFG)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 157, + "type": "ComfySwitchNode", + "pos": [ + 680, + -1470 + ], + "size": [ + 230, + 130 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 329 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 337 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 330 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 345 + ] + } + ], + "title": "Switch (Steps)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "ComfySwitchNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 116, + "type": "VAELoader", + "pos": [ + -950, + -1040 + ], + "size": [ + 400, + 110 + ], + "flags": { + "collapsed": false + }, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 375 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 298, + 299, + 300, + 314 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "VAELoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "qwen_image_vae.safetensors", + "url": "https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.0-ComfyUI/resolve/main/qwen_image_vae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "qwen_image_vae.safetensors" + ] + }, + { + "id": 115, + "type": "CLIPLoader", + "pos": [ + -960, + -1370 + ], + "size": [ + 400, + 150 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 374 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 296, + 297 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CLIPLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image", + "default" + ] + }, + { + "id": 151, + "type": "LoraLoaderModelOnly", + "pos": [ + 100, + -900 + ], + "size": [ + 400, + 140 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 316 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 376 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 325 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "LoraLoaderModelOnly", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "FireRed-Image-Edit-1.0-Lightning-8steps-v1.0.safetensors", + "url": "https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.0-ComfyUI/resolve/main/FireRed-Image-Edit-1.0-Lightning-8steps-v1.0.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "FireRed-Image-Edit-1.0-Lightning-8steps-v1.0.safetensors", + 1 + ] + }, + { + "id": 128, + "type": "UNETLoader", + "pos": [ + -960, + -1670 + ], + "size": [ + 400, + 110 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 373 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 316, + 324 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "UNETLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "FireRed-Image-Edit-1.1-transformer.safetensors", + "url": "https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.1-ComfyUI/resolve/main/FireRed-Image-Edit-1.1-transformer.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "FireRed-Image-Edit-1.1-transformer.safetensors", + "default" + ] + }, + { + "id": 125, + "type": "VAEEncode", + "pos": [ + -390, + -810 + ], + "size": [ + 390, + 100 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 368 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 300 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 303 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "VAEEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 153, + "type": "PrimitiveBoolean", + "pos": [ + 160, + -650 + ], + "size": [ + 400, + 100 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": 364 + } + ], + "outputs": [ + { + "localized_name": "BOOLEAN", + "name": "BOOLEAN", + "type": "BOOLEAN", + "links": [ + 323, + 330, + 336 + ] + } + ], + "title": "Enable Lightning LoRA?", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.15.1", + "Node name for S&R": "PrimitiveBoolean", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 118, + "type": "TextEncodeQwenImageEditPlus", + "pos": [ + -480, + -1690 + ], + "size": [ + 470, + 370 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 296 + }, + { + "localized_name": "vae", + "name": "vae", + "shape": 7, + "type": "VAE", + "link": 298 + }, + { + "localized_name": "image1", + "name": "image1", + "shape": 7, + "type": "IMAGE", + "link": 369 + }, + { + "localized_name": "image2", + "name": "image2", + "shape": 7, + "type": "IMAGE", + "link": 355 + }, + { + "localized_name": "image3", + "name": "image3", + "shape": 7, + "type": "IMAGE", + "link": 357 + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": 359 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 312 + ] + } + ], + "title": "TextEncodeQwenImageEditPlus (Positive)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "TextEncodeQwenImageEditPlus", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 117, + "type": "TextEncodeQwenImageEditPlus", + "pos": [ + -470, + -1240 + ], + "size": [ + 460, + 290 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 297 + }, + { + "localized_name": "vae", + "name": "vae", + "shape": 7, + "type": "VAE", + "link": 299 + }, + { + "localized_name": "image1", + "name": "image1", + "shape": 7, + "type": "IMAGE", + "link": 370 + }, + { + "localized_name": "image2", + "name": "image2", + "shape": 7, + "type": "IMAGE", + "link": 356 + }, + { + "localized_name": "image3", + "name": "image3", + "shape": 7, + "type": "IMAGE", + "link": 358 + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 313 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "TextEncodeQwenImageEditPlus", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 130, + "type": "KSampler", + "pos": [ + 1060, + -1420 + ], + "size": [ + 270, + 480 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 295 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 312 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 313 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 303 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 372 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": 345 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": 335 + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 273 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 43, + "fixed", + 40, + 4, + "euler", + "simple", + 1 + ] + }, + { + "id": 126, + "type": "VAEDecode", + "pos": [ + 1360, + -1420 + ], + "size": [ + 230, + 100 + ], + "flags": { + "collapsed": false + }, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 273 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 314 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 292 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 174, + "type": "ResizeImageMaskNode", + "pos": [ + -900, + -810 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": 371 + }, + { + "localized_name": "resize_type", + "name": "resize_type", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "resize_type" + }, + "link": null + }, + { + "localized_name": "resize_type.megapixels", + "name": "resize_type.megapixels", + "type": "FLOAT", + "widget": { + "name": "resize_type.megapixels" + }, + "link": null + }, + { + "localized_name": "scale_method", + "name": "scale_method", + "type": "COMBO", + "widget": { + "name": "scale_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "resized", + "name": "resized", + "type": "*", + "links": [ + 368, + 369, + 370 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ResizeImageMaskNode" + }, + "widgets_values": [ + "scale total pixels", + 1, + "area" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -990, + -1770, + 460, + 870 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Prompt", + "bounding": [ + -500, + -1770, + 510, + 870 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Original", + "bounding": [ + 40, + -1770, + 530, + 410 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 8, + "title": "Lightning LoRA", + "bounding": [ + 40, + -1330, + 560, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 326, + "origin_id": 154, + "origin_slot": 0, + "target_id": 120, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 324, + "origin_id": 128, + "origin_slot": 0, + "target_id": 154, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 325, + "origin_id": 151, + "origin_slot": 0, + "target_id": 154, + "target_slot": 1, + "type": "MODEL" + }, + { + "id": 323, + "origin_id": 153, + "origin_slot": 0, + "target_id": 154, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 294, + "origin_id": 120, + "origin_slot": 0, + "target_id": 123, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 333, + "origin_id": 162, + "origin_slot": 0, + "target_id": 164, + "target_slot": 0, + "type": "FLOAT" + }, + { + "id": 334, + "origin_id": 163, + "origin_slot": 0, + "target_id": 164, + "target_slot": 1, + "type": "FLOAT" + }, + { + "id": 336, + "origin_id": 153, + "origin_slot": 0, + "target_id": 164, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 329, + "origin_id": 155, + "origin_slot": 0, + "target_id": 157, + "target_slot": 0, + "type": "INT" + }, + { + "id": 337, + "origin_id": 156, + "origin_slot": 0, + "target_id": 157, + "target_slot": 1, + "type": "INT" + }, + { + "id": 330, + "origin_id": 153, + "origin_slot": 0, + "target_id": 157, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 297, + "origin_id": 115, + "origin_slot": 0, + "target_id": 117, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 299, + "origin_id": 116, + "origin_slot": 0, + "target_id": 117, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 316, + "origin_id": 128, + "origin_slot": 0, + "target_id": 151, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 296, + "origin_id": 115, + "origin_slot": 0, + "target_id": 118, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 298, + "origin_id": 116, + "origin_slot": 0, + "target_id": 118, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 300, + "origin_id": 116, + "origin_slot": 0, + "target_id": 125, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 295, + "origin_id": 123, + "origin_slot": 0, + "target_id": 130, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 312, + "origin_id": 118, + "origin_slot": 0, + "target_id": 130, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 313, + "origin_id": 117, + "origin_slot": 0, + "target_id": 130, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 303, + "origin_id": 125, + "origin_slot": 0, + "target_id": 130, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 345, + "origin_id": 157, + "origin_slot": 0, + "target_id": 130, + "target_slot": 5, + "type": "INT" + }, + { + "id": 335, + "origin_id": 164, + "origin_slot": 0, + "target_id": 130, + "target_slot": 6, + "type": "FLOAT" + }, + { + "id": 273, + "origin_id": 130, + "origin_slot": 0, + "target_id": 126, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 314, + "origin_id": 116, + "origin_slot": 0, + "target_id": 126, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 292, + "origin_id": 126, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 355, + "origin_id": -10, + "origin_slot": 1, + "target_id": 118, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 356, + "origin_id": -10, + "origin_slot": 1, + "target_id": 117, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 357, + "origin_id": -10, + "origin_slot": 2, + "target_id": 118, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 358, + "origin_id": -10, + "origin_slot": 2, + "target_id": 117, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 359, + "origin_id": -10, + "origin_slot": 3, + "target_id": 118, + "target_slot": 5, + "type": "STRING" + }, + { + "id": 364, + "origin_id": -10, + "origin_slot": 4, + "target_id": 153, + "target_slot": 0, + "type": "BOOLEAN" + }, + { + "id": 368, + "origin_id": 174, + "origin_slot": 0, + "target_id": 125, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 369, + "origin_id": 174, + "origin_slot": 0, + "target_id": 118, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 370, + "origin_id": 174, + "origin_slot": 0, + "target_id": 117, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 371, + "origin_id": -10, + "origin_slot": 0, + "target_id": 174, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 372, + "origin_id": -10, + "origin_slot": 5, + "target_id": 130, + "target_slot": 4, + "type": "INT" + }, + { + "id": 373, + "origin_id": -10, + "origin_slot": 6, + "target_id": 128, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 374, + "origin_id": -10, + "origin_slot": 7, + "target_id": 115, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 375, + "origin_id": -10, + "origin_slot": 8, + "target_id": 116, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 376, + "origin_id": -10, + "origin_slot": 9, + "target_id": 151, + "target_slot": 1, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Edit image" + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Image Edit (Flux.2 Klein 4B).json b/blueprints/Image Edit (Flux.2 Klein 4B).json index c87c7e122..6f2f7dc01 100644 --- a/blueprints/Image Edit (Flux.2 Klein 4B).json +++ b/blueprints/Image Edit (Flux.2 Klein 4B).json @@ -1 +1,1840 @@ -{"id": "6686cb78-8003-4289-b969-929755e9a84d", "revision": 0, "last_node_id": 81, "last_link_id": 179, "nodes": [{"id": 75, "type": "7b34ab90-36f9-45ba-a665-71d418f0df18", "pos": [311.66672468419983, 830], "size": [400, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "image", "type": "IMAGE", "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["-1", "text"], ["73", "noise_seed"], ["73", "control_after_generate"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.8.2", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", null, null, "flux-2-klein-base-4b-fp8.safetensors", "qwen_3_4b.safetensors", "flux2-vae.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "7b34ab90-36f9-45ba-a665-71d418f0df18", "version": 1, "state": {"lastGroupId": 4, "lastNodeId": 81, "lastLinkId": 179, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image Edit (Flux.2 Klein 4B)", "inputNode": {"id": -10, "bounding": [-576.3333463986639, 559.0277780034634, 120, 140]}, "outputNode": {"id": -20, "bounding": [1373.6666536013363, 549.0277780034634, 120, 60]}, "inputs": [{"id": "7061147a-fb75-450d-8e97-c8be594a8e16", "name": "text", "type": "STRING", "linkIds": [162], "label": "prompt", "pos": [-476.33334639866393, 579.0277780034634]}, {"id": "68629112-b7b0-41ce-8912-23adad00d3db", "name": "image", "type": "IMAGE", "linkIds": [175], "pos": [-476.33334639866393, 599.0277780034634]}, {"id": "006f0b42-cb11-4484-8b7e-c34a9fb12824", "name": "unet_name", "type": "COMBO", "linkIds": [177], "pos": [-476.33334639866393, 619.0277780034634]}, {"id": "0083499c-8e83-4974-a587-ba6e89e36acc", "name": "clip_name", "type": "COMBO", "linkIds": [178], "pos": [-476.33334639866393, 639.0277780034634]}, {"id": "7c95e27c-7920-43d5-a0ac-c6570653f5da", "name": "vae_name", "type": "COMBO", "linkIds": [179], "pos": [-476.33334639866393, 659.0277780034634]}], "outputs": [{"id": "c5e7966d-07ed-4c9a-ad89-9d378a41ea7b", "name": "IMAGE", "type": "IMAGE", "linkIds": [153], "localized_name": "IMAGE", "pos": [1393.6666536013363, 569.0277780034634]}], "widgets": [], "nodes": [{"id": 61, "type": "KSamplerSelect", "pos": [560, 460], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "links": [144]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["euler"]}, {"id": 62, "type": "Flux2Scheduler", "pos": [560, 560], "size": [270, 106], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 171}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 173}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "links": [145]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "Flux2Scheduler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [20, 1024, 1024]}, {"id": 63, "type": "CFGGuider", "pos": [560, 320], "size": [270, 98], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 139}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 167}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 168}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "links": [143]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "CFGGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [5]}, {"id": 65, "type": "VAEDecode", "pos": [1093.6666007601261, 154.02777277882814], "size": [220, 46], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 147}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 148}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [153]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 70, "type": "UNETLoader", "pos": [-386.3333318901398, 203.8611174586574], "size": [364.42708333333337, 82], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 177}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [139]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "UNETLoader", "models": [{"name": "flux-2-klein-base-4b-fp8.safetensors", "url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4b-fp8/resolve/main/flux-2-klein-base-4b-fp8.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["flux-2-klein-base-4b-fp8.safetensors", "default"]}, {"id": 71, "type": "CLIPLoader", "pos": [-386.3333318901398, 353.8611341117752], "size": [364.42708333333337, 106], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 178}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [151, 152]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_3_4b.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_3_4b.safetensors", "flux2", "default"]}, {"id": 74, "type": "CLIPTextEncode", "pos": [43.666666014853874, 204.02777159555063], "size": [430, 230], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 151}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 162}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [165]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 67, "type": "CLIPTextEncode", "pos": [43.666666014853874, 534.0277718670993], "size": [430, 88], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 152}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [166]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#322", "bgcolor": "#533"}, {"id": 72, "type": "VAELoader", "pos": [-386.3333318901398, 523.8611624133522], "size": [364.42708333333337, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 179}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [148, 176]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "VAELoader", "models": [{"name": "flux2-vae.safetensors", "url": "https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["flux2-vae.safetensors"]}, {"id": 66, "type": "EmptyFlux2LatentImage", "pos": [570, 740], "size": [270, 106], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 172}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 174}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [146]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "EmptyFlux2LatentImage", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1024, 1024, 1]}, {"id": 80, "type": "ImageScaleToTotalPixels", "pos": [-391.6666683297289, 715.194415255584], "size": [270, 106], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 175}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "megapixels", "name": "megapixels", "type": "FLOAT", "widget": {"name": "megapixels"}, "link": null}, {"localized_name": "resolution_steps", "name": "resolution_steps", "type": "INT", "widget": {"name": "resolution_steps"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [169, 170]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "ImageScaleToTotalPixels", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["nearest-exact", 1, 1]}, {"id": 79, "type": "6007e698-2ebd-4917-84d8-299b35d7b7ab", "pos": [238.33332484215495, 835.1944447404384], "size": [240, 86], "flags": {}, "order": 12, "mode": 0, "inputs": [{"label": "positive", "name": "conditioning", "type": "CONDITIONING", "link": 165}, {"label": "negative", "name": "conditioning_1", "type": "CONDITIONING", "link": 166}, {"name": "pixels", "type": "IMAGE", "link": 169}, {"name": "vae", "type": "VAE", "link": 176}], "outputs": [{"label": "positive", "name": "CONDITIONING", "type": "CONDITIONING", "links": [167]}, {"label": "negative", "name": "CONDITIONING_1", "type": "CONDITIONING", "links": [168]}], "properties": {"proxyWidgets": [], "cnr_id": "comfy-core", "ver": "0.8.2", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 81, "type": "GetImageSize", "pos": [310, 720], "size": [187.5, 66], "flags": {}, "order": 14, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 170}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [171, 172]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [173, 174]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": null}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "GetImageSize", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 64, "type": "SamplerCustomAdvanced", "pos": [860, 220], "size": [212.3638671875, 106], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 142}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 143}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 144}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 145}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 146}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "links": [147]}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 73, "type": "RandomNoise", "pos": [560, 200], "size": [270, 82], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "links": [142]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "RandomNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize"]}], "groups": [{"id": 1, "title": "Models", "bounding": [-390, 120, 380, 550], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Prompt", "bounding": [30, 120, 470, 550], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Sampler", "bounding": [540, 120, 532.3638671875, 550], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 139, "origin_id": 70, "origin_slot": 0, "target_id": 63, "target_slot": 0, "type": "MODEL"}, {"id": 142, "origin_id": 73, "origin_slot": 0, "target_id": 64, "target_slot": 0, "type": "NOISE"}, {"id": 143, "origin_id": 63, "origin_slot": 0, "target_id": 64, "target_slot": 1, "type": "GUIDER"}, {"id": 144, "origin_id": 61, "origin_slot": 0, "target_id": 64, "target_slot": 2, "type": "SAMPLER"}, {"id": 145, "origin_id": 62, "origin_slot": 0, "target_id": 64, "target_slot": 3, "type": "SIGMAS"}, {"id": 146, "origin_id": 66, "origin_slot": 0, "target_id": 64, "target_slot": 4, "type": "LATENT"}, {"id": 147, "origin_id": 64, "origin_slot": 0, "target_id": 65, "target_slot": 0, "type": "LATENT"}, {"id": 148, "origin_id": 72, "origin_slot": 0, "target_id": 65, "target_slot": 1, "type": "VAE"}, {"id": 152, "origin_id": 71, "origin_slot": 0, "target_id": 67, "target_slot": 0, "type": "CLIP"}, {"id": 151, "origin_id": 71, "origin_slot": 0, "target_id": 74, "target_slot": 0, "type": "CLIP"}, {"id": 153, "origin_id": 65, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 162, "origin_id": -10, "origin_slot": 0, "target_id": 74, "target_slot": 1, "type": "STRING"}, {"id": 165, "origin_id": 74, "origin_slot": 0, "target_id": 79, "target_slot": 0, "type": "CONDITIONING"}, {"id": 166, "origin_id": 67, "origin_slot": 0, "target_id": 79, "target_slot": 1, "type": "CONDITIONING"}, {"id": 167, "origin_id": 79, "origin_slot": 0, "target_id": 63, "target_slot": 1, "type": "CONDITIONING"}, {"id": 168, "origin_id": 79, "origin_slot": 1, "target_id": 63, "target_slot": 2, "type": "CONDITIONING"}, {"id": 169, "origin_id": 80, "origin_slot": 0, "target_id": 79, "target_slot": 2, "type": "IMAGE"}, {"id": 170, "origin_id": 80, "origin_slot": 0, "target_id": 81, "target_slot": 0, "type": "IMAGE"}, {"id": 171, "origin_id": 81, "origin_slot": 0, "target_id": 62, "target_slot": 1, "type": "INT"}, {"id": 172, "origin_id": 81, "origin_slot": 0, "target_id": 66, "target_slot": 0, "type": "INT"}, {"id": 173, "origin_id": 81, "origin_slot": 1, "target_id": 62, "target_slot": 2, "type": "INT"}, {"id": 174, "origin_id": 81, "origin_slot": 1, "target_id": 66, "target_slot": 1, "type": "INT"}, {"id": 175, "origin_id": -10, "origin_slot": 1, "target_id": 80, "target_slot": 0, "type": "IMAGE"}, {"id": 176, "origin_id": 72, "origin_slot": 0, "target_id": 79, "target_slot": 3, "type": "VAE"}, {"id": 177, "origin_id": -10, "origin_slot": 2, "target_id": 70, "target_slot": 0, "type": "COMBO"}, {"id": 178, "origin_id": -10, "origin_slot": 3, "target_id": 71, "target_slot": 0, "type": "COMBO"}, {"id": 179, "origin_id": -10, "origin_slot": 4, "target_id": 72, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image generation and editing/Edit image"}, {"id": "6007e698-2ebd-4917-84d8-299b35d7b7ab", "version": 1, "state": {"lastGroupId": 4, "lastNodeId": 81, "lastLinkId": 179, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Reference Conditioning", "inputNode": {"id": -10, "bounding": [-270, 990, 120, 120]}, "outputNode": {"id": -20, "bounding": [580, 970, 120, 80]}, "inputs": [{"id": "5c9a0f5e-8cee-4947-90bc-330de782043a", "name": "conditioning", "type": "CONDITIONING", "linkIds": [165], "label": "positive", "pos": [-170, 1010]}, {"id": "61826d46-4c21-4ad6-801c-3e3fa94115e2", "name": "conditioning_1", "type": "CONDITIONING", "linkIds": [166], "label": "negative", "pos": [-170, 1030]}, {"id": "345bf085-5939-47ff-9767-8f8f239a719c", "name": "pixels", "type": "IMAGE", "linkIds": [167], "pos": [-170, 1050]}, {"id": "f4594e34-e2f5-4f1e-b1fa-a1dc2aeb0a90", "name": "vae", "type": "VAE", "linkIds": [168], "pos": [-170, 1070]}], "outputs": [{"id": "b3357c0e-6428-4055-9cd3-3595f0896fa8", "name": "CONDITIONING", "type": "CONDITIONING", "linkIds": [169], "label": "positive", "pos": [600, 990]}, {"id": "01519713-2ed1-4694-a387-79f44e088e89", "name": "CONDITIONING_1", "type": "CONDITIONING", "linkIds": [170], "label": "negative", "pos": [600, 1010]}], "widgets": [], "nodes": [{"id": 76, "type": "ReferenceLatent", "pos": [170, 1050], "size": [204.134765625, 46], "flags": {"collapsed": false}, "order": 0, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 166}, {"localized_name": "latent", "name": "latent", "shape": 7, "type": "LATENT", "link": 163}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [170]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "ReferenceLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 78, "type": "VAEEncode", "pos": [-90, 1150], "size": [190, 46], "flags": {"collapsed": false}, "order": 2, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 167}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 168}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [163, 164]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "VAEEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 77, "type": "ReferenceLatent", "pos": [170, 940], "size": [210, 46], "flags": {"collapsed": false}, "order": 1, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 165}, {"localized_name": "latent", "name": "latent", "shape": 7, "type": "LATENT", "link": 164}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [169]}], "properties": {"cnr_id": "comfy-core", "ver": "0.8.2", "Node name for S&R": "ReferenceLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}], "groups": [], "links": [{"id": 163, "origin_id": 78, "origin_slot": 0, "target_id": 76, "target_slot": 1, "type": "LATENT"}, {"id": 164, "origin_id": 78, "origin_slot": 0, "target_id": 77, "target_slot": 1, "type": "LATENT"}, {"id": 165, "origin_id": -10, "origin_slot": 0, "target_id": 77, "target_slot": 0, "type": "CONDITIONING"}, {"id": 166, "origin_id": -10, "origin_slot": 1, "target_id": 76, "target_slot": 0, "type": "CONDITIONING"}, {"id": 167, "origin_id": -10, "origin_slot": 2, "target_id": 78, "target_slot": 0, "type": "IMAGE"}, {"id": 168, "origin_id": -10, "origin_slot": 3, "target_id": 78, "target_slot": 1, "type": "VAE"}, {"id": 169, "origin_id": 77, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "CONDITIONING"}, {"id": 170, "origin_id": 76, "origin_slot": 0, "target_id": -20, "target_slot": 1, "type": "CONDITIONING"}], "extra": {"workflowRendererVersion": "LG"}}]}, "config": {}, "extra": {"workflowRendererVersion": "LG", "ds": {"scale": 1.1478862047043865, "offset": [302.91933883258804, -648.9802050882657]}}, "version": 0.4} +{ + "id": "6686cb78-8003-4289-b969-929755e9a84d", + "revision": 0, + "last_node_id": 81, + "last_link_id": 179, + "nodes": [ + { + "id": 75, + "type": "7b34ab90-36f9-45ba-a665-71d418f0df18", + "pos": [ + 311.66672468419983, + 830 + ], + "size": [ + 400, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "73", + "noise_seed" + ], + [ + "73", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.8.2", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "", + null, + null, + "flux-2-klein-base-4b-fp8.safetensors", + "qwen_3_4b.safetensors", + "flux2-vae.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "7b34ab90-36f9-45ba-a665-71d418f0df18", + "version": 1, + "state": { + "lastGroupId": 4, + "lastNodeId": 81, + "lastLinkId": 179, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Edit (Flux.2 Klein 4B)", + "inputNode": { + "id": -10, + "bounding": [ + -576.3333463986639, + 559.0277780034634, + 120, + 140 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1373.6666536013363, + 549.0277780034634, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "7061147a-fb75-450d-8e97-c8be594a8e16", + "name": "text", + "type": "STRING", + "linkIds": [ + 162 + ], + "label": "prompt", + "pos": [ + -476.33334639866393, + 579.0277780034634 + ] + }, + { + "id": "68629112-b7b0-41ce-8912-23adad00d3db", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 175 + ], + "pos": [ + -476.33334639866393, + 599.0277780034634 + ] + }, + { + "id": "006f0b42-cb11-4484-8b7e-c34a9fb12824", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 177 + ], + "pos": [ + -476.33334639866393, + 619.0277780034634 + ] + }, + { + "id": "0083499c-8e83-4974-a587-ba6e89e36acc", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 178 + ], + "pos": [ + -476.33334639866393, + 639.0277780034634 + ] + }, + { + "id": "7c95e27c-7920-43d5-a0ac-c6570653f5da", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 179 + ], + "pos": [ + -476.33334639866393, + 659.0277780034634 + ] + } + ], + "outputs": [ + { + "id": "c5e7966d-07ed-4c9a-ad89-9d378a41ea7b", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 153 + ], + "localized_name": "IMAGE", + "pos": [ + 1393.6666536013363, + 569.0277780034634 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 61, + "type": "KSamplerSelect", + "pos": [ + 560, + 460 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 144 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 62, + "type": "Flux2Scheduler", + "pos": [ + 560, + 560 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 171 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 173 + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 145 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "Flux2Scheduler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 20, + 1024, + 1024 + ] + }, + { + "id": 63, + "type": "CFGGuider", + "pos": [ + 560, + 320 + ], + "size": [ + 270, + 98 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 139 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 167 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 168 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 143 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 5 + ] + }, + { + "id": 65, + "type": "VAEDecode", + "pos": [ + 1093.6666007601261, + 154.02777277882814 + ], + "size": [ + 220, + 46 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 147 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 148 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 153 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 70, + "type": "UNETLoader", + "pos": [ + -386.3333318901398, + 203.8611174586574 + ], + "size": [ + 364.42708333333337, + 82 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 177 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 139 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "flux-2-klein-base-4b-fp8.safetensors", + "url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4b-fp8/resolve/main/flux-2-klein-base-4b-fp8.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "flux-2-klein-base-4b-fp8.safetensors", + "default" + ] + }, + { + "id": 71, + "type": "CLIPLoader", + "pos": [ + -386.3333318901398, + 353.8611341117752 + ], + "size": [ + 364.42708333333337, + 106 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 178 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 151, + 152 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_3_4b.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_3_4b.safetensors", + "flux2", + "default" + ] + }, + { + "id": 74, + "type": "CLIPTextEncode", + "pos": [ + 43.666666014853874, + 204.02777159555063 + ], + "size": [ + 430, + 230 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 151 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 162 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 165 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 67, + "type": "CLIPTextEncode", + "pos": [ + 43.666666014853874, + 534.0277718670993 + ], + "size": [ + 430, + 88 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 152 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 166 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 72, + "type": "VAELoader", + "pos": [ + -386.3333318901398, + 523.8611624133522 + ], + "size": [ + 364.42708333333337, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 179 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 148, + 176 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "flux2-vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "flux2-vae.safetensors" + ] + }, + { + "id": 66, + "type": "EmptyFlux2LatentImage", + "pos": [ + 570, + 740 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 172 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 174 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 146 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "EmptyFlux2LatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 80, + "type": "ImageScaleToTotalPixels", + "pos": [ + -391.6666683297289, + 715.194415255584 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 175 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "megapixels", + "name": "megapixels", + "type": "FLOAT", + "widget": { + "name": "megapixels" + }, + "link": null + }, + { + "localized_name": "resolution_steps", + "name": "resolution_steps", + "type": "INT", + "widget": { + "name": "resolution_steps" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 169, + 170 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "ImageScaleToTotalPixels", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "nearest-exact", + 1, + 1 + ] + }, + { + "id": 79, + "type": "6007e698-2ebd-4917-84d8-299b35d7b7ab", + "pos": [ + 238.33332484215495, + 835.1944447404384 + ], + "size": [ + 240, + 86 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "label": "positive", + "name": "conditioning", + "type": "CONDITIONING", + "link": 165 + }, + { + "label": "negative", + "name": "conditioning_1", + "type": "CONDITIONING", + "link": 166 + }, + { + "name": "pixels", + "type": "IMAGE", + "link": 169 + }, + { + "name": "vae", + "type": "VAE", + "link": 176 + } + ], + "outputs": [ + { + "label": "positive", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 167 + ] + }, + { + "label": "negative", + "name": "CONDITIONING_1", + "type": "CONDITIONING", + "links": [ + 168 + ] + } + ], + "properties": { + "proxyWidgets": [], + "cnr_id": "comfy-core", + "ver": "0.8.2", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 81, + "type": "GetImageSize", + "pos": [ + 310, + 720 + ], + "size": [ + 187.5, + 66 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 170 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 171, + 172 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 173, + 174 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 64, + "type": "SamplerCustomAdvanced", + "pos": [ + 860, + 220 + ], + "size": [ + 212.3638671875, + 106 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 142 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 143 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 144 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 145 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 146 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 147 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 73, + "type": "RandomNoise", + "pos": [ + 560, + 200 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 142 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Models", + "bounding": [ + -390, + 120, + 380, + 550 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Prompt", + "bounding": [ + 30, + 120, + 470, + 550 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Sampler", + "bounding": [ + 540, + 120, + 532.3638671875, + 550 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 139, + "origin_id": 70, + "origin_slot": 0, + "target_id": 63, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 142, + "origin_id": 73, + "origin_slot": 0, + "target_id": 64, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 143, + "origin_id": 63, + "origin_slot": 0, + "target_id": 64, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 144, + "origin_id": 61, + "origin_slot": 0, + "target_id": 64, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 145, + "origin_id": 62, + "origin_slot": 0, + "target_id": 64, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 146, + "origin_id": 66, + "origin_slot": 0, + "target_id": 64, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 147, + "origin_id": 64, + "origin_slot": 0, + "target_id": 65, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 148, + "origin_id": 72, + "origin_slot": 0, + "target_id": 65, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 152, + "origin_id": 71, + "origin_slot": 0, + "target_id": 67, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 151, + "origin_id": 71, + "origin_slot": 0, + "target_id": 74, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 153, + "origin_id": 65, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 162, + "origin_id": -10, + "origin_slot": 0, + "target_id": 74, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 165, + "origin_id": 74, + "origin_slot": 0, + "target_id": 79, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 166, + "origin_id": 67, + "origin_slot": 0, + "target_id": 79, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 167, + "origin_id": 79, + "origin_slot": 0, + "target_id": 63, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 168, + "origin_id": 79, + "origin_slot": 1, + "target_id": 63, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 169, + "origin_id": 80, + "origin_slot": 0, + "target_id": 79, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 170, + "origin_id": 80, + "origin_slot": 0, + "target_id": 81, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 171, + "origin_id": 81, + "origin_slot": 0, + "target_id": 62, + "target_slot": 1, + "type": "INT" + }, + { + "id": 172, + "origin_id": 81, + "origin_slot": 0, + "target_id": 66, + "target_slot": 0, + "type": "INT" + }, + { + "id": 173, + "origin_id": 81, + "origin_slot": 1, + "target_id": 62, + "target_slot": 2, + "type": "INT" + }, + { + "id": 174, + "origin_id": 81, + "origin_slot": 1, + "target_id": 66, + "target_slot": 1, + "type": "INT" + }, + { + "id": 175, + "origin_id": -10, + "origin_slot": 1, + "target_id": 80, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 176, + "origin_id": 72, + "origin_slot": 0, + "target_id": 79, + "target_slot": 3, + "type": "VAE" + }, + { + "id": 177, + "origin_id": -10, + "origin_slot": 2, + "target_id": 70, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 178, + "origin_id": -10, + "origin_slot": 3, + "target_id": 71, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 179, + "origin_id": -10, + "origin_slot": 4, + "target_id": 72, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Edit image" + }, + { + "id": "6007e698-2ebd-4917-84d8-299b35d7b7ab", + "version": 1, + "state": { + "lastGroupId": 4, + "lastNodeId": 81, + "lastLinkId": 179, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Reference Conditioning", + "inputNode": { + "id": -10, + "bounding": [ + -270, + 990, + 120, + 120 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 580, + 970, + 120, + 80 + ] + }, + "inputs": [ + { + "id": "5c9a0f5e-8cee-4947-90bc-330de782043a", + "name": "conditioning", + "type": "CONDITIONING", + "linkIds": [ + 165 + ], + "label": "positive", + "pos": [ + -170, + 1010 + ] + }, + { + "id": "61826d46-4c21-4ad6-801c-3e3fa94115e2", + "name": "conditioning_1", + "type": "CONDITIONING", + "linkIds": [ + 166 + ], + "label": "negative", + "pos": [ + -170, + 1030 + ] + }, + { + "id": "345bf085-5939-47ff-9767-8f8f239a719c", + "name": "pixels", + "type": "IMAGE", + "linkIds": [ + 167 + ], + "pos": [ + -170, + 1050 + ] + }, + { + "id": "f4594e34-e2f5-4f1e-b1fa-a1dc2aeb0a90", + "name": "vae", + "type": "VAE", + "linkIds": [ + 168 + ], + "pos": [ + -170, + 1070 + ] + } + ], + "outputs": [ + { + "id": "b3357c0e-6428-4055-9cd3-3595f0896fa8", + "name": "CONDITIONING", + "type": "CONDITIONING", + "linkIds": [ + 169 + ], + "label": "positive", + "pos": [ + 600, + 990 + ] + }, + { + "id": "01519713-2ed1-4694-a387-79f44e088e89", + "name": "CONDITIONING_1", + "type": "CONDITIONING", + "linkIds": [ + 170 + ], + "label": "negative", + "pos": [ + 600, + 1010 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 76, + "type": "ReferenceLatent", + "pos": [ + 170, + 1050 + ], + "size": [ + 204.134765625, + 46 + ], + "flags": { + "collapsed": false + }, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 166 + }, + { + "localized_name": "latent", + "name": "latent", + "shape": 7, + "type": "LATENT", + "link": 163 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 170 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "ReferenceLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 78, + "type": "VAEEncode", + "pos": [ + -90, + 1150 + ], + "size": [ + 190, + 46 + ], + "flags": { + "collapsed": false + }, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 167 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 168 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 163, + 164 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "VAEEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 77, + "type": "ReferenceLatent", + "pos": [ + 170, + 940 + ], + "size": [ + 210, + 46 + ], + "flags": { + "collapsed": false + }, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 165 + }, + { + "localized_name": "latent", + "name": "latent", + "shape": 7, + "type": "LATENT", + "link": 164 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 169 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.8.2", + "Node name for S&R": "ReferenceLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + } + ], + "groups": [], + "links": [ + { + "id": 163, + "origin_id": 78, + "origin_slot": 0, + "target_id": 76, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 164, + "origin_id": 78, + "origin_slot": 0, + "target_id": 77, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 165, + "origin_id": -10, + "origin_slot": 0, + "target_id": 77, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 166, + "origin_id": -10, + "origin_slot": 1, + "target_id": 76, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 167, + "origin_id": -10, + "origin_slot": 2, + "target_id": 78, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 168, + "origin_id": -10, + "origin_slot": 3, + "target_id": 78, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 169, + "origin_id": 77, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 170, + "origin_id": 76, + "origin_slot": 0, + "target_id": -20, + "target_slot": 1, + "type": "CONDITIONING" + } + ], + "extra": { + "workflowRendererVersion": "LG" + } + } + ] + }, + "config": {}, + "extra": { + "workflowRendererVersion": "LG", + "ds": { + "scale": 1.1478862047043865, + "offset": [ + 302.91933883258804, + -648.9802050882657 + ] + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/blueprints/Image Edit (LongCat Image Edit).json b/blueprints/Image Edit (LongCat Image Edit).json new file mode 100644 index 000000000..5b4eb18f0 --- /dev/null +++ b/blueprints/Image Edit (LongCat Image Edit).json @@ -0,0 +1,1427 @@ +{ + "revision": 0, + "last_node_id": 176, + "last_link_id": 0, + "nodes": [ + { + "id": 176, + "type": "372a02a0-a79c-40b4-84a9-34f246fe0e9c", + "pos": [ + 967.0861152473078, + 4977.534165136897 + ], + "size": [ + 330, + 380 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + }, + { + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "27", + "prompt" + ], + [ + "33", + "steps" + ], + [ + "33", + "cfg" + ], + [ + "33", + "seed" + ], + [ + "34", + "unet_name" + ], + [ + "38", + "clip_name" + ], + [ + "26", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [], + "title": "Image Edit (LongCat Image Edit)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "372a02a0-a79c-40b4-84a9-34f246fe0e9c", + "version": 1, + "state": { + "lastGroupId": 8, + "lastNodeId": 176, + "lastLinkId": 376, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Edit (LongCat Image Edit)", + "inputNode": { + "id": -10, + "bounding": [ + -750, + 380, + 120, + 200 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1680, + 340, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "616c4f3e-8b64-4711-bee2-5ecbe1814fe4", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 14 + ], + "localized_name": "image", + "pos": [ + -650, + 400 + ] + }, + { + "id": "d39759fc-a5a9-4b82-a88f-df9b953f1d98", + "name": "prompt", + "type": "STRING", + "linkIds": [ + 36 + ], + "pos": [ + -650, + 420 + ] + }, + { + "id": "48627f43-cdf1-4ea9-9e11-ec13451a7323", + "name": "steps", + "type": "INT", + "linkIds": [ + 37 + ], + "pos": [ + -650, + 440 + ] + }, + { + "id": "2213f872-d40f-4fc3-be01-b8fc73f1d92c", + "name": "cfg", + "type": "FLOAT", + "linkIds": [ + 42 + ], + "pos": [ + -650, + 460 + ] + }, + { + "id": "2c7b3e65-e71e-4a9b-a9f8-d2e814ccb6af", + "name": "seed", + "type": "INT", + "linkIds": [ + 43 + ], + "pos": [ + -650, + 480 + ] + }, + { + "id": "bddb2317-7210-48d5-81fd-6b2d6fac33f4", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 44 + ], + "pos": [ + -650, + 500 + ] + }, + { + "id": "a283167b-6d7f-4d19-ad86-1fff2335c08d", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 45 + ], + "pos": [ + -650, + 520 + ] + }, + { + "id": "e033047f-cc37-4043-b4a0-25d7bab661af", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 46 + ], + "pos": [ + -650, + 540 + ] + } + ], + "outputs": [ + { + "id": "0a288e93-c03f-4805-80f3-4e320a6a492e", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 20 + ], + "localized_name": "IMAGE", + "pos": [ + 1700, + 360 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 26, + "type": "VAELoader", + "pos": [ + -360, + 590 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 46 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 4, + 5, + 6, + 7 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 27, + "type": "TextEncodeQwenImageEdit", + "pos": [ + 10, + 200 + ], + "size": [ + 280, + 190 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 2 + }, + { + "localized_name": "vae", + "name": "vae", + "shape": 7, + "type": "VAE", + "link": 4 + }, + { + "localized_name": "image", + "name": "image", + "shape": 7, + "type": "IMAGE", + "link": 15 + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": 36 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 8 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "TextEncodeQwenImageEdit" + }, + "widgets_values": [ + "" + ] + }, + { + "id": 28, + "type": "TextEncodeQwenImageEdit", + "pos": [ + 10, + 440 + ], + "size": [ + 280, + 190 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 3 + }, + { + "localized_name": "vae", + "name": "vae", + "shape": 7, + "type": "VAE", + "link": 5 + }, + { + "localized_name": "image", + "name": "image", + "shape": 7, + "type": "IMAGE", + "link": 16 + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 9 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "TextEncodeQwenImageEdit" + }, + "widgets_values": [ + "" + ] + }, + { + "id": 29, + "type": "FluxKontextMultiReferenceLatentMethod", + "pos": [ + 660, + 200 + ], + "size": [ + 270, + 80 + ], + "flags": {}, + "order": 3, + "mode": 0, + "showAdvanced": false, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 10 + }, + { + "localized_name": "reference_latents_method", + "name": "reference_latents_method", + "type": "COMBO", + "widget": { + "name": "reference_latents_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 12 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "FluxKontextMultiReferenceLatentMethod" + }, + "widgets_values": [ + "index" + ] + }, + { + "id": 30, + "type": "FluxGuidance", + "pos": [ + 330, + 440 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 9 + }, + { + "localized_name": "guidance", + "name": "guidance", + "type": "FLOAT", + "widget": { + "name": "guidance" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 11 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "FluxGuidance" + }, + "widgets_values": [ + 4.5 + ] + }, + { + "id": 31, + "type": "FluxGuidance", + "pos": [ + 330, + 200 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 8 + }, + { + "localized_name": "guidance", + "name": "guidance", + "type": "FLOAT", + "widget": { + "name": "guidance" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 10 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "FluxGuidance" + }, + "widgets_values": [ + 4.5 + ] + }, + { + "id": 32, + "type": "FluxKontextMultiReferenceLatentMethod", + "pos": [ + 660, + 440 + ], + "size": [ + 270, + 80 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 11 + }, + { + "localized_name": "reference_latents_method", + "name": "reference_latents_method", + "type": "COMBO", + "widget": { + "name": "reference_latents_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 13 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "FluxKontextMultiReferenceLatentMethod" + }, + "widgets_values": [ + "index" + ] + }, + { + "id": 33, + "type": "KSampler", + "pos": [ + 1080, + 210 + ], + "size": [ + 270, + 460 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 1 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 12 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 13 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 18 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 43 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": 37 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": 42 + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 19 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 43, + "fixed", + 50, + 4.5, + "euler", + "simple", + 1 + ] + }, + { + "id": 34, + "type": "UNETLoader", + "pos": [ + -360, + 170 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 44 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 1 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "longcat_image_edit_bf16.safetensors", + "url": "https://huggingface.co/TalmajM/LongCat-Image-Edit_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/longcat_image_edit_bf16.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "longcat_image_edit_bf16.safetensors", + "default" + ] + }, + { + "id": 35, + "type": "VAEEncode", + "pos": [ + 710, + 790 + ], + "size": [ + 260, + 100 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 17 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 6 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 18 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAEEncode" + } + }, + { + "id": 36, + "type": "VAEDecode", + "pos": [ + 1100, + 800 + ], + "size": [ + 230, + 100 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 19 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 7 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 20 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 37, + "type": "ImageScaleToTotalPixels", + "pos": [ + -370, + 790 + ], + "size": [ + 270, + 140 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 14 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "megapixels", + "name": "megapixels", + "type": "FLOAT", + "widget": { + "name": "megapixels" + }, + "link": null + }, + { + "localized_name": "resolution_steps", + "name": "resolution_steps", + "type": "INT", + "widget": { + "name": "resolution_steps" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 15, + 16, + 17 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ImageScaleToTotalPixels" + }, + "widgets_values": [ + "lanczos", + 1, + 16 + ] + }, + { + "id": 38, + "type": "CLIPLoader", + "pos": [ + -360, + 360 + ], + "size": [ + 270, + 150 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 45 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 2, + 3 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "longcat_image", + "default" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Models", + "bounding": [ + -380, + 100, + 320, + 630 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Conditioning", + "bounding": [ + -30, + 100, + 1030, + 630 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 4, + "title": "Sample", + "bounding": [ + 1030, + 100, + 360, + 630 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 2, + "origin_id": 38, + "origin_slot": 0, + "target_id": 27, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 4, + "origin_id": 26, + "origin_slot": 0, + "target_id": 27, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 15, + "origin_id": 37, + "origin_slot": 0, + "target_id": 27, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 3, + "origin_id": 38, + "origin_slot": 0, + "target_id": 28, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 5, + "origin_id": 26, + "origin_slot": 0, + "target_id": 28, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 16, + "origin_id": 37, + "origin_slot": 0, + "target_id": 28, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 10, + "origin_id": 31, + "origin_slot": 0, + "target_id": 29, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 9, + "origin_id": 28, + "origin_slot": 0, + "target_id": 30, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 8, + "origin_id": 27, + "origin_slot": 0, + "target_id": 31, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 11, + "origin_id": 30, + "origin_slot": 0, + "target_id": 32, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 1, + "origin_id": 34, + "origin_slot": 0, + "target_id": 33, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 12, + "origin_id": 29, + "origin_slot": 0, + "target_id": 33, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 13, + "origin_id": 32, + "origin_slot": 0, + "target_id": 33, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 18, + "origin_id": 35, + "origin_slot": 0, + "target_id": 33, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 17, + "origin_id": 37, + "origin_slot": 0, + "target_id": 35, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 6, + "origin_id": 26, + "origin_slot": 0, + "target_id": 35, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 19, + "origin_id": 33, + "origin_slot": 0, + "target_id": 36, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 7, + "origin_id": 26, + "origin_slot": 0, + "target_id": 36, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 14, + "origin_id": -10, + "origin_slot": 0, + "target_id": 37, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 20, + "origin_id": 36, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 36, + "origin_id": -10, + "origin_slot": 1, + "target_id": 27, + "target_slot": 3, + "type": "STRING" + }, + { + "id": 37, + "origin_id": -10, + "origin_slot": 2, + "target_id": 33, + "target_slot": 5, + "type": "INT" + }, + { + "id": 42, + "origin_id": -10, + "origin_slot": 3, + "target_id": 33, + "target_slot": 6, + "type": "FLOAT" + }, + { + "id": 43, + "origin_id": -10, + "origin_slot": 4, + "target_id": 33, + "target_slot": 4, + "type": "INT" + }, + { + "id": 44, + "origin_id": -10, + "origin_slot": 5, + "target_id": 34, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 45, + "origin_id": -10, + "origin_slot": 6, + "target_id": 38, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 46, + "origin_id": -10, + "origin_slot": 7, + "target_id": 26, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": {}, + "category": "Image generation and editing/Edit image" + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Image Edit (Qwen 2511).json b/blueprints/Image Edit (Qwen 2511).json index 33e85333b..582171fa0 100644 --- a/blueprints/Image Edit (Qwen 2511).json +++ b/blueprints/Image Edit (Qwen 2511).json @@ -1 +1,1492 @@ -{"id": "d84b7d1a-a73f-4e31-bd16-983ac0cf5f1b", "revision": 0, "last_node_id": 17, "last_link_id": 32, "nodes": [{"id": 17, "type": "9fa6af8b-8c99-4446-8681-bccf8ba4ea54", "pos": [183.33334355513557, -120.00000702649223], "size": [383.0729166666667, 381.10677083333337], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image 1", "name": "image1", "type": "IMAGE", "link": null}, {"label": "image 2 (optional)", "name": "image2", "type": "IMAGE", "link": null}, {"label": "image 3 (optional)", "name": "image3", "type": "IMAGE", "link": null}, {"name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": null}], "properties": {"proxyWidgets": [["-1", "prompt"], ["15", "seed"], ["15", "control_after_generate"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.11.0"}, "widgets_values": ["", null, null, "qwen_image_edit_2511_bf16.safetensors", "qwen_2.5_vl_7b_fp8_scaled.safetensors", "qwen_image_vae.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "9fa6af8b-8c99-4446-8681-bccf8ba4ea54", "version": 1, "state": {"lastGroupId": 2, "lastNodeId": 17, "lastLinkId": 32, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image Edit (Qwen 2511)", "inputNode": {"id": -10, "bounding": [-412.6162343565087, 327.2321295314722, 142.59765625, 180]}, "outputNode": {"id": -20, "bounding": [1631.0466138212807, 305.6854343585077, 120, 60]}, "inputs": [{"id": "6e401a3f-21a6-4552-8ee4-179c313c1910", "name": "image1", "type": "IMAGE", "linkIds": [25], "label": "image 1", "pos": [-290.0185781065087, 347.2321295314722]}, {"id": "a0a6307b-62b8-481e-bb17-d332eceadbe4", "name": "image2", "type": "IMAGE", "linkIds": [21, 26], "label": "image 2 (optional)", "pos": [-290.0185781065087, 367.2321295314722]}, {"id": "232fe944-fc3f-43dd-bb34-112d0360cb5f", "name": "image3", "type": "IMAGE", "linkIds": [22, 27], "label": "image 3 (optional)", "pos": [-290.0185781065087, 387.2321295314722]}, {"id": "9b8ed2f4-5875-4f59-b4c1-5ab79a412f4e", "name": "prompt", "type": "STRING", "linkIds": [23], "pos": [-290.0185781065087, 407.2321295314722]}, {"id": "403a6bd0-f170-4cfb-b72e-cd7fa1dbcd06", "name": "unet_name", "type": "COMBO", "linkIds": [30], "pos": [-290.0185781065087, 427.2321295314722]}, {"id": "86a53531-2fab-47da-9525-858c80737044", "name": "clip_name", "type": "COMBO", "linkIds": [31], "pos": [-290.0185781065087, 447.2321295314722]}, {"id": "499f39e9-d698-41dc-b126-b7ea6024cf5d", "name": "vae_name", "type": "COMBO", "linkIds": [32], "pos": [-290.0185781065087, 467.2321295314722]}], "outputs": [{"id": "f2ccd1fa-428e-4127-89a6-760906013172", "name": "IMAGE", "type": "IMAGE", "linkIds": [24], "pos": [1651.0466138212807, 325.6854343585077]}], "widgets": [], "nodes": [{"id": 2, "type": "ModelSamplingAuraFlow", "pos": [791.0465113899395, -54.3145423152618], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 29}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [4]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "ModelSamplingAuraFlow", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3.1]}, {"id": 3, "type": "VAELoader", "pos": [-174.9530552190643, 462.6706561999898], "size": [396.1328125, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 32}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [6, 10, 12, 15]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "VAELoader", "models": [{"name": "qwen_image_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_image_vae.safetensors"]}, {"id": 4, "type": "UNETLoader", "pos": [-174.9530552190643, -23.329297689188216], "size": [396.1328125, 82], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 30}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [29]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "UNETLoader", "models": [{"name": "qwen_image_edit_2511_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2511_bf16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_image_edit_2511_bf16.safetensors", "default"]}, {"id": 5, "type": "FluxKontextMultiReferenceLatentMethod", "pos": [781.0466382725523, 315.68545764091465], "size": [309.66145833333337, 58], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 2}, {"localized_name": "reference_latents_method", "name": "reference_latents_method", "type": "COMBO", "widget": {"name": "reference_latents_method"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [18]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "FluxKontextMultiReferenceLatentMethod", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["index_timestep_zero"], "color": "#222", "bgcolor": "#000"}, {"id": 6, "type": "FluxKontextMultiReferenceLatentMethod", "pos": [781.0466382725523, 185.68543791920104], "size": [309.66145833333337, 58], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 3}, {"localized_name": "reference_latents_method", "name": "reference_latents_method", "type": "COMBO", "widget": {"name": "reference_latents_method"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [17]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "FluxKontextMultiReferenceLatentMethod", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["index_timestep_zero"], "color": "#222", "bgcolor": "#000"}, {"id": 7, "type": "CFGNorm", "pos": [791.0465113899395, 55.68545297239743], "size": [270, 58], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 4}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "patched_model", "name": "patched_model", "type": "MODEL", "links": [16]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "CFGNorm", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 8, "type": "MarkdownNote", "pos": [1111.0466241355298, 555.6854726502876], "size": [270, 195.10416666666669], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [], "title": "KSampler settings", "properties": {}, "widgets_values": ["You can test and find the best setting by yourself. The following table is for reference.\n| | Qwen | Comfy | lightning LoRA |\n|--------|---------|------------|---------------------------|\n| Steps | 40 | 20 | 4 |\n| CFG | 4.0 | 4.0 | 1.0 |\n\nBy default, we use 20 steps as we just don't want it to take too long. Try 40 if you want a better result, but it will take longer."], "color": "#222", "bgcolor": "#000"}, {"id": 9, "type": "TextEncodeQwenImageEditPlus", "pos": [301.0466082538065, 305.6854454238875], "size": [420, 170], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 5}, {"localized_name": "vae", "name": "vae", "shape": 7, "type": "VAE", "link": 6}, {"localized_name": "image1", "name": "image1", "shape": 7, "type": "IMAGE", "link": 28}, {"localized_name": "image2", "name": "image2", "shape": 7, "type": "IMAGE", "link": 21}, {"localized_name": "image3", "name": "image3", "shape": 7, "type": "IMAGE", "link": 22}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [2]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "TextEncodeQwenImageEditPlus", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#322", "bgcolor": "#533"}, {"id": 10, "type": "Note", "pos": [801.0465236069665, 435.6854651456011], "size": [280, 88], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [], "properties": {}, "widgets_values": ["The \"Edit Model Reference Method\" nodes above are not needed if you use Comfy files, but may be needed if you use repackaged ones from other people."], "color": "#432", "bgcolor": "#653"}, {"id": 13, "type": "TextEncodeQwenImageEditPlus", "pos": [301.0466082538065, -14.314562996972978], "size": [426.6276041666667, 215.55989583333334], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 11}, {"localized_name": "vae", "name": "vae", "shape": 7, "type": "VAE", "link": 12}, {"localized_name": "image1", "name": "image1", "shape": 7, "type": "IMAGE", "link": 13}, {"localized_name": "image2", "name": "image2", "shape": 7, "type": "IMAGE", "link": 26}, {"localized_name": "image3", "name": "image3", "shape": 7, "type": "IMAGE", "link": 27}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": 23}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [3]}], "title": "TextEncodeQwenImageEditPlus (Positive)", "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "TextEncodeQwenImageEditPlus", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 14, "type": "VAEEncode", "pos": [511.0465866120977, 645.6854435038923], "size": [187.5, 46], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 14}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 15}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [19]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "VAEEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 15, "type": "KSampler", "pos": [1101.0466119185025, -54.3145423152618], "size": [280, 510], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 16}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 17}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 18}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 19}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [9]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize", 40, 4, "euler", "simple", 1]}, {"id": 12, "type": "VAEDecode", "pos": [1431.0464586818402, -44.31456487314459], "size": [187.5, 46], "flags": {"collapsed": false}, "order": 10, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 9}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 10}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [24]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 16, "type": "FluxKontextImageScale", "pos": [-170, 630], "size": [194.9458984375, 26], "flags": {}, "order": 14, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 25}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [7, 13, 14, 28]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "FluxKontextImageScale", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 1, "type": "CLIPLoader", "pos": [-170, 200], "size": [396.1328125, 106], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 31}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [5, 11]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_2.5_vl_7b_fp8_scaled.safetensors", "qwen_image", "default"]}], "groups": [{"id": 1, "title": "Models", "bounding": [-180, -90, 416.1419982910156, 630.0299011230469], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Prompt", "bounding": [250, -90, 510, 630], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 2, "origin_id": 9, "origin_slot": 0, "target_id": 5, "target_slot": 0, "type": "CONDITIONING"}, {"id": 3, "origin_id": 13, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "CONDITIONING"}, {"id": 4, "origin_id": 2, "origin_slot": 0, "target_id": 7, "target_slot": 0, "type": "MODEL"}, {"id": 5, "origin_id": 1, "origin_slot": 0, "target_id": 9, "target_slot": 0, "type": "CLIP"}, {"id": 6, "origin_id": 3, "origin_slot": 0, "target_id": 9, "target_slot": 1, "type": "VAE"}, {"id": 9, "origin_id": 15, "origin_slot": 0, "target_id": 12, "target_slot": 0, "type": "LATENT"}, {"id": 10, "origin_id": 3, "origin_slot": 0, "target_id": 12, "target_slot": 1, "type": "VAE"}, {"id": 11, "origin_id": 1, "origin_slot": 0, "target_id": 13, "target_slot": 0, "type": "CLIP"}, {"id": 12, "origin_id": 3, "origin_slot": 0, "target_id": 13, "target_slot": 1, "type": "VAE"}, {"id": 13, "origin_id": 16, "origin_slot": 0, "target_id": 13, "target_slot": 2, "type": "IMAGE"}, {"id": 14, "origin_id": 16, "origin_slot": 0, "target_id": 14, "target_slot": 0, "type": "IMAGE"}, {"id": 15, "origin_id": 3, "origin_slot": 0, "target_id": 14, "target_slot": 1, "type": "VAE"}, {"id": 16, "origin_id": 7, "origin_slot": 0, "target_id": 15, "target_slot": 0, "type": "MODEL"}, {"id": 17, "origin_id": 6, "origin_slot": 0, "target_id": 15, "target_slot": 1, "type": "CONDITIONING"}, {"id": 18, "origin_id": 5, "origin_slot": 0, "target_id": 15, "target_slot": 2, "type": "CONDITIONING"}, {"id": 19, "origin_id": 14, "origin_slot": 0, "target_id": 15, "target_slot": 3, "type": "LATENT"}, {"id": 21, "origin_id": -10, "origin_slot": 1, "target_id": 9, "target_slot": 3, "type": "IMAGE"}, {"id": 22, "origin_id": -10, "origin_slot": 2, "target_id": 9, "target_slot": 4, "type": "IMAGE"}, {"id": 23, "origin_id": -10, "origin_slot": 3, "target_id": 13, "target_slot": 5, "type": "STRING"}, {"id": 24, "origin_id": 12, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 25, "origin_id": -10, "origin_slot": 0, "target_id": 16, "target_slot": 0, "type": "IMAGE"}, {"id": 26, "origin_id": -10, "origin_slot": 1, "target_id": 13, "target_slot": 3, "type": "IMAGE"}, {"id": 27, "origin_id": -10, "origin_slot": 2, "target_id": 13, "target_slot": 4, "type": "IMAGE"}, {"id": 28, "origin_id": 16, "origin_slot": 0, "target_id": 9, "target_slot": 2, "type": "IMAGE"}, {"id": 29, "origin_id": 4, "origin_slot": 0, "target_id": 2, "target_slot": 0, "type": "MODEL"}, {"id": 30, "origin_id": -10, "origin_slot": 4, "target_id": 4, "target_slot": 0, "type": "COMBO"}, {"id": 31, "origin_id": -10, "origin_slot": 5, "target_id": 1, "target_slot": 0, "type": "COMBO"}, {"id": 32, "origin_id": -10, "origin_slot": 6, "target_id": 3, "target_slot": 0, "type": "COMBO"}], "extra": {"frontendVersion": "1.37.11", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true}, "category": "Image generation and editing/Edit image"}]}, "config": {}, "extra": {"frontendVersion": "1.37.11", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true, "ds": {"scale": 0.8597138248970195, "offset": [716.4750075519744, 479.19752576099086]}}, "version": 0.4} +{ + "id": "d84b7d1a-a73f-4e31-bd16-983ac0cf5f1b", + "revision": 0, + "last_node_id": 17, + "last_link_id": 32, + "nodes": [ + { + "id": 17, + "type": "9fa6af8b-8c99-4446-8681-bccf8ba4ea54", + "pos": [ + 183.33334355513557, + -120.00000702649223 + ], + "size": [ + 383.0729166666667, + 381.10677083333337 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "image 1", + "name": "image1", + "type": "IMAGE", + "link": null + }, + { + "label": "image 2 (optional)", + "name": "image2", + "type": "IMAGE", + "link": null + }, + { + "label": "image 3 (optional)", + "name": "image3", + "type": "IMAGE", + "link": null + }, + { + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "prompt" + ], + [ + "15", + "seed" + ], + [ + "15", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.11.0" + }, + "widgets_values": [ + "", + null, + null, + "qwen_image_edit_2511_bf16.safetensors", + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image_vae.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "9fa6af8b-8c99-4446-8681-bccf8ba4ea54", + "version": 1, + "state": { + "lastGroupId": 2, + "lastNodeId": 17, + "lastLinkId": 32, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Image Edit (Qwen 2511)", + "inputNode": { + "id": -10, + "bounding": [ + -412.6162343565087, + 327.2321295314722, + 142.59765625, + 180 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1631.0466138212807, + 305.6854343585077, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "6e401a3f-21a6-4552-8ee4-179c313c1910", + "name": "image1", + "type": "IMAGE", + "linkIds": [ + 25 + ], + "label": "image 1", + "pos": [ + -290.0185781065087, + 347.2321295314722 + ] + }, + { + "id": "a0a6307b-62b8-481e-bb17-d332eceadbe4", + "name": "image2", + "type": "IMAGE", + "linkIds": [ + 21, + 26 + ], + "label": "image 2 (optional)", + "pos": [ + -290.0185781065087, + 367.2321295314722 + ] + }, + { + "id": "232fe944-fc3f-43dd-bb34-112d0360cb5f", + "name": "image3", + "type": "IMAGE", + "linkIds": [ + 22, + 27 + ], + "label": "image 3 (optional)", + "pos": [ + -290.0185781065087, + 387.2321295314722 + ] + }, + { + "id": "9b8ed2f4-5875-4f59-b4c1-5ab79a412f4e", + "name": "prompt", + "type": "STRING", + "linkIds": [ + 23 + ], + "pos": [ + -290.0185781065087, + 407.2321295314722 + ] + }, + { + "id": "403a6bd0-f170-4cfb-b72e-cd7fa1dbcd06", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 30 + ], + "pos": [ + -290.0185781065087, + 427.2321295314722 + ] + }, + { + "id": "86a53531-2fab-47da-9525-858c80737044", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 31 + ], + "pos": [ + -290.0185781065087, + 447.2321295314722 + ] + }, + { + "id": "499f39e9-d698-41dc-b126-b7ea6024cf5d", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 32 + ], + "pos": [ + -290.0185781065087, + 467.2321295314722 + ] + } + ], + "outputs": [ + { + "id": "f2ccd1fa-428e-4127-89a6-760906013172", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 24 + ], + "pos": [ + 1651.0466138212807, + 325.6854343585077 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 2, + "type": "ModelSamplingAuraFlow", + "pos": [ + 791.0465113899395, + -54.3145423152618 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 29 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 4 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3.1 + ] + }, + { + "id": 3, + "type": "VAELoader", + "pos": [ + -174.9530552190643, + 462.6706561999898 + ], + "size": [ + 396.1328125, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 32 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 6, + 10, + 12, + 15 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "qwen_image_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_image_vae.safetensors" + ] + }, + { + "id": 4, + "type": "UNETLoader", + "pos": [ + -174.9530552190643, + -23.329297689188216 + ], + "size": [ + 396.1328125, + 82 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 30 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 29 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "qwen_image_edit_2511_bf16.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2511_bf16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_image_edit_2511_bf16.safetensors", + "default" + ] + }, + { + "id": 5, + "type": "FluxKontextMultiReferenceLatentMethod", + "pos": [ + 781.0466382725523, + 315.68545764091465 + ], + "size": [ + 309.66145833333337, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 2 + }, + { + "localized_name": "reference_latents_method", + "name": "reference_latents_method", + "type": "COMBO", + "widget": { + "name": "reference_latents_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 18 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "FluxKontextMultiReferenceLatentMethod", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "index_timestep_zero" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 6, + "type": "FluxKontextMultiReferenceLatentMethod", + "pos": [ + 781.0466382725523, + 185.68543791920104 + ], + "size": [ + 309.66145833333337, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 3 + }, + { + "localized_name": "reference_latents_method", + "name": "reference_latents_method", + "type": "COMBO", + "widget": { + "name": "reference_latents_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 17 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "FluxKontextMultiReferenceLatentMethod", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "index_timestep_zero" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 7, + "type": "CFGNorm", + "pos": [ + 791.0465113899395, + 55.68545297239743 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 4 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "patched_model", + "name": "patched_model", + "type": "MODEL", + "links": [ + 16 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CFGNorm", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 8, + "type": "MarkdownNote", + "pos": [ + 1111.0466241355298, + 555.6854726502876 + ], + "size": [ + 270, + 195.10416666666669 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "KSampler settings", + "properties": {}, + "widgets_values": [ + "You can test and find the best setting by yourself. The following table is for reference.\n| | Qwen | Comfy | lightning LoRA |\n|--------|---------|------------|---------------------------|\n| Steps | 40 | 20 | 4 |\n| CFG | 4.0 | 4.0 | 1.0 |\n\nBy default, we use 20 steps as we just don't want it to take too long. Try 40 if you want a better result, but it will take longer." + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 9, + "type": "TextEncodeQwenImageEditPlus", + "pos": [ + 301.0466082538065, + 305.6854454238875 + ], + "size": [ + 420, + 170 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 5 + }, + { + "localized_name": "vae", + "name": "vae", + "shape": 7, + "type": "VAE", + "link": 6 + }, + { + "localized_name": "image1", + "name": "image1", + "shape": 7, + "type": "IMAGE", + "link": 28 + }, + { + "localized_name": "image2", + "name": "image2", + "shape": 7, + "type": "IMAGE", + "link": 21 + }, + { + "localized_name": "image3", + "name": "image3", + "shape": 7, + "type": "IMAGE", + "link": 22 + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 2 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "TextEncodeQwenImageEditPlus", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 10, + "type": "Note", + "pos": [ + 801.0465236069665, + 435.6854651456011 + ], + "size": [ + 280, + 88 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "The \"Edit Model Reference Method\" nodes above are not needed if you use Comfy files, but may be needed if you use repackaged ones from other people." + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 13, + "type": "TextEncodeQwenImageEditPlus", + "pos": [ + 301.0466082538065, + -14.314562996972978 + ], + "size": [ + 426.6276041666667, + 215.55989583333334 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 11 + }, + { + "localized_name": "vae", + "name": "vae", + "shape": 7, + "type": "VAE", + "link": 12 + }, + { + "localized_name": "image1", + "name": "image1", + "shape": 7, + "type": "IMAGE", + "link": 13 + }, + { + "localized_name": "image2", + "name": "image2", + "shape": 7, + "type": "IMAGE", + "link": 26 + }, + { + "localized_name": "image3", + "name": "image3", + "shape": 7, + "type": "IMAGE", + "link": 27 + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": 23 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 3 + ] + } + ], + "title": "TextEncodeQwenImageEditPlus (Positive)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "TextEncodeQwenImageEditPlus", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 14, + "type": "VAEEncode", + "pos": [ + 511.0465866120977, + 645.6854435038923 + ], + "size": [ + 187.5, + 46 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 14 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 15 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 19 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "VAEEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 15, + "type": "KSampler", + "pos": [ + 1101.0466119185025, + -54.3145423152618 + ], + "size": [ + 280, + 510 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 16 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 17 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 18 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 19 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 9 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize", + 40, + 4, + "euler", + "simple", + 1 + ] + }, + { + "id": 12, + "type": "VAEDecode", + "pos": [ + 1431.0464586818402, + -44.31456487314459 + ], + "size": [ + 187.5, + 46 + ], + "flags": { + "collapsed": false + }, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 9 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 10 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 24 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 16, + "type": "FluxKontextImageScale", + "pos": [ + -170, + 630 + ], + "size": [ + 194.9458984375, + 26 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 25 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 7, + 13, + 14, + 28 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "FluxKontextImageScale", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 1, + "type": "CLIPLoader", + "pos": [ + -170, + 200 + ], + "size": [ + 396.1328125, + 106 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 31 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 5, + 11 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image", + "default" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Models", + "bounding": [ + -180, + -90, + 416.1419982910156, + 630.0299011230469 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Prompt", + "bounding": [ + 250, + -90, + 510, + 630 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 2, + "origin_id": 9, + "origin_slot": 0, + "target_id": 5, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 3, + "origin_id": 13, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 4, + "origin_id": 2, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 5, + "origin_id": 1, + "origin_slot": 0, + "target_id": 9, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 6, + "origin_id": 3, + "origin_slot": 0, + "target_id": 9, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 9, + "origin_id": 15, + "origin_slot": 0, + "target_id": 12, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 10, + "origin_id": 3, + "origin_slot": 0, + "target_id": 12, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 11, + "origin_id": 1, + "origin_slot": 0, + "target_id": 13, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 12, + "origin_id": 3, + "origin_slot": 0, + "target_id": 13, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 13, + "origin_id": 16, + "origin_slot": 0, + "target_id": 13, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 14, + "origin_id": 16, + "origin_slot": 0, + "target_id": 14, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 15, + "origin_id": 3, + "origin_slot": 0, + "target_id": 14, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 16, + "origin_id": 7, + "origin_slot": 0, + "target_id": 15, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 17, + "origin_id": 6, + "origin_slot": 0, + "target_id": 15, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 18, + "origin_id": 5, + "origin_slot": 0, + "target_id": 15, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 19, + "origin_id": 14, + "origin_slot": 0, + "target_id": 15, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 21, + "origin_id": -10, + "origin_slot": 1, + "target_id": 9, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 22, + "origin_id": -10, + "origin_slot": 2, + "target_id": 9, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 23, + "origin_id": -10, + "origin_slot": 3, + "target_id": 13, + "target_slot": 5, + "type": "STRING" + }, + { + "id": 24, + "origin_id": 12, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 25, + "origin_id": -10, + "origin_slot": 0, + "target_id": 16, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 26, + "origin_id": -10, + "origin_slot": 1, + "target_id": 13, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 27, + "origin_id": -10, + "origin_slot": 2, + "target_id": 13, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 28, + "origin_id": 16, + "origin_slot": 0, + "target_id": 9, + "target_slot": 2, + "type": "IMAGE" + }, + { + "id": 29, + "origin_id": 4, + "origin_slot": 0, + "target_id": 2, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 30, + "origin_id": -10, + "origin_slot": 4, + "target_id": 4, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 31, + "origin_id": -10, + "origin_slot": 5, + "target_id": 1, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 32, + "origin_id": -10, + "origin_slot": 6, + "target_id": 3, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "frontendVersion": "1.37.11", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "category": "Image generation and editing/Edit image" + } + ] + }, + "config": {}, + "extra": { + "frontendVersion": "1.37.11", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ds": { + "scale": 0.8597138248970195, + "offset": [ + 716.4750075519744, + 479.19752576099086 + ] + } + }, + "version": 0.4 +} diff --git a/blueprints/Image Inpainting (Flux.1 Fill Dev).json b/blueprints/Image Inpainting (Flux.1 Fill Dev).json new file mode 100644 index 000000000..d40d63594 --- /dev/null +++ b/blueprints/Image Inpainting (Flux.1 Fill Dev).json @@ -0,0 +1,1205 @@ +{ + "revision": 0, + "last_node_id": 232, + "last_link_id": 0, + "nodes": [ + { + "id": 232, + "type": "6e8d6e38-bdc3-436c-be85-ef9e67e70e07", + "pos": [ + 1270, + 4640 + ], + "size": [ + 400, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": null + }, + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": null + }, + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": null + }, + { + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "23", + "text" + ], + [ + "3", + "seed" + ], + [ + "31", + "unet_name" + ], + [ + "34", + "clip_name1" + ], + [ + "34", + "clip_name2" + ], + [ + "230", + "vae_name" + ] + ], + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1" + }, + "widgets_values": [], + "title": "Image Inpainting (Flux.1 Fill Dev)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "6e8d6e38-bdc3-436c-be85-ef9e67e70e07", + "version": 1, + "state": { + "lastGroupId": 22, + "lastNodeId": 232, + "lastLinkId": 286, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Inpainting (Flux.1 Fill Dev)", + "inputNode": { + "id": -10, + "bounding": [ + -850, + 164, + 120, + 200 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1230, + 140, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "65727ee9-09d0-40c9-bd86-11e0823eb676", + "name": "pixels", + "type": "IMAGE", + "linkIds": [ + 99 + ], + "localized_name": "pixels", + "label": "image", + "pos": [ + -750, + 184 + ] + }, + { + "id": "28424f77-56c5-49c1-ba41-6bd78287c186", + "name": "mask", + "type": "MASK", + "linkIds": [ + 100 + ], + "localized_name": "mask", + "pos": [ + -750, + 204 + ] + }, + { + "id": "2339e5e0-8f8d-4600-b158-7d7dae5f0535", + "name": "text", + "type": "STRING", + "linkIds": [ + 277 + ], + "label": "prompt", + "pos": [ + -750, + 224 + ] + }, + { + "id": "5f433d9b-b97e-4bac-bb88-eb668de2d5a7", + "name": "seed", + "type": "INT", + "linkIds": [ + 282 + ], + "pos": [ + -750, + 244 + ] + }, + { + "id": "35a8b6c1-c92c-4c1a-9b24-2e9bae7808f6", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 283 + ], + "pos": [ + -750, + 264 + ] + }, + { + "id": "3af8f8be-bce8-4ba0-aea0-ccf6b377d5f6", + "name": "clip_name1", + "type": "COMBO", + "linkIds": [ + 284 + ], + "pos": [ + -750, + 284 + ] + }, + { + "id": "d9a4af80-4fa1-4792-b955-78bdaef4596e", + "name": "clip_name2", + "type": "COMBO", + "linkIds": [ + 285 + ], + "pos": [ + -750, + 304 + ] + }, + { + "id": "d59398cf-7e9c-4dae-8c5a-08c4756f256a", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 286 + ], + "pos": [ + -750, + 324 + ] + } + ], + "outputs": [ + { + "id": "1dee24ec-54a8-41be-aa30-a8fb797d3d23", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 95 + ], + "localized_name": "IMAGE", + "pos": [ + 1250, + 160 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 34, + "type": "DualCLIPLoader", + "pos": [ + -590, + 150 + ], + "size": [ + 320, + 180 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name1", + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": 284 + }, + { + "localized_name": "clip_name2", + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": 285 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 62 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "DualCLIPLoader", + "models": [ + { + "name": "clip_l.safetensors", + "url": "https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors", + "directory": "text_encoders" + }, + { + "name": "t5xxl_fp16.safetensors", + "url": "https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "clip_l.safetensors", + "t5xxl_fp16.safetensors", + "flux", + "default" + ] + }, + { + "id": 229, + "type": "FluxGuidance", + "pos": [ + 410, + -40 + ], + "size": [ + 320, + 110 + ], + "flags": { + "collapsed": false + }, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 41 + }, + { + "localized_name": "guidance", + "name": "guidance", + "type": "FLOAT", + "widget": { + "name": "guidance" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 80 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "FluxGuidance" + }, + "widgets_values": [ + 30 + ] + }, + { + "id": 230, + "type": "VAELoader", + "pos": [ + -590, + 450 + ], + "size": [ + 320, + 110 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 286 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 60, + 82 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 31, + "type": "UNETLoader", + "pos": [ + -590, + -90 + ], + "size": [ + 320, + 110 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 283 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 85 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "flux1-fill-dev.safetensors", + "url": "https://huggingface.co/Comfy-Org/flux1-dev/resolve/main/split_files/diffusion_models/flux1-fill-dev.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "flux1-fill-dev.safetensors", + "default" + ] + }, + { + "id": 46, + "type": "ConditioningZeroOut", + "pos": [ + 90, + 420 + ], + "size": [ + 230, + 80 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 101 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 102 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "ConditioningZeroOut" + } + }, + { + "id": 23, + "type": "CLIPTextEncode", + "pos": [ + -160, + -70 + ], + "size": [ + 480, + 410 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 62 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 277 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 41, + 101 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 39, + "type": "DifferentialDiffusion", + "pos": [ + 780, + -110 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 85 + }, + { + "localized_name": "strength", + "name": "strength", + "shape": 7, + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 86 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "DifferentialDiffusion" + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 231, + "type": "VAEDecode", + "pos": [ + 780, + 590 + ], + "size": [ + 230, + 100 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 7 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 60 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 95 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 38, + "type": "InpaintModelConditioning", + "pos": [ + 420, + 120 + ], + "size": [ + 310, + 200 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 80 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 102 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 82 + }, + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 99 + }, + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 100 + }, + { + "localized_name": "noise_mask", + "name": "noise_mask", + "type": "BOOLEAN", + "widget": { + "name": "noise_mask" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 77 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "slot_index": 1, + "links": [ + 78 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "slot_index": 2, + "links": [ + 88 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "InpaintModelConditioning" + }, + "widgets_values": [ + true + ] + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 770, + 40 + ], + "size": [ + 290, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 86 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 77 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 78 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 88 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 282 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 7 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 0, + "randomize", + 20, + 1, + "euler", + "normal", + 1 + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Load models", + "bounding": [ + -620, + -160, + 410, + 790 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + -180, + -160, + 520, + 670 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 41, + "origin_id": 23, + "origin_slot": 0, + "target_id": 229, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 101, + "origin_id": 23, + "origin_slot": 0, + "target_id": 46, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 62, + "origin_id": 34, + "origin_slot": 0, + "target_id": 23, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 85, + "origin_id": 31, + "origin_slot": 0, + "target_id": 39, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 86, + "origin_id": 39, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 77, + "origin_id": 38, + "origin_slot": 0, + "target_id": 3, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 78, + "origin_id": 38, + "origin_slot": 1, + "target_id": 3, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 88, + "origin_id": 38, + "origin_slot": 2, + "target_id": 3, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 7, + "origin_id": 3, + "origin_slot": 0, + "target_id": 231, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 60, + "origin_id": 230, + "origin_slot": 0, + "target_id": 231, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 80, + "origin_id": 229, + "origin_slot": 0, + "target_id": 38, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 102, + "origin_id": 46, + "origin_slot": 0, + "target_id": 38, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 82, + "origin_id": 230, + "origin_slot": 0, + "target_id": 38, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 99, + "origin_id": -10, + "origin_slot": 0, + "target_id": 38, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 100, + "origin_id": -10, + "origin_slot": 1, + "target_id": 38, + "target_slot": 4, + "type": "MASK" + }, + { + "id": 95, + "origin_id": 231, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 277, + "origin_id": -10, + "origin_slot": 2, + "target_id": 23, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 282, + "origin_id": -10, + "origin_slot": 3, + "target_id": 3, + "target_slot": 4, + "type": "INT" + }, + { + "id": 283, + "origin_id": -10, + "origin_slot": 4, + "target_id": 31, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 284, + "origin_id": -10, + "origin_slot": 5, + "target_id": 34, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 285, + "origin_id": -10, + "origin_slot": 6, + "target_id": 34, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 286, + "origin_id": -10, + "origin_slot": 7, + "target_id": 230, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Inpaint image" + } + ] + }, + "extra": { + "ds": { + "scale": 0.8480949417360862, + "offset": [ + 833.9510730024642, + 210.32152847588895 + ] + }, + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Image Inpainting (Qwen-image).json b/blueprints/Image Inpainting (Qwen-image).json index 5f8ef81f9..95b2909fa 100644 --- a/blueprints/Image Inpainting (Qwen-image).json +++ b/blueprints/Image Inpainting (Qwen-image).json @@ -1 +1,1926 @@ -{"id": "84318cde-a839-41d4-8632-df6d7c50ffc5", "revision": 0, "last_node_id": 256, "last_link_id": 403, "nodes": [{"id": 256, "type": "c93d5779-7bfe-4511-98e2-6a665ed0dff2", "pos": [2271.698367680439, -460.52399024524993], "size": [420, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": null}, {"localized_name": "mask", "name": "mask", "type": "MASK", "link": null}, {"name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}, {"name": "control_net_name", "type": "COMBO", "widget": {"name": "control_net_name"}, "link": null}], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": null}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "clip_name"], ["-1", "vae_name"], ["-1", "control_net_name"], ["3", "seed"], ["3", "control_after_generate"]], "cnr_id": "comfy-core", "ver": "0.13.0"}, "widgets_values": ["", "qwen_2.5_vl_7b_fp8_scaled.safetensors", "qwen_image_vae.safetensors", "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "c93d5779-7bfe-4511-98e2-6a665ed0dff2", "version": 1, "state": {"lastGroupId": 14, "lastNodeId": 256, "lastLinkId": 403, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image Inpainting (Qwen-image)", "inputNode": {"id": -10, "bounding": [-860, 530, 140.587890625, 160]}, "outputNode": {"id": -20, "bounding": [1290, 530, 120, 60]}, "inputs": [{"id": "61dc027a-a7fc-4c40-8aa4-fd4a6e36d00f", "name": "image", "type": "IMAGE", "linkIds": [399], "localized_name": "image", "pos": [-739.412109375, 550]}, {"id": "28f4cf42-1c6d-49b8-abce-53ef9c628907", "name": "mask", "type": "MASK", "linkIds": [205], "localized_name": "mask", "pos": [-739.412109375, 570]}, {"id": "f082f9ab-9a31-4d99-b4fd-4900453a30a8", "name": "text", "type": "STRING", "linkIds": [394], "pos": [-739.412109375, 590]}, {"id": "9e692477-812a-4054-b780-471228a9821c", "name": "clip_name", "type": "COMBO", "linkIds": [401], "pos": [-739.412109375, 610]}, {"id": "dfbf7eac-1f92-4636-9ead-6a1c2595c5e2", "name": "vae_name", "type": "COMBO", "linkIds": [402], "pos": [-739.412109375, 630]}, {"id": "cfaf4549-e61b-4a88-a514-24894142433a", "name": "control_net_name", "type": "COMBO", "linkIds": [403], "pos": [-739.412109375, 650]}], "outputs": [{"id": "45b4d67e-3d8f-4936-9599-607a23161a3c", "name": "IMAGE", "type": "IMAGE", "linkIds": [400], "pos": [1310, 550]}], "widgets": [], "nodes": [{"id": 38, "type": "CLIPLoader", "pos": [-90, 70], "size": [380, 106], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 401}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "slot_index": 0, "links": [74, 75]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", "directory": "text_encoders"}]}, "widgets_values": ["qwen_2.5_vl_7b_fp8_scaled.safetensors", "qwen_image", "default"]}, {"id": 37, "type": "UNETLoader", "pos": [-90, -60], "size": [380, 82], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [145]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "UNETLoader", "models": [{"name": "qwen_image_fp8_e4m3fn.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors", "directory": "diffusion_models"}]}, "widgets_values": ["qwen_image_fp8_e4m3fn.safetensors", "default"]}, {"id": 7, "type": "CLIPTextEncode", "pos": [330, 320], "size": [460, 140], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 75}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [191]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "CLIPTextEncode"}, "widgets_values": [" "], "color": "#223", "bgcolor": "#335"}, {"id": 84, "type": "ControlNetLoader", "pos": [-90, 340], "size": [380, 58], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "control_net_name", "name": "control_net_name", "type": "COMBO", "widget": {"name": "control_net_name"}, "link": 403}], "outputs": [{"localized_name": "CONTROL_NET", "name": "CONTROL_NET", "type": "CONTROL_NET", "links": [192]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "ControlNetLoader", "models": [{"name": "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image-InstantX-ControlNets/resolve/main/split_files/controlnet/Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", "directory": "controlnet"}]}, "widgets_values": ["Qwen-Image-InstantX-ControlNet-Inpainting.safetensors"]}, {"id": 39, "type": "VAELoader", "pos": [-90, 230], "size": [380, 58], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 402}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [76, 144, 193]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "VAELoader", "models": [{"name": "qwen_image_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", "directory": "vae"}]}, "widgets_values": ["qwen_image_vae.safetensors"]}, {"id": 66, "type": "ModelSamplingAuraFlow", "pos": [860, -100], "size": [310, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 149}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [156]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "ModelSamplingAuraFlow"}, "widgets_values": [3.1000000000000005]}, {"id": 108, "type": "ControlNetInpaintingAliMamaApply", "pos": [430, 560], "size": [317.0093688964844, 206], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 190}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 191}, {"localized_name": "control_net", "name": "control_net", "type": "CONTROL_NET", "link": 192}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 193}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 397}, {"localized_name": "mask", "name": "mask", "type": "MASK", "link": 220}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}, {"localized_name": "start_percent", "name": "start_percent", "type": "FLOAT", "widget": {"name": "start_percent"}, "link": null}, {"localized_name": "end_percent", "name": "end_percent", "type": "FLOAT", "widget": {"name": "end_percent"}, "link": null}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [188]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [189]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ControlNetInpaintingAliMamaApply"}, "widgets_values": [1, 0, 1]}, {"id": 86, "type": "Note", "pos": [860, 500], "size": [307.4002380371094, 127.38092803955078], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [], "properties": {}, "widgets_values": ["Set cfg to 1.0 for a speed boost at the cost of consistency. Samplers like res_multistep work pretty well at cfg 1.0\n\nThe official number of steps is 50 but I think that's too much. Even just 10 steps seems to work."], "color": "#432", "bgcolor": "#653"}, {"id": 76, "type": "VAEEncode", "pos": [430, 830], "size": [140, 46], "flags": {"collapsed": true}, "order": 11, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 396}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 144}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [208]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "VAEEncode"}, "widgets_values": []}, {"id": 122, "type": "SetLatentNoiseMask", "pos": [430, 890], "size": [230, 50], "flags": {"collapsed": true}, "order": 15, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 208}, {"localized_name": "mask", "name": "mask", "type": "MASK", "link": 219}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [210]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "SetLatentNoiseMask"}, "widgets_values": []}, {"id": 223, "type": "MarkdownNote", "pos": [860, 670], "size": [300, 160], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [], "title": "Note: KSampler settings", "properties": {}, "widgets_values": ["You can test and find the best setting by yourself. The following table is for reference.\n| Parameters | Qwen Team | Comfy Original | with 4steps LoRA |\n|--------|---------|------------|---------------------------|\n| Steps | 50 | 20 | 4 |\n| CFG | 4.0 | 2.5 | 1.0 |"], "color": "#432", "bgcolor": "#653"}, {"id": 80, "type": "LoraLoaderModelOnly", "pos": [350, -70], "size": [430, 82], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 145}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [149]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "Qwen-Image-Lightning-4steps-V1.0.safetensors", "url": "https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-4steps-V1.0.safetensors", "directory": "loras"}]}, "widgets_values": ["Qwen-Image-Lightning-4steps-V1.0.safetensors", 1]}, {"id": 6, "type": "CLIPTextEncode", "pos": [330, 110], "size": [460, 164.31304931640625], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 74}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 394}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [190]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "CLIPTextEncode"}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 121, "type": "56a1f603-fbd2-40ed-94ef-c9ecbd96aca8", "pos": [430, 950], "size": [330, 100], "flags": {}, "order": 14, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 205}, {"name": "expand", "type": "INT", "widget": {"name": "expand"}, "link": null}, {"name": "blur_radius", "type": "INT", "widget": {"name": "blur_radius"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [215, 219, 220]}], "properties": {"proxyWidgets": [["-1", "expand"], ["-1", "blur_radius"]], "cnr_id": "comfy-core", "ver": "0.3.59"}, "widgets_values": [0, 1]}, {"id": 3, "type": "KSampler", "pos": [860, 20], "size": [310, 430], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 156}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 188}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 189}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 210}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [128]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "KSampler"}, "widgets_values": [0, "randomize", 4, 1, "euler", "simple", 1]}, {"id": 224, "type": "FluxKontextImageScale", "pos": [10, 1090], "size": [194.9458984375, 26], "flags": {}, "order": 17, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 399}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [396, 397]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "FluxKontextImageScale"}, "widgets_values": []}, {"id": 8, "type": "VAEDecode", "pos": [900, 880], "size": [250, 46], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 128}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 76}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [110, 400]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "VAEDecode"}, "widgets_values": []}, {"id": 124, "type": "MaskPreview", "pos": [440, 1100], "size": [320, 340], "flags": {}, "order": 16, "mode": 4, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 215}], "outputs": [], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "MaskPreview"}, "widgets_values": []}], "groups": [{"id": 1, "title": "Step 1 - Upload models", "bounding": [-100, -140, 400, 610], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 4, "title": "Step 3 - Prompt", "bounding": [320, 40, 490, 430], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 5, "title": "4 steps lightning LoRA", "bounding": [320, -140, 490, 160], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 14, "title": "Inpainting", "bounding": [-110, -180, 1340, 1650], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 75, "origin_id": 38, "origin_slot": 0, "target_id": 7, "target_slot": 0, "type": "CLIP"}, {"id": 149, "origin_id": 80, "origin_slot": 0, "target_id": 66, "target_slot": 0, "type": "MODEL"}, {"id": 190, "origin_id": 6, "origin_slot": 0, "target_id": 108, "target_slot": 0, "type": "CONDITIONING"}, {"id": 191, "origin_id": 7, "origin_slot": 0, "target_id": 108, "target_slot": 1, "type": "CONDITIONING"}, {"id": 192, "origin_id": 84, "origin_slot": 0, "target_id": 108, "target_slot": 2, "type": "CONTROL_NET"}, {"id": 193, "origin_id": 39, "origin_slot": 0, "target_id": 108, "target_slot": 3, "type": "VAE"}, {"id": 220, "origin_id": 121, "origin_slot": 0, "target_id": 108, "target_slot": 5, "type": "MASK"}, {"id": 144, "origin_id": 39, "origin_slot": 0, "target_id": 76, "target_slot": 1, "type": "VAE"}, {"id": 208, "origin_id": 76, "origin_slot": 0, "target_id": 122, "target_slot": 0, "type": "LATENT"}, {"id": 219, "origin_id": 121, "origin_slot": 0, "target_id": 122, "target_slot": 1, "type": "MASK"}, {"id": 215, "origin_id": 121, "origin_slot": 0, "target_id": 124, "target_slot": 0, "type": "MASK"}, {"id": 128, "origin_id": 3, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 76, "origin_id": 39, "origin_slot": 0, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 74, "origin_id": 38, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "CLIP"}, {"id": 145, "origin_id": 37, "origin_slot": 0, "target_id": 80, "target_slot": 0, "type": "MODEL"}, {"id": 156, "origin_id": 66, "origin_slot": 0, "target_id": 3, "target_slot": 0, "type": "MODEL"}, {"id": 188, "origin_id": 108, "origin_slot": 0, "target_id": 3, "target_slot": 1, "type": "CONDITIONING"}, {"id": 189, "origin_id": 108, "origin_slot": 1, "target_id": 3, "target_slot": 2, "type": "CONDITIONING"}, {"id": 210, "origin_id": 122, "origin_slot": 0, "target_id": 3, "target_slot": 3, "type": "LATENT"}, {"id": 205, "origin_id": -10, "origin_slot": 1, "target_id": 121, "target_slot": 0, "type": "MASK"}, {"id": 110, "origin_id": 8, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 394, "origin_id": -10, "origin_slot": 2, "target_id": 6, "target_slot": 1, "type": "STRING"}, {"id": 396, "origin_id": 224, "origin_slot": 0, "target_id": 76, "target_slot": 0, "type": "IMAGE"}, {"id": 397, "origin_id": 224, "origin_slot": 0, "target_id": 108, "target_slot": 4, "type": "IMAGE"}, {"id": 399, "origin_id": -10, "origin_slot": 0, "target_id": 224, "target_slot": 0, "type": "IMAGE"}, {"id": 400, "origin_id": 8, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 401, "origin_id": -10, "origin_slot": 3, "target_id": 38, "target_slot": 0, "type": "COMBO"}, {"id": 402, "origin_id": -10, "origin_slot": 4, "target_id": 39, "target_slot": 0, "type": "COMBO"}, {"id": 403, "origin_id": -10, "origin_slot": 5, "target_id": 84, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image generation and editing/Inpaint image"}, {"id": "56a1f603-fbd2-40ed-94ef-c9ecbd96aca8", "version": 1, "state": {"lastGroupId": 14, "lastNodeId": 256, "lastLinkId": 403, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Grow and Blur Mask", "inputNode": {"id": -10, "bounding": [290, 3536, 120, 100]}, "outputNode": {"id": -20, "bounding": [1130, 3536, 120, 60]}, "inputs": [{"id": "3ac60d5e-8f9d-4663-9b24-b3a15a3e9e20", "name": "mask", "type": "MASK", "linkIds": [279], "localized_name": "mask", "pos": [390, 3556]}, {"id": "d1ab0cf5-7062-41ac-9f4b-8c660fc4a714", "name": "expand", "type": "INT", "linkIds": [379], "pos": [390, 3576]}, {"id": "1a787af5-da9f-44c5-9f5a-3f71609ca0ef", "name": "blur_radius", "type": "INT", "linkIds": [380], "pos": [390, 3596]}], "outputs": [{"id": "1f97f683-13d3-4871-876d-678fca850d89", "name": "MASK", "type": "MASK", "linkIds": [378], "localized_name": "MASK", "pos": [1150, 3556]}], "widgets": [], "nodes": [{"id": 253, "type": "ImageToMask", "pos": [800, 3630], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 377}, {"localized_name": "channel", "name": "channel", "type": "COMBO", "widget": {"name": "channel"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [378]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageToMask"}, "widgets_values": ["red"]}, {"id": 251, "type": "MaskToImage", "pos": [780, 3470], "size": [260, 70], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 372}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [373]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "MaskToImage"}, "widgets_values": []}, {"id": 199, "type": "GrowMask", "pos": [470, 3460], "size": [270, 82], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 279}, {"localized_name": "expand", "name": "expand", "type": "INT", "widget": {"name": "expand"}, "link": 379}, {"localized_name": "tapered_corners", "name": "tapered_corners", "type": "BOOLEAN", "widget": {"name": "tapered_corners"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [372]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "GrowMask"}, "widgets_values": [0, true]}, {"id": 252, "type": "ImageBlur", "pos": [480, 3620], "size": [270, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 373}, {"localized_name": "blur_radius", "name": "blur_radius", "type": "INT", "widget": {"name": "blur_radius"}, "link": 380}, {"localized_name": "sigma", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [377]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageBlur"}, "widgets_values": [1, 1]}], "groups": [], "links": [{"id": 373, "origin_id": 251, "origin_slot": 0, "target_id": 252, "target_slot": 0, "type": "IMAGE"}, {"id": 377, "origin_id": 252, "origin_slot": 0, "target_id": 253, "target_slot": 0, "type": "IMAGE"}, {"id": 372, "origin_id": 199, "origin_slot": 0, "target_id": 251, "target_slot": 0, "type": "MASK"}, {"id": 279, "origin_id": -10, "origin_slot": 0, "target_id": 199, "target_slot": 0, "type": "MASK"}, {"id": 378, "origin_id": 253, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "MASK"}, {"id": 379, "origin_id": -10, "origin_slot": 1, "target_id": 199, "target_slot": 1, "type": "INT"}, {"id": 380, "origin_id": -10, "origin_slot": 2, "target_id": 252, "target_slot": 1, "type": "INT"}], "extra": {"workflowRendererVersion": "LG"}}]}, "config": {}, "extra": {"ds": {"scale": 1.088930769230769, "offset": [-1576.5829757292656, 657.608356702113]}, "workflowRendererVersion": "LG"}, "version": 0.4} +{ + "id": "84318cde-a839-41d4-8632-df6d7c50ffc5", + "revision": 0, + "last_node_id": 256, + "last_link_id": 403, + "nodes": [ + { + "id": 256, + "type": "c93d5779-7bfe-4511-98e2-6a665ed0dff2", + "pos": [ + 2271.698367680439, + -460.52399024524993 + ], + "size": [ + 420, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": null + }, + { + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "name": "control_net_name", + "type": "COMBO", + "widget": { + "name": "control_net_name" + }, + "link": null + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ], + [ + "-1", + "control_net_name" + ], + [ + "3", + "seed" + ], + [ + "3", + "control_after_generate" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.13.0" + }, + "widgets_values": [ + "", + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image_vae.safetensors", + "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "c93d5779-7bfe-4511-98e2-6a665ed0dff2", + "version": 1, + "state": { + "lastGroupId": 14, + "lastNodeId": 256, + "lastLinkId": 403, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Inpainting (Qwen-image)", + "inputNode": { + "id": -10, + "bounding": [ + -860, + 530, + 140.587890625, + 160 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1290, + 530, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "61dc027a-a7fc-4c40-8aa4-fd4a6e36d00f", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 399 + ], + "localized_name": "image", + "pos": [ + -739.412109375, + 550 + ] + }, + { + "id": "28f4cf42-1c6d-49b8-abce-53ef9c628907", + "name": "mask", + "type": "MASK", + "linkIds": [ + 205 + ], + "localized_name": "mask", + "pos": [ + -739.412109375, + 570 + ] + }, + { + "id": "f082f9ab-9a31-4d99-b4fd-4900453a30a8", + "name": "text", + "type": "STRING", + "linkIds": [ + 394 + ], + "pos": [ + -739.412109375, + 590 + ] + }, + { + "id": "9e692477-812a-4054-b780-471228a9821c", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 401 + ], + "pos": [ + -739.412109375, + 610 + ] + }, + { + "id": "dfbf7eac-1f92-4636-9ead-6a1c2595c5e2", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 402 + ], + "pos": [ + -739.412109375, + 630 + ] + }, + { + "id": "cfaf4549-e61b-4a88-a514-24894142433a", + "name": "control_net_name", + "type": "COMBO", + "linkIds": [ + 403 + ], + "pos": [ + -739.412109375, + 650 + ] + } + ], + "outputs": [ + { + "id": "45b4d67e-3d8f-4936-9599-607a23161a3c", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 400 + ], + "pos": [ + 1310, + 550 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 38, + "type": "CLIPLoader", + "pos": [ + -90, + 70 + ], + "size": [ + 380, + 106 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 401 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 74, + 75 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image", + "default" + ] + }, + { + "id": 37, + "type": "UNETLoader", + "pos": [ + -90, + -60 + ], + "size": [ + 380, + 82 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 145 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "qwen_image_fp8_e4m3fn.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "qwen_image_fp8_e4m3fn.safetensors", + "default" + ] + }, + { + "id": 7, + "type": "CLIPTextEncode", + "pos": [ + 330, + 320 + ], + "size": [ + 460, + 140 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 75 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 191 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + " " + ], + "color": "#223", + "bgcolor": "#335" + }, + { + "id": 84, + "type": "ControlNetLoader", + "pos": [ + -90, + 340 + ], + "size": [ + 380, + 58 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "control_net_name", + "name": "control_net_name", + "type": "COMBO", + "widget": { + "name": "control_net_name" + }, + "link": 403 + } + ], + "outputs": [ + { + "localized_name": "CONTROL_NET", + "name": "CONTROL_NET", + "type": "CONTROL_NET", + "links": [ + 192 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "ControlNetLoader", + "models": [ + { + "name": "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image-InstantX-ControlNets/resolve/main/split_files/controlnet/Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", + "directory": "controlnet" + } + ] + }, + "widgets_values": [ + "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors" + ] + }, + { + "id": 39, + "type": "VAELoader", + "pos": [ + -90, + 230 + ], + "size": [ + 380, + 58 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 402 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 76, + 144, + 193 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "qwen_image_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "qwen_image_vae.safetensors" + ] + }, + { + "id": 66, + "type": "ModelSamplingAuraFlow", + "pos": [ + 860, + -100 + ], + "size": [ + 310, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 149 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 156 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "ModelSamplingAuraFlow" + }, + "widgets_values": [ + 3.1000000000000005 + ] + }, + { + "id": 108, + "type": "ControlNetInpaintingAliMamaApply", + "pos": [ + 430, + 560 + ], + "size": [ + 317.0093688964844, + 206 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 190 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 191 + }, + { + "localized_name": "control_net", + "name": "control_net", + "type": "CONTROL_NET", + "link": 192 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 193 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 397 + }, + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 220 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "localized_name": "start_percent", + "name": "start_percent", + "type": "FLOAT", + "widget": { + "name": "start_percent" + }, + "link": null + }, + { + "localized_name": "end_percent", + "name": "end_percent", + "type": "FLOAT", + "widget": { + "name": "end_percent" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 188 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 189 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ControlNetInpaintingAliMamaApply" + }, + "widgets_values": [ + 1, + 0, + 1 + ] + }, + { + "id": 86, + "type": "Note", + "pos": [ + 860, + 500 + ], + "size": [ + 307.4002380371094, + 127.38092803955078 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Set cfg to 1.0 for a speed boost at the cost of consistency. Samplers like res_multistep work pretty well at cfg 1.0\n\nThe official number of steps is 50 but I think that's too much. Even just 10 steps seems to work." + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 76, + "type": "VAEEncode", + "pos": [ + 430, + 830 + ], + "size": [ + 140, + 46 + ], + "flags": { + "collapsed": true + }, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 396 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 144 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 208 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "VAEEncode" + }, + "widgets_values": [] + }, + { + "id": 122, + "type": "SetLatentNoiseMask", + "pos": [ + 430, + 890 + ], + "size": [ + 230, + 50 + ], + "flags": { + "collapsed": true + }, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 208 + }, + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 219 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 210 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "SetLatentNoiseMask" + }, + "widgets_values": [] + }, + { + "id": 223, + "type": "MarkdownNote", + "pos": [ + 860, + 670 + ], + "size": [ + 300, + 160 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: KSampler settings", + "properties": {}, + "widgets_values": [ + "You can test and find the best setting by yourself. The following table is for reference.\n| Parameters | Qwen Team | Comfy Original | with 4steps LoRA |\n|--------|---------|------------|---------------------------|\n| Steps | 50 | 20 | 4 |\n| CFG | 4.0 | 2.5 | 1.0 |" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 80, + "type": "LoraLoaderModelOnly", + "pos": [ + 350, + -70 + ], + "size": [ + 430, + 82 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 145 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 149 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "Qwen-Image-Lightning-4steps-V1.0.safetensors", + "url": "https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-4steps-V1.0.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "Qwen-Image-Lightning-4steps-V1.0.safetensors", + 1 + ] + }, + { + "id": 6, + "type": "CLIPTextEncode", + "pos": [ + 330, + 110 + ], + "size": [ + 460, + 164.31304931640625 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 74 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 394 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 190 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 121, + "type": "56a1f603-fbd2-40ed-94ef-c9ecbd96aca8", + "pos": [ + 430, + 950 + ], + "size": [ + 330, + 100 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 205 + }, + { + "name": "expand", + "type": "INT", + "widget": { + "name": "expand" + }, + "link": null + }, + { + "name": "blur_radius", + "type": "INT", + "widget": { + "name": "blur_radius" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 215, + 219, + 220 + ] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "expand" + ], + [ + "-1", + "blur_radius" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.3.59" + }, + "widgets_values": [ + 0, + 1 + ] + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 860, + 20 + ], + "size": [ + 310, + 430 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 156 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 188 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 189 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 210 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 128 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 0, + "randomize", + 4, + 1, + "euler", + "simple", + 1 + ] + }, + { + "id": 224, + "type": "FluxKontextImageScale", + "pos": [ + 10, + 1090 + ], + "size": [ + 194.9458984375, + 26 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 399 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 396, + 397 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "FluxKontextImageScale" + }, + "widgets_values": [] + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 900, + 880 + ], + "size": [ + 250, + 46 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 128 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 76 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 110, + 400 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "VAEDecode" + }, + "widgets_values": [] + }, + { + "id": 124, + "type": "MaskPreview", + "pos": [ + 440, + 1100 + ], + "size": [ + 320, + 340 + ], + "flags": {}, + "order": 16, + "mode": 4, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 215 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "MaskPreview" + }, + "widgets_values": [] + } + ], + "groups": [ + { + "id": 1, + "title": "Step 1 - Upload models", + "bounding": [ + -100, + -140, + 400, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 4, + "title": "Step 3 - Prompt", + "bounding": [ + 320, + 40, + 490, + 430 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "4 steps lightning LoRA", + "bounding": [ + 320, + -140, + 490, + 160 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 14, + "title": "Inpainting", + "bounding": [ + -110, + -180, + 1340, + 1650 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 75, + "origin_id": 38, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 149, + "origin_id": 80, + "origin_slot": 0, + "target_id": 66, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 190, + "origin_id": 6, + "origin_slot": 0, + "target_id": 108, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 191, + "origin_id": 7, + "origin_slot": 0, + "target_id": 108, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 192, + "origin_id": 84, + "origin_slot": 0, + "target_id": 108, + "target_slot": 2, + "type": "CONTROL_NET" + }, + { + "id": 193, + "origin_id": 39, + "origin_slot": 0, + "target_id": 108, + "target_slot": 3, + "type": "VAE" + }, + { + "id": 220, + "origin_id": 121, + "origin_slot": 0, + "target_id": 108, + "target_slot": 5, + "type": "MASK" + }, + { + "id": 144, + "origin_id": 39, + "origin_slot": 0, + "target_id": 76, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 208, + "origin_id": 76, + "origin_slot": 0, + "target_id": 122, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 219, + "origin_id": 121, + "origin_slot": 0, + "target_id": 122, + "target_slot": 1, + "type": "MASK" + }, + { + "id": 215, + "origin_id": 121, + "origin_slot": 0, + "target_id": 124, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 128, + "origin_id": 3, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 76, + "origin_id": 39, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 74, + "origin_id": 38, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 145, + "origin_id": 37, + "origin_slot": 0, + "target_id": 80, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 156, + "origin_id": 66, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 188, + "origin_id": 108, + "origin_slot": 0, + "target_id": 3, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 189, + "origin_id": 108, + "origin_slot": 1, + "target_id": 3, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 210, + "origin_id": 122, + "origin_slot": 0, + "target_id": 3, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 205, + "origin_id": -10, + "origin_slot": 1, + "target_id": 121, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 110, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 394, + "origin_id": -10, + "origin_slot": 2, + "target_id": 6, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 396, + "origin_id": 224, + "origin_slot": 0, + "target_id": 76, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 397, + "origin_id": 224, + "origin_slot": 0, + "target_id": 108, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 399, + "origin_id": -10, + "origin_slot": 0, + "target_id": 224, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 400, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 401, + "origin_id": -10, + "origin_slot": 3, + "target_id": 38, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 402, + "origin_id": -10, + "origin_slot": 4, + "target_id": 39, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 403, + "origin_id": -10, + "origin_slot": 5, + "target_id": 84, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Inpaint image" + }, + { + "id": "56a1f603-fbd2-40ed-94ef-c9ecbd96aca8", + "version": 1, + "state": { + "lastGroupId": 14, + "lastNodeId": 256, + "lastLinkId": 403, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Grow and Blur Mask", + "inputNode": { + "id": -10, + "bounding": [ + 290, + 3536, + 120, + 100 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1130, + 3536, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "3ac60d5e-8f9d-4663-9b24-b3a15a3e9e20", + "name": "mask", + "type": "MASK", + "linkIds": [ + 279 + ], + "localized_name": "mask", + "pos": [ + 390, + 3556 + ] + }, + { + "id": "d1ab0cf5-7062-41ac-9f4b-8c660fc4a714", + "name": "expand", + "type": "INT", + "linkIds": [ + 379 + ], + "pos": [ + 390, + 3576 + ] + }, + { + "id": "1a787af5-da9f-44c5-9f5a-3f71609ca0ef", + "name": "blur_radius", + "type": "INT", + "linkIds": [ + 380 + ], + "pos": [ + 390, + 3596 + ] + } + ], + "outputs": [ + { + "id": "1f97f683-13d3-4871-876d-678fca850d89", + "name": "MASK", + "type": "MASK", + "linkIds": [ + 378 + ], + "localized_name": "MASK", + "pos": [ + 1150, + 3556 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 253, + "type": "ImageToMask", + "pos": [ + 800, + 3630 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 377 + }, + { + "localized_name": "channel", + "name": "channel", + "type": "COMBO", + "widget": { + "name": "channel" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 378 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageToMask" + }, + "widgets_values": [ + "red" + ] + }, + { + "id": 251, + "type": "MaskToImage", + "pos": [ + 780, + 3470 + ], + "size": [ + 260, + 70 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 372 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 373 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "MaskToImage" + }, + "widgets_values": [] + }, + { + "id": 199, + "type": "GrowMask", + "pos": [ + 470, + 3460 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 279 + }, + { + "localized_name": "expand", + "name": "expand", + "type": "INT", + "widget": { + "name": "expand" + }, + "link": 379 + }, + { + "localized_name": "tapered_corners", + "name": "tapered_corners", + "type": "BOOLEAN", + "widget": { + "name": "tapered_corners" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 372 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "GrowMask" + }, + "widgets_values": [ + 0, + true + ] + }, + { + "id": 252, + "type": "ImageBlur", + "pos": [ + 480, + 3620 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 373 + }, + { + "localized_name": "blur_radius", + "name": "blur_radius", + "type": "INT", + "widget": { + "name": "blur_radius" + }, + "link": 380 + }, + { + "localized_name": "sigma", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 377 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageBlur" + }, + "widgets_values": [ + 1, + 1 + ] + } + ], + "groups": [], + "links": [ + { + "id": 373, + "origin_id": 251, + "origin_slot": 0, + "target_id": 252, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 377, + "origin_id": 252, + "origin_slot": 0, + "target_id": 253, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 372, + "origin_id": 199, + "origin_slot": 0, + "target_id": 251, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 279, + "origin_id": -10, + "origin_slot": 0, + "target_id": 199, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 378, + "origin_id": 253, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 379, + "origin_id": -10, + "origin_slot": 1, + "target_id": 199, + "target_slot": 1, + "type": "INT" + }, + { + "id": 380, + "origin_id": -10, + "origin_slot": 2, + "target_id": 252, + "target_slot": 1, + "type": "INT" + } + ], + "extra": { + "workflowRendererVersion": "LG" + } + } + ] + }, + "config": {}, + "extra": { + "ds": { + "scale": 1.088930769230769, + "offset": [ + -1576.5829757292656, + 657.608356702113 + ] + }, + "workflowRendererVersion": "LG" + }, + "version": 0.4 +} \ No newline at end of file diff --git a/blueprints/Image Levels.json b/blueprints/Image Levels.json index f028662bd..ef256a1aa 100644 --- a/blueprints/Image Levels.json +++ b/blueprints/Image Levels.json @@ -1 +1,750 @@ -{"revision": 0, "last_node_id": 139, "last_link_id": 0, "nodes": [{"id": 139, "type": "75bf8a72-aad8-4f3e-83ee-380e70248240", "pos": [620, 900], "size": [240, 178], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["5", "choice"], ["3", "value"], ["6", "value"], ["7", "value"], ["8", "value"], ["9", "value"]]}, "widgets_values": [], "title": "Image Levels"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "75bf8a72-aad8-4f3e-83ee-380e70248240", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 144, "lastLinkId": 118, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Levels", "inputNode": {"id": -10, "bounding": [3840, -3430, 120, 60]}, "outputNode": {"id": -20, "bounding": [4950, -3430, 120, 60]}, "inputs": [{"id": "b53e5012-fa47-400f-a324-28c74854ccae", "name": "images.image0", "type": "IMAGE", "linkIds": [1], "localized_name": "images.image0", "label": "image", "pos": [3940, -3410]}], "outputs": [{"id": "de7f2ffa-155f-41fd-b054-aa4d91ef49ca", "name": "IMAGE0", "type": "IMAGE", "linkIds": [8], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [4970, -3410]}], "widgets": [], "nodes": [{"id": 5, "type": "CustomCombo", "pos": [4020, -3350], "size": [270, 198], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "channel", "localized_name": "choice", "name": "choice", "type": "COMBO", "widget": {"name": "choice"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": null}, {"localized_name": "INDEX", "name": "INDEX", "type": "INT", "links": [3]}], "title": "Channel", "properties": {"Node name for S&R": "CustomCombo"}, "widgets_values": ["RGB", 0, "RGB", "R", "G", "B", ""]}, {"id": 8, "type": "PrimitiveFloat", "pos": [4020, -3550], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "output_black", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [6]}], "title": "Output Black", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 255, "min": 0, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 0, 0]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [0]}, {"id": 3, "type": "PrimitiveFloat", "pos": [4020, -3850], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "input_black", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [2]}], "title": "Input Black", "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 255, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 0, 0]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [0]}, {"id": 6, "type": "PrimitiveFloat", "pos": [4020, -3750], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "input_white", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [4]}], "title": "Input White", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 255, "min": 0, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 0, 0]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [255]}, {"id": 7, "type": "PrimitiveFloat", "pos": [4020, -3650], "size": [270, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "gamma", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [5]}], "title": "Gamma", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 10, "min": 0, "step": 0.01, "precision": 2, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 0, 0]}, {"offset": 0.5, "color": [128, 128, 128]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [1]}, {"id": 9, "type": "PrimitiveFloat", "pos": [4020, -3450], "size": [270, 58], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "output_white", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [7]}], "title": "Output White", "properties": {"Node name for S&R": "PrimitiveFloat", "max": 255, "min": 0, "step": 1, "display": "gradientslider", "gradient_stops": [{"offset": 0, "color": [0, 0, 0]}, {"offset": 1, "color": [255, 255, 255]}]}, "widgets_values": [255]}, {"id": 1, "type": "GLSLShader", "pos": [4310, -3850], "size": [580, 272], "flags": {}, "order": 6, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 1}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 2}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 4}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": 5}, {"label": "u_float3", "localized_name": "floats.u_float3", "name": "floats.u_float3", "shape": 7, "type": "FLOAT", "link": 6}, {"label": "u_float4", "localized_name": "floats.u_float4", "name": "floats.u_float4", "shape": 7, "type": "FLOAT", "link": 7}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": 3}, {"label": "u_int1", "localized_name": "ints.u_int1", "name": "ints.u_int1", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [8]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\n// Levels Adjustment\n// u_int0: channel (0=RGB, 1=R, 2=G, 3=B) default: 0\n// u_float0: input black (0-255) default: 0\n// u_float1: input white (0-255) default: 255\n// u_float2: gamma (0.01-9.99) default: 1.0\n// u_float3: output black (0-255) default: 0\n// u_float4: output white (0-255) default: 255\n\nuniform sampler2D u_image0;\nuniform int u_int0;\nuniform float u_float0;\nuniform float u_float1;\nuniform float u_float2;\nuniform float u_float3;\nuniform float u_float4;\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nvec3 applyLevels(vec3 color, float inBlack, float inWhite, float gamma, float outBlack, float outWhite) {\n float inRange = max(inWhite - inBlack, 0.0001);\n vec3 result = clamp((color - inBlack) / inRange, 0.0, 1.0);\n result = pow(result, vec3(1.0 / gamma));\n result = mix(vec3(outBlack), vec3(outWhite), result);\n return result;\n}\n\nfloat applySingleChannel(float value, float inBlack, float inWhite, float gamma, float outBlack, float outWhite) {\n float inRange = max(inWhite - inBlack, 0.0001);\n float result = clamp((value - inBlack) / inRange, 0.0, 1.0);\n result = pow(result, 1.0 / gamma);\n result = mix(outBlack, outWhite, result);\n return result;\n}\n\nvoid main() {\n vec4 texColor = texture(u_image0, v_texCoord);\n vec3 color = texColor.rgb;\n \n float inBlack = u_float0 / 255.0;\n float inWhite = u_float1 / 255.0;\n float gamma = u_float2;\n float outBlack = u_float3 / 255.0;\n float outWhite = u_float4 / 255.0;\n \n vec3 result;\n \n if (u_int0 == 0) {\n result = applyLevels(color, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else if (u_int0 == 1) {\n result = color;\n result.r = applySingleChannel(color.r, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else if (u_int0 == 2) {\n result = color;\n result.g = applySingleChannel(color.g, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else if (u_int0 == 3) {\n result = color;\n result.b = applySingleChannel(color.b, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else {\n result = color;\n }\n \n fragColor = vec4(result, texColor.a);\n}", "from_input"]}], "groups": [], "links": [{"id": 2, "origin_id": 3, "origin_slot": 0, "target_id": 1, "target_slot": 2, "type": "FLOAT"}, {"id": 4, "origin_id": 6, "origin_slot": 0, "target_id": 1, "target_slot": 3, "type": "FLOAT"}, {"id": 5, "origin_id": 7, "origin_slot": 0, "target_id": 1, "target_slot": 4, "type": "FLOAT"}, {"id": 6, "origin_id": 8, "origin_slot": 0, "target_id": 1, "target_slot": 5, "type": "FLOAT"}, {"id": 7, "origin_id": 9, "origin_slot": 0, "target_id": 1, "target_slot": 6, "type": "FLOAT"}, {"id": 3, "origin_id": 5, "origin_slot": 1, "target_id": 1, "target_slot": 7, "type": "INT"}, {"id": 1, "origin_id": -10, "origin_slot": 0, "target_id": 1, "target_slot": 0, "type": "IMAGE"}, {"id": 8, "origin_id": 1, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}, "extra": {}} +{ + "revision": 0, + "last_node_id": 139, + "last_link_id": 0, + "nodes": [ + { + "id": 139, + "type": "75bf8a72-aad8-4f3e-83ee-380e70248240", + "pos": [ + 620, + 900 + ], + "size": [ + 240, + 178 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "5", + "choice" + ], + [ + "3", + "value" + ], + [ + "6", + "value" + ], + [ + "7", + "value" + ], + [ + "8", + "value" + ], + [ + "9", + "value" + ] + ] + }, + "widgets_values": [], + "title": "Image Levels" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "75bf8a72-aad8-4f3e-83ee-380e70248240", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 144, + "lastLinkId": 118, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Levels", + "inputNode": { + "id": -10, + "bounding": [ + 3840, + -3430, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4950, + -3430, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "b53e5012-fa47-400f-a324-28c74854ccae", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 1 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 3940, + -3410 + ] + } + ], + "outputs": [ + { + "id": "de7f2ffa-155f-41fd-b054-aa4d91ef49ca", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 8 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 4970, + -3410 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 5, + "type": "CustomCombo", + "pos": [ + 4020, + -3350 + ], + "size": [ + 270, + 198 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "channel", + "localized_name": "choice", + "name": "choice", + "type": "COMBO", + "widget": { + "name": "choice" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": null + }, + { + "localized_name": "INDEX", + "name": "INDEX", + "type": "INT", + "links": [ + 3 + ] + } + ], + "title": "Channel", + "properties": { + "Node name for S&R": "CustomCombo" + }, + "widgets_values": [ + "RGB", + 0, + "RGB", + "R", + "G", + "B", + "" + ] + }, + { + "id": 8, + "type": "PrimitiveFloat", + "pos": [ + 4020, + -3550 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "output_black", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 6 + ] + } + ], + "title": "Output Black", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 255, + "min": 0, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 3, + "type": "PrimitiveFloat", + "pos": [ + 4020, + -3850 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "input_black", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 2 + ] + } + ], + "title": "Input Black", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 255, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 6, + "type": "PrimitiveFloat", + "pos": [ + 4020, + -3750 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "input_white", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 4 + ] + } + ], + "title": "Input White", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 255, + "min": 0, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 255 + ] + }, + { + "id": 7, + "type": "PrimitiveFloat", + "pos": [ + 4020, + -3650 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "gamma", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 5 + ] + } + ], + "title": "Gamma", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 10, + "min": 0, + "step": 0.01, + "precision": 2, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 0.5, + "color": [ + 128, + 128, + 128 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 9, + "type": "PrimitiveFloat", + "pos": [ + 4020, + -3450 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "label": "output_white", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 7 + ] + } + ], + "title": "Output White", + "properties": { + "Node name for S&R": "PrimitiveFloat", + "max": 255, + "min": 0, + "step": 1, + "display": "gradientslider", + "gradient_stops": [ + { + "offset": 0, + "color": [ + 0, + 0, + 0 + ] + }, + { + "offset": 1, + "color": [ + 255, + 255, + 255 + ] + } + ] + }, + "widgets_values": [ + 255 + ] + }, + { + "id": 1, + "type": "GLSLShader", + "pos": [ + 4310, + -3850 + ], + "size": [ + 580, + 272 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 1 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 2 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 4 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": 5 + }, + { + "label": "u_float3", + "localized_name": "floats.u_float3", + "name": "floats.u_float3", + "shape": 7, + "type": "FLOAT", + "link": 6 + }, + { + "label": "u_float4", + "localized_name": "floats.u_float4", + "name": "floats.u_float4", + "shape": 7, + "type": "FLOAT", + "link": 7 + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": 3 + }, + { + "label": "u_int1", + "localized_name": "ints.u_int1", + "name": "ints.u_int1", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 8 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\n// Levels Adjustment\n// u_int0: channel (0=RGB, 1=R, 2=G, 3=B) default: 0\n// u_float0: input black (0-255) default: 0\n// u_float1: input white (0-255) default: 255\n// u_float2: gamma (0.01-9.99) default: 1.0\n// u_float3: output black (0-255) default: 0\n// u_float4: output white (0-255) default: 255\n\nuniform sampler2D u_image0;\nuniform int u_int0;\nuniform float u_float0;\nuniform float u_float1;\nuniform float u_float2;\nuniform float u_float3;\nuniform float u_float4;\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nvec3 applyLevels(vec3 color, float inBlack, float inWhite, float gamma, float outBlack, float outWhite) {\n float inRange = max(inWhite - inBlack, 0.0001);\n vec3 result = clamp((color - inBlack) / inRange, 0.0, 1.0);\n result = pow(result, vec3(1.0 / gamma));\n result = mix(vec3(outBlack), vec3(outWhite), result);\n return result;\n}\n\nfloat applySingleChannel(float value, float inBlack, float inWhite, float gamma, float outBlack, float outWhite) {\n float inRange = max(inWhite - inBlack, 0.0001);\n float result = clamp((value - inBlack) / inRange, 0.0, 1.0);\n result = pow(result, 1.0 / gamma);\n result = mix(outBlack, outWhite, result);\n return result;\n}\n\nvoid main() {\n vec4 texColor = texture(u_image0, v_texCoord);\n vec3 color = texColor.rgb;\n \n float inBlack = u_float0 / 255.0;\n float inWhite = u_float1 / 255.0;\n float gamma = u_float2;\n float outBlack = u_float3 / 255.0;\n float outWhite = u_float4 / 255.0;\n \n vec3 result;\n \n if (u_int0 == 0) {\n result = applyLevels(color, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else if (u_int0 == 1) {\n result = color;\n result.r = applySingleChannel(color.r, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else if (u_int0 == 2) {\n result = color;\n result.g = applySingleChannel(color.g, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else if (u_int0 == 3) {\n result = color;\n result.b = applySingleChannel(color.b, inBlack, inWhite, gamma, outBlack, outWhite);\n }\n else {\n result = color;\n }\n \n fragColor = vec4(result, texColor.a);\n}", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 2, + "origin_id": 3, + "origin_slot": 0, + "target_id": 1, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 4, + "origin_id": 6, + "origin_slot": 0, + "target_id": 1, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 5, + "origin_id": 7, + "origin_slot": 0, + "target_id": 1, + "target_slot": 4, + "type": "FLOAT" + }, + { + "id": 6, + "origin_id": 8, + "origin_slot": 0, + "target_id": 1, + "target_slot": 5, + "type": "FLOAT" + }, + { + "id": 7, + "origin_id": 9, + "origin_slot": 0, + "target_id": 1, + "target_slot": 6, + "type": "FLOAT" + }, + { + "id": 3, + "origin_id": 5, + "origin_slot": 1, + "target_id": 1, + "target_slot": 7, + "type": "INT" + }, + { + "id": 1, + "origin_id": -10, + "origin_slot": 0, + "target_id": 1, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 8, + "origin_id": 1, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Color adjust" + } + ] + }, + "extra": {} +} diff --git a/blueprints/Image Outpainting (Qwen-Image).json b/blueprints/Image Outpainting (Qwen-Image).json index f36e0bd77..218fdc775 100644 --- a/blueprints/Image Outpainting (Qwen-Image).json +++ b/blueprints/Image Outpainting (Qwen-Image).json @@ -1 +1,2752 @@ -{"id": "8f79c27f-bec4-412e-9b82-7c5b3b778ecf", "revision": 0, "last_node_id": 255, "last_link_id": 401, "nodes": [{"id": 224, "type": "fbf07656-8ff8-4299-a3fc-7378e0f4a004", "pos": [3200, 740], "size": [400, 460], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": null}, {"name": "left", "type": "INT", "widget": {"name": "left"}, "link": null}, {"name": "top", "type": "INT", "widget": {"name": "top"}, "link": null}, {"name": "right", "type": "INT", "widget": {"name": "right"}, "link": null}, {"name": "bottom", "type": "INT", "widget": {"name": "bottom"}, "link": null}, {"name": "feathering", "type": "INT", "widget": {"name": "feathering"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}, {"name": "control_net_name", "type": "COMBO", "widget": {"name": "control_net_name"}, "link": null}, {"name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["182", "text"], ["-1", "left"], ["-1", "top"], ["-1", "right"], ["-1", "bottom"], ["-1", "feathering"], ["190", "seed"], ["190", "control_after_generate"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"], ["-1", "control_net_name"], ["-1", "lora_name"]], "cnr_id": "comfy-core", "ver": "0.13.0"}, "widgets_values": [null, 0, 0, 0, 0, 0, null, null, "qwen_image_fp8_e4m3fn.safetensors", "qwen_2.5_vl_7b_fp8_scaled.safetensors", "qwen_image_vae.safetensors", "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", "Qwen-Image-Lightning-4steps-V1.0.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "fbf07656-8ff8-4299-a3fc-7378e0f4a004", "version": 1, "state": {"lastGroupId": 14, "lastNodeId": 255, "lastLinkId": 401, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image Outpainting (Qwen-Image)", "inputNode": {"id": -10, "bounding": [1940, 610, 140.587890625, 260]}, "outputNode": {"id": -20, "bounding": [4240, 765, 120, 60]}, "inputs": [{"id": "466b9998-797f-4c6f-92e9-39120712c1a9", "name": "image", "type": "IMAGE", "linkIds": [351], "localized_name": "image", "pos": [2060.587890625, 630]}, {"id": "c5befee8-d6c4-493e-8ae1-e09d46268d10", "name": "left", "type": "INT", "linkIds": [392], "pos": [2060.587890625, 650]}, {"id": "c0b028a1-fcc0-4a54-9bdf-fa9e76992c40", "name": "top", "type": "INT", "linkIds": [393], "pos": [2060.587890625, 670]}, {"id": "22e43278-694c-410f-9043-f88b8dfdca28", "name": "right", "type": "INT", "linkIds": [394], "pos": [2060.587890625, 690]}, {"id": "f19fec20-a43d-4562-a0f8-bd6955091c1b", "name": "bottom", "type": "INT", "linkIds": [395], "pos": [2060.587890625, 710]}, {"id": "ba832b36-2199-4e1e-a28d-5f2e8acc99a3", "name": "feathering", "type": "INT", "linkIds": [396], "pos": [2060.587890625, 730]}, {"id": "437d6324-2d3c-4c50-ac21-1ea9aab57f4e", "name": "unet_name", "type": "COMBO", "linkIds": [397], "pos": [2060.587890625, 750]}, {"id": "4d58dde7-4402-45d5-ade9-9c41e99e0757", "name": "clip_name", "type": "COMBO", "linkIds": [398], "pos": [2060.587890625, 770]}, {"id": "a7558cc4-d4c4-4b4a-b2a3-0d7229a8ff65", "name": "vae_name", "type": "COMBO", "linkIds": [399], "pos": [2060.587890625, 790]}, {"id": "7d8ffb86-2ff3-49fc-8e96-94d3e530f154", "name": "control_net_name", "type": "COMBO", "linkIds": [400], "pos": [2060.587890625, 810]}, {"id": "a81e0fa5-5984-47ae-bb4f-108a2b92d373", "name": "lora_name", "type": "COMBO", "linkIds": [401], "pos": [2060.587890625, 830]}], "outputs": [{"id": "506ced76-78be-4eb2-ae70-eaa708a4cb98", "name": "IMAGE", "type": "IMAGE", "linkIds": [314], "localized_name": "IMAGE", "pos": [4260, 785]}], "widgets": [], "nodes": [{"id": 174, "type": "CLIPLoader", "pos": [2430, 60], "size": [380, 106], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 398}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "slot_index": 0, "links": [296, 305]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", "directory": "text_encoders"}]}, "widgets_values": ["qwen_2.5_vl_7b_fp8_scaled.safetensors", "qwen_image", "default"]}, {"id": 175, "type": "UNETLoader", "pos": [2430, -70], "size": [380, 82], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 397}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [306]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "UNETLoader", "models": [{"name": "qwen_image_fp8_e4m3fn.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors", "directory": "diffusion_models"}]}, "widgets_values": ["qwen_image_fp8_e4m3fn.safetensors", "default"]}, {"id": 177, "type": "ControlNetLoader", "pos": [2430, 330], "size": [380, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "control_net_name", "name": "control_net_name", "type": "COMBO", "widget": {"name": "control_net_name"}, "link": 400}], "outputs": [{"localized_name": "CONTROL_NET", "name": "CONTROL_NET", "type": "CONTROL_NET", "links": [301]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "ControlNetLoader", "models": [{"name": "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image-InstantX-ControlNets/resolve/main/split_files/controlnet/Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", "directory": "controlnet"}]}, "widgets_values": ["Qwen-Image-InstantX-ControlNet-Inpainting.safetensors"]}, {"id": 180, "type": "ModelSamplingAuraFlow", "pos": [3400, -110], "size": [310, 58], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 298}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [308]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "ModelSamplingAuraFlow"}, "widgets_values": [3.1000000000000005]}, {"id": 185, "type": "LoraLoaderModelOnly", "pos": [2870, -80], "size": [430, 82], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 306}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 401}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [298]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "Qwen-Image-Lightning-4steps-V1.0.safetensors", "url": "https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-4steps-V1.0.safetensors", "directory": "loras"}]}, "widgets_values": ["Qwen-Image-Lightning-4steps-V1.0.safetensors", 1]}, {"id": 190, "type": "KSampler", "pos": [3400, 10], "size": [310, 474], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 308}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 386}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 387}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 358}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [312]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "KSampler"}, "widgets_values": [375729975350303, "randomize", 4, 1, "euler", "simple", 1]}, {"id": 220, "type": "f93c215e-c393-460e-9534-ed2c3d8a652e", "pos": [2480, 1450], "size": [330, 100], "flags": {}, "order": 17, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 377}, {"name": "expand", "type": "INT", "widget": {"name": "expand"}, "link": null}, {"name": "blur_radius", "type": "INT", "widget": {"name": "blur_radius"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [374, 375, 376]}], "properties": {"proxyWidgets": [["-1", "expand"], ["-1", "blur_radius"]], "cnr_id": "comfy-core", "ver": "0.3.59"}, "widgets_values": [20, 31]}, {"id": 195, "type": "VAEEncode", "pos": [2950, 820], "size": [140, 46], "flags": {"collapsed": false}, "order": 11, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 371}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 317}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [358]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "VAEEncode"}, "widgets_values": []}, {"id": 181, "type": "ControlNetInpaintingAliMamaApply", "pos": [2940, 560], "size": [317.0093688964844, 206], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 299}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 300}, {"localized_name": "control_net", "name": "control_net", "type": "CONTROL_NET", "link": 301}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 384}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 385}, {"localized_name": "mask", "name": "mask", "type": "MASK", "link": 375}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}, {"localized_name": "start_percent", "name": "start_percent", "type": "FLOAT", "widget": {"name": "start_percent"}, "link": null}, {"localized_name": "end_percent", "name": "end_percent", "type": "FLOAT", "widget": {"name": "end_percent"}, "link": null}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [386]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [387]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ControlNetInpaintingAliMamaApply"}, "widgets_values": [1, 0, 1]}, {"id": 178, "type": "VAELoader", "pos": [2430, 220], "size": [380, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 399}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [313, 317, 384]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "VAELoader", "models": [{"name": "qwen_image_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", "directory": "vae"}]}, "widgets_values": ["qwen_image_vae.safetensors"]}, {"id": 182, "type": "CLIPTextEncode", "pos": [2850, 100], "size": [460, 164.31304931640625], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 305}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [299]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "CLIPTextEncode"}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 176, "type": "CLIPTextEncode", "pos": [2850, 310], "size": [460, 140], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 296}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [300]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "CLIPTextEncode"}, "widgets_values": [""], "color": "#223", "bgcolor": "#335"}, {"id": 191, "type": "VAEDecode", "pos": [3440, 580], "size": [250, 46], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 312}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 313}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [314, 323]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "VAEDecode"}, "widgets_values": []}, {"id": 219, "type": "2a4b2cc0-db37-4302-a067-da392f38f06b", "pos": [2480, 1260], "size": [280, 80], "flags": {}, "order": 16, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 365}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 366}, {"name": "value", "type": "INT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [377]}, {"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [369, 370, 371, 385]}], "properties": {"proxyWidgets": [["-1", "value"]], "cnr_id": "comfy-core", "ver": "0.3.65"}, "widgets_values": [1536]}, {"id": 207, "type": "MaskPreview", "pos": [3430, 1270], "size": [340, 430], "flags": {}, "order": 15, "mode": 4, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 376}], "outputs": [], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "MaskPreview"}, "widgets_values": []}, {"id": 203, "type": "PreviewImage", "pos": [2990, 1270], "size": [310, 430], "flags": {}, "order": 14, "mode": 4, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 370}], "outputs": [], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "PreviewImage"}, "widgets_values": []}, {"id": 200, "type": "ImageCompositeMasked", "pos": [3850, 1280], "size": [250, 150], "flags": {}, "order": 12, "mode": 4, "inputs": [{"localized_name": "destination", "name": "destination", "type": "IMAGE", "link": 369}, {"localized_name": "source", "name": "source", "type": "IMAGE", "link": 323}, {"localized_name": "mask", "name": "mask", "shape": 7, "type": "MASK", "link": 374}, {"localized_name": "x", "name": "x", "type": "INT", "widget": {"name": "x"}, "link": null}, {"localized_name": "y", "name": "y", "type": "INT", "widget": {"name": "y"}, "link": null}, {"localized_name": "resize_source", "name": "resize_source", "type": "BOOLEAN", "widget": {"name": "resize_source"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageCompositeMasked"}, "widgets_values": [0, 0, false]}, {"id": 202, "type": "ImagePadForOutpaint", "pos": [2490, 1030], "size": [270, 174], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 351}, {"localized_name": "left", "name": "left", "type": "INT", "widget": {"name": "left"}, "link": 392}, {"localized_name": "top", "name": "top", "type": "INT", "widget": {"name": "top"}, "link": 393}, {"localized_name": "right", "name": "right", "type": "INT", "widget": {"name": "right"}, "link": 394}, {"localized_name": "bottom", "name": "bottom", "type": "INT", "widget": {"name": "bottom"}, "link": 395}, {"localized_name": "feathering", "name": "feathering", "type": "INT", "widget": {"name": "feathering"}, "link": 396}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [366]}, {"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [365]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImagePadForOutpaint"}, "widgets_values": [0, 0, 0, 0, 0]}], "groups": [{"id": 12, "title": "For outpainting Ctrl-B to enable", "bounding": [2410, -190, 1770, 1970], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 7, "title": "Step 1 - Upload models", "bounding": [2420, -150, 400, 610], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 9, "title": "Step 3 - Prompt", "bounding": [2840, 30, 490, 430], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 10, "title": "4 steps lightning LoRA", "bounding": [2840, -150, 490, 160], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 11, "title": "Ctrl-B to enable it", "bounding": [2420, 940, 430, 460], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 298, "origin_id": 185, "origin_slot": 0, "target_id": 180, "target_slot": 0, "type": "MODEL"}, {"id": 306, "origin_id": 175, "origin_slot": 0, "target_id": 185, "target_slot": 0, "type": "MODEL"}, {"id": 308, "origin_id": 180, "origin_slot": 0, "target_id": 190, "target_slot": 0, "type": "MODEL"}, {"id": 386, "origin_id": 181, "origin_slot": 0, "target_id": 190, "target_slot": 1, "type": "CONDITIONING"}, {"id": 387, "origin_id": 181, "origin_slot": 1, "target_id": 190, "target_slot": 2, "type": "CONDITIONING"}, {"id": 358, "origin_id": 195, "origin_slot": 0, "target_id": 190, "target_slot": 3, "type": "LATENT"}, {"id": 377, "origin_id": 219, "origin_slot": 0, "target_id": 220, "target_slot": 0, "type": "MASK"}, {"id": 371, "origin_id": 219, "origin_slot": 1, "target_id": 195, "target_slot": 0, "type": "IMAGE"}, {"id": 317, "origin_id": 178, "origin_slot": 0, "target_id": 195, "target_slot": 1, "type": "VAE"}, {"id": 299, "origin_id": 182, "origin_slot": 0, "target_id": 181, "target_slot": 0, "type": "CONDITIONING"}, {"id": 300, "origin_id": 176, "origin_slot": 0, "target_id": 181, "target_slot": 1, "type": "CONDITIONING"}, {"id": 301, "origin_id": 177, "origin_slot": 0, "target_id": 181, "target_slot": 2, "type": "CONTROL_NET"}, {"id": 384, "origin_id": 178, "origin_slot": 0, "target_id": 181, "target_slot": 3, "type": "VAE"}, {"id": 385, "origin_id": 219, "origin_slot": 1, "target_id": 181, "target_slot": 4, "type": "IMAGE"}, {"id": 375, "origin_id": 220, "origin_slot": 0, "target_id": 181, "target_slot": 5, "type": "MASK"}, {"id": 305, "origin_id": 174, "origin_slot": 0, "target_id": 182, "target_slot": 0, "type": "CLIP"}, {"id": 296, "origin_id": 174, "origin_slot": 0, "target_id": 176, "target_slot": 0, "type": "CLIP"}, {"id": 312, "origin_id": 190, "origin_slot": 0, "target_id": 191, "target_slot": 0, "type": "LATENT"}, {"id": 313, "origin_id": 178, "origin_slot": 0, "target_id": 191, "target_slot": 1, "type": "VAE"}, {"id": 365, "origin_id": 202, "origin_slot": 1, "target_id": 219, "target_slot": 0, "type": "MASK"}, {"id": 366, "origin_id": 202, "origin_slot": 0, "target_id": 219, "target_slot": 1, "type": "IMAGE"}, {"id": 376, "origin_id": 220, "origin_slot": 0, "target_id": 207, "target_slot": 0, "type": "MASK"}, {"id": 370, "origin_id": 219, "origin_slot": 1, "target_id": 203, "target_slot": 0, "type": "IMAGE"}, {"id": 369, "origin_id": 219, "origin_slot": 1, "target_id": 200, "target_slot": 0, "type": "IMAGE"}, {"id": 323, "origin_id": 191, "origin_slot": 0, "target_id": 200, "target_slot": 1, "type": "IMAGE"}, {"id": 374, "origin_id": 220, "origin_slot": 0, "target_id": 200, "target_slot": 2, "type": "MASK"}, {"id": 351, "origin_id": -10, "origin_slot": 0, "target_id": 202, "target_slot": 0, "type": "IMAGE"}, {"id": 314, "origin_id": 191, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 392, "origin_id": -10, "origin_slot": 1, "target_id": 202, "target_slot": 1, "type": "INT"}, {"id": 393, "origin_id": -10, "origin_slot": 2, "target_id": 202, "target_slot": 2, "type": "INT"}, {"id": 394, "origin_id": -10, "origin_slot": 3, "target_id": 202, "target_slot": 3, "type": "INT"}, {"id": 395, "origin_id": -10, "origin_slot": 4, "target_id": 202, "target_slot": 4, "type": "INT"}, {"id": 396, "origin_id": -10, "origin_slot": 5, "target_id": 202, "target_slot": 5, "type": "INT"}, {"id": 397, "origin_id": -10, "origin_slot": 6, "target_id": 175, "target_slot": 0, "type": "COMBO"}, {"id": 398, "origin_id": -10, "origin_slot": 7, "target_id": 174, "target_slot": 0, "type": "COMBO"}, {"id": 399, "origin_id": -10, "origin_slot": 8, "target_id": 178, "target_slot": 0, "type": "COMBO"}, {"id": 400, "origin_id": -10, "origin_slot": 9, "target_id": 177, "target_slot": 0, "type": "COMBO"}, {"id": 401, "origin_id": -10, "origin_slot": 10, "target_id": 185, "target_slot": 1, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image generation and editing/Outpaint image"}, {"id": "f93c215e-c393-460e-9534-ed2c3d8a652e", "version": 1, "state": {"lastGroupId": 14, "lastNodeId": 255, "lastLinkId": 401, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Grow and Blur Mask", "inputNode": {"id": -10, "bounding": [290, 3536, 120, 100]}, "outputNode": {"id": -20, "bounding": [1130, 3536, 120, 60]}, "inputs": [{"id": "3ac60d5e-8f9d-4663-9b24-b3a15a3e9e20", "name": "mask", "type": "MASK", "linkIds": [279], "localized_name": "mask", "pos": [390, 3556]}, {"id": "d1ab0cf5-7062-41ac-9f4b-8c660fc4a714", "name": "expand", "type": "INT", "linkIds": [379], "pos": [390, 3576]}, {"id": "1a787af5-da9f-44c5-9f5a-3f71609ca0ef", "name": "blur_radius", "type": "INT", "linkIds": [380], "pos": [390, 3596]}], "outputs": [{"id": "1f97f683-13d3-4871-876d-678fca850d89", "name": "MASK", "type": "MASK", "linkIds": [378], "localized_name": "MASK", "pos": [1150, 3556]}], "widgets": [], "nodes": [{"id": 253, "type": "ImageToMask", "pos": [800, 3630], "size": [270, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 377}, {"localized_name": "channel", "name": "channel", "type": "COMBO", "widget": {"name": "channel"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [378]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageToMask"}, "widgets_values": ["red"]}, {"id": 251, "type": "MaskToImage", "pos": [780, 3470], "size": [260, 70], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 372}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [373]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "MaskToImage"}, "widgets_values": []}, {"id": 199, "type": "GrowMask", "pos": [470, 3460], "size": [270, 82], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 279}, {"localized_name": "expand", "name": "expand", "type": "INT", "widget": {"name": "expand"}, "link": 379}, {"localized_name": "tapered_corners", "name": "tapered_corners", "type": "BOOLEAN", "widget": {"name": "tapered_corners"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [372]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "GrowMask"}, "widgets_values": [20, true]}, {"id": 252, "type": "ImageBlur", "pos": [480, 3620], "size": [270, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 373}, {"localized_name": "blur_radius", "name": "blur_radius", "type": "INT", "widget": {"name": "blur_radius"}, "link": 380}, {"localized_name": "sigma", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [377]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageBlur"}, "widgets_values": [31, 1]}], "groups": [], "links": [{"id": 373, "origin_id": 251, "origin_slot": 0, "target_id": 252, "target_slot": 0, "type": "IMAGE"}, {"id": 377, "origin_id": 252, "origin_slot": 0, "target_id": 253, "target_slot": 0, "type": "IMAGE"}, {"id": 372, "origin_id": 199, "origin_slot": 0, "target_id": 251, "target_slot": 0, "type": "MASK"}, {"id": 279, "origin_id": -10, "origin_slot": 0, "target_id": 199, "target_slot": 0, "type": "MASK"}, {"id": 378, "origin_id": 253, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "MASK"}, {"id": 379, "origin_id": -10, "origin_slot": 1, "target_id": 199, "target_slot": 1, "type": "INT"}, {"id": 380, "origin_id": -10, "origin_slot": 2, "target_id": 252, "target_slot": 1, "type": "INT"}], "extra": {"workflowRendererVersion": "LG"}}, {"id": "2a4b2cc0-db37-4302-a067-da392f38f06b", "version": 1, "state": {"lastGroupId": 14, "lastNodeId": 255, "lastLinkId": 401, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Scale image and mask", "inputNode": {"id": -10, "bounding": [2110, 1406, 120, 100]}, "outputNode": {"id": -20, "bounding": [3320, 1406, 120, 80]}, "inputs": [{"id": "53ec80db-b075-446c-a79b-891d82ae3cf1", "name": "mask", "type": "MASK", "linkIds": [360], "localized_name": "mask", "pos": [2210, 1426]}, {"id": "37820e3d-f495-4b41-b0c6-58765a0c1766", "name": "image", "type": "IMAGE", "linkIds": [350], "localized_name": "image", "pos": [2210, 1446]}, {"id": "d388f5f1-7a36-4563-b104-9f7ec77f636d", "name": "value", "type": "INT", "linkIds": [365], "pos": [2210, 1466]}], "outputs": [{"id": "7ef75a31-2e69-4dce-8e13-76cd17b4c272", "name": "MASK", "type": "MASK", "linkIds": [364], "localized_name": "MASK", "pos": [3340, 1426]}, {"id": "36058145-b72c-4bd4-bb63-e2e22456d003", "name": "IMAGE", "type": "IMAGE", "linkIds": [352, 353, 354], "localized_name": "IMAGE", "pos": [3340, 1446]}], "widgets": [], "nodes": [{"id": 218, "type": "ImageToMask", "pos": [2990, 1540], "size": [270, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 363}, {"localized_name": "channel", "name": "channel", "type": "COMBO", "widget": {"name": "channel"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [364]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.65", "Node name for S&R": "ImageToMask"}, "widgets_values": ["red"]}, {"id": 216, "type": "ImageScaleToMaxDimension", "pos": [2610, 1570], "size": [281.2027282714844, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 361}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "largest_size", "name": "largest_size", "type": "INT", "widget": {"name": "largest_size"}, "link": 362}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [363]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageScaleToMaxDimension"}, "widgets_values": ["area", 1536]}, {"id": 217, "type": "MaskToImage", "pos": [2700, 1420], "size": [193.2779296875, 26], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 360}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [361]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.65", "Node name for S&R": "MaskToImage"}, "widgets_values": []}, {"id": 194, "type": "ImageScaleToMaxDimension", "pos": [2590, 1280], "size": [281.2027282714844, 82], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 350}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "largest_size", "name": "largest_size", "type": "INT", "widget": {"name": "largest_size"}, "link": 359}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [352, 353, 354]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageScaleToMaxDimension"}, "widgets_values": ["area", 1536]}, {"id": 215, "type": "PrimitiveInt", "pos": [2260, 1560], "size": [270, 82], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "INT", "widget": {"name": "value"}, "link": 365}], "outputs": [{"localized_name": "INT", "name": "INT", "type": "INT", "links": [359, 362]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.65", "Node name for S&R": "PrimitiveInt"}, "widgets_values": [1536, "fixed"]}], "groups": [], "links": [{"id": 363, "origin_id": 216, "origin_slot": 0, "target_id": 218, "target_slot": 0, "type": "IMAGE"}, {"id": 361, "origin_id": 217, "origin_slot": 0, "target_id": 216, "target_slot": 0, "type": "IMAGE"}, {"id": 362, "origin_id": 215, "origin_slot": 0, "target_id": 216, "target_slot": 2, "type": "INT"}, {"id": 359, "origin_id": 215, "origin_slot": 0, "target_id": 194, "target_slot": 2, "type": "INT"}, {"id": 360, "origin_id": -10, "origin_slot": 0, "target_id": 217, "target_slot": 0, "type": "MASK"}, {"id": 350, "origin_id": -10, "origin_slot": 1, "target_id": 194, "target_slot": 0, "type": "IMAGE"}, {"id": 364, "origin_id": 218, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "MASK"}, {"id": 352, "origin_id": 194, "origin_slot": 0, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 353, "origin_id": 194, "origin_slot": 0, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 354, "origin_id": 194, "origin_slot": 0, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 365, "origin_id": -10, "origin_slot": 2, "target_id": 215, "target_slot": 0, "type": "INT"}], "extra": {"workflowRendererVersion": "LG"}}]}, "config": {}, "extra": {"workflowRendererVersion": "LG", "ds": {"scale": 1.170393777345649, "offset": [-2589.3260157061272, -547.3616692627206]}}, "version": 0.4} +{ + "id": "8f79c27f-bec4-412e-9b82-7c5b3b778ecf", + "revision": 0, + "last_node_id": 255, + "last_link_id": 401, + "nodes": [ + { + "id": 224, + "type": "fbf07656-8ff8-4299-a3fc-7378e0f4a004", + "pos": [ + 3200, + 740 + ], + "size": [ + 400, + 460 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "name": "left", + "type": "INT", + "widget": { + "name": "left" + }, + "link": null + }, + { + "name": "top", + "type": "INT", + "widget": { + "name": "top" + }, + "link": null + }, + { + "name": "right", + "type": "INT", + "widget": { + "name": "right" + }, + "link": null + }, + { + "name": "bottom", + "type": "INT", + "widget": { + "name": "bottom" + }, + "link": null + }, + { + "name": "feathering", + "type": "INT", + "widget": { + "name": "feathering" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "name": "control_net_name", + "type": "COMBO", + "widget": { + "name": "control_net_name" + }, + "link": null + }, + { + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "182", + "text" + ], + [ + "-1", + "left" + ], + [ + "-1", + "top" + ], + [ + "-1", + "right" + ], + [ + "-1", + "bottom" + ], + [ + "-1", + "feathering" + ], + [ + "190", + "seed" + ], + [ + "190", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ], + [ + "-1", + "control_net_name" + ], + [ + "-1", + "lora_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.13.0" + }, + "widgets_values": [ + null, + 0, + 0, + 0, + 0, + 0, + null, + null, + "qwen_image_fp8_e4m3fn.safetensors", + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image_vae.safetensors", + "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", + "Qwen-Image-Lightning-4steps-V1.0.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "fbf07656-8ff8-4299-a3fc-7378e0f4a004", + "version": 1, + "state": { + "lastGroupId": 14, + "lastNodeId": 255, + "lastLinkId": 401, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image Outpainting (Qwen-Image)", + "inputNode": { + "id": -10, + "bounding": [ + 1940, + 610, + 140.587890625, + 260 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4240, + 765, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "466b9998-797f-4c6f-92e9-39120712c1a9", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 351 + ], + "localized_name": "image", + "pos": [ + 2060.587890625, + 630 + ] + }, + { + "id": "c5befee8-d6c4-493e-8ae1-e09d46268d10", + "name": "left", + "type": "INT", + "linkIds": [ + 392 + ], + "pos": [ + 2060.587890625, + 650 + ] + }, + { + "id": "c0b028a1-fcc0-4a54-9bdf-fa9e76992c40", + "name": "top", + "type": "INT", + "linkIds": [ + 393 + ], + "pos": [ + 2060.587890625, + 670 + ] + }, + { + "id": "22e43278-694c-410f-9043-f88b8dfdca28", + "name": "right", + "type": "INT", + "linkIds": [ + 394 + ], + "pos": [ + 2060.587890625, + 690 + ] + }, + { + "id": "f19fec20-a43d-4562-a0f8-bd6955091c1b", + "name": "bottom", + "type": "INT", + "linkIds": [ + 395 + ], + "pos": [ + 2060.587890625, + 710 + ] + }, + { + "id": "ba832b36-2199-4e1e-a28d-5f2e8acc99a3", + "name": "feathering", + "type": "INT", + "linkIds": [ + 396 + ], + "pos": [ + 2060.587890625, + 730 + ] + }, + { + "id": "437d6324-2d3c-4c50-ac21-1ea9aab57f4e", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 397 + ], + "pos": [ + 2060.587890625, + 750 + ] + }, + { + "id": "4d58dde7-4402-45d5-ade9-9c41e99e0757", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 398 + ], + "pos": [ + 2060.587890625, + 770 + ] + }, + { + "id": "a7558cc4-d4c4-4b4a-b2a3-0d7229a8ff65", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 399 + ], + "pos": [ + 2060.587890625, + 790 + ] + }, + { + "id": "7d8ffb86-2ff3-49fc-8e96-94d3e530f154", + "name": "control_net_name", + "type": "COMBO", + "linkIds": [ + 400 + ], + "pos": [ + 2060.587890625, + 810 + ] + }, + { + "id": "a81e0fa5-5984-47ae-bb4f-108a2b92d373", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 401 + ], + "pos": [ + 2060.587890625, + 830 + ] + } + ], + "outputs": [ + { + "id": "506ced76-78be-4eb2-ae70-eaa708a4cb98", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 314 + ], + "localized_name": "IMAGE", + "pos": [ + 4260, + 785 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 174, + "type": "CLIPLoader", + "pos": [ + 2430, + 60 + ], + "size": [ + 380, + 106 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 398 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 296, + 305 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image", + "default" + ] + }, + { + "id": 175, + "type": "UNETLoader", + "pos": [ + 2430, + -70 + ], + "size": [ + 380, + 82 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 397 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 306 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "qwen_image_fp8_e4m3fn.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "qwen_image_fp8_e4m3fn.safetensors", + "default" + ] + }, + { + "id": 177, + "type": "ControlNetLoader", + "pos": [ + 2430, + 330 + ], + "size": [ + 380, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "control_net_name", + "name": "control_net_name", + "type": "COMBO", + "widget": { + "name": "control_net_name" + }, + "link": 400 + } + ], + "outputs": [ + { + "localized_name": "CONTROL_NET", + "name": "CONTROL_NET", + "type": "CONTROL_NET", + "links": [ + 301 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "ControlNetLoader", + "models": [ + { + "name": "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image-InstantX-ControlNets/resolve/main/split_files/controlnet/Qwen-Image-InstantX-ControlNet-Inpainting.safetensors", + "directory": "controlnet" + } + ] + }, + "widgets_values": [ + "Qwen-Image-InstantX-ControlNet-Inpainting.safetensors" + ] + }, + { + "id": 180, + "type": "ModelSamplingAuraFlow", + "pos": [ + 3400, + -110 + ], + "size": [ + 310, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 298 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 308 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "ModelSamplingAuraFlow" + }, + "widgets_values": [ + 3.1000000000000005 + ] + }, + { + "id": 185, + "type": "LoraLoaderModelOnly", + "pos": [ + 2870, + -80 + ], + "size": [ + 430, + 82 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 306 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 401 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 298 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "Qwen-Image-Lightning-4steps-V1.0.safetensors", + "url": "https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-4steps-V1.0.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "Qwen-Image-Lightning-4steps-V1.0.safetensors", + 1 + ] + }, + { + "id": 190, + "type": "KSampler", + "pos": [ + 3400, + 10 + ], + "size": [ + 310, + 474 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 308 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 386 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 387 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 358 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 312 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 375729975350303, + "randomize", + 4, + 1, + "euler", + "simple", + 1 + ] + }, + { + "id": 220, + "type": "f93c215e-c393-460e-9534-ed2c3d8a652e", + "pos": [ + 2480, + 1450 + ], + "size": [ + 330, + 100 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 377 + }, + { + "name": "expand", + "type": "INT", + "widget": { + "name": "expand" + }, + "link": null + }, + { + "name": "blur_radius", + "type": "INT", + "widget": { + "name": "blur_radius" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 374, + 375, + 376 + ] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "expand" + ], + [ + "-1", + "blur_radius" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.3.59" + }, + "widgets_values": [ + 20, + 31 + ] + }, + { + "id": 195, + "type": "VAEEncode", + "pos": [ + 2950, + 820 + ], + "size": [ + 140, + 46 + ], + "flags": { + "collapsed": false + }, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 371 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 317 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 358 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "VAEEncode" + }, + "widgets_values": [] + }, + { + "id": 181, + "type": "ControlNetInpaintingAliMamaApply", + "pos": [ + 2940, + 560 + ], + "size": [ + 317.0093688964844, + 206 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 299 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 300 + }, + { + "localized_name": "control_net", + "name": "control_net", + "type": "CONTROL_NET", + "link": 301 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 384 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 385 + }, + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 375 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "localized_name": "start_percent", + "name": "start_percent", + "type": "FLOAT", + "widget": { + "name": "start_percent" + }, + "link": null + }, + { + "localized_name": "end_percent", + "name": "end_percent", + "type": "FLOAT", + "widget": { + "name": "end_percent" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 386 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 387 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ControlNetInpaintingAliMamaApply" + }, + "widgets_values": [ + 1, + 0, + 1 + ] + }, + { + "id": 178, + "type": "VAELoader", + "pos": [ + 2430, + 220 + ], + "size": [ + 380, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 399 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 313, + 317, + 384 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "qwen_image_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "qwen_image_vae.safetensors" + ] + }, + { + "id": 182, + "type": "CLIPTextEncode", + "pos": [ + 2850, + 100 + ], + "size": [ + 460, + 164.31304931640625 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 305 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 299 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 176, + "type": "CLIPTextEncode", + "pos": [ + 2850, + 310 + ], + "size": [ + 460, + 140 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 296 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 300 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ], + "color": "#223", + "bgcolor": "#335" + }, + { + "id": 191, + "type": "VAEDecode", + "pos": [ + 3440, + 580 + ], + "size": [ + 250, + 46 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 312 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 313 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 314, + 323 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "VAEDecode" + }, + "widgets_values": [] + }, + { + "id": 219, + "type": "2a4b2cc0-db37-4302-a067-da392f38f06b", + "pos": [ + 2480, + 1260 + ], + "size": [ + 280, + 80 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 365 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 366 + }, + { + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 377 + ] + }, + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 369, + 370, + 371, + 385 + ] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "value" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.3.65" + }, + "widgets_values": [ + 1536 + ] + }, + { + "id": 207, + "type": "MaskPreview", + "pos": [ + 3430, + 1270 + ], + "size": [ + 340, + 430 + ], + "flags": {}, + "order": 15, + "mode": 4, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 376 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "MaskPreview" + }, + "widgets_values": [] + }, + { + "id": 203, + "type": "PreviewImage", + "pos": [ + 2990, + 1270 + ], + "size": [ + 310, + 430 + ], + "flags": {}, + "order": 14, + "mode": 4, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 370 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "PreviewImage" + }, + "widgets_values": [] + }, + { + "id": 200, + "type": "ImageCompositeMasked", + "pos": [ + 3850, + 1280 + ], + "size": [ + 250, + 150 + ], + "flags": {}, + "order": 12, + "mode": 4, + "inputs": [ + { + "localized_name": "destination", + "name": "destination", + "type": "IMAGE", + "link": 369 + }, + { + "localized_name": "source", + "name": "source", + "type": "IMAGE", + "link": 323 + }, + { + "localized_name": "mask", + "name": "mask", + "shape": 7, + "type": "MASK", + "link": 374 + }, + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": null + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": null + }, + { + "localized_name": "resize_source", + "name": "resize_source", + "type": "BOOLEAN", + "widget": { + "name": "resize_source" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageCompositeMasked" + }, + "widgets_values": [ + 0, + 0, + false + ] + }, + { + "id": 202, + "type": "ImagePadForOutpaint", + "pos": [ + 2490, + 1030 + ], + "size": [ + 270, + 174 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 351 + }, + { + "localized_name": "left", + "name": "left", + "type": "INT", + "widget": { + "name": "left" + }, + "link": 392 + }, + { + "localized_name": "top", + "name": "top", + "type": "INT", + "widget": { + "name": "top" + }, + "link": 393 + }, + { + "localized_name": "right", + "name": "right", + "type": "INT", + "widget": { + "name": "right" + }, + "link": 394 + }, + { + "localized_name": "bottom", + "name": "bottom", + "type": "INT", + "widget": { + "name": "bottom" + }, + "link": 395 + }, + { + "localized_name": "feathering", + "name": "feathering", + "type": "INT", + "widget": { + "name": "feathering" + }, + "link": 396 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 366 + ] + }, + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 365 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImagePadForOutpaint" + }, + "widgets_values": [ + 0, + 0, + 0, + 0, + 0 + ] + } + ], + "groups": [ + { + "id": 12, + "title": "For outpainting Ctrl-B to enable", + "bounding": [ + 2410, + -190, + 1770, + 1970 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Step 1 - Upload models", + "bounding": [ + 2420, + -150, + 400, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 9, + "title": "Step 3 - Prompt", + "bounding": [ + 2840, + 30, + 490, + 430 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 10, + "title": "4 steps lightning LoRA", + "bounding": [ + 2840, + -150, + 490, + 160 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 11, + "title": "Ctrl-B to enable it", + "bounding": [ + 2420, + 940, + 430, + 460 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 298, + "origin_id": 185, + "origin_slot": 0, + "target_id": 180, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 306, + "origin_id": 175, + "origin_slot": 0, + "target_id": 185, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 308, + "origin_id": 180, + "origin_slot": 0, + "target_id": 190, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 386, + "origin_id": 181, + "origin_slot": 0, + "target_id": 190, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 387, + "origin_id": 181, + "origin_slot": 1, + "target_id": 190, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 358, + "origin_id": 195, + "origin_slot": 0, + "target_id": 190, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 377, + "origin_id": 219, + "origin_slot": 0, + "target_id": 220, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 371, + "origin_id": 219, + "origin_slot": 1, + "target_id": 195, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 317, + "origin_id": 178, + "origin_slot": 0, + "target_id": 195, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 299, + "origin_id": 182, + "origin_slot": 0, + "target_id": 181, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 300, + "origin_id": 176, + "origin_slot": 0, + "target_id": 181, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 301, + "origin_id": 177, + "origin_slot": 0, + "target_id": 181, + "target_slot": 2, + "type": "CONTROL_NET" + }, + { + "id": 384, + "origin_id": 178, + "origin_slot": 0, + "target_id": 181, + "target_slot": 3, + "type": "VAE" + }, + { + "id": 385, + "origin_id": 219, + "origin_slot": 1, + "target_id": 181, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 375, + "origin_id": 220, + "origin_slot": 0, + "target_id": 181, + "target_slot": 5, + "type": "MASK" + }, + { + "id": 305, + "origin_id": 174, + "origin_slot": 0, + "target_id": 182, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 296, + "origin_id": 174, + "origin_slot": 0, + "target_id": 176, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 312, + "origin_id": 190, + "origin_slot": 0, + "target_id": 191, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 313, + "origin_id": 178, + "origin_slot": 0, + "target_id": 191, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 365, + "origin_id": 202, + "origin_slot": 1, + "target_id": 219, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 366, + "origin_id": 202, + "origin_slot": 0, + "target_id": 219, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 376, + "origin_id": 220, + "origin_slot": 0, + "target_id": 207, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 370, + "origin_id": 219, + "origin_slot": 1, + "target_id": 203, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 369, + "origin_id": 219, + "origin_slot": 1, + "target_id": 200, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 323, + "origin_id": 191, + "origin_slot": 0, + "target_id": 200, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 374, + "origin_id": 220, + "origin_slot": 0, + "target_id": 200, + "target_slot": 2, + "type": "MASK" + }, + { + "id": 351, + "origin_id": -10, + "origin_slot": 0, + "target_id": 202, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 314, + "origin_id": 191, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 392, + "origin_id": -10, + "origin_slot": 1, + "target_id": 202, + "target_slot": 1, + "type": "INT" + }, + { + "id": 393, + "origin_id": -10, + "origin_slot": 2, + "target_id": 202, + "target_slot": 2, + "type": "INT" + }, + { + "id": 394, + "origin_id": -10, + "origin_slot": 3, + "target_id": 202, + "target_slot": 3, + "type": "INT" + }, + { + "id": 395, + "origin_id": -10, + "origin_slot": 4, + "target_id": 202, + "target_slot": 4, + "type": "INT" + }, + { + "id": 396, + "origin_id": -10, + "origin_slot": 5, + "target_id": 202, + "target_slot": 5, + "type": "INT" + }, + { + "id": 397, + "origin_id": -10, + "origin_slot": 6, + "target_id": 175, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 398, + "origin_id": -10, + "origin_slot": 7, + "target_id": 174, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 399, + "origin_id": -10, + "origin_slot": 8, + "target_id": 178, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 400, + "origin_id": -10, + "origin_slot": 9, + "target_id": 177, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 401, + "origin_id": -10, + "origin_slot": 10, + "target_id": 185, + "target_slot": 1, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Outpaint image" + }, + { + "id": "f93c215e-c393-460e-9534-ed2c3d8a652e", + "version": 1, + "state": { + "lastGroupId": 14, + "lastNodeId": 255, + "lastLinkId": 401, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Grow and Blur Mask", + "inputNode": { + "id": -10, + "bounding": [ + 290, + 3536, + 120, + 100 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1130, + 3536, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "3ac60d5e-8f9d-4663-9b24-b3a15a3e9e20", + "name": "mask", + "type": "MASK", + "linkIds": [ + 279 + ], + "localized_name": "mask", + "pos": [ + 390, + 3556 + ] + }, + { + "id": "d1ab0cf5-7062-41ac-9f4b-8c660fc4a714", + "name": "expand", + "type": "INT", + "linkIds": [ + 379 + ], + "pos": [ + 390, + 3576 + ] + }, + { + "id": "1a787af5-da9f-44c5-9f5a-3f71609ca0ef", + "name": "blur_radius", + "type": "INT", + "linkIds": [ + 380 + ], + "pos": [ + 390, + 3596 + ] + } + ], + "outputs": [ + { + "id": "1f97f683-13d3-4871-876d-678fca850d89", + "name": "MASK", + "type": "MASK", + "linkIds": [ + 378 + ], + "localized_name": "MASK", + "pos": [ + 1150, + 3556 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 253, + "type": "ImageToMask", + "pos": [ + 800, + 3630 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 377 + }, + { + "localized_name": "channel", + "name": "channel", + "type": "COMBO", + "widget": { + "name": "channel" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 378 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageToMask" + }, + "widgets_values": [ + "red" + ] + }, + { + "id": 251, + "type": "MaskToImage", + "pos": [ + 780, + 3470 + ], + "size": [ + 260, + 70 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 372 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 373 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "MaskToImage" + }, + "widgets_values": [] + }, + { + "id": 199, + "type": "GrowMask", + "pos": [ + 470, + 3460 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 279 + }, + { + "localized_name": "expand", + "name": "expand", + "type": "INT", + "widget": { + "name": "expand" + }, + "link": 379 + }, + { + "localized_name": "tapered_corners", + "name": "tapered_corners", + "type": "BOOLEAN", + "widget": { + "name": "tapered_corners" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 372 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "GrowMask" + }, + "widgets_values": [ + 20, + true + ] + }, + { + "id": 252, + "type": "ImageBlur", + "pos": [ + 480, + 3620 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 373 + }, + { + "localized_name": "blur_radius", + "name": "blur_radius", + "type": "INT", + "widget": { + "name": "blur_radius" + }, + "link": 380 + }, + { + "localized_name": "sigma", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 377 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageBlur" + }, + "widgets_values": [ + 31, + 1 + ] + } + ], + "groups": [], + "links": [ + { + "id": 373, + "origin_id": 251, + "origin_slot": 0, + "target_id": 252, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 377, + "origin_id": 252, + "origin_slot": 0, + "target_id": 253, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 372, + "origin_id": 199, + "origin_slot": 0, + "target_id": 251, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 279, + "origin_id": -10, + "origin_slot": 0, + "target_id": 199, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 378, + "origin_id": 253, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 379, + "origin_id": -10, + "origin_slot": 1, + "target_id": 199, + "target_slot": 1, + "type": "INT" + }, + { + "id": 380, + "origin_id": -10, + "origin_slot": 2, + "target_id": 252, + "target_slot": 1, + "type": "INT" + } + ], + "extra": { + "workflowRendererVersion": "LG" + } + }, + { + "id": "2a4b2cc0-db37-4302-a067-da392f38f06b", + "version": 1, + "state": { + "lastGroupId": 14, + "lastNodeId": 255, + "lastLinkId": 401, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Scale image and mask", + "inputNode": { + "id": -10, + "bounding": [ + 2110, + 1406, + 120, + 100 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 3320, + 1406, + 120, + 80 + ] + }, + "inputs": [ + { + "id": "53ec80db-b075-446c-a79b-891d82ae3cf1", + "name": "mask", + "type": "MASK", + "linkIds": [ + 360 + ], + "localized_name": "mask", + "pos": [ + 2210, + 1426 + ] + }, + { + "id": "37820e3d-f495-4b41-b0c6-58765a0c1766", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 350 + ], + "localized_name": "image", + "pos": [ + 2210, + 1446 + ] + }, + { + "id": "d388f5f1-7a36-4563-b104-9f7ec77f636d", + "name": "value", + "type": "INT", + "linkIds": [ + 365 + ], + "pos": [ + 2210, + 1466 + ] + } + ], + "outputs": [ + { + "id": "7ef75a31-2e69-4dce-8e13-76cd17b4c272", + "name": "MASK", + "type": "MASK", + "linkIds": [ + 364 + ], + "localized_name": "MASK", + "pos": [ + 3340, + 1426 + ] + }, + { + "id": "36058145-b72c-4bd4-bb63-e2e22456d003", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 352, + 353, + 354 + ], + "localized_name": "IMAGE", + "pos": [ + 3340, + 1446 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 218, + "type": "ImageToMask", + "pos": [ + 2990, + 1540 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 363 + }, + { + "localized_name": "channel", + "name": "channel", + "type": "COMBO", + "widget": { + "name": "channel" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 364 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.65", + "Node name for S&R": "ImageToMask" + }, + "widgets_values": [ + "red" + ] + }, + { + "id": 216, + "type": "ImageScaleToMaxDimension", + "pos": [ + 2610, + 1570 + ], + "size": [ + 281.2027282714844, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 361 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "largest_size", + "name": "largest_size", + "type": "INT", + "widget": { + "name": "largest_size" + }, + "link": 362 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 363 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageScaleToMaxDimension" + }, + "widgets_values": [ + "area", + 1536 + ] + }, + { + "id": 217, + "type": "MaskToImage", + "pos": [ + 2700, + 1420 + ], + "size": [ + 193.2779296875, + 26 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 360 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 361 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.65", + "Node name for S&R": "MaskToImage" + }, + "widgets_values": [] + }, + { + "id": 194, + "type": "ImageScaleToMaxDimension", + "pos": [ + 2590, + 1280 + ], + "size": [ + 281.2027282714844, + 82 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 350 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "largest_size", + "name": "largest_size", + "type": "INT", + "widget": { + "name": "largest_size" + }, + "link": 359 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 352, + 353, + 354 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageScaleToMaxDimension" + }, + "widgets_values": [ + "area", + 1536 + ] + }, + { + "id": 215, + "type": "PrimitiveInt", + "pos": [ + 2260, + 1560 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 365 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 359, + 362 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.65", + "Node name for S&R": "PrimitiveInt" + }, + "widgets_values": [ + 1536, + "fixed" + ] + } + ], + "groups": [], + "links": [ + { + "id": 363, + "origin_id": 216, + "origin_slot": 0, + "target_id": 218, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 361, + "origin_id": 217, + "origin_slot": 0, + "target_id": 216, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 362, + "origin_id": 215, + "origin_slot": 0, + "target_id": 216, + "target_slot": 2, + "type": "INT" + }, + { + "id": 359, + "origin_id": 215, + "origin_slot": 0, + "target_id": 194, + "target_slot": 2, + "type": "INT" + }, + { + "id": 360, + "origin_id": -10, + "origin_slot": 0, + "target_id": 217, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 350, + "origin_id": -10, + "origin_slot": 1, + "target_id": 194, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 364, + "origin_id": 218, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 352, + "origin_id": 194, + "origin_slot": 0, + "target_id": -20, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 353, + "origin_id": 194, + "origin_slot": 0, + "target_id": -20, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 354, + "origin_id": 194, + "origin_slot": 0, + "target_id": -20, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 365, + "origin_id": -10, + "origin_slot": 2, + "target_id": 215, + "target_slot": 0, + "type": "INT" + } + ], + "extra": { + "workflowRendererVersion": "LG" + } + } + ] + }, + "config": {}, + "extra": { + "workflowRendererVersion": "LG", + "ds": { + "scale": 1.170393777345649, + "offset": [ + -2589.3260157061272, + -547.3616692627206 + ] + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/blueprints/Image Upscale(Z-image-Turbo).json b/blueprints/Image Upscale(Z-image-Turbo).json index a67d6a2d8..0d2b6e240 100644 --- a/blueprints/Image Upscale(Z-image-Turbo).json +++ b/blueprints/Image Upscale(Z-image-Turbo).json @@ -1 +1,1314 @@ -{"id": "bf8108f3-d857-46c9-aef5-0e8ad2a64bf5", "revision": 0, "last_node_id": 95, "last_link_id": 115, "nodes": [{"id": 87, "type": "dd15cfd3-cd53-428c-b3e2-33ed4ff8fa78", "pos": [960.6668984200231, 332.66676187423354], "size": [400, 469.9869791666667], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}, {"label": "upscale_model", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": null}, {"name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE_1", "name": "IMAGE_1", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["67", "text"], ["69", "seed"], ["69", "control_after_generate"], ["-1", "denoise"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"], ["-1", "model_name"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": [null, null, null, 0.33, "z_image_turbo_bf16.safetensors", "qwen_3_4b.safetensors", "ae.safetensors", "RealESRGAN_x4plus.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "dd15cfd3-cd53-428c-b3e2-33ed4ff8fa78", "version": 1, "state": {"lastGroupId": 5, "lastNodeId": 95, "lastLinkId": 115, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image Upscale(Z-image-Turbo)", "inputNode": {"id": -10, "bounding": [-150, 390, 125.224609375, 160]}, "outputNode": {"id": -20, "bounding": [2070, 490, 120, 60]}, "inputs": [{"id": "e9a14390-4f93-4065-8b02-323f999527c0", "name": "image", "type": "IMAGE", "linkIds": [86], "localized_name": "image", "pos": [-44.775390625, 410]}, {"id": "c5655e11-9531-4949-996c-958b5fe92085", "name": "unet_name", "type": "COMBO", "linkIds": [109], "pos": [-44.775390625, 430]}, {"id": "82576043-dd69-4604-b572-09fabb6e602d", "name": "clip_name", "type": "COMBO", "linkIds": [110], "pos": [-44.775390625, 450]}, {"id": "59e20fb5-cd61-4d4b-a1fd-15a90c7ba6c2", "name": "vae_name", "type": "COMBO", "linkIds": [111], "pos": [-44.775390625, 470]}, {"id": "adc35153-dc52-4bac-be7e-9da19471f441", "name": "model_name", "type": "COMBO", "linkIds": [112], "label": "upscale_model", "pos": [-44.775390625, 490]}, {"id": "c1b2f097-616e-4420-93c8-04eb79f4ba1e", "name": "denoise", "type": "FLOAT", "linkIds": [115], "pos": [-44.775390625, 510]}], "outputs": [{"id": "f138a0aa-489a-42e1-92f7-e3747688c94d", "name": "IMAGE_1", "type": "IMAGE", "linkIds": [97, 103], "localized_name": "IMAGE_1", "label": "IMAGE", "pos": [2090, 510]}], "widgets": [], "nodes": [{"id": 71, "type": "CLIPTextEncode", "pos": [648.333324162179, 398.3333435177784], "size": [491.6666666666667, 150], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 82}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [83]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#323", "bgcolor": "#535"}, {"id": 79, "type": "ImageUpscaleWithModel", "pos": [623.3333541162552, 714.9999406294688], "size": [233.5689453125, 60], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "upscale_model", "name": "upscale_model", "type": "UPSCALE_MODEL", "link": 87}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 88}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [92]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "ImageUpscaleWithModel"}, "widgets_values": []}, {"id": 80, "type": "VAEEncode", "pos": [1173.3330331592938, 631.6665944654844], "size": [187.5, 60], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 93}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 90}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [91]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "VAEEncode"}, "widgets_values": []}, {"id": 81, "type": "ImageScaleBy", "pos": [865.0000410901742, 714.9999828835583], "size": [225, 95.546875], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 92}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "scale_by", "name": "scale_by", "type": "FLOAT", "widget": {"name": "scale_by"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [93]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "ImageScaleBy"}, "widgets_values": ["lanczos", 0.5]}, {"id": 66, "type": "UNETLoader", "pos": [280, -20], "size": [323.984375, 118.64583333333334], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 109}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [104]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "UNETLoader", "models": [{"name": "z_image_turbo_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["z_image_turbo_bf16.safetensors", "default"]}, {"id": 62, "type": "CLIPLoader", "pos": [280, 140], "size": [323.984375, 150.65104166666669], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 110}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [78, 82]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_3_4b.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_3_4b.safetensors", "lumina2", "default"]}, {"id": 67, "type": "CLIPTextEncode", "pos": [650.621298596813, -33.81729273975067], "size": [491.9791666666667, 377.98177083333337], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 78}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [75]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["masterpiece, 8k"], "color": "#232", "bgcolor": "#353"}, {"id": 63, "type": "VAELoader", "pos": [280, 330], "size": [323.984375, 83.99739583333334], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 111}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [73, 90]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "VAELoader", "models": [{"name": "ae.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ae.safetensors"]}, {"id": 76, "type": "UpscaleModelLoader", "pos": [264.07395879037364, 704.8118881098496], "size": [323.984375, 83.99739583333334], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": 112}], "outputs": [{"localized_name": "UPSCALE_MODEL", "name": "UPSCALE_MODEL", "type": "UPSCALE_MODEL", "links": [87]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "UpscaleModelLoader", "models": [{"name": "RealESRGAN_x4plus.safetensors", "url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors", "directory": "upscale_models"}]}, "widgets_values": ["RealESRGAN_x4plus.safetensors"]}, {"id": 70, "type": "ModelSamplingAuraFlow", "pos": [1200, -50], "size": [371.9791666666667, 80.1171875], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 104}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [74]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "ModelSamplingAuraFlow", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 65, "type": "VAEDecode", "pos": [1610, -50], "size": [251.97916666666669, 72.13541666666667], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 72}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 73}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [97, 103]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 78, "type": "ImageScaleToTotalPixels", "pos": [260, 850], "size": [325, 122.21354166666667], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 86}, {"localized_name": "upscale_method", "name": "upscale_method", "type": "COMBO", "widget": {"name": "upscale_method"}, "link": null}, {"localized_name": "megapixels", "name": "megapixels", "type": "FLOAT", "widget": {"name": "megapixels"}, "link": null}, {"localized_name": "resolution_steps", "name": "resolution_steps", "type": "INT", "widget": {"name": "resolution_steps"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [88]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "ImageScaleToTotalPixels"}, "widgets_values": ["lanczos", 1, 1]}, {"id": 69, "type": "KSampler", "pos": [1200, 80], "size": [366.6666666666667, 474], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 74}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 75}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 83}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 91}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": 115}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [72]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1098688918602660, "randomize", 5, 1, "dpmpp_2m_sde", "beta", 0.33]}], "groups": [{"id": 3, "title": "Prompt", "bounding": [640, -90, 508.64583333333337, 662.0666813520016], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 5, "title": "Models", "bounding": [260, -90, 344.6965254233087, 516.414685926878], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 104, "origin_id": 66, "origin_slot": 0, "target_id": 70, "target_slot": 0, "type": "MODEL"}, {"id": 82, "origin_id": 62, "origin_slot": 0, "target_id": 71, "target_slot": 0, "type": "CLIP"}, {"id": 87, "origin_id": 76, "origin_slot": 0, "target_id": 79, "target_slot": 0, "type": "UPSCALE_MODEL"}, {"id": 88, "origin_id": 78, "origin_slot": 0, "target_id": 79, "target_slot": 1, "type": "IMAGE"}, {"id": 93, "origin_id": 81, "origin_slot": 0, "target_id": 80, "target_slot": 0, "type": "IMAGE"}, {"id": 90, "origin_id": 63, "origin_slot": 0, "target_id": 80, "target_slot": 1, "type": "VAE"}, {"id": 92, "origin_id": 79, "origin_slot": 0, "target_id": 81, "target_slot": 0, "type": "IMAGE"}, {"id": 74, "origin_id": 70, "origin_slot": 0, "target_id": 69, "target_slot": 0, "type": "MODEL"}, {"id": 75, "origin_id": 67, "origin_slot": 0, "target_id": 69, "target_slot": 1, "type": "CONDITIONING"}, {"id": 83, "origin_id": 71, "origin_slot": 0, "target_id": 69, "target_slot": 2, "type": "CONDITIONING"}, {"id": 91, "origin_id": 80, "origin_slot": 0, "target_id": 69, "target_slot": 3, "type": "LATENT"}, {"id": 72, "origin_id": 69, "origin_slot": 0, "target_id": 65, "target_slot": 0, "type": "LATENT"}, {"id": 73, "origin_id": 63, "origin_slot": 0, "target_id": 65, "target_slot": 1, "type": "VAE"}, {"id": 78, "origin_id": 62, "origin_slot": 0, "target_id": 67, "target_slot": 0, "type": "CLIP"}, {"id": 86, "origin_id": -10, "origin_slot": 0, "target_id": 78, "target_slot": 0, "type": "IMAGE"}, {"id": 97, "origin_id": 65, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 103, "origin_id": 65, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 109, "origin_id": -10, "origin_slot": 1, "target_id": 66, "target_slot": 0, "type": "COMBO"}, {"id": 110, "origin_id": -10, "origin_slot": 2, "target_id": 62, "target_slot": 0, "type": "COMBO"}, {"id": 111, "origin_id": -10, "origin_slot": 3, "target_id": 63, "target_slot": 0, "type": "COMBO"}, {"id": 112, "origin_id": -10, "origin_slot": 4, "target_id": 76, "target_slot": 0, "type": "COMBO"}, {"id": 115, "origin_id": -10, "origin_slot": 5, "target_id": 69, "target_slot": 9, "type": "FLOAT"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image generation and editing/Enhance"}]}, "config": {}, "extra": {"workflowRendererVersion": "LG"}, "version": 0.4} +{ + "id": "bf8108f3-d857-46c9-aef5-0e8ad2a64bf5", + "revision": 0, + "last_node_id": 95, + "last_link_id": 115, + "nodes": [ + { + "id": 87, + "type": "dd15cfd3-cd53-428c-b3e2-33ed4ff8fa78", + "pos": [ + 960.6668984200231, + 332.66676187423354 + ], + "size": [ + 400, + 469.9869791666667 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "label": "upscale_model", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": null + }, + { + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE_1", + "name": "IMAGE_1", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "67", + "text" + ], + [ + "69", + "seed" + ], + [ + "69", + "control_after_generate" + ], + [ + "-1", + "denoise" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ], + [ + "-1", + "model_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.14.1" + }, + "widgets_values": [ + null, + null, + null, + 0.33, + "z_image_turbo_bf16.safetensors", + "qwen_3_4b.safetensors", + "ae.safetensors", + "RealESRGAN_x4plus.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "dd15cfd3-cd53-428c-b3e2-33ed4ff8fa78", + "version": 1, + "state": { + "lastGroupId": 5, + "lastNodeId": 95, + "lastLinkId": 115, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Image Upscale(Z-image-Turbo)", + "inputNode": { + "id": -10, + "bounding": [ + -150, + 390, + 125.224609375, + 160 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 2070, + 490, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "e9a14390-4f93-4065-8b02-323f999527c0", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 86 + ], + "localized_name": "image", + "pos": [ + -44.775390625, + 410 + ] + }, + { + "id": "c5655e11-9531-4949-996c-958b5fe92085", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 109 + ], + "pos": [ + -44.775390625, + 430 + ] + }, + { + "id": "82576043-dd69-4604-b572-09fabb6e602d", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 110 + ], + "pos": [ + -44.775390625, + 450 + ] + }, + { + "id": "59e20fb5-cd61-4d4b-a1fd-15a90c7ba6c2", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 111 + ], + "pos": [ + -44.775390625, + 470 + ] + }, + { + "id": "adc35153-dc52-4bac-be7e-9da19471f441", + "name": "model_name", + "type": "COMBO", + "linkIds": [ + 112 + ], + "label": "upscale_model", + "pos": [ + -44.775390625, + 490 + ] + }, + { + "id": "c1b2f097-616e-4420-93c8-04eb79f4ba1e", + "name": "denoise", + "type": "FLOAT", + "linkIds": [ + 115 + ], + "pos": [ + -44.775390625, + 510 + ] + } + ], + "outputs": [ + { + "id": "f138a0aa-489a-42e1-92f7-e3747688c94d", + "name": "IMAGE_1", + "type": "IMAGE", + "linkIds": [ + 97, + 103 + ], + "localized_name": "IMAGE_1", + "label": "IMAGE", + "pos": [ + 2090, + 510 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 71, + "type": "CLIPTextEncode", + "pos": [ + 648.333324162179, + 398.3333435177784 + ], + "size": [ + 491.6666666666667, + 150 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 82 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 83 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 79, + "type": "ImageUpscaleWithModel", + "pos": [ + 623.3333541162552, + 714.9999406294688 + ], + "size": [ + 233.5689453125, + 60 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "upscale_model", + "name": "upscale_model", + "type": "UPSCALE_MODEL", + "link": 87 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 88 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 92 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "ImageUpscaleWithModel" + }, + "widgets_values": [] + }, + { + "id": 80, + "type": "VAEEncode", + "pos": [ + 1173.3330331592938, + 631.6665944654844 + ], + "size": [ + 187.5, + 60 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 93 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 90 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 91 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "VAEEncode" + }, + "widgets_values": [] + }, + { + "id": 81, + "type": "ImageScaleBy", + "pos": [ + 865.0000410901742, + 714.9999828835583 + ], + "size": [ + 225, + 95.546875 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 92 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "scale_by", + "name": "scale_by", + "type": "FLOAT", + "widget": { + "name": "scale_by" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 93 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "ImageScaleBy" + }, + "widgets_values": [ + "lanczos", + 0.5 + ] + }, + { + "id": 66, + "type": "UNETLoader", + "pos": [ + 280, + -20 + ], + "size": [ + 323.984375, + 118.64583333333334 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 109 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 104 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "z_image_turbo_bf16.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "z_image_turbo_bf16.safetensors", + "default" + ] + }, + { + "id": 62, + "type": "CLIPLoader", + "pos": [ + 280, + 140 + ], + "size": [ + 323.984375, + 150.65104166666669 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 110 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 78, + 82 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_3_4b.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_3_4b.safetensors", + "lumina2", + "default" + ] + }, + { + "id": 67, + "type": "CLIPTextEncode", + "pos": [ + 650.621298596813, + -33.81729273975067 + ], + "size": [ + 491.9791666666667, + 377.98177083333337 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 78 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 75 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "masterpiece, 8k" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 63, + "type": "VAELoader", + "pos": [ + 280, + 330 + ], + "size": [ + 323.984375, + 83.99739583333334 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 111 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 73, + 90 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 76, + "type": "UpscaleModelLoader", + "pos": [ + 264.07395879037364, + 704.8118881098496 + ], + "size": [ + 323.984375, + 83.99739583333334 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model_name", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": 112 + } + ], + "outputs": [ + { + "localized_name": "UPSCALE_MODEL", + "name": "UPSCALE_MODEL", + "type": "UPSCALE_MODEL", + "links": [ + 87 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "UpscaleModelLoader", + "models": [ + { + "name": "RealESRGAN_x4plus.safetensors", + "url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors", + "directory": "upscale_models" + } + ] + }, + "widgets_values": [ + "RealESRGAN_x4plus.safetensors" + ] + }, + { + "id": 70, + "type": "ModelSamplingAuraFlow", + "pos": [ + 1200, + -50 + ], + "size": [ + 371.9791666666667, + 80.1171875 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 104 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 74 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 65, + "type": "VAEDecode", + "pos": [ + 1610, + -50 + ], + "size": [ + 251.97916666666669, + 72.13541666666667 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 72 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 73 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 97, + 103 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 78, + "type": "ImageScaleToTotalPixels", + "pos": [ + 260, + 850 + ], + "size": [ + 325, + 122.21354166666667 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 86 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "megapixels", + "name": "megapixels", + "type": "FLOAT", + "widget": { + "name": "megapixels" + }, + "link": null + }, + { + "localized_name": "resolution_steps", + "name": "resolution_steps", + "type": "INT", + "widget": { + "name": "resolution_steps" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 88 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "ImageScaleToTotalPixels" + }, + "widgets_values": [ + "lanczos", + 1, + 1 + ] + }, + { + "id": 69, + "type": "KSampler", + "pos": [ + 1200, + 80 + ], + "size": [ + 366.6666666666667, + 474 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 74 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 75 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 83 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 91 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": 115 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 72 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1098688918602660, + "randomize", + 5, + 1, + "dpmpp_2m_sde", + "beta", + 0.33 + ] + } + ], + "groups": [ + { + "id": 3, + "title": "Prompt", + "bounding": [ + 640, + -90, + 508.64583333333337, + 662.0666813520016 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "Models", + "bounding": [ + 260, + -90, + 344.6965254233087, + 516.414685926878 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 104, + "origin_id": 66, + "origin_slot": 0, + "target_id": 70, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 82, + "origin_id": 62, + "origin_slot": 0, + "target_id": 71, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 87, + "origin_id": 76, + "origin_slot": 0, + "target_id": 79, + "target_slot": 0, + "type": "UPSCALE_MODEL" + }, + { + "id": 88, + "origin_id": 78, + "origin_slot": 0, + "target_id": 79, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 93, + "origin_id": 81, + "origin_slot": 0, + "target_id": 80, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 90, + "origin_id": 63, + "origin_slot": 0, + "target_id": 80, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 92, + "origin_id": 79, + "origin_slot": 0, + "target_id": 81, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 74, + "origin_id": 70, + "origin_slot": 0, + "target_id": 69, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 75, + "origin_id": 67, + "origin_slot": 0, + "target_id": 69, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 83, + "origin_id": 71, + "origin_slot": 0, + "target_id": 69, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 91, + "origin_id": 80, + "origin_slot": 0, + "target_id": 69, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 72, + "origin_id": 69, + "origin_slot": 0, + "target_id": 65, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 73, + "origin_id": 63, + "origin_slot": 0, + "target_id": 65, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 78, + "origin_id": 62, + "origin_slot": 0, + "target_id": 67, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 86, + "origin_id": -10, + "origin_slot": 0, + "target_id": 78, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 97, + "origin_id": 65, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 103, + "origin_id": 65, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 109, + "origin_id": -10, + "origin_slot": 1, + "target_id": 66, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 110, + "origin_id": -10, + "origin_slot": 2, + "target_id": 62, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 111, + "origin_id": -10, + "origin_slot": 3, + "target_id": 63, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 112, + "origin_id": -10, + "origin_slot": 4, + "target_id": 76, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 115, + "origin_id": -10, + "origin_slot": 5, + "target_id": 69, + "target_slot": 9, + "type": "FLOAT" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Enhance" + } + ] + }, + "config": {}, + "extra": { + "workflowRendererVersion": "LG" + }, + "version": 0.4 +} diff --git a/blueprints/Image to Depth Map (Lotus).json b/blueprints/Image to Depth Map (Lotus).json index 5b3f7a1d6..089f2cd42 100644 --- a/blueprints/Image to Depth Map (Lotus).json +++ b/blueprints/Image to Depth Map (Lotus).json @@ -1 +1,967 @@ -{"id": "6af0a6c1-0161-4528-8685-65776e838d44", "revision": 0, "last_node_id": 75, "last_link_id": 245, "nodes": [{"id": 75, "type": "488652fd-6edf-4d06-8f9f-4d84d3a34eaf", "pos": [600, 830], "size": [400, 110], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": null}, {"label": "depth_intensity", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["-1", "sigma"], ["-1", "unet_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": [999.0000000000002, "lotus-depth-d-v1-1.safetensors", "vae-ft-mse-840000-ema-pruned.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "488652fd-6edf-4d06-8f9f-4d84d3a34eaf", "version": 1, "state": {"lastGroupId": 1, "lastNodeId": 75, "lastLinkId": 245, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image to Depth Map (Lotus)", "inputNode": {"id": -10, "bounding": [-60, -172.61268043518066, 126.625, 120]}, "outputNode": {"id": -20, "bounding": [1650, -172.61268043518066, 120, 60]}, "inputs": [{"id": "3bdd30c3-4ec9-485a-814b-e7d39fb6b5cc", "name": "pixels", "type": "IMAGE", "linkIds": [37], "localized_name": "pixels", "pos": [46.625, -152.61268043518066]}, {"id": "f9a1017c-f4b9-43b4-94c2-41c088b3a492", "name": "sigma", "type": "FLOAT", "linkIds": [243], "label": "depth_intensity", "pos": [46.625, -132.61268043518066]}, {"id": "cb96b9fe-93e7-41cf-b27f-6d6dc3a1890b", "name": "unet_name", "type": "COMBO", "linkIds": [244], "pos": [46.625, -112.61268043518066]}, {"id": "42c8efad-1661-49c7-89b5-2b735b72424d", "name": "vae_name", "type": "COMBO", "linkIds": [245], "pos": [46.625, -92.61268043518066]}], "outputs": [{"id": "2ec278bd-0b66-4b30-9c5b-994d5f638214", "name": "IMAGE", "type": "IMAGE", "linkIds": [242], "localized_name": "IMAGE", "pos": [1670, -152.61268043518066]}], "widgets": [], "nodes": [{"id": 10, "type": "UNETLoader", "pos": [108.05555555555557, -253.05555555555557], "size": [254.93706597222226, 82], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 244}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [31, 241]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "UNETLoader", "models": [{"name": "lotus-depth-d-v1-1.safetensors", "url": "https://huggingface.co/Comfy-Org/lotus/resolve/main/lotus-depth-d-v1-1.safetensors", "directory": "diffusion_models"}], "widget_ue_connectable": {}}, "widgets_values": ["lotus-depth-d-v1-1.safetensors", "default"]}, {"id": 18, "type": "DisableNoise", "pos": [607.0641494069639, -268.33337840371513], "size": [175, 33.333333333333336], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "slot_index": 0, "links": [237]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "DisableNoise", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 23, "type": "VAEEncode", "pos": [620, 160], "size": [175, 50], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 37}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 38}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [201]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAEEncode", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 21, "type": "KSamplerSelect", "pos": [610, -60], "size": [210, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "slot_index": 0, "links": [33]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "KSamplerSelect", "widget_ue_connectable": {}}, "widgets_values": ["euler"]}, {"id": 19, "type": "BasicGuider", "pos": [610, -170], "size": [175, 50], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 241}, {"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 238}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "slot_index": 0, "links": [27]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "BasicGuider", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 16, "type": "SamplerCustomAdvanced", "pos": [890, -130], "size": [295.99609375, 271.65798611111114], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 237}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 27}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 33}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 194}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 201}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "slot_index": 0, "links": [232]}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "slot_index": 1, "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "SamplerCustomAdvanced", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 28, "type": "SetFirstSigma", "pos": [620, 50], "size": [210, 58], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 66}, {"localized_name": "sigma", "name": "sigma", "type": "FLOAT", "widget": {"name": "sigma"}, "link": 243}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "slot_index": 0, "links": [194]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "SetFirstSigma", "widget_ue_connectable": {}}, "widgets_values": [999.0000000000002]}, {"id": 8, "type": "VAEDecode", "pos": [1210, -120], "size": [175, 50], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 232}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 240}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [35]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAEDecode", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 22, "type": "ImageInvert", "pos": [1200, -220], "size": [175, 33.333333333333336], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 35}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [242]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "ImageInvert", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 14, "type": "VAELoader", "pos": [120, -90], "size": [254.93706597222226, 58], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 245}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [38, 240]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAELoader", "models": [{"name": "vae-ft-mse-840000-ema-pruned.safetensors", "url": "https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors", "directory": "vae"}], "widget_ue_connectable": {}}, "widgets_values": ["vae-ft-mse-840000-ema-pruned.safetensors"]}, {"id": 68, "type": "LotusConditioning", "pos": [400, -150], "size": [175, 33.333333333333336], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "slot_index": 0, "links": [238]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "LotusConditioning", "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 20, "type": "BasicScheduler", "pos": [170, 40], "size": [210, 106], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 31}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "slot_index": 0, "links": [66]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "BasicScheduler", "widget_ue_connectable": {}}, "widgets_values": ["normal", 1, 1]}], "groups": [], "links": [{"id": 232, "origin_id": 16, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 240, "origin_id": 14, "origin_slot": 0, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 237, "origin_id": 18, "origin_slot": 0, "target_id": 16, "target_slot": 0, "type": "NOISE"}, {"id": 27, "origin_id": 19, "origin_slot": 0, "target_id": 16, "target_slot": 1, "type": "GUIDER"}, {"id": 33, "origin_id": 21, "origin_slot": 0, "target_id": 16, "target_slot": 2, "type": "SAMPLER"}, {"id": 194, "origin_id": 28, "origin_slot": 0, "target_id": 16, "target_slot": 3, "type": "SIGMAS"}, {"id": 201, "origin_id": 23, "origin_slot": 0, "target_id": 16, "target_slot": 4, "type": "LATENT"}, {"id": 241, "origin_id": 10, "origin_slot": 0, "target_id": 19, "target_slot": 0, "type": "MODEL"}, {"id": 238, "origin_id": 68, "origin_slot": 0, "target_id": 19, "target_slot": 1, "type": "CONDITIONING"}, {"id": 31, "origin_id": 10, "origin_slot": 0, "target_id": 20, "target_slot": 0, "type": "MODEL"}, {"id": 35, "origin_id": 8, "origin_slot": 0, "target_id": 22, "target_slot": 0, "type": "IMAGE"}, {"id": 38, "origin_id": 14, "origin_slot": 0, "target_id": 23, "target_slot": 1, "type": "VAE"}, {"id": 66, "origin_id": 20, "origin_slot": 0, "target_id": 28, "target_slot": 0, "type": "SIGMAS"}, {"id": 37, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 242, "origin_id": 22, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 243, "origin_id": -10, "origin_slot": 1, "target_id": 28, "target_slot": 1, "type": "FLOAT"}, {"id": 244, "origin_id": -10, "origin_slot": 2, "target_id": 10, "target_slot": 0, "type": "COMBO"}, {"id": 245, "origin_id": -10, "origin_slot": 3, "target_id": 14, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image generation and editing/Depth to image"}]}, "config": {}, "extra": {"ds": {"scale": 1.3589709866044692, "offset": [-138.53613935617864, -786.0629126022195]}, "workflowRendererVersion": "LG"}, "version": 0.4} +{ + "id": "6af0a6c1-0161-4528-8685-65776e838d44", + "revision": 0, + "last_node_id": 75, + "last_link_id": 245, + "nodes": [ + { + "id": 75, + "type": "488652fd-6edf-4d06-8f9f-4d84d3a34eaf", + "pos": [ + 600, + 830 + ], + "size": [ + 400, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": null + }, + { + "label": "depth_intensity", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "sigma" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.14.1" + }, + "widgets_values": [ + 999.0000000000002, + "lotus-depth-d-v1-1.safetensors", + "vae-ft-mse-840000-ema-pruned.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "488652fd-6edf-4d06-8f9f-4d84d3a34eaf", + "version": 1, + "state": { + "lastGroupId": 1, + "lastNodeId": 75, + "lastLinkId": 245, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Image to Depth Map (Lotus)", + "inputNode": { + "id": -10, + "bounding": [ + -60, + -172.61268043518066, + 126.625, + 120 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1650, + -172.61268043518066, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "3bdd30c3-4ec9-485a-814b-e7d39fb6b5cc", + "name": "pixels", + "type": "IMAGE", + "linkIds": [ + 37 + ], + "localized_name": "pixels", + "pos": [ + 46.625, + -152.61268043518066 + ] + }, + { + "id": "f9a1017c-f4b9-43b4-94c2-41c088b3a492", + "name": "sigma", + "type": "FLOAT", + "linkIds": [ + 243 + ], + "label": "depth_intensity", + "pos": [ + 46.625, + -132.61268043518066 + ] + }, + { + "id": "cb96b9fe-93e7-41cf-b27f-6d6dc3a1890b", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 244 + ], + "pos": [ + 46.625, + -112.61268043518066 + ] + }, + { + "id": "42c8efad-1661-49c7-89b5-2b735b72424d", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 245 + ], + "pos": [ + 46.625, + -92.61268043518066 + ] + } + ], + "outputs": [ + { + "id": "2ec278bd-0b66-4b30-9c5b-994d5f638214", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 242 + ], + "localized_name": "IMAGE", + "pos": [ + 1670, + -152.61268043518066 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 10, + "type": "UNETLoader", + "pos": [ + 108.05555555555557, + -253.05555555555557 + ], + "size": [ + 254.93706597222226, + 82 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 244 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 31, + 241 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "lotus-depth-d-v1-1.safetensors", + "url": "https://huggingface.co/Comfy-Org/lotus/resolve/main/lotus-depth-d-v1-1.safetensors", + "directory": "diffusion_models" + } + ], + "widget_ue_connectable": {} + }, + "widgets_values": [ + "lotus-depth-d-v1-1.safetensors", + "default" + ] + }, + { + "id": 18, + "type": "DisableNoise", + "pos": [ + 607.0641494069639, + -268.33337840371513 + ], + "size": [ + 175, + 33.333333333333336 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "slot_index": 0, + "links": [ + 237 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "DisableNoise", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 23, + "type": "VAEEncode", + "pos": [ + 620, + 160 + ], + "size": [ + 175, + 50 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 37 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 38 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 201 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAEEncode", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 21, + "type": "KSamplerSelect", + "pos": [ + 610, + -60 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "slot_index": 0, + "links": [ + 33 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "KSamplerSelect", + "widget_ue_connectable": {} + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 19, + "type": "BasicGuider", + "pos": [ + 610, + -170 + ], + "size": [ + 175, + 50 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 241 + }, + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 238 + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "slot_index": 0, + "links": [ + 27 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "BasicGuider", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 16, + "type": "SamplerCustomAdvanced", + "pos": [ + 890, + -130 + ], + "size": [ + 295.99609375, + 271.65798611111114 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 237 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 27 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 33 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 194 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 201 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "slot_index": 0, + "links": [ + 232 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "slot_index": 1, + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "SamplerCustomAdvanced", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 28, + "type": "SetFirstSigma", + "pos": [ + 620, + 50 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 66 + }, + { + "localized_name": "sigma", + "name": "sigma", + "type": "FLOAT", + "widget": { + "name": "sigma" + }, + "link": 243 + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "slot_index": 0, + "links": [ + 194 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "SetFirstSigma", + "widget_ue_connectable": {} + }, + "widgets_values": [ + 999.0000000000002 + ] + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 1210, + -120 + ], + "size": [ + 175, + 50 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 232 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 240 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 35 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAEDecode", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 22, + "type": "ImageInvert", + "pos": [ + 1200, + -220 + ], + "size": [ + 175, + 33.333333333333336 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 35 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 242 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "ImageInvert", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 14, + "type": "VAELoader", + "pos": [ + 120, + -90 + ], + "size": [ + 254.93706597222226, + 58 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 245 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 38, + 240 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "vae-ft-mse-840000-ema-pruned.safetensors", + "url": "https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors", + "directory": "vae" + } + ], + "widget_ue_connectable": {} + }, + "widgets_values": [ + "vae-ft-mse-840000-ema-pruned.safetensors" + ] + }, + { + "id": 68, + "type": "LotusConditioning", + "pos": [ + 400, + -150 + ], + "size": [ + 175, + 33.333333333333336 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 238 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "LotusConditioning", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 20, + "type": "BasicScheduler", + "pos": [ + 170, + 40 + ], + "size": [ + 210, + 106 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 31 + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "slot_index": 0, + "links": [ + 66 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "BasicScheduler", + "widget_ue_connectable": {} + }, + "widgets_values": [ + "normal", + 1, + 1 + ] + } + ], + "groups": [], + "links": [ + { + "id": 232, + "origin_id": 16, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 240, + "origin_id": 14, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 237, + "origin_id": 18, + "origin_slot": 0, + "target_id": 16, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 27, + "origin_id": 19, + "origin_slot": 0, + "target_id": 16, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 33, + "origin_id": 21, + "origin_slot": 0, + "target_id": 16, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 194, + "origin_id": 28, + "origin_slot": 0, + "target_id": 16, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 201, + "origin_id": 23, + "origin_slot": 0, + "target_id": 16, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 241, + "origin_id": 10, + "origin_slot": 0, + "target_id": 19, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 238, + "origin_id": 68, + "origin_slot": 0, + "target_id": 19, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 31, + "origin_id": 10, + "origin_slot": 0, + "target_id": 20, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 35, + "origin_id": 8, + "origin_slot": 0, + "target_id": 22, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 38, + "origin_id": 14, + "origin_slot": 0, + "target_id": 23, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 66, + "origin_id": 20, + "origin_slot": 0, + "target_id": 28, + "target_slot": 0, + "type": "SIGMAS" + }, + { + "id": 37, + "origin_id": -10, + "origin_slot": 0, + "target_id": 23, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 242, + "origin_id": 22, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 243, + "origin_id": -10, + "origin_slot": 1, + "target_id": 28, + "target_slot": 1, + "type": "FLOAT" + }, + { + "id": 244, + "origin_id": -10, + "origin_slot": 2, + "target_id": 10, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 245, + "origin_id": -10, + "origin_slot": 3, + "target_id": 14, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Depth to image" + } + ] + }, + "config": {}, + "extra": { + "ds": { + "scale": 1.3589709866044692, + "offset": [ + -138.53613935617864, + -786.0629126022195 + ] + }, + "workflowRendererVersion": "LG" + }, + "version": 0.4 +} diff --git a/blueprints/Image to Layers(Qwen-Image Layered).json b/blueprints/Image to Layers(Qwen-Image Layered).json deleted file mode 100644 index f4c7f0b5f..000000000 --- a/blueprints/Image to Layers(Qwen-Image Layered).json +++ /dev/null @@ -1 +0,0 @@ -{"id": "1a761372-7c82-4016-b9bf-fa285967e1e9", "revision": 0, "last_node_id": 83, "last_link_id": 0, "nodes": [{"id": 83, "type": "f754a936-daaf-4b6e-9658-41fdc54d301d", "pos": [61.999827823554256, 153.3332507624185], "size": [400, 550], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": null}, {"name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"name": "layers", "type": "INT", "widget": {"name": "layers"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "steps"], ["-1", "cfg"], ["-1", "layers"], ["3", "seed"], ["3", "control_after_generate"]], "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", 20, 2.5, 2]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "f754a936-daaf-4b6e-9658-41fdc54d301d", "version": 1, "state": {"lastGroupId": 3, "lastNodeId": 83, "lastLinkId": 159, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image to Layers (Qwen-Image-Layered)", "inputNode": {"id": -10, "bounding": [-510, 523, 120, 140]}, "outputNode": {"id": -20, "bounding": [1160, 523, 120, 60]}, "inputs": [{"id": "6c36b5bc-c9a5-4b07-8b52-6fe0df434cce", "name": "image", "type": "IMAGE", "linkIds": [148, 149], "localized_name": "image", "pos": [-410, 543]}, {"id": "8497fe33-124d-4e3e-9ab6-fc4a56a98dde", "name": "text", "type": "STRING", "linkIds": [150], "pos": [-410, 563]}, {"id": "509ab2c1-e6da-47ba-8714-023100ab92bd", "name": "steps", "type": "INT", "linkIds": [153], "pos": [-410, 583]}, {"id": "dd81894e-5def-4c75-9b17-d8f89fe095d6", "name": "cfg", "type": "FLOAT", "linkIds": [154], "pos": [-410, 603]}, {"id": "66da7c8a-3369-4a3f-92f2-3073afc55e7d", "name": "layers", "type": "INT", "linkIds": [159], "pos": [-410, 623]}], "outputs": [{"id": "7df75921-6729-4aad-bfc1-fcc536c2d298", "name": "IMAGE", "type": "IMAGE", "linkIds": [110], "localized_name": "IMAGE", "pos": [1180, 543]}], "widgets": [], "nodes": [{"id": 38, "type": "CLIPLoader", "pos": [-320, 310], "size": [346.7470703125, 106], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "slot_index": 0, "links": [74, 75]}], "properties": {"Node name for S&R": "CLIPLoader", "cnr_id": "comfy-core", "ver": "0.5.1", "models": [{"name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_2.5_vl_7b_fp8_scaled.safetensors", "qwen_image", "default"]}, {"id": 39, "type": "VAELoader", "pos": [-320, 460], "size": [346.7470703125, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [76, 139]}], "properties": {"Node name for S&R": "VAELoader", "cnr_id": "comfy-core", "ver": "0.5.1", "models": [{"name": "qwen_image_layered_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image-Layered_ComfyUI/resolve/main/split_files/vae/qwen_image_layered_vae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_image_layered_vae.safetensors"]}, {"id": 7, "type": "CLIPTextEncode", "pos": [70, 420], "size": [425.27801513671875, 180.6060791015625], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 75}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [131]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"Node name for S&R": "CLIPTextEncode", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#322", "bgcolor": "#533"}, {"id": 70, "type": "ReferenceLatent", "pos": [330, 670], "size": [204.1666717529297, 46], "flags": {"collapsed": true}, "order": 9, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 131}, {"localized_name": "latent", "name": "latent", "shape": 7, "type": "LATENT", "link": 134}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [132]}], "properties": {"Node name for S&R": "ReferenceLatent", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 69, "type": "ReferenceLatent", "pos": [330, 710], "size": [204.1666717529297, 46], "flags": {"collapsed": true}, "order": 8, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 129}, {"localized_name": "latent", "name": "latent", "shape": 7, "type": "LATENT", "link": 133}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [130]}], "properties": {"Node name for S&R": "ReferenceLatent", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 66, "type": "ModelSamplingAuraFlow", "pos": [530, 150], "size": [270, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 126}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [125]}], "properties": {"Node name for S&R": "ModelSamplingAuraFlow", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 76, "type": "LatentCutToBatch", "pos": [830, 160], "size": [270, 82], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 142}, {"localized_name": "dim", "name": "dim", "type": "COMBO", "widget": {"name": "dim"}, "link": null}, {"localized_name": "slice_size", "name": "slice_size", "type": "INT", "widget": {"name": "slice_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [143]}], "properties": {"Node name for S&R": "LatentCutToBatch", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["t", 1]}, {"id": 71, "type": "VAEEncode", "pos": [100, 690], "size": [140, 46], "flags": {"collapsed": false}, "order": 10, "mode": 0, "inputs": [{"localized_name": "pixels", "name": "pixels", "type": "IMAGE", "link": 149}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 139}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [133, 134]}], "properties": {"Node name for S&R": "VAEEncode", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 8, "type": "VAEDecode", "pos": [850, 310], "size": [210, 46], "flags": {"collapsed": true}, "order": 7, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 143}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 76}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [110]}], "properties": {"Node name for S&R": "VAEDecode", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 6, "type": "CLIPTextEncode", "pos": [70, 180], "size": [422.84503173828125, 164.31304931640625], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 74}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 150}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [129]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"Node name for S&R": "CLIPTextEncode", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 3, "type": "KSampler", "pos": [530, 280], "size": [270, 400], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 125}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 130}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 132}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 157}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": 153}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": 154}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [142]}], "properties": {"Node name for S&R": "KSampler", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize", 20, 2.5, "euler", "simple", 1]}, {"id": 78, "type": "GetImageSize", "pos": [80, 790], "size": [210, 136], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 148}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [155]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [156]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": null}], "properties": {"Node name for S&R": "GetImageSize", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 83, "type": "EmptyQwenImageLayeredLatentImage", "pos": [320, 790], "size": [330.9341796875, 130], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 155}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 156}, {"localized_name": "layers", "name": "layers", "type": "INT", "widget": {"name": "layers"}, "link": 159}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [157]}], "properties": {"Node name for S&R": "EmptyQwenImageLayeredLatentImage", "cnr_id": "comfy-core", "ver": "0.5.1", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [640, 640, 2, 1]}, {"id": 37, "type": "UNETLoader", "pos": [-320, 180], "size": [346.7470703125, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [126]}], "properties": {"Node name for S&R": "UNETLoader", "cnr_id": "comfy-core", "ver": "0.5.1", "models": [{"name": "qwen_image_layered_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen-Image-Layered_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_layered_bf16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_image_layered_bf16.safetensors", "default"]}], "groups": [{"id": 1, "title": "Prompt(Optional)", "bounding": [60, 110, 450, 510], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Load Models", "bounding": [-330, 110, 366.7470703125, 421.6], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 75, "origin_id": 38, "origin_slot": 0, "target_id": 7, "target_slot": 0, "type": "CLIP"}, {"id": 131, "origin_id": 7, "origin_slot": 0, "target_id": 70, "target_slot": 0, "type": "CONDITIONING"}, {"id": 134, "origin_id": 71, "origin_slot": 0, "target_id": 70, "target_slot": 1, "type": "LATENT"}, {"id": 129, "origin_id": 6, "origin_slot": 0, "target_id": 69, "target_slot": 0, "type": "CONDITIONING"}, {"id": 133, "origin_id": 71, "origin_slot": 0, "target_id": 69, "target_slot": 1, "type": "LATENT"}, {"id": 126, "origin_id": 37, "origin_slot": 0, "target_id": 66, "target_slot": 0, "type": "MODEL"}, {"id": 125, "origin_id": 66, "origin_slot": 0, "target_id": 3, "target_slot": 0, "type": "MODEL"}, {"id": 130, "origin_id": 69, "origin_slot": 0, "target_id": 3, "target_slot": 1, "type": "CONDITIONING"}, {"id": 132, "origin_id": 70, "origin_slot": 0, "target_id": 3, "target_slot": 2, "type": "CONDITIONING"}, {"id": 142, "origin_id": 3, "origin_slot": 0, "target_id": 76, "target_slot": 0, "type": "LATENT"}, {"id": 74, "origin_id": 38, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "CLIP"}, {"id": 139, "origin_id": 39, "origin_slot": 0, "target_id": 71, "target_slot": 1, "type": "VAE"}, {"id": 143, "origin_id": 76, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 76, "origin_id": 39, "origin_slot": 0, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 148, "origin_id": -10, "origin_slot": 0, "target_id": 78, "target_slot": 0, "type": "IMAGE"}, {"id": 149, "origin_id": -10, "origin_slot": 0, "target_id": 71, "target_slot": 0, "type": "IMAGE"}, {"id": 110, "origin_id": 8, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 150, "origin_id": -10, "origin_slot": 1, "target_id": 6, "target_slot": 1, "type": "STRING"}, {"id": 153, "origin_id": -10, "origin_slot": 2, "target_id": 3, "target_slot": 5, "type": "INT"}, {"id": 154, "origin_id": -10, "origin_slot": 3, "target_id": 3, "target_slot": 6, "type": "FLOAT"}, {"id": 155, "origin_id": 78, "origin_slot": 0, "target_id": 83, "target_slot": 0, "type": "INT"}, {"id": 156, "origin_id": 78, "origin_slot": 1, "target_id": 83, "target_slot": 1, "type": "INT"}, {"id": 157, "origin_id": 83, "origin_slot": 0, "target_id": 3, "target_slot": 3, "type": "LATENT"}, {"id": 159, "origin_id": -10, "origin_slot": 4, "target_id": 83, "target_slot": 2, "type": "INT"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image generation and editing/Image to layers"}]}, "config": {}, "extra": {"ds": {"scale": 1.14, "offset": [695.5933739308316, 6.855893974423647]}, "workflowRendererVersion": "LG"}, "version": 0.4} diff --git a/blueprints/Image to Layers(Qwen-Image-Layered).json b/blueprints/Image to Layers(Qwen-Image-Layered).json new file mode 100644 index 000000000..8a525e7a5 --- /dev/null +++ b/blueprints/Image to Layers(Qwen-Image-Layered).json @@ -0,0 +1,1603 @@ +{ + "revision": 0, + "last_node_id": 176, + "last_link_id": 0, + "nodes": [ + { + "id": 176, + "type": "2d2e3c8e-53b3-4618-be52-6d1d99382f0e", + "pos": [ + -1150, + 200 + ], + "size": [ + 400, + 550 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "name": "layers", + "type": "INT", + "widget": { + "name": "layers" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "title": "Image to Layers (Qwen-Image-Layered)", + "properties": { + "proxyWidgets": [ + [ + "6", + "text" + ], + [ + "3", + "steps" + ], + [ + "3", + "cfg" + ], + [ + "83", + "layers" + ], + [ + "3", + "seed" + ], + [ + "37", + "unet_name" + ], + [ + "38", + "clip_name" + ], + [ + "39", + "vae_name" + ], + [ + "3", + "control_after_generate" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "2d2e3c8e-53b3-4618-be52-6d1d99382f0e", + "version": 1, + "state": { + "lastGroupId": 8, + "lastNodeId": 176, + "lastLinkId": 380, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image to Layers (Qwen-Image-Layered)", + "inputNode": { + "id": -10, + "bounding": [ + -720, + 720, + 120, + 220 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1160, + 523, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "6c36b5bc-c9a5-4b07-8b52-6fe0df434cce", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 148, + 149 + ], + "localized_name": "image", + "pos": [ + -620, + 740 + ] + }, + { + "id": "8497fe33-124d-4e3e-9ab6-fc4a56a98dde", + "name": "text", + "type": "STRING", + "linkIds": [ + 150 + ], + "pos": [ + -620, + 760 + ] + }, + { + "id": "509ab2c1-e6da-47ba-8714-023100ab92bd", + "name": "steps", + "type": "INT", + "linkIds": [ + 153 + ], + "pos": [ + -620, + 780 + ] + }, + { + "id": "dd81894e-5def-4c75-9b17-d8f89fe095d6", + "name": "cfg", + "type": "FLOAT", + "linkIds": [ + 154 + ], + "pos": [ + -620, + 800 + ] + }, + { + "id": "66da7c8a-3369-4a3f-92f2-3073afc55e7d", + "name": "layers", + "type": "INT", + "linkIds": [ + 159 + ], + "pos": [ + -620, + 820 + ] + }, + { + "id": "9f76338b-f4ca-4bb3-b61a-57b3f233061e", + "name": "seed", + "type": "INT", + "linkIds": [ + 377 + ], + "pos": [ + -620, + 840 + ] + }, + { + "id": "8d0422d5-5eee-4f7e-9817-dc613cc62eca", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 378 + ], + "pos": [ + -620, + 860 + ] + }, + { + "id": "552eece2-a735-4d00-ae78-ded454622bc1", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 379 + ], + "pos": [ + -620, + 880 + ] + }, + { + "id": "1e6d141c-d0f9-4a2b-895c-b6780e57cfa0", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 380 + ], + "pos": [ + -620, + 900 + ] + } + ], + "outputs": [ + { + "id": "7df75921-6729-4aad-bfc1-fcc536c2d298", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 110 + ], + "localized_name": "IMAGE", + "pos": [ + 1180, + 543 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 38, + "type": "CLIPLoader", + "pos": [ + -320, + 360 + ], + "size": [ + 350, + 150 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 379 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 74, + 75 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image", + "default" + ] + }, + { + "id": 39, + "type": "VAELoader", + "pos": [ + -320, + 580 + ], + "size": [ + 350, + 110 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 380 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 76, + 139 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "qwen_image_layered_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image-Layered_ComfyUI/resolve/main/split_files/vae/qwen_image_layered_vae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_image_layered_vae.safetensors" + ] + }, + { + "id": 7, + "type": "CLIPTextEncode", + "pos": [ + 70, + 420 + ], + "size": [ + 430, + 190 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 75 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 131 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 70, + "type": "ReferenceLatent", + "pos": [ + 140, + 700 + ], + "size": [ + 210, + 50 + ], + "flags": { + "collapsed": true + }, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 131 + }, + { + "localized_name": "latent", + "name": "latent", + "shape": 7, + "type": "LATENT", + "link": 134 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 132 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "ReferenceLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 69, + "type": "ReferenceLatent", + "pos": [ + 160, + 820 + ], + "size": [ + 210, + 50 + ], + "flags": { + "collapsed": true + }, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 129 + }, + { + "localized_name": "latent", + "name": "latent", + "shape": 7, + "type": "LATENT", + "link": 133 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 130 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "ReferenceLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 66, + "type": "ModelSamplingAuraFlow", + "pos": [ + 530, + 150 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 126 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 125 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 76, + "type": "LatentCutToBatch", + "pos": [ + 830, + 140 + ], + "size": [ + 270, + 140 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 142 + }, + { + "localized_name": "dim", + "name": "dim", + "type": "COMBO", + "widget": { + "name": "dim" + }, + "link": null + }, + { + "localized_name": "slice_size", + "name": "slice_size", + "type": "INT", + "widget": { + "name": "slice_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 143 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "LatentCutToBatch", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "t", + 1 + ] + }, + { + "id": 71, + "type": "VAEEncode", + "pos": [ + -280, + 780 + ], + "size": [ + 230, + 100 + ], + "flags": { + "collapsed": false + }, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "pixels", + "name": "pixels", + "type": "IMAGE", + "link": 149 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 139 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 133, + 134 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "VAEEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 850, + 370 + ], + "size": [ + 210, + 50 + ], + "flags": { + "collapsed": true + }, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 143 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 76 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 110 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 6, + "type": "CLIPTextEncode", + "pos": [ + 70, + 180 + ], + "size": [ + 430, + 170 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 74 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 150 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 129 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 530, + 340 + ], + "size": [ + 270, + 400 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 125 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 130 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 132 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 157 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 377 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": 153 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": 154 + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 142 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize", + 20, + 2.5, + "euler", + "simple", + 1 + ] + }, + { + "id": 78, + "type": "GetImageSize", + "pos": [ + -280, + 930 + ], + "size": [ + 230, + 140 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 148 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 155 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 156 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 83, + "type": "EmptyQwenImageLayeredLatentImage", + "pos": [ + -280, + 1120 + ], + "size": [ + 340, + 200 + ], + "flags": {}, + "order": 13, + "mode": 0, + "showAdvanced": true, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 155 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 156 + }, + { + "localized_name": "layers", + "name": "layers", + "type": "INT", + "widget": { + "name": "layers" + }, + "link": 159 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 157 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "EmptyQwenImageLayeredLatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 640, + 640, + 2, + 1 + ] + }, + { + "id": 37, + "type": "UNETLoader", + "pos": [ + -320, + 180 + ], + "size": [ + 350, + 110 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 378 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 126 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.7" + }, + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "qwen_image_layered_bf16.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image-Layered_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_layered_bf16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_image_layered_bf16.safetensors", + "default" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Prompt(Optional)", + "bounding": [ + 60, + 110, + 450, + 510 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Load Models", + "bounding": [ + -330, + 110, + 370, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 75, + "origin_id": 38, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 131, + "origin_id": 7, + "origin_slot": 0, + "target_id": 70, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 134, + "origin_id": 71, + "origin_slot": 0, + "target_id": 70, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 129, + "origin_id": 6, + "origin_slot": 0, + "target_id": 69, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 133, + "origin_id": 71, + "origin_slot": 0, + "target_id": 69, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 126, + "origin_id": 37, + "origin_slot": 0, + "target_id": 66, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 125, + "origin_id": 66, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 130, + "origin_id": 69, + "origin_slot": 0, + "target_id": 3, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 132, + "origin_id": 70, + "origin_slot": 0, + "target_id": 3, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 142, + "origin_id": 3, + "origin_slot": 0, + "target_id": 76, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 74, + "origin_id": 38, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 139, + "origin_id": 39, + "origin_slot": 0, + "target_id": 71, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 143, + "origin_id": 76, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 76, + "origin_id": 39, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 148, + "origin_id": -10, + "origin_slot": 0, + "target_id": 78, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 149, + "origin_id": -10, + "origin_slot": 0, + "target_id": 71, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 110, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 150, + "origin_id": -10, + "origin_slot": 1, + "target_id": 6, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 153, + "origin_id": -10, + "origin_slot": 2, + "target_id": 3, + "target_slot": 5, + "type": "INT" + }, + { + "id": 154, + "origin_id": -10, + "origin_slot": 3, + "target_id": 3, + "target_slot": 6, + "type": "FLOAT" + }, + { + "id": 155, + "origin_id": 78, + "origin_slot": 0, + "target_id": 83, + "target_slot": 0, + "type": "INT" + }, + { + "id": 156, + "origin_id": 78, + "origin_slot": 1, + "target_id": 83, + "target_slot": 1, + "type": "INT" + }, + { + "id": 157, + "origin_id": 83, + "origin_slot": 0, + "target_id": 3, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 159, + "origin_id": -10, + "origin_slot": 4, + "target_id": 83, + "target_slot": 2, + "type": "INT" + }, + { + "id": 377, + "origin_id": -10, + "origin_slot": 5, + "target_id": 3, + "target_slot": 4, + "type": "INT" + }, + { + "id": 378, + "origin_id": -10, + "origin_slot": 6, + "target_id": 37, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 379, + "origin_id": -10, + "origin_slot": 7, + "target_id": 38, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 380, + "origin_id": -10, + "origin_slot": 8, + "target_id": 39, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Image to layers" + } + ] + }, + "extra": { + "ds": { + "scale": 1.14, + "offset": [ + 695.5933739308316, + 6.855893974423647 + ] + }, + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Image to Model (Hunyuan3d 2.1).json b/blueprints/Image to Model (Hunyuan3d 2.1).json index 04b2d9bc9..4705603a8 100644 --- a/blueprints/Image to Model (Hunyuan3d 2.1).json +++ b/blueprints/Image to Model (Hunyuan3d 2.1).json @@ -1 +1,784 @@ -{"id": "8fe311ec-2147-47a8-b618-7bd6fb6d4f9d", "revision": 0, "last_node_id": 23, "last_link_id": 24, "nodes": [{"id": 19, "type": "feb7d184-edf3-4851-9fd6-57a92c00ec42", "pos": [277.7327250391088, 256.4066470374603], "size": [340, 70], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": null}, {"name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": null}], "outputs": [{"localized_name": "MESH", "name": "MESH", "type": "MESH", "links": []}], "properties": {"proxyWidgets": [["-1", "ckpt_name"]], "cnr_id": "comfy-core", "ver": "0.3.65"}, "widgets_values": ["hunyuan_3d_v2.1.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "feb7d184-edf3-4851-9fd6-57a92c00ec42", "version": 1, "state": {"lastGroupId": 2, "lastNodeId": 23, "lastLinkId": 24, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image to Model (Hunyuan3d 2.1)", "inputNode": {"id": -10, "bounding": [-138.94803619384766, -392.62060546875, 120, 80]}, "outputNode": {"id": -20, "bounding": [1090, -310, 120, 60]}, "inputs": [{"id": "ab9b5b83-88f9-4698-954d-93f644bd07aa", "name": "image", "type": "IMAGE", "linkIds": [21], "localized_name": "image", "pos": [-38.948036193847656, -372.62060546875]}, {"id": "e15b0ba4-b5fe-41eb-9266-006ce1f1cf79", "name": "ckpt_name", "type": "COMBO", "linkIds": [23], "pos": [-38.948036193847656, -352.62060546875]}], "outputs": [{"id": "c8744662-e812-49b3-8bc8-744d557db6d6", "name": "MESH", "type": "MESH", "linkIds": [11], "localized_name": "MESH", "pos": [1110, -290]}], "widgets": [], "nodes": [{"id": 7, "type": "KSampler", "pos": [760, -510], "size": [270, 262], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 19}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 5}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 6}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 7}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [8]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "KSampler"}, "widgets_values": [894796671366012, "randomize", 30, 5, "euler", "normal", 1]}, {"id": 13, "type": "CLIPVisionEncode", "pos": [450, -410], "size": [270, 80], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "clip_vision", "name": "clip_vision", "type": "CLIP_VISION", "link": 20}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 21}, {"localized_name": "crop", "name": "crop", "type": "COMBO", "widget": {"name": "crop"}, "link": null}], "outputs": [{"localized_name": "CLIP_VISION_OUTPUT", "name": "CLIP_VISION_OUTPUT", "type": "CLIP_VISION_OUTPUT", "links": [22]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "CLIPVisionEncode"}, "widgets_values": ["center"]}, {"id": 6, "type": "Hunyuan3Dv2Conditioning", "pos": [510, -280], "size": [217.82578125, 46], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "clip_vision_output", "name": "clip_vision_output", "type": "CLIP_VISION_OUTPUT", "link": 22}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [5]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [6]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "Hunyuan3Dv2Conditioning"}, "widgets_values": []}, {"id": 4, "type": "EmptyLatentHunyuan3Dv2", "pos": [450, -180], "size": [270, 82], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "resolution", "name": "resolution", "type": "INT", "widget": {"name": "resolution"}, "link": null}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [7]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "EmptyLatentHunyuan3Dv2"}, "widgets_values": [4096, 1]}, {"id": 9, "type": "VoxelToMesh", "pos": [760, -40], "size": [270, 82], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "voxel", "name": "voxel", "type": "VOXEL", "link": 10}, {"localized_name": "algorithm", "name": "algorithm", "type": "COMBO", "widget": {"name": "algorithm"}, "link": null}, {"localized_name": "threshold", "name": "threshold", "type": "FLOAT", "widget": {"name": "threshold"}, "link": null}], "outputs": [{"localized_name": "MESH", "name": "MESH", "type": "MESH", "links": [11]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "VoxelToMesh"}, "widgets_values": ["surface net", 0.6]}, {"id": 8, "type": "VAEDecodeHunyuan3D", "pos": [760, -200], "size": [270, 102], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 8}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 18}, {"localized_name": "num_chunks", "name": "num_chunks", "type": "INT", "widget": {"name": "num_chunks"}, "link": null}, {"localized_name": "octree_resolution", "name": "octree_resolution", "type": "INT", "widget": {"name": "octree_resolution"}, "link": null}], "outputs": [{"localized_name": "VOXEL", "name": "VOXEL", "type": "VOXEL", "links": [10]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "VAEDecodeHunyuan3D"}, "widgets_values": [8000, 256]}, {"id": 1, "type": "ImageOnlyCheckpointLoader", "pos": [60, -510], "size": [356.0005859375, 100], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 23}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [16]}, {"localized_name": "CLIP_VISION", "name": "CLIP_VISION", "type": "CLIP_VISION", "links": [20]}, {"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [18]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ImageOnlyCheckpointLoader", "models": [{"name": "hunyuan_3d_v2.1.safetensors", "url": "https://huggingface.co/Comfy-Org/hunyuan3D_2.1_repackaged/resolve/main/hunyuan_3d_v2.1.safetensors", "directory": "checkpoints"}]}, "widgets_values": ["hunyuan_3d_v2.1.safetensors"]}, {"id": 3, "type": "ModelSamplingAuraFlow", "pos": [450, -510], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 16}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [19]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.59", "Node name for S&R": "ModelSamplingAuraFlow"}, "widgets_values": [1]}], "groups": [], "links": [{"id": 16, "origin_id": 1, "origin_slot": 0, "target_id": 3, "target_slot": 0, "type": "MODEL"}, {"id": 19, "origin_id": 3, "origin_slot": 0, "target_id": 7, "target_slot": 0, "type": "MODEL"}, {"id": 5, "origin_id": 6, "origin_slot": 0, "target_id": 7, "target_slot": 1, "type": "CONDITIONING"}, {"id": 6, "origin_id": 6, "origin_slot": 1, "target_id": 7, "target_slot": 2, "type": "CONDITIONING"}, {"id": 7, "origin_id": 4, "origin_slot": 0, "target_id": 7, "target_slot": 3, "type": "LATENT"}, {"id": 8, "origin_id": 7, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 18, "origin_id": 1, "origin_slot": 2, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 10, "origin_id": 8, "origin_slot": 0, "target_id": 9, "target_slot": 0, "type": "VOXEL"}, {"id": 20, "origin_id": 1, "origin_slot": 1, "target_id": 13, "target_slot": 0, "type": "CLIP_VISION"}, {"id": 22, "origin_id": 13, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "CLIP_VISION_OUTPUT"}, {"id": 21, "origin_id": -10, "origin_slot": 0, "target_id": 13, "target_slot": 1, "type": "IMAGE"}, {"id": 11, "origin_id": 9, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "MESH"}, {"id": 23, "origin_id": -10, "origin_slot": 1, "target_id": 1, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "3D/Image to 3D Model"}]}, "config": {}, "extra": {"ds": {"scale": 0.620921323059155, "offset": [1636.2881100217016, 965.23503257945]}, "workflowRendererVersion": "LG"}, "version": 0.4} +{ + "id": "8fe311ec-2147-47a8-b618-7bd6fb6d4f9d", + "revision": 0, + "last_node_id": 23, + "last_link_id": 24, + "nodes": [ + { + "id": 19, + "type": "feb7d184-edf3-4851-9fd6-57a92c00ec42", + "pos": [ + 277.7327250391088, + 256.4066470374603 + ], + "size": [ + 340, + 70 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MESH", + "name": "MESH", + "type": "MESH", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "ckpt_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.3.65" + }, + "widgets_values": [ + "hunyuan_3d_v2.1.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "feb7d184-edf3-4851-9fd6-57a92c00ec42", + "version": 1, + "state": { + "lastGroupId": 2, + "lastNodeId": 23, + "lastLinkId": 24, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Image to Model (Hunyuan3d 2.1)", + "inputNode": { + "id": -10, + "bounding": [ + -138.94803619384766, + -392.62060546875, + 120, + 80 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1090, + -310, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "ab9b5b83-88f9-4698-954d-93f644bd07aa", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 21 + ], + "localized_name": "image", + "pos": [ + -38.948036193847656, + -372.62060546875 + ] + }, + { + "id": "e15b0ba4-b5fe-41eb-9266-006ce1f1cf79", + "name": "ckpt_name", + "type": "COMBO", + "linkIds": [ + 23 + ], + "pos": [ + -38.948036193847656, + -352.62060546875 + ] + } + ], + "outputs": [ + { + "id": "c8744662-e812-49b3-8bc8-744d557db6d6", + "name": "MESH", + "type": "MESH", + "linkIds": [ + 11 + ], + "localized_name": "MESH", + "pos": [ + 1110, + -290 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 7, + "type": "KSampler", + "pos": [ + 760, + -510 + ], + "size": [ + 270, + 262 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 19 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 5 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 6 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 7 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 8 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 894796671366012, + "randomize", + 30, + 5, + "euler", + "normal", + 1 + ] + }, + { + "id": 13, + "type": "CLIPVisionEncode", + "pos": [ + 450, + -410 + ], + "size": [ + 270, + 80 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_vision", + "name": "clip_vision", + "type": "CLIP_VISION", + "link": 20 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 21 + }, + { + "localized_name": "crop", + "name": "crop", + "type": "COMBO", + "widget": { + "name": "crop" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP_VISION_OUTPUT", + "name": "CLIP_VISION_OUTPUT", + "type": "CLIP_VISION_OUTPUT", + "links": [ + 22 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "CLIPVisionEncode" + }, + "widgets_values": [ + "center" + ] + }, + { + "id": 6, + "type": "Hunyuan3Dv2Conditioning", + "pos": [ + 510, + -280 + ], + "size": [ + 217.82578125, + 46 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_vision_output", + "name": "clip_vision_output", + "type": "CLIP_VISION_OUTPUT", + "link": 22 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 5 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 6 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "Hunyuan3Dv2Conditioning" + }, + "widgets_values": [] + }, + { + "id": 4, + "type": "EmptyLatentHunyuan3Dv2", + "pos": [ + 450, + -180 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "resolution", + "name": "resolution", + "type": "INT", + "widget": { + "name": "resolution" + }, + "link": null + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 7 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "EmptyLatentHunyuan3Dv2" + }, + "widgets_values": [ + 4096, + 1 + ] + }, + { + "id": 9, + "type": "VoxelToMesh", + "pos": [ + 760, + -40 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "voxel", + "name": "voxel", + "type": "VOXEL", + "link": 10 + }, + { + "localized_name": "algorithm", + "name": "algorithm", + "type": "COMBO", + "widget": { + "name": "algorithm" + }, + "link": null + }, + { + "localized_name": "threshold", + "name": "threshold", + "type": "FLOAT", + "widget": { + "name": "threshold" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MESH", + "name": "MESH", + "type": "MESH", + "links": [ + 11 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "VoxelToMesh" + }, + "widgets_values": [ + "surface net", + 0.6 + ] + }, + { + "id": 8, + "type": "VAEDecodeHunyuan3D", + "pos": [ + 760, + -200 + ], + "size": [ + 270, + 102 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 8 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 18 + }, + { + "localized_name": "num_chunks", + "name": "num_chunks", + "type": "INT", + "widget": { + "name": "num_chunks" + }, + "link": null + }, + { + "localized_name": "octree_resolution", + "name": "octree_resolution", + "type": "INT", + "widget": { + "name": "octree_resolution" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VOXEL", + "name": "VOXEL", + "type": "VOXEL", + "links": [ + 10 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "VAEDecodeHunyuan3D" + }, + "widgets_values": [ + 8000, + 256 + ] + }, + { + "id": 1, + "type": "ImageOnlyCheckpointLoader", + "pos": [ + 60, + -510 + ], + "size": [ + 356.0005859375, + 100 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 23 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 16 + ] + }, + { + "localized_name": "CLIP_VISION", + "name": "CLIP_VISION", + "type": "CLIP_VISION", + "links": [ + 20 + ] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 18 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ImageOnlyCheckpointLoader", + "models": [ + { + "name": "hunyuan_3d_v2.1.safetensors", + "url": "https://huggingface.co/Comfy-Org/hunyuan3D_2.1_repackaged/resolve/main/hunyuan_3d_v2.1.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "hunyuan_3d_v2.1.safetensors" + ] + }, + { + "id": 3, + "type": "ModelSamplingAuraFlow", + "pos": [ + 450, + -510 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 16 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 19 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.59", + "Node name for S&R": "ModelSamplingAuraFlow" + }, + "widgets_values": [ + 1 + ] + } + ], + "groups": [], + "links": [ + { + "id": 16, + "origin_id": 1, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 19, + "origin_id": 3, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 5, + "origin_id": 6, + "origin_slot": 0, + "target_id": 7, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 6, + "origin_id": 6, + "origin_slot": 1, + "target_id": 7, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 7, + "origin_id": 4, + "origin_slot": 0, + "target_id": 7, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 8, + "origin_id": 7, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 18, + "origin_id": 1, + "origin_slot": 2, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 10, + "origin_id": 8, + "origin_slot": 0, + "target_id": 9, + "target_slot": 0, + "type": "VOXEL" + }, + { + "id": 20, + "origin_id": 1, + "origin_slot": 1, + "target_id": 13, + "target_slot": 0, + "type": "CLIP_VISION" + }, + { + "id": 22, + "origin_id": 13, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "CLIP_VISION_OUTPUT" + }, + { + "id": 21, + "origin_id": -10, + "origin_slot": 0, + "target_id": 13, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 11, + "origin_id": 9, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "MESH" + }, + { + "id": 23, + "origin_id": -10, + "origin_slot": 1, + "target_id": 1, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "3D/Image to 3D Model" + } + ] + }, + "config": {}, + "extra": { + "ds": { + "scale": 0.620921323059155, + "offset": [ + 1636.2881100217016, + 965.23503257945 + ] + }, + "workflowRendererVersion": "LG" + }, + "version": 0.4 +} diff --git a/blueprints/Image to Video (LTX-2.3).json b/blueprints/Image to Video (LTX-2.3).json new file mode 100644 index 000000000..86a601130 --- /dev/null +++ b/blueprints/Image to Video (LTX-2.3).json @@ -0,0 +1,4233 @@ +{ + "revision": 0, + "last_node_id": 320, + "last_link_id": 0, + "nodes": [ + { + "id": 320, + "type": "2454ad83-157c-40dd-9f19-5daaf4041ce0", + "pos": [ + 30, + 4150 + ], + "size": [ + 390, + 466.625 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "first_frame", + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": null + }, + { + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": null + }, + { + "label": "width", + "name": "value_2", + "type": "INT", + "widget": { + "name": "value_2" + }, + "link": null + }, + { + "label": "height", + "name": "value_3", + "type": "INT", + "widget": { + "name": "value_3" + }, + "link": null + }, + { + "label": "duration", + "name": "value_4", + "type": "INT", + "widget": { + "name": "value_4" + }, + "link": null + }, + { + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": null + }, + { + "label": "distilled_lora", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": null + }, + { + "label": "latent_upscale_model", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": null + }, + { + "label": "fps", + "name": "value_5", + "type": "INT", + "widget": { + "name": "value_5" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "title": "Image to Video (LTX-2.3)", + "properties": { + "proxyWidgets": [ + [ + "319", + "value" + ], + [ + "312", + "value" + ], + [ + "299", + "value" + ], + [ + "301", + "value" + ], + [ + "300", + "value" + ], + [ + "316", + "ckpt_name" + ], + [ + "277", + "control_after_generate" + ], + [ + "277", + "noise_seed" + ], + [ + "285", + "lora_name" + ], + [ + "317", + "text_encoder" + ], + [ + "311", + "model_name" + ] + ], + "ue_properties": { + "widget_ue_connectable": { + "value_1": true, + "value_2": true, + "value_3": true, + "value_4": true, + "lora_name": true, + "model_name": true, + "value_5": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "2454ad83-157c-40dd-9f19-5daaf4041ce0", + "version": 1, + "state": { + "lastGroupId": 25, + "lastNodeId": 323, + "lastLinkId": 631, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Image to Video (LTX-2.3)", + "inputNode": { + "id": -10, + "bounding": [ + 730, + 4110, + 162.162109375, + 240 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 6590, + 4360, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "7afd6ea8-c738-4fd9-97b8-66fa905cd381", + "name": "input", + "type": "IMAGE,MASK", + "linkIds": [ + 535 + ], + "localized_name": "input", + "label": "first_frame", + "pos": [ + 872.162109375, + 4130 + ] + }, + { + "id": "9494c550-4172-49c6-930e-5b508f775e77", + "name": "value", + "type": "STRING", + "linkIds": [ + 595 + ], + "pos": [ + 872.162109375, + 4150 + ] + }, + { + "id": "58dbb3f6-f924-4548-96ef-e0e34610bd4e", + "name": "value_2", + "type": "INT", + "linkIds": [ + 597 + ], + "label": "width", + "pos": [ + 872.162109375, + 4170 + ] + }, + { + "id": "6086d5b8-2586-448c-a641-dd14d76dd102", + "name": "value_3", + "type": "INT", + "linkIds": [ + 598 + ], + "label": "height", + "pos": [ + 872.162109375, + 4190 + ] + }, + { + "id": "feb8c2eb-ae48-4fa8-bc24-929552d656c3", + "name": "value_4", + "type": "INT", + "linkIds": [ + 599 + ], + "label": "duration", + "pos": [ + 872.162109375, + 4210 + ] + }, + { + "id": "d7255058-319a-4880-8f9a-7e542c8f3c3c", + "name": "ckpt_name", + "type": "COMBO", + "linkIds": [ + 601, + 604, + 605 + ], + "pos": [ + 872.162109375, + 4230 + ] + }, + { + "id": "4afce68d-8f65-4342-9d6d-ae0a7688c3e3", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 602 + ], + "label": "distilled_lora", + "pos": [ + 872.162109375, + 4250 + ] + }, + { + "id": "ab842b4b-c977-4679-b421-424722785b57", + "name": "text_encoder", + "type": "COMBO", + "linkIds": [ + 606 + ], + "pos": [ + 872.162109375, + 4270 + ] + }, + { + "id": "9e47372d-28d9-4311-91e9-e90d03f4eb43", + "name": "model_name", + "type": "COMBO", + "linkIds": [ + 607 + ], + "label": "latent_upscale_model", + "pos": [ + 872.162109375, + 4290 + ] + }, + { + "id": "3e32ce15-0ae7-4cd0-909f-a354e8e9c4c9", + "name": "value_5", + "type": "INT", + "linkIds": [ + 624 + ], + "label": "fps", + "pos": [ + 872.162109375, + 4310 + ] + } + ], + "outputs": [ + { + "id": "954ef307-c897-4eea-8b5c-5c6ce15a5357", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 536 + ], + "localized_name": "VIDEO", + "pos": [ + 6610, + 4380 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 276, + "type": "RandomNoise", + "pos": [ + 4700, + 3650 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 490 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 42, + "fixed" + ] + }, + { + "id": 277, + "type": "RandomNoise", + "pos": [ + 3160, + 3630 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 483 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 519681071352364, + "randomize" + ] + }, + { + "id": 278, + "type": "LTXVConcatAVLatent", + "pos": [ + 4710, + 4490 + ], + "size": [ + 280, + 100 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 512 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 513 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 494 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 279, + "type": "LTXVAudioVAELoader", + "pos": [ + 1660, + 4100 + ], + "size": [ + 430, + 110 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 604 + } + ], + "outputs": [ + { + "localized_name": "Audio VAE", + "name": "Audio VAE", + "type": "VAE", + "links": [ + 481, + 496 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVAudioVAELoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-dev-fp8.safetensors" + ] + }, + { + "id": 280, + "type": "KSamplerSelect", + "pos": [ + 4700, + 4100 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 492 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler_cfg_pp" + ] + }, + { + "id": 281, + "type": "ManualSigmas", + "pos": [ + 4700, + 4290 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 493 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "0.85, 0.7250, 0.4219, 0.0" + ] + }, + { + "id": 282, + "type": "CFGGuider", + "pos": [ + 4700, + 3850 + ], + "size": [ + 280, + 160 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 478 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 479 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 480 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 491 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.71", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 283, + "type": "SamplerCustomAdvanced", + "pos": [ + 3550, + 3630 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 483 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 484 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 485 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 544 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 487 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 488 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 284, + "type": "LTXVCropGuides", + "pos": [ + 3830, + 3810 + ], + "size": [ + 250, + 120 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 475 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 476 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 477 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 479 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 480 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "slot_index": 2, + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVCropGuides", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 285, + "type": "LoraLoaderModelOnly", + "pos": [ + 1660, + 3890 + ], + "size": [ + 430, + 140 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 520 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 602 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 478, + 541 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "LoraLoaderModelOnly", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-distilled-lora-384.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-22b-distilled-lora-384.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-distilled-lora-384.safetensors", + 0.5 + ] + }, + { + "id": 286, + "type": "ResizeImagesByLongerEdge", + "pos": [ + 2070, + 4810 + ], + "size": [ + 310, + 110 + ], + "flags": { + "collapsed": false + }, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 523 + }, + { + "localized_name": "longer_edge", + "name": "longer_edge", + "type": "INT", + "widget": { + "name": "longer_edge" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "links": [ + 505 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ResizeImagesByLongerEdge", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1536 + ] + }, + { + "id": 287, + "type": "LTXVLatentUpsampler", + "pos": [ + 4250, + 3760 + ], + "size": [ + 330, + 120 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 547 + }, + { + "localized_name": "upscale_model", + "name": "upscale_model", + "type": "LATENT_UPSCALE_MODEL", + "link": 545 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 554 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 548 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "LTXVLatentUpsampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 288, + "type": "LTXVImgToVideoInplace", + "pos": [ + 4230, + 4100 + ], + "size": [ + 300, + 180 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 552 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 515 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 548 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 543 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 512 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 289, + "type": "LTXVPreprocess", + "pos": [ + 2100, + 5010 + ], + "size": [ + 290, + 110 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 505 + }, + { + "localized_name": "img_compression", + "name": "img_compression", + "type": "INT", + "widget": { + "name": "img_compression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "output_image", + "name": "output_image", + "type": "IMAGE", + "links": [ + 510, + 515 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVPreprocess", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 18 + ] + }, + { + "id": 290, + "type": "ResizeImageMaskNode", + "pos": [ + 1660, + 4810 + ], + "size": [ + 300, + 160 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": 535 + }, + { + "localized_name": "resize_type", + "name": "resize_type", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "resize_type" + }, + "link": null + }, + { + "localized_name": "width", + "name": "resize_type.width", + "type": "INT", + "widget": { + "name": "resize_type.width" + }, + "link": 558 + }, + { + "localized_name": "height", + "name": "resize_type.height", + "type": "INT", + "widget": { + "name": "resize_type.height" + }, + "link": 559 + }, + { + "localized_name": "crop", + "name": "resize_type.crop", + "type": "COMBO", + "widget": { + "name": "resize_type.crop" + }, + "link": null + }, + { + "localized_name": "scale_method", + "name": "scale_method", + "type": "COMBO", + "widget": { + "name": "scale_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "resized", + "name": "resized", + "type": "*", + "links": [ + 523 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "ResizeImageMaskNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "scale dimensions", + 1920, + 1088, + "center", + "lanczos" + ] + }, + { + "id": 291, + "type": "KSamplerSelect", + "pos": [ + 3160, + 4040 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 485 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler_ancestral_cfg_pp" + ] + }, + { + "id": 292, + "type": "ComfyMathExpression", + "pos": [ + 2540, + 4830 + ], + "size": [ + 210, + 80 + ], + "flags": { + "collapsed": true + }, + "order": 18, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 560 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 561 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "ComfyMathExpression", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "a/2" + ] + }, + { + "id": 293, + "type": "Reroute", + "pos": [ + 3850, + 4050 + ], + "size": [ + 230, + 40 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 557 + } + ], + "outputs": [ + { + "name": "", + "type": "VAE", + "links": [ + 552, + 553, + 554 + ] + } + ], + "properties": { + "showOutputText": false, + "horizontal": false, + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + } + } + }, + { + "id": 294, + "type": "ComfyMathExpression", + "pos": [ + 2550, + 4890 + ], + "size": [ + 210, + 80 + ], + "flags": { + "collapsed": true + }, + "order": 20, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 562 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 563 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "ComfyMathExpression", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "a/2" + ] + }, + { + "id": 295, + "type": "EmptyLTXVLatentVideo", + "pos": [ + 2870, + 4940 + ], + "size": [ + 280, + 200 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 561 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 563 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 631 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 511 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "EmptyLTXVLatentVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 512, + 97, + 1 + ] + }, + { + "id": 296, + "type": "LTXVImgToVideoInplace", + "pos": [ + 3230, + 4810 + ], + "size": [ + 280, + 180 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 556 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 510 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 511 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 542 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 497 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0.7, + false + ] + }, + { + "id": 297, + "type": "LTXVAudioVAEDecode", + "pos": [ + 5760, + 3970 + ], + "size": [ + 270, + 100 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 495 + }, + { + "label": "Audio VAE", + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 496 + } + ], + "outputs": [ + { + "localized_name": "Audio", + "name": "Audio", + "type": "AUDIO", + "links": [ + 534 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVAudioVAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 298, + "type": "ComfyMathExpression", + "pos": [ + 2540, + 5030 + ], + "size": [ + 210, + 80 + ], + "flags": { + "collapsed": true + }, + "order": 24, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 564 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 566, + 591 + ] + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 565 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "ComfyMathExpression", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "a" + ] + }, + { + "id": 299, + "type": "PrimitiveInt", + "pos": [ + 1190, + 4650 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 598 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 559, + 562 + ] + } + ], + "title": "Height", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 720, + "fixed" + ] + }, + { + "id": 300, + "type": "PrimitiveInt", + "pos": [ + 1190, + 4840 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 624 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 564, + 629 + ] + } + ], + "title": "Frame Rate", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25, + "fixed" + ] + }, + { + "id": 301, + "type": "PrimitiveInt", + "pos": [ + 1190, + 4280 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 599 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 628 + ] + } + ], + "title": "Duration", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 5, + "fixed" + ] + }, + { + "id": 302, + "type": "PrimitiveBoolean", + "pos": [ + 1190, + 4110 + ], + "size": [ + 370, + 100 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "BOOLEAN", + "name": "BOOLEAN", + "type": "BOOLEAN", + "links": [ + 542, + 543 + ] + } + ], + "title": "Switch to Text to Video?", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.0", + "Node name for S&R": "PrimitiveBoolean", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 303, + "type": "CLIPTextEncode", + "pos": [ + 2170, + 3640 + ], + "size": [ + 600, + 390 + ], + "flags": {}, + "order": 28, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 615 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 625 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 526 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 304, + "type": "LTXVConditioning", + "pos": [ + 2800, + 3810 + ], + "size": [ + 280, + 130 + ], + "flags": {}, + "order": 29, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 526 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 527 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "FLOAT", + "widget": { + "name": "frame_rate" + }, + "link": 566 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 475, + 518 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 476, + 519 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "LTXVConditioning", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 305, + "type": "LTXVEmptyLatentAudio", + "pos": [ + 3540, + 4960 + ], + "size": [ + 280, + 170 + ], + "flags": {}, + "order": 30, + "mode": 0, + "inputs": [ + { + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 481 + }, + { + "localized_name": "frames_number", + "name": "frames_number", + "type": "INT", + "widget": { + "name": "frames_number" + }, + "link": 630 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "INT", + "widget": { + "name": "frame_rate" + }, + "link": 565 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "Latent", + "name": "Latent", + "type": "LATENT", + "links": [ + 498 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVEmptyLatentAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 97, + 25, + 1 + ] + }, + { + "id": 306, + "type": "ManualSigmas", + "pos": [ + 3160, + 4220 + ], + "size": [ + 500, + 110 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 544 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "1.0, 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0" + ] + }, + { + "id": 307, + "type": "LTXVSeparateAVLatent", + "pos": [ + 3820, + 3630 + ], + "size": [ + 250, + 100 + ], + "flags": {}, + "order": 31, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 488 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 477, + 547 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 513 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 308, + "type": "SamplerCustomAdvanced", + "pos": [ + 5050, + 3650 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 32, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 490 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 491 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 492 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 493 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 494 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 578 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 309, + "type": "LTXVSeparateAVLatent", + "pos": [ + 5390, + 3650 + ], + "size": [ + 230, + 100 + ], + "flags": {}, + "order": 33, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 578 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 539 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 495 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 310, + "type": "CreateVideo", + "pos": [ + 6050, + 4490 + ], + "size": [ + 280, + 130 + ], + "flags": {}, + "order": 34, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 538 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 534 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 591 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 536 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CreateVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 311, + "type": "LatentUpscaleModelLoader", + "pos": [ + 1670, + 4550 + ], + "size": [ + 400, + 110 + ], + "flags": {}, + "order": 35, + "mode": 0, + "inputs": [ + { + "localized_name": "model_name", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": 607 + } + ], + "outputs": [ + { + "localized_name": "LATENT_UPSCALE_MODEL", + "name": "LATENT_UPSCALE_MODEL", + "type": "LATENT_UPSCALE_MODEL", + "links": [ + 545 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LatentUpscaleModelLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-spatial-upscaler-x2-1.1.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors", + "directory": "latent_upscale_models" + } + ] + }, + "widgets_values": [ + "ltx-2.3-spatial-upscaler-x2-1.1.safetensors" + ] + }, + { + "id": 312, + "type": "PrimitiveInt", + "pos": [ + 1190, + 4470 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 36, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 597 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 558, + 560 + ] + } + ], + "title": "Width", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1280, + "fixed" + ] + }, + { + "id": 313, + "type": "CLIPTextEncode", + "pos": [ + 2180, + 4120 + ], + "size": [ + 600, + 170 + ], + "flags": {}, + "order": 37, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 627 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 527 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "pc game, console game, video game, cartoon, childish, ugly" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 314, + "type": "CFGGuider", + "pos": [ + 3160, + 3810 + ], + "size": [ + 280, + 160 + ], + "flags": {}, + "order": 38, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 541 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 518 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 519 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 484 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 315, + "type": "VAEDecodeTiled", + "pos": [ + 5750, + 3610 + ], + "size": [ + 280, + 200 + ], + "flags": {}, + "order": 39, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 539 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 553 + }, + { + "localized_name": "tile_size", + "name": "tile_size", + "type": "INT", + "widget": { + "name": "tile_size" + }, + "link": null + }, + { + "localized_name": "overlap", + "name": "overlap", + "type": "INT", + "widget": { + "name": "overlap" + }, + "link": null + }, + { + "localized_name": "temporal_size", + "name": "temporal_size", + "type": "INT", + "widget": { + "name": "temporal_size" + }, + "link": null + }, + { + "localized_name": "temporal_overlap", + "name": "temporal_overlap", + "type": "INT", + "widget": { + "name": "temporal_overlap" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 538 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "VAEDecodeTiled", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 64, + 4096, + 4 + ] + }, + { + "id": 316, + "type": "CheckpointLoaderSimple", + "pos": [ + 1660, + 3660 + ], + "size": [ + 430, + 160 + ], + "flags": {}, + "order": 40, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 601 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 520 + ] + }, + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 556, + 557 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CheckpointLoaderSimple", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-dev-fp8.safetensors" + ] + }, + { + "id": 317, + "type": "LTXAVTextEncoderLoader", + "pos": [ + 1660, + 4280 + ], + "size": [ + 430, + 170 + ], + "flags": {}, + "order": 41, + "mode": 0, + "showAdvanced": false, + "inputs": [ + { + "localized_name": "text_encoder", + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": 606 + }, + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 605 + }, + { + "localized_name": "device", + "name": "device", + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 615, + 627 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXAVTextEncoderLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors", + "directory": "checkpoints" + }, + { + "name": "gemma_3_12B_it_fp4_mixed.safetensors", + "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2.3-22b-dev-fp8.safetensors", + "default" + ] + }, + { + "id": 318, + "type": "LTXVConcatAVLatent", + "pos": [ + 3860, + 4830 + ], + "size": [ + 240, + 100 + ], + "flags": {}, + "order": 42, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 497 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 498 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 487 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 319, + "type": "PrimitiveStringMultiline", + "pos": [ + 1190, + 3680 + ], + "size": [ + 370, + 350 + ], + "flags": {}, + "order": 43, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": 595 + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 625 + ] + } + ], + "title": "Prompt", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveStringMultiline", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ] + }, + { + "id": 323, + "type": "ComfyMathExpression", + "pos": [ + 1210, + 5040 + ], + "size": [ + 360, + 210 + ], + "flags": { + "collapsed": true + }, + "order": 44, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 628 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 629 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 630, + 631 + ] + } + ], + "title": "Math Expression (length)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "a * b + 1" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + 1630, + 3550, + 480, + 1140 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Generate Low Resolution", + "bounding": [ + 3130, + 3550, + 1000, + 1140 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + 2140, + 3550, + 960, + 1140 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Generate High Resolution", + "bounding": [ + 4670, + 3550, + 990, + 1130 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Lantent Upscale", + "bounding": [ + 4160, + 3550, + 480, + 1130 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 19, + "title": "Video Settings", + "bounding": [ + 1150, + 3550, + 460, + 1610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 20, + "title": "Image Preprocess", + "bounding": [ + 1630, + 4720, + 830, + 440 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 21, + "title": "Empty Latent", + "bounding": [ + 2820, + 4720, + 1310, + 450 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 22, + "title": "Number conversion", + "bounding": [ + 2480, + 4720, + 310, + 440 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 512, + "origin_id": 288, + "origin_slot": 0, + "target_id": 278, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 513, + "origin_id": 307, + "origin_slot": 1, + "target_id": 278, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 478, + "origin_id": 285, + "origin_slot": 0, + "target_id": 282, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 479, + "origin_id": 284, + "origin_slot": 0, + "target_id": 282, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 480, + "origin_id": 284, + "origin_slot": 1, + "target_id": 282, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 541, + "origin_id": 285, + "origin_slot": 0, + "target_id": 314, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 518, + "origin_id": 304, + "origin_slot": 0, + "target_id": 314, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 519, + "origin_id": 304, + "origin_slot": 1, + "target_id": 314, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 483, + "origin_id": 277, + "origin_slot": 0, + "target_id": 283, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 484, + "origin_id": 314, + "origin_slot": 0, + "target_id": 283, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 485, + "origin_id": 291, + "origin_slot": 0, + "target_id": 283, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 544, + "origin_id": 306, + "origin_slot": 0, + "target_id": 283, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 487, + "origin_id": 318, + "origin_slot": 0, + "target_id": 283, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 475, + "origin_id": 304, + "origin_slot": 0, + "target_id": 284, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 476, + "origin_id": 304, + "origin_slot": 1, + "target_id": 284, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 477, + "origin_id": 307, + "origin_slot": 0, + "target_id": 284, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 520, + "origin_id": 316, + "origin_slot": 0, + "target_id": 285, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 523, + "origin_id": 290, + "origin_slot": 0, + "target_id": 286, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 547, + "origin_id": 307, + "origin_slot": 0, + "target_id": 287, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 545, + "origin_id": 311, + "origin_slot": 0, + "target_id": 287, + "target_slot": 1, + "type": "LATENT_UPSCALE_MODEL" + }, + { + "id": 554, + "origin_id": 293, + "origin_slot": 0, + "target_id": 287, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 552, + "origin_id": 293, + "origin_slot": 0, + "target_id": 288, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 515, + "origin_id": 289, + "origin_slot": 0, + "target_id": 288, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 548, + "origin_id": 287, + "origin_slot": 0, + "target_id": 288, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 543, + "origin_id": 302, + "origin_slot": 0, + "target_id": 288, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 505, + "origin_id": 286, + "origin_slot": 0, + "target_id": 289, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 558, + "origin_id": 312, + "origin_slot": 0, + "target_id": 290, + "target_slot": 2, + "type": "INT" + }, + { + "id": 559, + "origin_id": 299, + "origin_slot": 0, + "target_id": 290, + "target_slot": 3, + "type": "INT" + }, + { + "id": 560, + "origin_id": 312, + "origin_slot": 0, + "target_id": 292, + "target_slot": 0, + "type": "INT" + }, + { + "id": 557, + "origin_id": 316, + "origin_slot": 2, + "target_id": 293, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 562, + "origin_id": 299, + "origin_slot": 0, + "target_id": 294, + "target_slot": 0, + "type": "INT" + }, + { + "id": 561, + "origin_id": 292, + "origin_slot": 1, + "target_id": 295, + "target_slot": 0, + "type": "INT" + }, + { + "id": 563, + "origin_id": 294, + "origin_slot": 1, + "target_id": 295, + "target_slot": 1, + "type": "INT" + }, + { + "id": 556, + "origin_id": 316, + "origin_slot": 2, + "target_id": 296, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 510, + "origin_id": 289, + "origin_slot": 0, + "target_id": 296, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 511, + "origin_id": 295, + "origin_slot": 0, + "target_id": 296, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 542, + "origin_id": 302, + "origin_slot": 0, + "target_id": 296, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 495, + "origin_id": 309, + "origin_slot": 1, + "target_id": 297, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 496, + "origin_id": 279, + "origin_slot": 0, + "target_id": 297, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 564, + "origin_id": 300, + "origin_slot": 0, + "target_id": 298, + "target_slot": 0, + "type": "INT" + }, + { + "id": 526, + "origin_id": 303, + "origin_slot": 0, + "target_id": 304, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 527, + "origin_id": 313, + "origin_slot": 0, + "target_id": 304, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 566, + "origin_id": 298, + "origin_slot": 0, + "target_id": 304, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 497, + "origin_id": 296, + "origin_slot": 0, + "target_id": 318, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 498, + "origin_id": 305, + "origin_slot": 0, + "target_id": 318, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 481, + "origin_id": 279, + "origin_slot": 0, + "target_id": 305, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 565, + "origin_id": 298, + "origin_slot": 1, + "target_id": 305, + "target_slot": 2, + "type": "INT" + }, + { + "id": 488, + "origin_id": 283, + "origin_slot": 0, + "target_id": 307, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 490, + "origin_id": 276, + "origin_slot": 0, + "target_id": 308, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 491, + "origin_id": 282, + "origin_slot": 0, + "target_id": 308, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 492, + "origin_id": 280, + "origin_slot": 0, + "target_id": 308, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 493, + "origin_id": 281, + "origin_slot": 0, + "target_id": 308, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 494, + "origin_id": 278, + "origin_slot": 0, + "target_id": 308, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 578, + "origin_id": 308, + "origin_slot": 0, + "target_id": 309, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 539, + "origin_id": 309, + "origin_slot": 0, + "target_id": 315, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 553, + "origin_id": 293, + "origin_slot": 0, + "target_id": 315, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 538, + "origin_id": 315, + "origin_slot": 0, + "target_id": 310, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 534, + "origin_id": 297, + "origin_slot": 0, + "target_id": 310, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 591, + "origin_id": 298, + "origin_slot": 0, + "target_id": 310, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 535, + "origin_id": -10, + "origin_slot": 0, + "target_id": 290, + "target_slot": 0, + "type": "IMAGE,MASK" + }, + { + "id": 536, + "origin_id": 310, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 595, + "origin_id": -10, + "origin_slot": 1, + "target_id": 319, + "target_slot": 0, + "type": "STRING" + }, + { + "id": 597, + "origin_id": -10, + "origin_slot": 2, + "target_id": 312, + "target_slot": 0, + "type": "INT" + }, + { + "id": 598, + "origin_id": -10, + "origin_slot": 3, + "target_id": 299, + "target_slot": 0, + "type": "INT" + }, + { + "id": 599, + "origin_id": -10, + "origin_slot": 4, + "target_id": 301, + "target_slot": 0, + "type": "INT" + }, + { + "id": 601, + "origin_id": -10, + "origin_slot": 5, + "target_id": 316, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 602, + "origin_id": -10, + "origin_slot": 6, + "target_id": 285, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 604, + "origin_id": -10, + "origin_slot": 5, + "target_id": 279, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 605, + "origin_id": -10, + "origin_slot": 5, + "target_id": 317, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 606, + "origin_id": -10, + "origin_slot": 7, + "target_id": 317, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 607, + "origin_id": -10, + "origin_slot": 8, + "target_id": 311, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 615, + "origin_id": 317, + "origin_slot": 0, + "target_id": 303, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 624, + "origin_id": -10, + "origin_slot": 9, + "target_id": 300, + "target_slot": 0, + "type": "INT" + }, + { + "id": 625, + "origin_id": 319, + "origin_slot": 0, + "target_id": 303, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 627, + "origin_id": 317, + "origin_slot": 0, + "target_id": 313, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 628, + "origin_id": 301, + "origin_slot": 0, + "target_id": 323, + "target_slot": 0, + "type": "INT" + }, + { + "id": 629, + "origin_id": 300, + "origin_slot": 0, + "target_id": 323, + "target_slot": 1, + "type": "INT" + }, + { + "id": 630, + "origin_id": 323, + "origin_slot": 1, + "target_id": 305, + "target_slot": 1, + "type": "INT" + }, + { + "id": 631, + "origin_id": 323, + "origin_slot": 1, + "target_id": 295, + "target_slot": 2, + "type": "INT" + } + ], + "extra": { + "workflowRendererVersion": "Vue-corrected" + }, + "category": "Video generation and editing/Image to video" + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Image to Video (Wan 2.2).json b/blueprints/Image to Video (Wan 2.2).json index cd0b44a72..a8dafd3c9 100644 --- a/blueprints/Image to Video (Wan 2.2).json +++ b/blueprints/Image to Video (Wan 2.2).json @@ -1 +1,2052 @@ -{"id": "ec7da562-7e21-4dac-a0d2-f4441e1efd3b", "revision": 0, "last_node_id": 119, "last_link_id": 231, "nodes": [{"id": 116, "type": "296b573f-1e7d-43df-a2df-925fe5e17063", "pos": [1098.3332694531493, -268.3334707134305], "size": [400, 470], "flags": {"collapsed": false}, "order": 0, "mode": 0, "inputs": [{"label": "start image", "localized_name": "start_image", "name": "start_image", "type": "IMAGE", "link": null}, {"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "width", "type": "INT", "widget": {"name": "width"}, "link": null}, {"name": "height", "type": "INT", "widget": {"name": "height"}, "link": null}, {"name": "length", "type": "INT", "widget": {"name": "length"}, "link": null}, {"label": "low_noise_unet", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"label": "low_noise_lora", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"label": "high_noise_unet", "name": "unet_name_1", "type": "COMBO", "widget": {"name": "unet_name_1"}, "link": null}, {"label": "high_noise_lora", "name": "lora_name_1", "type": "COMBO", "widget": {"name": "lora_name_1"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"name": "VIDEO", "type": "VIDEO", "links": null}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "width"], ["-1", "height"], ["-1", "length"], ["86", "noise_seed"], ["86", "control_after_generate"], ["-1", "unet_name"], ["-1", "lora_name"], ["-1", "unet_name_1"], ["-1", "lora_name_1"], ["-1", "clip_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.11.0"}, "widgets_values": ["", 640, 640, 81, null, null, "wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", "wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", "wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", "wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", "umt5_xxl_fp8_e4m3fn_scaled.safetensors", "wan_2.1_vae.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "296b573f-1e7d-43df-a2df-925fe5e17063", "version": 1, "state": {"lastGroupId": 16, "lastNodeId": 119, "lastLinkId": 231, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Image to Video (Wan 2.2)", "inputNode": {"id": -10, "bounding": [-250, 570, 131.435546875, 260]}, "outputNode": {"id": -20, "bounding": [1723.4786916118696, 716.3650158766799, 120, 60]}, "inputs": [{"id": "69d8b033-5601-446e-9634-f5cafbd373e2", "name": "start_image", "type": "IMAGE", "linkIds": [186], "localized_name": "start_image", "label": "start image", "shape": 7, "pos": [-138.564453125, 590]}, {"id": "88ae2af6-63c1-41be-90e8-6359f4d5f133", "name": "text", "type": "STRING", "linkIds": [222], "label": "prompt", "pos": [-138.564453125, 610]}, {"id": "fad9d346-653e-4be5-9e52-38cef6fa59f3", "name": "width", "type": "INT", "linkIds": [223], "pos": [-138.564453125, 630]}, {"id": "a4f34897-8063-4613-a2eb-6c2503167eb1", "name": "height", "type": "INT", "linkIds": [224], "pos": [-138.564453125, 650]}, {"id": "dc4d4472-cff7-41e0-9a4a-d118fcd4a21a", "name": "length", "type": "INT", "linkIds": [225], "pos": [-138.564453125, 670]}, {"id": "f7317e79-4a52-460b-9d71-89ec450dc333", "name": "unet_name", "type": "COMBO", "linkIds": [226], "label": "low_noise_unet", "pos": [-138.564453125, 690]}, {"id": "7a470f86-503a-474f-9571-830c8eb99231", "name": "lora_name", "type": "COMBO", "linkIds": [227], "label": "low_noise_lora", "pos": [-138.564453125, 710]}, {"id": "1d88c531-f68e-41b9-95c5-16f944a55b7d", "name": "unet_name_1", "type": "COMBO", "linkIds": [228], "label": "high_noise_unet", "pos": [-138.564453125, 730]}, {"id": "67a79742-33e5-4c38-89d8-ecb021d067c8", "name": "lora_name_1", "type": "COMBO", "linkIds": [229], "label": "high_noise_lora", "pos": [-138.564453125, 750]}, {"id": "9d184b83-37c6-4891-bbdf-ffcdf5ab2016", "name": "clip_name", "type": "COMBO", "linkIds": [230], "pos": [-138.564453125, 770]}, {"id": "24c568ec-aeb2-4c31-9f87-54ee9099d55f", "name": "vae_name", "type": "COMBO", "linkIds": [231], "pos": [-138.564453125, 790]}], "outputs": [{"id": "994c9c48-5f35-48ed-8c9d-0f2b21990cb6", "name": "VIDEO", "type": "VIDEO", "linkIds": [221], "pos": [1743.4786916118696, 736.3650158766799]}], "widgets": [], "nodes": [{"id": 84, "type": "CLIPLoader", "pos": [59.999957705045404, 29.99977085410412], "size": [346.38020833333337, 106], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 230}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "slot_index": 0, "links": [178, 181]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "CLIPLoader", "models": [{"name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors", "directory": "text_encoders"}], "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["umt5_xxl_fp8_e4m3fn_scaled.safetensors", "wan", "default"]}, {"id": 90, "type": "VAELoader", "pos": [59.999957705045404, 189.9997708925786], "size": [344.7265625, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 231}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [176, 185]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "VAELoader", "models": [{"name": "wan_2.1_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors", "directory": "vae"}], "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["wan_2.1_vae.safetensors"]}, {"id": 95, "type": "UNETLoader", "pos": [49.99996468306838, -230.00013148243067], "size": [346.7447916666667, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 226}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [194]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "UNETLoader", "models": [{"name": "wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", "directory": "diffusion_models"}], "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", "default"]}, {"id": 96, "type": "UNETLoader", "pos": [49.99996468306838, -100.00008258817711], "size": [346.7447916666667, 82], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 228}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [196]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "UNETLoader", "models": [{"name": "wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", "directory": "diffusion_models"}], "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", "default"]}, {"id": 103, "type": "ModelSamplingSD3", "pos": [739.9998741034308, -100.00008258817711], "size": [210, 58], "flags": {"collapsed": false}, "order": 12, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 189}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [192]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "ModelSamplingSD3", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": [5.000000000000001]}, {"id": 93, "type": "CLIPTextEncode", "pos": [439.99997175727736, 89.99984067280784], "size": [510, 88], "flags": {}, "order": 16, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 181}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 222}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [183]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "CLIPTextEncode", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 89, "type": "CLIPTextEncode", "pos": [439.99997175727736, 289.99986864261126], "size": [510, 88], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 178}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [184]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "CLIPTextEncode", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"], "color": "#322", "bgcolor": "#533"}, {"id": 101, "type": "LoraLoaderModelOnly", "pos": [449.99996477925447, -230.00013148243067], "size": [280, 82], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 194}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 227}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [190]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.49", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", "directory": "loras"}], "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", 1.0000000000000002]}, {"id": 102, "type": "LoraLoaderModelOnly", "pos": [449.99996477925447, -100.00008258817711], "size": [280, 82], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 196}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 229}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [189]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.49", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", "directory": "loras"}], "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", 1.0000000000000002]}, {"id": 104, "type": "ModelSamplingSD3", "pos": [739.9998741034308, -230.00013148243067], "size": [210, 58], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 190}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [195]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "ModelSamplingSD3", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": [5.000000000000001]}, {"id": 98, "type": "WanImageToVideo", "pos": [530.0000206419123, 529.9999245437435], "size": [342.59114583333337, 210], "flags": {}, "order": 17, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 183}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 184}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 185}, {"localized_name": "clip_vision_output", "name": "clip_vision_output", "shape": 7, "type": "CLIP_VISION_OUTPUT", "link": null}, {"localized_name": "start_image", "name": "start_image", "shape": 7, "type": "IMAGE", "link": 186}, {"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 223}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 224}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": 225}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "slot_index": 0, "links": [168, 172]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "slot_index": 1, "links": [169, 173]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "slot_index": 2, "links": [174]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "WanImageToVideo", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": [640, 640, 81, 1]}, {"id": 86, "type": "KSamplerAdvanced", "pos": [989.9999230265402, -250.00014544809514], "size": [304.73958333333337, 334], "flags": {}, "order": 14, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 195}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 172}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 173}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 174}, {"localized_name": "add_noise", "name": "add_noise", "type": "COMBO", "widget": {"name": "add_noise"}, "link": null}, {"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "start_at_step", "name": "start_at_step", "type": "INT", "widget": {"name": "start_at_step"}, "link": null}, {"localized_name": "end_at_step", "name": "end_at_step", "type": "INT", "widget": {"name": "end_at_step"}, "link": null}, {"localized_name": "return_with_leftover_noise", "name": "return_with_leftover_noise", "type": "COMBO", "widget": {"name": "return_with_leftover_noise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [170]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "KSamplerAdvanced", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["enable", 0, "randomize", 4, 1, "euler", "simple", 0, 2, "enable"]}, {"id": 85, "type": "KSamplerAdvanced", "pos": [1336.748028098344, -250.00014544809514], "size": [304.73958333333337, 334], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 192}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 168}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 169}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 170}, {"localized_name": "add_noise", "name": "add_noise", "type": "COMBO", "widget": {"name": "add_noise"}, "link": null}, {"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "start_at_step", "name": "start_at_step", "type": "INT", "widget": {"name": "start_at_step"}, "link": null}, {"localized_name": "end_at_step", "name": "end_at_step", "type": "INT", "widget": {"name": "end_at_step"}, "link": null}, {"localized_name": "return_with_leftover_noise", "name": "return_with_leftover_noise", "type": "COMBO", "widget": {"name": "return_with_leftover_noise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [175]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "KSamplerAdvanced", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["disable", 0, "fixed", 4, 1, "euler", "simple", 2, 4, "disable"]}, {"id": 67, "type": "Note", "pos": [510.0000345979581, 819.9999455547611], "size": [390, 88], "flags": {}, "order": 4, "mode": 0, "inputs": [], "outputs": [], "title": "Video Size", "properties": {"ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["By default, we set the video to a smaller size for users with low VRAM. If you have enough VRAM, you can change the size"], "color": "#222", "bgcolor": "#000"}, {"id": 105, "type": "MarkdownNote", "pos": [-469.9999795985529, 279.9998197772136], "size": [480, 170.65104166666669], "flags": {}, "order": 5, "mode": 0, "inputs": [], "outputs": [], "title": "VRAM Usage", "properties": {"ue_properties": {"version": "7.1", "widget_ue_connectable": {}, "input_ue_unconnectable": {}}}, "widgets_values": ["## GPU:RTX4090D 24GB\n\n| Model | Size |VRAM Usage | 1st Generation | 2nd Generation |\n|---------------------|-------|-----------|---------------|-----------------|\n| fp8_scaled |640*640| 84% | ≈ 536s | ≈ 513s |\n| fp8_scaled + 4steps LoRA | 640*640 | 83% | ≈ 97s | ≈ 71s |"], "color": "#222", "bgcolor": "#000"}, {"id": 66, "type": "MarkdownNote", "pos": [-469.9999795985529, -320.00012452364496], "size": [480, 572.1354166666667], "flags": {}, "order": 6, "mode": 0, "inputs": [], "outputs": [], "title": "Model Links", "properties": {"ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["[Tutorial](https://docs.comfy.org/tutorials/video/wan/wan2_2\n)\n\n**Diffusion Model**\n- [wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors)\n- [wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors)\n\n**LoRA**\n- [wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors)\n- [wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors)\n\n**VAE**\n- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)\n\n**Text Encoder** \n- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)\n\n\nFile save location\n\n```\nComfyUI/\n├───📂 models/\n│ ├───📂 diffusion_models/\n│ │ ├─── wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors\n│ │ └─── wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors\n│ ├───📂 loras/\n│ │ ├─── wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors\n│ │ └─── wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors\n│ ├───📂 text_encoders/\n│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors \n│ └───📂 vae/\n│ └── wan_2.1_vae.safetensors\n```\n"], "color": "#222", "bgcolor": "#000"}, {"id": 115, "type": "Note", "pos": [29.999978639114225, -470.00010361843204], "size": [360, 88], "flags": {}, "order": 7, "mode": 0, "inputs": [], "outputs": [], "title": "About 4 Steps LoRA", "properties": {"ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": ["Using the Wan2.2 Lighting LoRA will result in the loss of video dynamics, but it will reduce the generation time. This template provides two workflows, and you can enable one as needed."], "color": "#222", "bgcolor": "#000"}, {"id": 117, "type": "CreateVideo", "pos": [1030, 650], "size": [270, 78], "flags": {}, "order": 18, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 220}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [221]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "CreateVideo"}, "widgets_values": [16]}, {"id": 87, "type": "VAEDecode", "pos": [1020, 540], "size": [210, 46], "flags": {}, "order": 15, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 175}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 176}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [220]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "VAEDecode", "ue_properties": {"widget_ue_connectable": {}, "version": "7.1", "input_ue_unconnectable": {}}}, "widgets_values": []}], "groups": [{"id": 15, "title": "fp8_scaled + 4steps LoRA", "bounding": [30, -350, 1630, 1120], "color": "#444", "font_size": 24, "flags": {}}, {"id": 11, "title": "Step1 - Load models", "bounding": [40, -310, 371.0310363769531, 571.3974609375], "color": "#444", "font_size": 24, "flags": {}}, {"id": 13, "title": "Step4 - Prompt", "bounding": [430, 20, 530, 420], "color": "#444", "font_size": 24, "flags": {}}, {"id": 14, "title": "Step3 - Video size & length", "bounding": [430, 460, 530, 290], "color": "#444", "font_size": 24, "flags": {}}, {"id": 16, "title": "Lightx2v 4steps LoRA", "bounding": [430, -310, 530, 310], "color": "#444", "font_size": 24, "flags": {}}], "links": [{"id": 189, "origin_id": 102, "origin_slot": 0, "target_id": 103, "target_slot": 0, "type": "MODEL"}, {"id": 181, "origin_id": 84, "origin_slot": 0, "target_id": 93, "target_slot": 0, "type": "CLIP"}, {"id": 178, "origin_id": 84, "origin_slot": 0, "target_id": 89, "target_slot": 0, "type": "CLIP"}, {"id": 194, "origin_id": 95, "origin_slot": 0, "target_id": 101, "target_slot": 0, "type": "MODEL"}, {"id": 196, "origin_id": 96, "origin_slot": 0, "target_id": 102, "target_slot": 0, "type": "MODEL"}, {"id": 190, "origin_id": 101, "origin_slot": 0, "target_id": 104, "target_slot": 0, "type": "MODEL"}, {"id": 183, "origin_id": 93, "origin_slot": 0, "target_id": 98, "target_slot": 0, "type": "CONDITIONING"}, {"id": 184, "origin_id": 89, "origin_slot": 0, "target_id": 98, "target_slot": 1, "type": "CONDITIONING"}, {"id": 185, "origin_id": 90, "origin_slot": 0, "target_id": 98, "target_slot": 2, "type": "VAE"}, {"id": 175, "origin_id": 85, "origin_slot": 0, "target_id": 87, "target_slot": 0, "type": "LATENT"}, {"id": 176, "origin_id": 90, "origin_slot": 0, "target_id": 87, "target_slot": 1, "type": "VAE"}, {"id": 195, "origin_id": 104, "origin_slot": 0, "target_id": 86, "target_slot": 0, "type": "MODEL"}, {"id": 172, "origin_id": 98, "origin_slot": 0, "target_id": 86, "target_slot": 1, "type": "CONDITIONING"}, {"id": 173, "origin_id": 98, "origin_slot": 1, "target_id": 86, "target_slot": 2, "type": "CONDITIONING"}, {"id": 174, "origin_id": 98, "origin_slot": 2, "target_id": 86, "target_slot": 3, "type": "LATENT"}, {"id": 192, "origin_id": 103, "origin_slot": 0, "target_id": 85, "target_slot": 0, "type": "MODEL"}, {"id": 168, "origin_id": 98, "origin_slot": 0, "target_id": 85, "target_slot": 1, "type": "CONDITIONING"}, {"id": 169, "origin_id": 98, "origin_slot": 1, "target_id": 85, "target_slot": 2, "type": "CONDITIONING"}, {"id": 170, "origin_id": 86, "origin_slot": 0, "target_id": 85, "target_slot": 3, "type": "LATENT"}, {"id": 186, "origin_id": -10, "origin_slot": 0, "target_id": 98, "target_slot": 4, "type": "IMAGE"}, {"id": 220, "origin_id": 87, "origin_slot": 0, "target_id": 117, "target_slot": 0, "type": "IMAGE"}, {"id": 221, "origin_id": 117, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 222, "origin_id": -10, "origin_slot": 1, "target_id": 93, "target_slot": 1, "type": "STRING"}, {"id": 223, "origin_id": -10, "origin_slot": 2, "target_id": 98, "target_slot": 5, "type": "INT"}, {"id": 224, "origin_id": -10, "origin_slot": 3, "target_id": 98, "target_slot": 6, "type": "INT"}, {"id": 225, "origin_id": -10, "origin_slot": 4, "target_id": 98, "target_slot": 7, "type": "INT"}, {"id": 226, "origin_id": -10, "origin_slot": 5, "target_id": 95, "target_slot": 0, "type": "COMBO"}, {"id": 227, "origin_id": -10, "origin_slot": 6, "target_id": 101, "target_slot": 1, "type": "COMBO"}, {"id": 228, "origin_id": -10, "origin_slot": 7, "target_id": 96, "target_slot": 0, "type": "COMBO"}, {"id": 229, "origin_id": -10, "origin_slot": 8, "target_id": 102, "target_slot": 1, "type": "COMBO"}, {"id": 230, "origin_id": -10, "origin_slot": 9, "target_id": 84, "target_slot": 0, "type": "COMBO"}, {"id": 231, "origin_id": -10, "origin_slot": 10, "target_id": 90, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Image to video"}]}, "config": {}, "extra": {"ds": {"scale": 0.7926047855889957, "offset": [-30.12529469925767, 690.3829855122884]}, "frontendVersion": "1.37.11", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true, "ue_links": []}, "version": 0.4} +{ + "id": "ec7da562-7e21-4dac-a0d2-f4441e1efd3b", + "revision": 0, + "last_node_id": 119, + "last_link_id": 231, + "nodes": [ + { + "id": 116, + "type": "296b573f-1e7d-43df-a2df-925fe5e17063", + "pos": [ + 1098.3332694531493, + -268.3334707134305 + ], + "size": [ + 400, + 470 + ], + "flags": { + "collapsed": false + }, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "start image", + "localized_name": "start_image", + "name": "start_image", + "type": "IMAGE", + "link": null + }, + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": null + }, + { + "label": "low_noise_unet", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "label": "low_noise_lora", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "label": "high_noise_unet", + "name": "unet_name_1", + "type": "COMBO", + "widget": { + "name": "unet_name_1" + }, + "link": null + }, + { + "label": "high_noise_lora", + "name": "lora_name_1", + "type": "COMBO", + "widget": { + "name": "lora_name_1" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "name": "VIDEO", + "type": "VIDEO", + "links": null + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "width" + ], + [ + "-1", + "height" + ], + [ + "-1", + "length" + ], + [ + "86", + "noise_seed" + ], + [ + "86", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "lora_name" + ], + [ + "-1", + "unet_name_1" + ], + [ + "-1", + "lora_name_1" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.11.0" + }, + "widgets_values": [ + "", + 640, + 640, + 81, + null, + null, + "wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", + "wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", + "wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", + "wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", + "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "wan_2.1_vae.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "296b573f-1e7d-43df-a2df-925fe5e17063", + "version": 1, + "state": { + "lastGroupId": 16, + "lastNodeId": 119, + "lastLinkId": 231, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Image to Video (Wan 2.2)", + "inputNode": { + "id": -10, + "bounding": [ + -250, + 570, + 131.435546875, + 260 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1723.4786916118696, + 716.3650158766799, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "69d8b033-5601-446e-9634-f5cafbd373e2", + "name": "start_image", + "type": "IMAGE", + "linkIds": [ + 186 + ], + "localized_name": "start_image", + "label": "start image", + "shape": 7, + "pos": [ + -138.564453125, + 590 + ] + }, + { + "id": "88ae2af6-63c1-41be-90e8-6359f4d5f133", + "name": "text", + "type": "STRING", + "linkIds": [ + 222 + ], + "label": "prompt", + "pos": [ + -138.564453125, + 610 + ] + }, + { + "id": "fad9d346-653e-4be5-9e52-38cef6fa59f3", + "name": "width", + "type": "INT", + "linkIds": [ + 223 + ], + "pos": [ + -138.564453125, + 630 + ] + }, + { + "id": "a4f34897-8063-4613-a2eb-6c2503167eb1", + "name": "height", + "type": "INT", + "linkIds": [ + 224 + ], + "pos": [ + -138.564453125, + 650 + ] + }, + { + "id": "dc4d4472-cff7-41e0-9a4a-d118fcd4a21a", + "name": "length", + "type": "INT", + "linkIds": [ + 225 + ], + "pos": [ + -138.564453125, + 670 + ] + }, + { + "id": "f7317e79-4a52-460b-9d71-89ec450dc333", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 226 + ], + "label": "low_noise_unet", + "pos": [ + -138.564453125, + 690 + ] + }, + { + "id": "7a470f86-503a-474f-9571-830c8eb99231", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 227 + ], + "label": "low_noise_lora", + "pos": [ + -138.564453125, + 710 + ] + }, + { + "id": "1d88c531-f68e-41b9-95c5-16f944a55b7d", + "name": "unet_name_1", + "type": "COMBO", + "linkIds": [ + 228 + ], + "label": "high_noise_unet", + "pos": [ + -138.564453125, + 730 + ] + }, + { + "id": "67a79742-33e5-4c38-89d8-ecb021d067c8", + "name": "lora_name_1", + "type": "COMBO", + "linkIds": [ + 229 + ], + "label": "high_noise_lora", + "pos": [ + -138.564453125, + 750 + ] + }, + { + "id": "9d184b83-37c6-4891-bbdf-ffcdf5ab2016", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 230 + ], + "pos": [ + -138.564453125, + 770 + ] + }, + { + "id": "24c568ec-aeb2-4c31-9f87-54ee9099d55f", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 231 + ], + "pos": [ + -138.564453125, + 790 + ] + } + ], + "outputs": [ + { + "id": "994c9c48-5f35-48ed-8c9d-0f2b21990cb6", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 221 + ], + "pos": [ + 1743.4786916118696, + 736.3650158766799 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 84, + "type": "CLIPLoader", + "pos": [ + 59.999957705045404, + 29.99977085410412 + ], + "size": [ + 346.38020833333337, + 106 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 230 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 178, + 181 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "directory": "text_encoders" + } + ], + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "wan", + "default" + ] + }, + { + "id": 90, + "type": "VAELoader", + "pos": [ + 59.999957705045404, + 189.9997708925786 + ], + "size": [ + 344.7265625, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 231 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 176, + 185 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "wan_2.1_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors", + "directory": "vae" + } + ], + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "wan_2.1_vae.safetensors" + ] + }, + { + "id": 95, + "type": "UNETLoader", + "pos": [ + 49.99996468306838, + -230.00013148243067 + ], + "size": [ + 346.7447916666667, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 226 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 194 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", + "directory": "diffusion_models" + } + ], + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors", + "default" + ] + }, + { + "id": 96, + "type": "UNETLoader", + "pos": [ + 49.99996468306838, + -100.00008258817711 + ], + "size": [ + 346.7447916666667, + 82 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 228 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 196 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", + "directory": "diffusion_models" + } + ], + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors", + "default" + ] + }, + { + "id": 103, + "type": "ModelSamplingSD3", + "pos": [ + 739.9998741034308, + -100.00008258817711 + ], + "size": [ + 210, + 58 + ], + "flags": { + "collapsed": false + }, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 189 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 192 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "ModelSamplingSD3", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + 5.000000000000001 + ] + }, + { + "id": 93, + "type": "CLIPTextEncode", + "pos": [ + 439.99997175727736, + 89.99984067280784 + ], + "size": [ + 510, + 88 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 181 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 222 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 183 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "CLIPTextEncode", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 89, + "type": "CLIPTextEncode", + "pos": [ + 439.99997175727736, + 289.99986864261126 + ], + "size": [ + 510, + 88 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 178 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 184 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "CLIPTextEncode", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 101, + "type": "LoraLoaderModelOnly", + "pos": [ + 449.99996477925447, + -230.00013148243067 + ], + "size": [ + 280, + 82 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 194 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 227 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 190 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.49", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", + "directory": "loras" + } + ], + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors", + 1.0000000000000002 + ] + }, + { + "id": 102, + "type": "LoraLoaderModelOnly", + "pos": [ + 449.99996477925447, + -100.00008258817711 + ], + "size": [ + 280, + 82 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 196 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 229 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 189 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.49", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", + "directory": "loras" + } + ], + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors", + 1.0000000000000002 + ] + }, + { + "id": 104, + "type": "ModelSamplingSD3", + "pos": [ + 739.9998741034308, + -230.00013148243067 + ], + "size": [ + 210, + 58 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 190 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 195 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "ModelSamplingSD3", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + 5.000000000000001 + ] + }, + { + "id": 98, + "type": "WanImageToVideo", + "pos": [ + 530.0000206419123, + 529.9999245437435 + ], + "size": [ + 342.59114583333337, + 210 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 183 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 184 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 185 + }, + { + "localized_name": "clip_vision_output", + "name": "clip_vision_output", + "shape": 7, + "type": "CLIP_VISION_OUTPUT", + "link": null + }, + { + "localized_name": "start_image", + "name": "start_image", + "shape": 7, + "type": "IMAGE", + "link": 186 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 223 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 224 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 225 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 168, + 172 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "slot_index": 1, + "links": [ + 169, + 173 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "slot_index": 2, + "links": [ + 174 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "WanImageToVideo", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + 640, + 640, + 81, + 1 + ] + }, + { + "id": 86, + "type": "KSamplerAdvanced", + "pos": [ + 989.9999230265402, + -250.00014544809514 + ], + "size": [ + 304.73958333333337, + 334 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 195 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 172 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 173 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 174 + }, + { + "localized_name": "add_noise", + "name": "add_noise", + "type": "COMBO", + "widget": { + "name": "add_noise" + }, + "link": null + }, + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "start_at_step", + "name": "start_at_step", + "type": "INT", + "widget": { + "name": "start_at_step" + }, + "link": null + }, + { + "localized_name": "end_at_step", + "name": "end_at_step", + "type": "INT", + "widget": { + "name": "end_at_step" + }, + "link": null + }, + { + "localized_name": "return_with_leftover_noise", + "name": "return_with_leftover_noise", + "type": "COMBO", + "widget": { + "name": "return_with_leftover_noise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 170 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "KSamplerAdvanced", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "enable", + 0, + "randomize", + 4, + 1, + "euler", + "simple", + 0, + 2, + "enable" + ] + }, + { + "id": 85, + "type": "KSamplerAdvanced", + "pos": [ + 1336.748028098344, + -250.00014544809514 + ], + "size": [ + 304.73958333333337, + 334 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 192 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 168 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 169 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 170 + }, + { + "localized_name": "add_noise", + "name": "add_noise", + "type": "COMBO", + "widget": { + "name": "add_noise" + }, + "link": null + }, + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "start_at_step", + "name": "start_at_step", + "type": "INT", + "widget": { + "name": "start_at_step" + }, + "link": null + }, + { + "localized_name": "end_at_step", + "name": "end_at_step", + "type": "INT", + "widget": { + "name": "end_at_step" + }, + "link": null + }, + { + "localized_name": "return_with_leftover_noise", + "name": "return_with_leftover_noise", + "type": "COMBO", + "widget": { + "name": "return_with_leftover_noise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 175 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "KSamplerAdvanced", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "disable", + 0, + "fixed", + 4, + 1, + "euler", + "simple", + 2, + 4, + "disable" + ] + }, + { + "id": 67, + "type": "Note", + "pos": [ + 510.0000345979581, + 819.9999455547611 + ], + "size": [ + 390, + 88 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Video Size", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "By default, we set the video to a smaller size for users with low VRAM. If you have enough VRAM, you can change the size" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 105, + "type": "MarkdownNote", + "pos": [ + -469.9999795985529, + 279.9998197772136 + ], + "size": [ + 480, + 170.65104166666669 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "VRAM Usage", + "properties": { + "ue_properties": { + "version": "7.1", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "## GPU:RTX4090D 24GB\n\n| Model | Size |VRAM Usage | 1st Generation | 2nd Generation |\n|---------------------|-------|-----------|---------------|-----------------|\n| fp8_scaled |640*640| 84% | ≈ 536s | ≈ 513s |\n| fp8_scaled + 4steps LoRA | 640*640 | 83% | ≈ 97s | ≈ 71s |" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 66, + "type": "MarkdownNote", + "pos": [ + -469.9999795985529, + -320.00012452364496 + ], + "size": [ + 480, + 572.1354166666667 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Model Links", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "[Tutorial](https://docs.comfy.org/tutorials/video/wan/wan2_2\n)\n\n**Diffusion Model**\n- [wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors)\n- [wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors)\n\n**LoRA**\n- [wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors)\n- [wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors)\n\n**VAE**\n- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)\n\n**Text Encoder** \n- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)\n\n\nFile save location\n\n```\nComfyUI/\n├───📂 models/\n│ ├───📂 diffusion_models/\n│ │ ├─── wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors\n│ │ └─── wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors\n│ ├───📂 loras/\n│ │ ├─── wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors\n│ │ └─── wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors\n│ ├───📂 text_encoders/\n│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors \n│ └───📂 vae/\n│ └── wan_2.1_vae.safetensors\n```\n" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 115, + "type": "Note", + "pos": [ + 29.999978639114225, + -470.00010361843204 + ], + "size": [ + 360, + 88 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "About 4 Steps LoRA", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "Using the Wan2.2 Lighting LoRA will result in the loss of video dynamics, but it will reduce the generation time. This template provides two workflows, and you can enable one as needed." + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 117, + "type": "CreateVideo", + "pos": [ + 1030, + 650 + ], + "size": [ + 270, + 78 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 220 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": null + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 221 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.0", + "Node name for S&R": "CreateVideo" + }, + "widgets_values": [ + 16 + ] + }, + { + "id": 87, + "type": "VAEDecode", + "pos": [ + 1020, + 540 + ], + "size": [ + 210, + 46 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 175 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 176 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 220 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "VAEDecode", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.1", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [] + } + ], + "groups": [ + { + "id": 15, + "title": "fp8_scaled + 4steps LoRA", + "bounding": [ + 30, + -350, + 1630, + 1120 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 11, + "title": "Step1 - Load models", + "bounding": [ + 40, + -310, + 371.0310363769531, + 571.3974609375 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 13, + "title": "Step4 - Prompt", + "bounding": [ + 430, + 20, + 530, + 420 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 14, + "title": "Step3 - Video size & length", + "bounding": [ + 430, + 460, + 530, + 290 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 16, + "title": "Lightx2v 4steps LoRA", + "bounding": [ + 430, + -310, + 530, + 310 + ], + "color": "#444", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 189, + "origin_id": 102, + "origin_slot": 0, + "target_id": 103, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 181, + "origin_id": 84, + "origin_slot": 0, + "target_id": 93, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 178, + "origin_id": 84, + "origin_slot": 0, + "target_id": 89, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 194, + "origin_id": 95, + "origin_slot": 0, + "target_id": 101, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 196, + "origin_id": 96, + "origin_slot": 0, + "target_id": 102, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 190, + "origin_id": 101, + "origin_slot": 0, + "target_id": 104, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 183, + "origin_id": 93, + "origin_slot": 0, + "target_id": 98, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 184, + "origin_id": 89, + "origin_slot": 0, + "target_id": 98, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 185, + "origin_id": 90, + "origin_slot": 0, + "target_id": 98, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 175, + "origin_id": 85, + "origin_slot": 0, + "target_id": 87, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 176, + "origin_id": 90, + "origin_slot": 0, + "target_id": 87, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 195, + "origin_id": 104, + "origin_slot": 0, + "target_id": 86, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 172, + "origin_id": 98, + "origin_slot": 0, + "target_id": 86, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 173, + "origin_id": 98, + "origin_slot": 1, + "target_id": 86, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 174, + "origin_id": 98, + "origin_slot": 2, + "target_id": 86, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 192, + "origin_id": 103, + "origin_slot": 0, + "target_id": 85, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 168, + "origin_id": 98, + "origin_slot": 0, + "target_id": 85, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 169, + "origin_id": 98, + "origin_slot": 1, + "target_id": 85, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 170, + "origin_id": 86, + "origin_slot": 0, + "target_id": 85, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 186, + "origin_id": -10, + "origin_slot": 0, + "target_id": 98, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 220, + "origin_id": 87, + "origin_slot": 0, + "target_id": 117, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 221, + "origin_id": 117, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 222, + "origin_id": -10, + "origin_slot": 1, + "target_id": 93, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 223, + "origin_id": -10, + "origin_slot": 2, + "target_id": 98, + "target_slot": 5, + "type": "INT" + }, + { + "id": 224, + "origin_id": -10, + "origin_slot": 3, + "target_id": 98, + "target_slot": 6, + "type": "INT" + }, + { + "id": 225, + "origin_id": -10, + "origin_slot": 4, + "target_id": 98, + "target_slot": 7, + "type": "INT" + }, + { + "id": 226, + "origin_id": -10, + "origin_slot": 5, + "target_id": 95, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 227, + "origin_id": -10, + "origin_slot": 6, + "target_id": 101, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 228, + "origin_id": -10, + "origin_slot": 7, + "target_id": 96, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 229, + "origin_id": -10, + "origin_slot": 8, + "target_id": 102, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 230, + "origin_id": -10, + "origin_slot": 9, + "target_id": 84, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 231, + "origin_id": -10, + "origin_slot": 10, + "target_id": 90, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video generation and editing/Image to video" + } + ] + }, + "config": {}, + "extra": { + "ds": { + "scale": 0.7926047855889957, + "offset": [ + -30.12529469925767, + 690.3829855122884 + ] + }, + "frontendVersion": "1.37.11", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [] + }, + "version": 0.4 +} diff --git a/blueprints/Pose to Image (Z-Image-Turbo).json b/blueprints/Pose to Image (Z-Image-Turbo).json index f4c224249..a55410ba4 100644 --- a/blueprints/Pose to Image (Z-Image-Turbo).json +++ b/blueprints/Pose to Image (Z-Image-Turbo).json @@ -1 +1,1322 @@ -{"id": "e046dd74-e2a7-4f31-a75b-5e11a8c72d4e", "revision": 0, "last_node_id": 26, "last_link_id": 46, "nodes": [{"id": 13, "type": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", "pos": [400, 3630], "size": [400, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image", "name": "image", "type": "IMAGE", "link": null}, {"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}, {"name": "name", "type": "COMBO", "widget": {"name": "name"}, "link": null}], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": null}], "properties": {"proxyWidgets": [["-1", "text"], ["19", "seed"], ["19", "control_after_generate"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"], ["-1", "name"]], "cnr_id": "comfy-core", "ver": "0.11.0"}, "widgets_values": ["", null, null, "z_image_turbo_bf16.safetensors", "qwen_3_4b.safetensors", "ae.safetensors", "Z-Image-Turbo-Fun-Controlnet-Union.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", "version": 1, "state": {"lastGroupId": 3, "lastNodeId": 26, "lastLinkId": 46, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Pose to Image (Z-Image-Turbo)", "inputNode": {"id": -10, "bounding": [27.60368520069494, 4936.043696127976, 120, 160]}, "outputNode": {"id": -20, "bounding": [1598.6038576146689, 4936.043696127976, 120, 60]}, "inputs": [{"id": "29ca271b-8f63-4e7b-a4b8-c9b4192ada0b", "name": "image", "type": "IMAGE", "linkIds": [41, 42], "label": "image", "pos": [127.60368520069494, 4956.043696127976]}, {"id": "b6549f90-39ee-4b79-9e00-af4d9df969fe", "name": "text", "type": "STRING", "linkIds": [37], "label": "prompt", "pos": [127.60368520069494, 4976.043696127976]}, {"id": "9f23df20-75de-4782-8ff7-225bc7976bbe", "name": "unet_name", "type": "COMBO", "linkIds": [43], "pos": [127.60368520069494, 4996.043696127976]}, {"id": "fc8aa3eb-a537-4976-8b5f-666f0dc5af4b", "name": "clip_name", "type": "COMBO", "linkIds": [44], "pos": [127.60368520069494, 5016.043696127976]}, {"id": "ed2c5269-91ac-4f93-b68d-6b546cef20d8", "name": "vae_name", "type": "COMBO", "linkIds": [45], "pos": [127.60368520069494, 5036.043696127976]}, {"id": "560ba519-ec0c-4ca4-b8f0-f02174012475", "name": "name", "type": "COMBO", "linkIds": [46], "pos": [127.60368520069494, 5056.043696127976]}], "outputs": [{"id": "47f9a22d-6619-4917-9447-a7d5d08dceb5", "name": "IMAGE", "type": "IMAGE", "linkIds": [35], "pos": [1618.6038576146689, 4956.043696127976]}], "widgets": [], "nodes": [{"id": 14, "type": "CLIPLoader", "pos": [340, 4820], "size": [269.9609375, 106], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 44}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [33]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_3_4b.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_3_4b.safetensors", "lumina2", "default"]}, {"id": 15, "type": "UNETLoader", "pos": [340, 4670], "size": [269.9609375, 82], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 43}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [28]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "UNETLoader", "models": [{"name": "z_image_turbo_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["z_image_turbo_bf16.safetensors", "default"]}, {"id": 16, "type": "VAELoader", "pos": [340, 5000], "size": [269.9609375, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 45}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [21, 30]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "VAELoader", "models": [{"name": "ae.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ae.safetensors"]}, {"id": 17, "type": "ModelPatchLoader", "pos": [340, 5130], "size": [269.9609375, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "name", "name": "name", "type": "COMBO", "widget": {"name": "name"}, "link": 46}], "outputs": [{"localized_name": "MODEL_PATCH", "name": "MODEL_PATCH", "type": "MODEL_PATCH", "links": [29]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.51", "Node name for S&R": "ModelPatchLoader", "models": [{"name": "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", "url": "https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union/resolve/main/Z-Image-Turbo-Fun-Controlnet-Union.safetensors", "directory": "model_patches"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["Z-Image-Turbo-Fun-Controlnet-Union.safetensors"]}, {"id": 18, "type": "ModelSamplingAuraFlow", "pos": [1110, 4610], "size": [289.97395833333337, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 22}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [23]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "ModelSamplingAuraFlow", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 19, "type": "KSampler", "pos": [1110, 4720], "size": [300, 309.9609375], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 23}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 24}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 25}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 26}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [20]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize", 9, 1, "res_multistep", "simple", 1]}, {"id": 20, "type": "ConditioningZeroOut", "pos": [860, 5160], "size": [204.134765625, 26], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 27}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [25]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "ConditioningZeroOut", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 21, "type": "QwenImageDiffsynthControlnet", "pos": [720, 5320], "size": [289.97395833333337, 138], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 28}, {"localized_name": "model_patch", "name": "model_patch", "type": "MODEL_PATCH", "link": 29}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 30}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 42}, {"localized_name": "mask", "name": "mask", "shape": 7, "type": "MASK", "link": null}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [22]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.76", "Node name for S&R": "QwenImageDiffsynthControlnet", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 23, "type": "CLIPTextEncode", "pos": [660, 4660], "size": [400, 179.9609375], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 33}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 37}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [24, 27]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 24, "type": "VAEDecode", "pos": [1450, 4620], "size": [200, 46], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 20}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 21}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [35]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 25, "type": "GetImageSize", "pos": [330, 5540], "size": [140, 66], "flags": {"collapsed": false}, "order": 11, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 41}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [31]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [32]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.76", "Node name for S&R": "GetImageSize", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 22, "type": "EmptySD3LatentImage", "pos": [1110, 5540], "size": [259.9609375, 106], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 31}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 32}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [26]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "EmptySD3LatentImage", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1024, 1024, 1]}], "groups": [{"id": 1, "title": "Prompt", "bounding": [640, 4590, 440, 630], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Models", "bounding": [320, 4590, 300, 640], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Apple ControlNet", "bounding": [640, 5240, 440, 260], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 20, "origin_id": 19, "origin_slot": 0, "target_id": 24, "target_slot": 0, "type": "LATENT"}, {"id": 21, "origin_id": 16, "origin_slot": 0, "target_id": 24, "target_slot": 1, "type": "VAE"}, {"id": 22, "origin_id": 21, "origin_slot": 0, "target_id": 18, "target_slot": 0, "type": "MODEL"}, {"id": 23, "origin_id": 18, "origin_slot": 0, "target_id": 19, "target_slot": 0, "type": "MODEL"}, {"id": 24, "origin_id": 23, "origin_slot": 0, "target_id": 19, "target_slot": 1, "type": "CONDITIONING"}, {"id": 25, "origin_id": 20, "origin_slot": 0, "target_id": 19, "target_slot": 2, "type": "CONDITIONING"}, {"id": 26, "origin_id": 22, "origin_slot": 0, "target_id": 19, "target_slot": 3, "type": "LATENT"}, {"id": 27, "origin_id": 23, "origin_slot": 0, "target_id": 20, "target_slot": 0, "type": "CONDITIONING"}, {"id": 28, "origin_id": 15, "origin_slot": 0, "target_id": 21, "target_slot": 0, "type": "MODEL"}, {"id": 29, "origin_id": 17, "origin_slot": 0, "target_id": 21, "target_slot": 1, "type": "MODEL_PATCH"}, {"id": 30, "origin_id": 16, "origin_slot": 0, "target_id": 21, "target_slot": 2, "type": "VAE"}, {"id": 31, "origin_id": 25, "origin_slot": 0, "target_id": 22, "target_slot": 0, "type": "INT"}, {"id": 32, "origin_id": 25, "origin_slot": 1, "target_id": 22, "target_slot": 1, "type": "INT"}, {"id": 33, "origin_id": 14, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "CLIP"}, {"id": 35, "origin_id": 24, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 37, "origin_id": -10, "origin_slot": 1, "target_id": 23, "target_slot": 1, "type": "STRING"}, {"id": 41, "origin_id": -10, "origin_slot": 0, "target_id": 25, "target_slot": 0, "type": "IMAGE"}, {"id": 42, "origin_id": -10, "origin_slot": 0, "target_id": 21, "target_slot": 3, "type": "IMAGE"}, {"id": 43, "origin_id": -10, "origin_slot": 2, "target_id": 15, "target_slot": 0, "type": "COMBO"}, {"id": 44, "origin_id": -10, "origin_slot": 3, "target_id": 14, "target_slot": 0, "type": "COMBO"}, {"id": 45, "origin_id": -10, "origin_slot": 4, "target_id": 16, "target_slot": 0, "type": "COMBO"}, {"id": 46, "origin_id": -10, "origin_slot": 5, "target_id": 17, "target_slot": 0, "type": "COMBO"}], "extra": {"frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true}, "category": "Image generation and editing/Pose to image"}]}, "config": {}, "extra": {"frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true, "ds": {"scale": 0.6479518372239997, "offset": [852.9773200429215, -3036.34291480022]}}, "version": 0.4} +{ + "id": "e046dd74-e2a7-4f31-a75b-5e11a8c72d4e", + "revision": 0, + "last_node_id": 26, + "last_link_id": 46, + "nodes": [ + { + "id": 13, + "type": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", + "pos": [ + 400, + 3630 + ], + "size": [ + 400, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "image", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "name": "name", + "type": "COMBO", + "widget": { + "name": "name" + }, + "link": null + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "19", + "seed" + ], + [ + "19", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ], + [ + "-1", + "name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.11.0" + }, + "widgets_values": [ + "", + null, + null, + "z_image_turbo_bf16.safetensors", + "qwen_3_4b.safetensors", + "ae.safetensors", + "Z-Image-Turbo-Fun-Controlnet-Union.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "d8492a46-9e6c-4917-b5ea-4273aabf5f51", + "version": 1, + "state": { + "lastGroupId": 3, + "lastNodeId": 26, + "lastLinkId": 46, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Pose to Image (Z-Image-Turbo)", + "inputNode": { + "id": -10, + "bounding": [ + 27.60368520069494, + 4936.043696127976, + 120, + 160 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1598.6038576146689, + 4936.043696127976, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "29ca271b-8f63-4e7b-a4b8-c9b4192ada0b", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 41, + 42 + ], + "label": "image", + "pos": [ + 127.60368520069494, + 4956.043696127976 + ] + }, + { + "id": "b6549f90-39ee-4b79-9e00-af4d9df969fe", + "name": "text", + "type": "STRING", + "linkIds": [ + 37 + ], + "label": "prompt", + "pos": [ + 127.60368520069494, + 4976.043696127976 + ] + }, + { + "id": "9f23df20-75de-4782-8ff7-225bc7976bbe", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 43 + ], + "pos": [ + 127.60368520069494, + 4996.043696127976 + ] + }, + { + "id": "fc8aa3eb-a537-4976-8b5f-666f0dc5af4b", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 44 + ], + "pos": [ + 127.60368520069494, + 5016.043696127976 + ] + }, + { + "id": "ed2c5269-91ac-4f93-b68d-6b546cef20d8", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 45 + ], + "pos": [ + 127.60368520069494, + 5036.043696127976 + ] + }, + { + "id": "560ba519-ec0c-4ca4-b8f0-f02174012475", + "name": "name", + "type": "COMBO", + "linkIds": [ + 46 + ], + "pos": [ + 127.60368520069494, + 5056.043696127976 + ] + } + ], + "outputs": [ + { + "id": "47f9a22d-6619-4917-9447-a7d5d08dceb5", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 35 + ], + "pos": [ + 1618.6038576146689, + 4956.043696127976 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 14, + "type": "CLIPLoader", + "pos": [ + 340, + 4820 + ], + "size": [ + 269.9609375, + 106 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 44 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 33 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_3_4b.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_3_4b.safetensors", + "lumina2", + "default" + ] + }, + { + "id": 15, + "type": "UNETLoader", + "pos": [ + 340, + 4670 + ], + "size": [ + 269.9609375, + 82 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 43 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 28 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "z_image_turbo_bf16.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "z_image_turbo_bf16.safetensors", + "default" + ] + }, + { + "id": 16, + "type": "VAELoader", + "pos": [ + 340, + 5000 + ], + "size": [ + 269.9609375, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 45 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 21, + 30 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 17, + "type": "ModelPatchLoader", + "pos": [ + 340, + 5130 + ], + "size": [ + 269.9609375, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "name", + "name": "name", + "type": "COMBO", + "widget": { + "name": "name" + }, + "link": 46 + } + ], + "outputs": [ + { + "localized_name": "MODEL_PATCH", + "name": "MODEL_PATCH", + "type": "MODEL_PATCH", + "links": [ + 29 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.51", + "Node name for S&R": "ModelPatchLoader", + "models": [ + { + "name": "Z-Image-Turbo-Fun-Controlnet-Union.safetensors", + "url": "https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union/resolve/main/Z-Image-Turbo-Fun-Controlnet-Union.safetensors", + "directory": "model_patches" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "Z-Image-Turbo-Fun-Controlnet-Union.safetensors" + ] + }, + { + "id": 18, + "type": "ModelSamplingAuraFlow", + "pos": [ + 1110, + 4610 + ], + "size": [ + 289.97395833333337, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 22 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 23 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 19, + "type": "KSampler", + "pos": [ + 1110, + 4720 + ], + "size": [ + 300, + 309.9609375 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 23 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 24 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 25 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 26 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 20 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize", + 9, + 1, + "res_multistep", + "simple", + 1 + ] + }, + { + "id": 20, + "type": "ConditioningZeroOut", + "pos": [ + 860, + 5160 + ], + "size": [ + 204.134765625, + 26 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 27 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 25 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "ConditioningZeroOut", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 21, + "type": "QwenImageDiffsynthControlnet", + "pos": [ + 720, + 5320 + ], + "size": [ + 289.97395833333337, + 138 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 28 + }, + { + "localized_name": "model_patch", + "name": "model_patch", + "type": "MODEL_PATCH", + "link": 29 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 30 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 42 + }, + { + "localized_name": "mask", + "name": "mask", + "shape": 7, + "type": "MASK", + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 22 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.76", + "Node name for S&R": "QwenImageDiffsynthControlnet", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 23, + "type": "CLIPTextEncode", + "pos": [ + 660, + 4660 + ], + "size": [ + 400, + 179.9609375 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 33 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 37 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 24, + 27 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 24, + "type": "VAEDecode", + "pos": [ + 1450, + 4620 + ], + "size": [ + 200, + 46 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 20 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 21 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 35 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 25, + "type": "GetImageSize", + "pos": [ + 330, + 5540 + ], + "size": [ + 140, + 66 + ], + "flags": { + "collapsed": false + }, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 41 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 31 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 32 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.76", + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 22, + "type": "EmptySD3LatentImage", + "pos": [ + 1110, + 5540 + ], + "size": [ + 259.9609375, + 106 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 31 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 32 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 26 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "EmptySD3LatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Prompt", + "bounding": [ + 640, + 4590, + 440, + 630 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Models", + "bounding": [ + 320, + 4590, + 300, + 640 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Apple ControlNet", + "bounding": [ + 640, + 5240, + 440, + 260 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 20, + "origin_id": 19, + "origin_slot": 0, + "target_id": 24, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 21, + "origin_id": 16, + "origin_slot": 0, + "target_id": 24, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 22, + "origin_id": 21, + "origin_slot": 0, + "target_id": 18, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 23, + "origin_id": 18, + "origin_slot": 0, + "target_id": 19, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 24, + "origin_id": 23, + "origin_slot": 0, + "target_id": 19, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 25, + "origin_id": 20, + "origin_slot": 0, + "target_id": 19, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 26, + "origin_id": 22, + "origin_slot": 0, + "target_id": 19, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 27, + "origin_id": 23, + "origin_slot": 0, + "target_id": 20, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 28, + "origin_id": 15, + "origin_slot": 0, + "target_id": 21, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 29, + "origin_id": 17, + "origin_slot": 0, + "target_id": 21, + "target_slot": 1, + "type": "MODEL_PATCH" + }, + { + "id": 30, + "origin_id": 16, + "origin_slot": 0, + "target_id": 21, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 31, + "origin_id": 25, + "origin_slot": 0, + "target_id": 22, + "target_slot": 0, + "type": "INT" + }, + { + "id": 32, + "origin_id": 25, + "origin_slot": 1, + "target_id": 22, + "target_slot": 1, + "type": "INT" + }, + { + "id": 33, + "origin_id": 14, + "origin_slot": 0, + "target_id": 23, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 35, + "origin_id": 24, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 37, + "origin_id": -10, + "origin_slot": 1, + "target_id": 23, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 41, + "origin_id": -10, + "origin_slot": 0, + "target_id": 25, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 42, + "origin_id": -10, + "origin_slot": 0, + "target_id": 21, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 43, + "origin_id": -10, + "origin_slot": 2, + "target_id": 15, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 44, + "origin_id": -10, + "origin_slot": 3, + "target_id": 14, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 45, + "origin_id": -10, + "origin_slot": 4, + "target_id": 16, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 46, + "origin_id": -10, + "origin_slot": 5, + "target_id": 17, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "category": "Image generation and editing/Pose to image" + } + ] + }, + "config": {}, + "extra": { + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ds": { + "scale": 0.6479518372239997, + "offset": [ + 852.9773200429215, + -3036.34291480022 + ] + } + }, + "version": 0.4 +} diff --git a/blueprints/Pose to Video (LTX 2.0).json b/blueprints/Pose to Video (LTX 2.0).json index 78c098798..580900bc0 100644 --- a/blueprints/Pose to Video (LTX 2.0).json +++ b/blueprints/Pose to Video (LTX 2.0).json @@ -1 +1,3880 @@ -{"id": "01cd475b-52df-43bf-aafa-484a5976d2d2", "revision": 0, "last_node_id": 160, "last_link_id": 410, "nodes": [{"id": 1, "type": "f0e58a6b-7246-4103-9fec-73b423634b1f", "pos": [210, 3830], "size": [420, 500], "flags": {"collapsed": false}, "order": 0, "mode": 0, "inputs": [{"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"label": "first_frame_strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}, {"label": "disable_first_frame", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": null}, {"label": "first frame", "name": "image", "type": "IMAGE", "link": null}, {"label": "control image", "name": "input", "type": "IMAGE,MASK", "link": null}, {"name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": null}, {"name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"label": "distll_lora", "name": "lora_name_1", "type": "COMBO", "widget": {"name": "lora_name_1"}, "link": null}, {"label": "upscale_model", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": null}, {"name": "resize_type.width", "type": "INT", "widget": {"name": "resize_type.width"}, "link": null}, {"name": "resize_type.height", "type": "INT", "widget": {"name": "resize_type.height"}, "link": null}, {"name": "length", "type": "INT", "widget": {"name": "length"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "resize_type.width"], ["-1", "resize_type.height"], ["-1", "length"], ["-1", "strength"], ["-1", "bypass"], ["126", "noise_seed"], ["126", "control_after_generate"], ["-1", "ckpt_name"], ["-1", "lora_name"], ["-1", "model_name"], ["-1", "lora_name_1"]], "cnr_id": "comfy-core", "ver": "0.7.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", 1280, 720, 97, 1, false, null, null, "ltx-2-19b-dev-fp8.safetensors", "ltx-2-19b-ic-lora-pose-control.safetensors", "ltx-2-spatial-upscaler-x2-1.0.safetensors", "ltx-2-19b-distilled-lora-384.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "f0e58a6b-7246-4103-9fec-73b423634b1f", "version": 1, "state": {"lastGroupId": 11, "lastNodeId": 160, "lastLinkId": 410, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Pose to Video (LTX 2.0)", "inputNode": {"id": -10, "bounding": [-2220, 4180, 153.3203125, 280]}, "outputNode": {"id": -20, "bounding": [1750.2777777777776, 4091.1111111111113, 120, 60]}, "inputs": [{"id": "0f1d2f96-933a-4a7b-8f1a-7b49fc4ade09", "name": "text", "type": "STRING", "linkIds": [345], "label": "prompt", "pos": [-2086.6796875, 4200]}, {"id": "59430efe-1090-4e36-8afe-b21ce7f4268b", "name": "strength", "type": "FLOAT", "linkIds": [370, 371], "label": "first_frame_strength", "pos": [-2086.6796875, 4220]}, {"id": "6145a9b9-68ed-4956-89f7-7a5ebdd5c99e", "name": "bypass", "type": "BOOLEAN", "linkIds": [363, 368], "label": "disable_first_frame", "pos": [-2086.6796875, 4240]}, {"id": "f7aa8c12-bdba-4bbd-84cf-b49cfc32a1dd", "name": "image", "type": "IMAGE", "linkIds": [398, 399], "label": "first frame", "pos": [-2086.6796875, 4260]}, {"id": "da40a4c0-cd19-46c6-8eb3-62d0026fbe85", "name": "input", "type": "IMAGE,MASK", "linkIds": [400], "label": "control image", "pos": [-2086.6796875, 4280]}, {"id": "8005344b-99d6-4829-a619-c4e8ef640eb9", "name": "ckpt_name", "type": "COMBO", "linkIds": [401, 402, 403], "pos": [-2086.6796875, 4300]}, {"id": "25e7c4e8-850c-4f37-bc14-e3f4b5f228c0", "name": "lora_name", "type": "COMBO", "linkIds": [404, 405], "pos": [-2086.6796875, 4320]}, {"id": "f16a18dd-947e-400a-8889-02cf998f760a", "name": "lora_name_1", "type": "COMBO", "linkIds": [406], "label": "distll_lora", "pos": [-2086.6796875, 4340]}, {"id": "1abf156c-4c85-4ee5-8671-62df3177d835", "name": "model_name", "type": "COMBO", "linkIds": [407], "label": "upscale_model", "pos": [-2086.6796875, 4360]}, {"id": "203402cf-4253-4daf-bf78-5def9496e0af", "name": "resize_type.width", "type": "INT", "linkIds": [408], "pos": [-2086.6796875, 4380]}, {"id": "e6d8ac4a-34d4-46c6-bcb2-4e66a696438c", "name": "resize_type.height", "type": "INT", "linkIds": [409], "pos": [-2086.6796875, 4400]}, {"id": "6aa6cf2c-bc4f-4f8b-be62-aa15793375dc", "name": "length", "type": "INT", "linkIds": [410], "pos": [-2086.6796875, 4420]}], "outputs": [{"id": "4e837941-de2d-4df8-8f94-686e24036897", "name": "VIDEO", "type": "VIDEO", "linkIds": [304], "localized_name": "VIDEO", "pos": [1770.2777777777776, 4111.111111111111]}], "widgets": [], "nodes": [{"id": 93, "type": "CFGGuider", "pos": [-697.721823660531, 3671.1105325465196], "size": [269.97395833333337, 98], "flags": {}, "order": 16, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 326}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 309}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 311}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "links": [261]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "CFGGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 94, "type": "KSamplerSelect", "pos": [-697.721823660531, 3841.1107362825187], "size": [269.97395833333337, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "links": [262]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["euler"]}, {"id": 99, "type": "ManualSigmas", "pos": [410.27824286284044, 3851.110970278795], "size": [269.97395833333337, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "sigmas", "name": "sigmas", "type": "STRING", "widget": {"name": "sigmas"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "links": [278]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "ManualSigmas", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["0.909375, 0.725, 0.421875, 0.0"]}, {"id": 100, "type": "LatentUpscaleModelLoader", "pos": [-69.72208571196083, 3701.1104657166875], "size": [389.97395833333337, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": 407}], "outputs": [{"localized_name": "LATENT_UPSCALE_MODEL", "name": "LATENT_UPSCALE_MODEL", "type": "LATENT_UPSCALE_MODEL", "links": [288]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LatentUpscaleModelLoader", "models": [{"name": "ltx-2-spatial-upscaler-x2-1.0.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-spatial-upscaler-x2-1.0.safetensors", "directory": "latent_upscale_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-spatial-upscaler-x2-1.0.safetensors"]}, {"id": 101, "type": "LTXVConcatAVLatent", "pos": [410.27824286284044, 4101.110949206838], "size": [269.97395833333337, 46], "flags": {}, "order": 18, "mode": 0, "inputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "link": 365}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "link": 266}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [279]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVConcatAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 108, "type": "CFGGuider", "pos": [410.27824286284044, 3701.1104657166875], "size": [269.97395833333337, 98], "flags": {}, "order": 22, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 280}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 281}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 282}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}], "outputs": [{"localized_name": "GUIDER", "name": "GUIDER", "type": "GUIDER", "links": [276]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.71", "Node name for S&R": "CFGGuider", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1]}, {"id": 123, "type": "SamplerCustomAdvanced", "pos": [-387.72197839215096, 3521.1103425011374], "size": [213.09895833333334, 106], "flags": {}, "order": 31, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 260}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 261}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 262}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 263}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 323}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "links": [272]}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.60", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 114, "type": "LTXVConditioning", "pos": [-1133.7215420073496, 4141.110347554622], "size": [269.97395833333337, 78], "flags": {}, "order": 27, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 292}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 293}, {"localized_name": "frame_rate", "name": "frame_rate", "type": "FLOAT", "widget": {"name": "frame_rate"}, "link": 355}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [313]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [314]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "LTXVConditioning", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [25]}, {"id": 119, "type": "CLIPTextEncode", "pos": [-1163.7218246405453, 3881.1109034489627], "size": [400, 88], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 294}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [293]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["blurry, low quality, still frame, frames, watermark, overlay, titles, has blurbox, has subtitles"], "color": "#323", "bgcolor": "#535"}, {"id": 116, "type": "LTXVConcatAVLatent", "pos": [-519.7217122979332, 4701.110031965835], "size": [187.5, 46], "flags": {}, "order": 29, "mode": 0, "inputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "link": 324}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "link": 300}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [322, 323]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVConcatAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 122, "type": "LTXVSeparateAVLatent", "pos": [-393.72183921949465, 3801.1107787938904], "size": [239.97395833333334, 46], "flags": {}, "order": 30, "mode": 0, "inputs": [{"localized_name": "av_latent", "name": "av_latent", "type": "LATENT", "link": 272}], "outputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "links": [270]}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "links": [266]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVSeparateAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 124, "type": "CLIPTextEncode", "pos": [-1174.7214530029996, 3515.1112854387566], "size": [409.97395833333337, 88], "flags": {}, "order": 32, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 295}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 345}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [292]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 98, "type": "KSamplerSelect", "pos": [410.27824286284044, 3981.1101681370833], "size": [269.97395833333337, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}], "outputs": [{"localized_name": "SAMPLER", "name": "SAMPLER", "type": "SAMPLER", "links": [277]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "KSamplerSelect", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["gradient_estimation"]}, {"id": 105, "type": "LoraLoaderModelOnly", "pos": [-69.72208571196083, 3571.110499039739], "size": [389.97395833333337, 82], "flags": {}, "order": 15, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 327}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 406}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [280]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "ltx-2-19b-distilled-lora-384.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-lora-384.safetensors", "directory": "loras"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-distilled-lora-384.safetensors", 1]}, {"id": 95, "type": "LTXVScheduler", "pos": [-699.7218704597861, 3981.1101681370833], "size": [269.97395833333337, 154], "flags": {}, "order": 17, "mode": 0, "inputs": [{"localized_name": "latent", "name": "latent", "shape": 7, "type": "LATENT", "link": 322}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "max_shift", "name": "max_shift", "type": "FLOAT", "widget": {"name": "max_shift"}, "link": null}, {"localized_name": "base_shift", "name": "base_shift", "type": "FLOAT", "widget": {"name": "base_shift"}, "link": null}, {"localized_name": "stretch", "name": "stretch", "type": "BOOLEAN", "widget": {"name": "stretch"}, "link": null}, {"localized_name": "terminal", "name": "terminal", "type": "FLOAT", "widget": {"name": "terminal"}, "link": null}], "outputs": [{"localized_name": "SIGMAS", "name": "SIGMAS", "type": "SIGMAS", "links": [263]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "LTXVScheduler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [20, 2.05, 0.95, true, 0.1]}, {"id": 126, "type": "RandomNoise", "pos": [-697.721823660531, 3521.1103425011374], "size": [269.97395833333337, 82], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "links": [260]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "RandomNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize"]}, {"id": 107, "type": "SamplerCustomAdvanced", "pos": [710.2782734905775, 3571.110499039739], "size": [212.36979166666669, 106], "flags": {}, "order": 21, "mode": 0, "inputs": [{"localized_name": "noise", "name": "noise", "type": "NOISE", "link": 347}, {"localized_name": "guider", "name": "guider", "type": "GUIDER", "link": 276}, {"localized_name": "sampler", "name": "sampler", "type": "SAMPLER", "link": 277}, {"localized_name": "sigmas", "name": "sigmas", "type": "SIGMAS", "link": 278}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 279}], "outputs": [{"localized_name": "output", "name": "output", "type": "LATENT", "links": []}, {"localized_name": "denoised_output", "name": "denoised_output", "type": "LATENT", "links": [336]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "SamplerCustomAdvanced", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 143, "type": "RandomNoise", "pos": [410.27824286284044, 3571.110499039739], "size": [269.97395833333337, 82], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}], "outputs": [{"localized_name": "NOISE", "name": "NOISE", "type": "NOISE", "links": [347]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "RandomNoise", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "fixed"]}, {"id": 139, "type": "LTXVAudioVAEDecode", "pos": [1130.2783163694094, 3841.1107362825187], "size": [239.97395833333334, 46], "flags": {}, "order": 35, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 338}, {"label": "Audio VAE", "localized_name": "audio_vae", "name": "audio_vae", "type": "VAE", "link": 383}], "outputs": [{"localized_name": "Audio", "name": "Audio", "type": "AUDIO", "links": [339]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVAudioVAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 106, "type": "CreateVideo", "pos": [1420.2783925712918, 3761.1104019496292], "size": [269.97395833333337, 78], "flags": {}, "order": 20, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 352}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 339}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 356}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [304]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "CreateVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [25]}, {"id": 134, "type": "LoraLoaderModelOnly", "pos": [-1649.721454901846, 3761.1104019496292], "size": [419.97395833333337, 82], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 325}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 404}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [326, 327]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "ltx-2-19b-ic-lora-pose-control.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Pose-Control/resolve/main/ltx-2-19b-ic-lora-pose-control.safetensors", "directory": "loras"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-ic-lora-pose-control.safetensors", 1], "color": "#322", "bgcolor": "#533"}, {"id": 138, "type": "LTXVSeparateAVLatent", "pos": [730.2784619127078, 3731.1109580277], "size": [193.2916015625, 46], "flags": {}, "order": 34, "mode": 0, "inputs": [{"localized_name": "av_latent", "name": "av_latent", "type": "LATENT", "link": 336}], "outputs": [{"localized_name": "video_latent", "name": "video_latent", "type": "LATENT", "links": [337, 351]}, {"localized_name": "audio_latent", "name": "audio_latent", "type": "LATENT", "links": [338]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "LTXVSeparateAVLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 144, "type": "VAEDecodeTiled", "pos": [1120.2783619435547, 3641.110599376351], "size": [269.97395833333337, 150], "flags": {}, "order": 36, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 351}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 353}, {"localized_name": "tile_size", "name": "tile_size", "type": "INT", "widget": {"name": "tile_size"}, "link": null}, {"localized_name": "overlap", "name": "overlap", "type": "INT", "widget": {"name": "overlap"}, "link": null}, {"localized_name": "temporal_size", "name": "temporal_size", "type": "INT", "widget": {"name": "temporal_size"}, "link": null}, {"localized_name": "temporal_overlap", "name": "temporal_overlap", "type": "INT", "widget": {"name": "temporal_overlap"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [352]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "VAEDecodeTiled", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [512, 64, 4096, 8]}, {"id": 113, "type": "VAEDecode", "pos": [1130.2783163694094, 3531.1113453160738], "size": [239.97395833333334, 46], "flags": {}, "order": 26, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 337}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 291}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 145, "type": "PrimitiveInt", "pos": [-1600, 4940], "size": [269.97395833333337, 82], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "INT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "INT", "name": "INT", "type": "INT", "links": [354]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "PrimitiveInt", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [24, "fixed"]}, {"id": 148, "type": "PrimitiveFloat", "pos": [-1600, 5070], "size": [269.97395833333337, 58], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [355, 356]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "PrimitiveFloat", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [24]}, {"id": 118, "type": "Reroute", "pos": [-229.7217758812614, 4211.111007032079], "size": [75, 26], "flags": {}, "order": 14, "mode": 0, "inputs": [{"name": "", "type": "*", "link": 303}], "outputs": [{"name": "", "type": "VAE", "links": [289, 291, 367]}], "properties": {"showOutputText": false, "horizontal": false}}, {"id": 151, "type": "LTXVImgToVideoInplace", "pos": [-19.72161465663438, 4071.1107364662485], "size": [269.97395833333337, 122], "flags": {}, "order": 38, "mode": 0, "inputs": [{"localized_name": "vae", "name": "vae", "type": "VAE", "link": 367}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 398}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 366}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": 371}, {"localized_name": "bypass", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": 368}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [365]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVImgToVideoInplace", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1, false]}, {"id": 104, "type": "LTXVCropGuides", "pos": [-9.721939801202097, 3841.1107362825187], "size": [239.97395833333334, 66], "flags": {}, "order": 19, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 310}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 312}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 270}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [281]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [282]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "slot_index": 2, "links": [287]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.68", "Node name for S&R": "LTXVCropGuides", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 112, "type": "LTXVLatentUpsampler", "pos": [-9.721939801202097, 3961.111517352274], "size": [259.97395833333337, 66], "flags": {}, "order": 25, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 287}, {"localized_name": "upscale_model", "name": "upscale_model", "type": "LATENT_UPSCALE_MODEL", "link": 288}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 289}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [366]}], "title": "spatial", "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVLatentUpsampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 97, "type": "LTXAVTextEncoderLoader", "pos": [-1649.721454901846, 4041.1110828665023], "size": [419.97395833333337, 106], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "text_encoder", "name": "text_encoder", "type": "COMBO", "widget": {"name": "text_encoder"}, "link": 405}, {"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 403}, {"localized_name": "device", "name": "device", "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [294, 295]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXAVTextEncoderLoader", "models": [{"name": "ltx-2-19b-dev-fp8.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", "directory": "checkpoints"}, {"name": "gemma_3_12B_it_fp4_mixed.safetensors", "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-ic-lora-pose-control.safetensors", "ltx-2-19b-dev-fp8.safetensors", "default"]}, {"id": 103, "type": "CheckpointLoaderSimple", "pos": [-1649.721454901846, 3591.1104777840524], "size": [419.97395833333337, 98], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 401}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [325]}, {"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": []}, {"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [303, 328, 353, 359]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.56", "Node name for S&R": "CheckpointLoaderSimple", "models": [{"name": "ltx-2-19b-dev-fp8.safetensors", "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", "directory": "checkpoints"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ltx-2-19b-dev-fp8.safetensors"]}, {"id": 156, "type": "LTXVAudioVAELoader", "pos": [-1636.9543279290153, 3911.095334870057], "size": [399.0494791666667, 58], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "ckpt_name", "name": "ckpt_name", "type": "COMBO", "widget": {"name": "ckpt_name"}, "link": 402}], "outputs": [{"localized_name": "Audio VAE", "name": "Audio VAE", "type": "VAE", "links": [382, 383]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "LTXVAudioVAELoader"}, "widgets_values": ["ltx-2-19b-dev-fp8.safetensors"]}, {"id": 149, "type": "LTXVImgToVideoInplace", "pos": [-1089.7215608128167, 4401.110560478942], "size": [269.97395833333337, 122], "flags": {}, "order": 37, "mode": 0, "inputs": [{"localized_name": "vae", "name": "vae", "type": "VAE", "link": 359}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 399}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 360}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": 370}, {"localized_name": "bypass", "name": "bypass", "type": "BOOLEAN", "widget": {"name": "bypass"}, "link": 363}], "outputs": [{"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [357]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "LTXVImgToVideoInplace", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1, false]}, {"id": 132, "type": "LTXVAddGuide", "pos": [-599.7217670603999, 4421.110609115862], "size": [269.97395833333337, 162], "flags": {}, "order": 33, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 313}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 314}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 328}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "link": 357}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 395}, {"localized_name": "frame_idx", "name": "frame_idx", "type": "INT", "widget": {"name": "frame_idx"}, "link": null}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [309, 310]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [311, 312]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [324]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.75", "Node name for S&R": "LTXVAddGuide", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, 1]}, {"id": 154, "type": "MarkdownNote", "pos": [-1630, 5190], "size": [350, 88], "flags": {"collapsed": false}, "order": 11, "mode": 0, "inputs": [], "outputs": [], "title": "Frame Rate Note", "properties": {}, "widgets_values": ["Please make sure the frame rate value is the same in both boxes"], "color": "#432", "bgcolor": "#653"}, {"id": 159, "type": "ResizeImageMaskNode", "pos": [-1610, 4580], "size": [284.375, 154], "flags": {}, "order": 39, "mode": 0, "inputs": [{"localized_name": "input", "name": "input", "type": "IMAGE,MASK", "link": 400}, {"localized_name": "resize_type", "name": "resize_type", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "resize_type"}, "link": null}, {"localized_name": "width", "name": "resize_type.width", "type": "INT", "widget": {"name": "resize_type.width"}, "link": 408}, {"localized_name": "height", "name": "resize_type.height", "type": "INT", "widget": {"name": "resize_type.height"}, "link": 409}, {"localized_name": "crop", "name": "resize_type.crop", "type": "COMBO", "widget": {"name": "resize_type.crop"}, "link": null}, {"localized_name": "scale_method", "name": "scale_method", "type": "COMBO", "widget": {"name": "scale_method"}, "link": null}], "outputs": [{"localized_name": "resized", "name": "resized", "type": "IMAGE,MASK", "links": [391, 392, 395]}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "ResizeImageMaskNode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["scale dimensions", 1280, 720, "center", "lanczos"]}, {"id": 110, "type": "GetImageSize", "pos": [-1600, 4780], "size": [259.97395833333337, 66], "flags": {}, "order": 23, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 391}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": [296]}, {"localized_name": "height", "name": "height", "type": "INT", "links": [297]}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": []}], "properties": {"cnr_id": "comfy-core", "ver": "0.7.0", "Node name for S&R": "GetImageSize", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 115, "type": "EmptyLTXVLatentVideo", "pos": [-1099.721794809093, 4611.11072170357], "size": [269.97395833333337, 130], "flags": {}, "order": 28, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 296}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 297}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": 410}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [360]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.60", "Node name for S&R": "EmptyLTXVLatentVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [768, 512, 97, 1]}, {"id": 111, "type": "LTXVEmptyLatentAudio", "pos": [-1099.721794809093, 4811.110229576288], "size": [269.97395833333337, 106], "flags": {}, "order": 24, "mode": 0, "inputs": [{"localized_name": "audio_vae", "name": "audio_vae", "type": "VAE", "link": 382}, {"localized_name": "frames_number", "name": "frames_number", "type": "INT", "widget": {"name": "frames_number"}, "link": null}, {"localized_name": "frame_rate", "name": "frame_rate", "type": "INT", "widget": {"name": "frame_rate"}, "link": 354}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "Latent", "name": "Latent", "type": "LATENT", "links": [300]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.68", "Node name for S&R": "LTXVEmptyLatentAudio", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [97, 25, 1]}], "groups": [{"id": 1, "title": "Model", "bounding": [-1660, 3440, 440, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Basic Sampling", "bounding": [-700, 3440, 570, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Prompt", "bounding": [-1180, 3440, 440, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 5, "title": "Latent", "bounding": [-1180, 4290, 1050, 680], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 9, "title": "Upscale Sampling(2x)", "bounding": [-100, 3440, 1090, 820], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 6, "title": "Sampler", "bounding": [350, 3480, 620, 750], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 7, "title": "Model", "bounding": [-90, 3480, 430, 310], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 11, "title": "Frame rate", "bounding": [-1610, 4860, 290, 271.6], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 326, "origin_id": 134, "origin_slot": 0, "target_id": 93, "target_slot": 0, "type": "MODEL"}, {"id": 309, "origin_id": 132, "origin_slot": 0, "target_id": 93, "target_slot": 1, "type": "CONDITIONING"}, {"id": 311, "origin_id": 132, "origin_slot": 1, "target_id": 93, "target_slot": 2, "type": "CONDITIONING"}, {"id": 266, "origin_id": 122, "origin_slot": 1, "target_id": 101, "target_slot": 1, "type": "LATENT"}, {"id": 280, "origin_id": 105, "origin_slot": 0, "target_id": 108, "target_slot": 0, "type": "MODEL"}, {"id": 281, "origin_id": 104, "origin_slot": 0, "target_id": 108, "target_slot": 1, "type": "CONDITIONING"}, {"id": 282, "origin_id": 104, "origin_slot": 1, "target_id": 108, "target_slot": 2, "type": "CONDITIONING"}, {"id": 260, "origin_id": 126, "origin_slot": 0, "target_id": 123, "target_slot": 0, "type": "NOISE"}, {"id": 261, "origin_id": 93, "origin_slot": 0, "target_id": 123, "target_slot": 1, "type": "GUIDER"}, {"id": 262, "origin_id": 94, "origin_slot": 0, "target_id": 123, "target_slot": 2, "type": "SAMPLER"}, {"id": 263, "origin_id": 95, "origin_slot": 0, "target_id": 123, "target_slot": 3, "type": "SIGMAS"}, {"id": 323, "origin_id": 116, "origin_slot": 0, "target_id": 123, "target_slot": 4, "type": "LATENT"}, {"id": 296, "origin_id": 110, "origin_slot": 0, "target_id": 115, "target_slot": 0, "type": "INT"}, {"id": 297, "origin_id": 110, "origin_slot": 1, "target_id": 115, "target_slot": 1, "type": "INT"}, {"id": 325, "origin_id": 103, "origin_slot": 0, "target_id": 134, "target_slot": 0, "type": "MODEL"}, {"id": 292, "origin_id": 124, "origin_slot": 0, "target_id": 114, "target_slot": 0, "type": "CONDITIONING"}, {"id": 293, "origin_id": 119, "origin_slot": 0, "target_id": 114, "target_slot": 1, "type": "CONDITIONING"}, {"id": 294, "origin_id": 97, "origin_slot": 0, "target_id": 119, "target_slot": 0, "type": "CLIP"}, {"id": 324, "origin_id": 132, "origin_slot": 2, "target_id": 116, "target_slot": 0, "type": "LATENT"}, {"id": 300, "origin_id": 111, "origin_slot": 0, "target_id": 116, "target_slot": 1, "type": "LATENT"}, {"id": 313, "origin_id": 114, "origin_slot": 0, "target_id": 132, "target_slot": 0, "type": "CONDITIONING"}, {"id": 314, "origin_id": 114, "origin_slot": 1, "target_id": 132, "target_slot": 1, "type": "CONDITIONING"}, {"id": 328, "origin_id": 103, "origin_slot": 2, "target_id": 132, "target_slot": 2, "type": "VAE"}, {"id": 272, "origin_id": 123, "origin_slot": 0, "target_id": 122, "target_slot": 0, "type": "LATENT"}, {"id": 336, "origin_id": 107, "origin_slot": 1, "target_id": 138, "target_slot": 0, "type": "LATENT"}, {"id": 339, "origin_id": 139, "origin_slot": 0, "target_id": 106, "target_slot": 1, "type": "AUDIO"}, {"id": 295, "origin_id": 97, "origin_slot": 0, "target_id": 124, "target_slot": 0, "type": "CLIP"}, {"id": 303, "origin_id": 103, "origin_slot": 2, "target_id": 118, "target_slot": 0, "type": "VAE"}, {"id": 338, "origin_id": 138, "origin_slot": 1, "target_id": 139, "target_slot": 0, "type": "LATENT"}, {"id": 337, "origin_id": 138, "origin_slot": 0, "target_id": 113, "target_slot": 0, "type": "LATENT"}, {"id": 291, "origin_id": 118, "origin_slot": 0, "target_id": 113, "target_slot": 1, "type": "VAE"}, {"id": 276, "origin_id": 108, "origin_slot": 0, "target_id": 107, "target_slot": 1, "type": "GUIDER"}, {"id": 277, "origin_id": 98, "origin_slot": 0, "target_id": 107, "target_slot": 2, "type": "SAMPLER"}, {"id": 278, "origin_id": 99, "origin_slot": 0, "target_id": 107, "target_slot": 3, "type": "SIGMAS"}, {"id": 279, "origin_id": 101, "origin_slot": 0, "target_id": 107, "target_slot": 4, "type": "LATENT"}, {"id": 327, "origin_id": 134, "origin_slot": 0, "target_id": 105, "target_slot": 0, "type": "MODEL"}, {"id": 310, "origin_id": 132, "origin_slot": 0, "target_id": 104, "target_slot": 0, "type": "CONDITIONING"}, {"id": 312, "origin_id": 132, "origin_slot": 1, "target_id": 104, "target_slot": 1, "type": "CONDITIONING"}, {"id": 270, "origin_id": 122, "origin_slot": 0, "target_id": 104, "target_slot": 2, "type": "LATENT"}, {"id": 287, "origin_id": 104, "origin_slot": 2, "target_id": 112, "target_slot": 0, "type": "LATENT"}, {"id": 288, "origin_id": 100, "origin_slot": 0, "target_id": 112, "target_slot": 1, "type": "LATENT_UPSCALE_MODEL"}, {"id": 289, "origin_id": 118, "origin_slot": 0, "target_id": 112, "target_slot": 2, "type": "VAE"}, {"id": 322, "origin_id": 116, "origin_slot": 0, "target_id": 95, "target_slot": 0, "type": "LATENT"}, {"id": 304, "origin_id": 106, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 345, "origin_id": -10, "origin_slot": 0, "target_id": 124, "target_slot": 1, "type": "STRING"}, {"id": 347, "origin_id": 143, "origin_slot": 0, "target_id": 107, "target_slot": 0, "type": "NOISE"}, {"id": 351, "origin_id": 138, "origin_slot": 0, "target_id": 144, "target_slot": 0, "type": "LATENT"}, {"id": 352, "origin_id": 144, "origin_slot": 0, "target_id": 106, "target_slot": 0, "type": "IMAGE"}, {"id": 353, "origin_id": 103, "origin_slot": 2, "target_id": 144, "target_slot": 1, "type": "VAE"}, {"id": 354, "origin_id": 145, "origin_slot": 0, "target_id": 111, "target_slot": 2, "type": "INT"}, {"id": 355, "origin_id": 148, "origin_slot": 0, "target_id": 114, "target_slot": 2, "type": "FLOAT"}, {"id": 356, "origin_id": 148, "origin_slot": 0, "target_id": 106, "target_slot": 2, "type": "FLOAT"}, {"id": 357, "origin_id": 149, "origin_slot": 0, "target_id": 132, "target_slot": 3, "type": "LATENT"}, {"id": 359, "origin_id": 103, "origin_slot": 2, "target_id": 149, "target_slot": 0, "type": "VAE"}, {"id": 360, "origin_id": 115, "origin_slot": 0, "target_id": 149, "target_slot": 2, "type": "LATENT"}, {"id": 363, "origin_id": -10, "origin_slot": 2, "target_id": 149, "target_slot": 4, "type": "BOOLEAN"}, {"id": 365, "origin_id": 151, "origin_slot": 0, "target_id": 101, "target_slot": 0, "type": "LATENT"}, {"id": 366, "origin_id": 112, "origin_slot": 0, "target_id": 151, "target_slot": 2, "type": "LATENT"}, {"id": 367, "origin_id": 118, "origin_slot": 0, "target_id": 151, "target_slot": 0, "type": "VAE"}, {"id": 368, "origin_id": -10, "origin_slot": 2, "target_id": 151, "target_slot": 4, "type": "BOOLEAN"}, {"id": 370, "origin_id": -10, "origin_slot": 1, "target_id": 149, "target_slot": 3, "type": "FLOAT"}, {"id": 371, "origin_id": -10, "origin_slot": 1, "target_id": 151, "target_slot": 3, "type": "FLOAT"}, {"id": 382, "origin_id": 156, "origin_slot": 0, "target_id": 111, "target_slot": 0, "type": "VAE"}, {"id": 383, "origin_id": 156, "origin_slot": 0, "target_id": 139, "target_slot": 1, "type": "VAE"}, {"id": 391, "origin_id": 159, "origin_slot": 0, "target_id": 110, "target_slot": 0, "type": "IMAGE"}, {"id": 395, "origin_id": 159, "origin_slot": 0, "target_id": 132, "target_slot": 4, "type": "IMAGE"}, {"id": 398, "origin_id": -10, "origin_slot": 3, "target_id": 151, "target_slot": 1, "type": "IMAGE"}, {"id": 399, "origin_id": -10, "origin_slot": 3, "target_id": 149, "target_slot": 1, "type": "IMAGE"}, {"id": 400, "origin_id": -10, "origin_slot": 4, "target_id": 159, "target_slot": 0, "type": "IMAGE,MASK"}, {"id": 401, "origin_id": -10, "origin_slot": 5, "target_id": 103, "target_slot": 0, "type": "COMBO"}, {"id": 402, "origin_id": -10, "origin_slot": 5, "target_id": 156, "target_slot": 0, "type": "COMBO"}, {"id": 403, "origin_id": -10, "origin_slot": 5, "target_id": 97, "target_slot": 1, "type": "COMBO"}, {"id": 404, "origin_id": -10, "origin_slot": 6, "target_id": 134, "target_slot": 1, "type": "COMBO"}, {"id": 405, "origin_id": -10, "origin_slot": 6, "target_id": 97, "target_slot": 0, "type": "COMBO"}, {"id": 406, "origin_id": -10, "origin_slot": 7, "target_id": 105, "target_slot": 1, "type": "COMBO"}, {"id": 407, "origin_id": -10, "origin_slot": 8, "target_id": 100, "target_slot": 0, "type": "COMBO"}, {"id": 408, "origin_id": -10, "origin_slot": 9, "target_id": 159, "target_slot": 2, "type": "INT"}, {"id": 409, "origin_id": -10, "origin_slot": 10, "target_id": 159, "target_slot": 3, "type": "INT"}, {"id": 410, "origin_id": -10, "origin_slot": 11, "target_id": 115, "target_slot": 2, "type": "INT"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Pose to video"}]}, "config": {}, "extra": {"ds": {"scale": 1.3889423076923078, "offset": [217.0560747663551, -3703.3333333333335]}, "frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true}, "version": 0.4} +{ + "revision": 0, + "last_node_id": 143, + "last_link_id": 0, + "nodes": [ + { + "id": 143, + "type": "68857357-cbc2-4c3a-a786-c3a58d43f9b1", + "pos": [ + 290, + 3960 + ], + "size": [ + 400, + 500 + ], + "flags": { + "collapsed": false + }, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "label": "control_images", + "name": "image", + "type": "IMAGE", + "link": null + }, + { + "label": "first_frame", + "name": "image_1", + "type": "IMAGE", + "link": null + }, + { + "label": "image_strength", + "name": "strength_1", + "type": "FLOAT", + "widget": { + "name": "strength_1" + }, + "link": null + }, + { + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + }, + { + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": null + }, + { + "label": "control_lora", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": null + }, + { + "label": "distill_lora", + "name": "lora_name_1", + "type": "COMBO", + "widget": { + "name": "lora_name_1" + }, + "link": null + }, + { + "label": "upscale_model", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "124", + "text" + ], + [ + "149", + "strength" + ], + [ + "126", + "noise_seed" + ], + [ + "103", + "ckpt_name" + ], + [ + "134", + "lora_name" + ], + [ + "97", + "text_encoder" + ], + [ + "105", + "lora_name" + ], + [ + "100", + "model_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": { + "lora_name": true, + "strength": true, + "bypass": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [], + "title": "Pose to Video (LTX 2.0)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "68857357-cbc2-4c3a-a786-c3a58d43f9b1", + "version": 1, + "state": { + "lastGroupId": 14, + "lastNodeId": 701, + "lastLinkId": 1774, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Pose to Video (LTX 2.0)", + "inputNode": { + "id": -10, + "bounding": [ + -2050, + 4100, + 127.029296875, + 240 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1750, + 4090, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "0f1d2f96-933a-4a7b-8f1a-7b49fc4ade09", + "name": "text", + "type": "STRING", + "linkIds": [ + 345 + ], + "pos": [ + -1942.970703125, + 4120 + ] + }, + { + "id": "35a07084-3ecf-482a-a330-b40278770ca3", + "name": "image", + "type": "IMAGE", + "linkIds": [ + 348, + 380 + ], + "label": "control_images", + "pos": [ + -1942.970703125, + 4140 + ] + }, + { + "id": "bea20802-d654-4287-a8ef-0f834314bcf9", + "name": "image_1", + "type": "IMAGE", + "linkIds": [ + 364, + 379 + ], + "label": "first_frame", + "pos": [ + -1942.970703125, + 4160 + ] + }, + { + "id": "b9b4151d-df88-40c0-a2bd-6e35b94557fe", + "name": "strength_1", + "type": "FLOAT", + "linkIds": [ + 1758, + 1759 + ], + "label": "image_strength", + "pos": [ + -1942.970703125, + 4180 + ] + }, + { + "id": "b51f6a12-9152-4526-b115-443cfd23003f", + "name": "noise_seed", + "type": "INT", + "linkIds": [ + 1767 + ], + "pos": [ + -1942.970703125, + 4200 + ] + }, + { + "id": "47248f12-f174-4e35-854c-fa5eebea2903", + "name": "ckpt_name", + "type": "COMBO", + "linkIds": [ + 1768, + 1770, + 1771 + ], + "pos": [ + -1942.970703125, + 4220 + ] + }, + { + "id": "6feb34cf-7972-4d3a-91fc-11070a84dc5f", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 1769 + ], + "label": "control_lora", + "pos": [ + -1942.970703125, + 4240 + ] + }, + { + "id": "6b423a3e-6c0e-445d-93c0-2cc3945400d1", + "name": "text_encoder", + "type": "COMBO", + "linkIds": [ + 1772 + ], + "pos": [ + -1942.970703125, + 4260 + ] + }, + { + "id": "ffd38c52-cc57-4e68-b140-94e7b03499b1", + "name": "lora_name_1", + "type": "COMBO", + "linkIds": [ + 1773 + ], + "label": "distill_lora", + "pos": [ + -1942.970703125, + 4280 + ] + }, + { + "id": "6d8b9605-acf0-4dd7-8d45-f824c2fd5895", + "name": "model_name", + "type": "COMBO", + "linkIds": [ + 1774 + ], + "label": "upscale_model", + "pos": [ + -1942.970703125, + 4300 + ] + } + ], + "outputs": [ + { + "id": "4e837941-de2d-4df8-8f94-686e24036897", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 304 + ], + "localized_name": "VIDEO", + "pos": [ + 1770, + 4110 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 93, + "type": "CFGGuider", + "pos": [ + -690, + 3710 + ], + "size": [ + 270, + 160 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 326 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 309 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 311 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 261 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 94, + "type": "KSamplerSelect", + "pos": [ + -690, + 3940 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 262 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 99, + "type": "ManualSigmas", + "pos": [ + 450, + 3910 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 278 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "0.909375, 0.725, 0.421875, 0.0" + ] + }, + { + "id": 100, + "type": "LatentUpscaleModelLoader", + "pos": [ + -70, + 3790 + ], + "size": [ + 390, + 110 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "model_name", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": 1774 + } + ], + "outputs": [ + { + "localized_name": "LATENT_UPSCALE_MODEL", + "name": "LATENT_UPSCALE_MODEL", + "type": "LATENT_UPSCALE_MODEL", + "links": [ + 288 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LatentUpscaleModelLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2-spatial-upscaler-x2-1.0.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-spatial-upscaler-x2-1.0.safetensors", + "directory": "latent_upscale_models" + } + ] + }, + "widgets_values": [ + "ltx-2-spatial-upscaler-x2-1.0.safetensors" + ] + }, + { + "id": 101, + "type": "LTXVConcatAVLatent", + "pos": [ + 450, + 4220 + ], + "size": [ + 270, + 120 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 365 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 266 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 279 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 108, + "type": "CFGGuider", + "pos": [ + 450, + 3720 + ], + "size": [ + 270, + 160 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 280 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 281 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 282 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 276 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.71", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 111, + "type": "LTXVEmptyLatentAudio", + "pos": [ + -1100, + 4940 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 285 + }, + { + "localized_name": "frames_number", + "name": "frames_number", + "type": "INT", + "widget": { + "name": "frames_number" + }, + "link": 329 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "INT", + "widget": { + "name": "frame_rate" + }, + "link": 354 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "Latent", + "name": "Latent", + "type": "LATENT", + "links": [ + 300 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVEmptyLatentAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 97, + 25, + 1 + ] + }, + { + "id": 123, + "type": "SamplerCustomAdvanced", + "pos": [ + -380, + 3530 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 29, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 260 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 261 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 262 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 263 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 323 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 272 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.60", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 114, + "type": "LTXVConditioning", + "pos": [ + -1130, + 4140 + ], + "size": [ + 270, + 130 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 292 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 293 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "FLOAT", + "widget": { + "name": "frame_rate" + }, + "link": 355 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 313 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 314 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVConditioning", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 119, + "type": "CLIPTextEncode", + "pos": [ + -1160, + 3880 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 294 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 293 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "blurry, low quality, still frame, frames, watermark, overlay, titles, has blurbox, has subtitles" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 116, + "type": "LTXVConcatAVLatent", + "pos": [ + -520, + 4830 + ], + "size": [ + 230, + 100 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 324 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 300 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 322, + 323 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 122, + "type": "LTXVSeparateAVLatent", + "pos": [ + -380, + 3810 + ], + "size": [ + 240, + 100 + ], + "flags": {}, + "order": 28, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 272 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 270 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 266 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 124, + "type": "CLIPTextEncode", + "pos": [ + -1170, + 3510 + ], + "size": [ + 410, + 320 + ], + "flags": {}, + "order": 30, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 295 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 345 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 292 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 98, + "type": "KSamplerSelect", + "pos": [ + 450, + 4070 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 277 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "gradient_estimation" + ] + }, + { + "id": 105, + "type": "LoraLoaderModelOnly", + "pos": [ + -70, + 3570 + ], + "size": [ + 390, + 140 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 327 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 1773 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 280 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LoraLoaderModelOnly", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2-19b-distilled-lora-384.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-lora-384.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "ltx-2-19b-distilled-lora-384.safetensors", + 1 + ] + }, + { + "id": 95, + "type": "LTXVScheduler", + "pos": [ + -690, + 4130 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "latent", + "name": "latent", + "shape": 7, + "type": "LATENT", + "link": 322 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "max_shift", + "name": "max_shift", + "type": "FLOAT", + "widget": { + "name": "max_shift" + }, + "link": null + }, + { + "localized_name": "base_shift", + "name": "base_shift", + "type": "FLOAT", + "widget": { + "name": "base_shift" + }, + "link": null + }, + { + "localized_name": "stretch", + "name": "stretch", + "type": "BOOLEAN", + "widget": { + "name": "stretch" + }, + "link": null + }, + { + "localized_name": "terminal", + "name": "terminal", + "type": "FLOAT", + "widget": { + "name": "terminal" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 263 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVScheduler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 20, + 2.05, + 0.95, + true, + 0.1 + ] + }, + { + "id": 126, + "type": "RandomNoise", + "pos": [ + -690, + 3520 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 31, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": 1767 + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 260 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "fixed" + ] + }, + { + "id": 107, + "type": "SamplerCustomAdvanced", + "pos": [ + 730, + 3570 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 347 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 276 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 277 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 278 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 279 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [ + 336 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 187, + "type": "RandomNoise", + "pos": [ + 450, + 3570 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 347 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "fixed" + ] + }, + { + "id": 139, + "type": "LTXVAudioVAEDecode", + "pos": [ + 1130, + 3840 + ], + "size": [ + 240, + 100 + ], + "flags": {}, + "order": 35, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 338 + }, + { + "label": "Audio VAE", + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 340 + } + ], + "outputs": [ + { + "localized_name": "Audio", + "name": "Audio", + "type": "AUDIO", + "links": [ + 339 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVAudioVAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 106, + "type": "CreateVideo", + "pos": [ + 1420, + 3760 + ], + "size": [ + 270, + 130 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 352 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 339 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 356 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 304 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CreateVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25 + ] + }, + { + "id": 134, + "type": "LoraLoaderModelOnly", + "pos": [ + -1650, + 3750 + ], + "size": [ + 420, + 140 + ], + "flags": {}, + "order": 33, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 325 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 1769 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 326, + 327 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LoraLoaderModelOnly", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2-19b-ic-lora-pose-control.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Pose-Control/resolve/main/ltx-2-19b-ic-lora-pose-control.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "ltx-2-19b-ic-lora-pose-control.safetensors", + 1 + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 138, + "type": "LTXVSeparateAVLatent", + "pos": [ + 740, + 3810 + ], + "size": [ + 230, + 100 + ], + "flags": {}, + "order": 34, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 336 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 337, + 351 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 338 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 188, + "type": "VAEDecodeTiled", + "pos": [ + 1120, + 3640 + ], + "size": [ + 270, + 150 + ], + "flags": {}, + "order": 38, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 351 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 353 + }, + { + "localized_name": "tile_size", + "name": "tile_size", + "type": "INT", + "widget": { + "name": "tile_size" + }, + "link": null + }, + { + "localized_name": "overlap", + "name": "overlap", + "type": "INT", + "widget": { + "name": "overlap" + }, + "link": null + }, + { + "localized_name": "temporal_size", + "name": "temporal_size", + "type": "INT", + "widget": { + "name": "temporal_size" + }, + "link": null + }, + { + "localized_name": "temporal_overlap", + "name": "temporal_overlap", + "type": "INT", + "widget": { + "name": "temporal_overlap" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 352 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAEDecodeTiled", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 512, + 64, + 4096, + 8 + ] + }, + { + "id": 113, + "type": "VAEDecode", + "pos": [ + 1130, + 3530 + ], + "size": [ + 240, + 100 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 337 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 291 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 145, + "type": "PrimitiveInt", + "pos": [ + -1610, + 4800 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 354 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24, + "fixed" + ] + }, + { + "id": 148, + "type": "PrimitiveFloat", + "pos": [ + -1610, + 4930 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 355, + 356 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 115, + "type": "EmptyLTXVLatentVideo", + "pos": [ + -1100, + 4740 + ], + "size": [ + 270, + 200 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 296 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 297 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 330 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 360 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.60", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "EmptyLTXVLatentVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 512, + 97, + 1 + ] + }, + { + "id": 118, + "type": "Reroute", + "pos": [ + -350, + 3980 + ], + "size": [ + 230, + 40 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 303 + } + ], + "outputs": [ + { + "name": "", + "type": "VAE", + "links": [ + 289, + 291, + 367 + ] + } + ], + "properties": { + "showOutputText": false, + "horizontal": false, + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + } + } + }, + { + "id": 189, + "type": "LTXVImgToVideoInplace", + "pos": [ + 180, + 4040 + ], + "size": [ + 260, + 190 + ], + "flags": { + "collapsed": false + }, + "order": 39, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 367 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 379 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 366 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": 1759 + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 368 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 365 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 104, + "type": "LTXVCropGuides", + "pos": [ + -90, + 4210 + ], + "size": [ + 240, + 120 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 310 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 312 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 270 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 281 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 282 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "slot_index": 2, + "links": [ + 287 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVCropGuides", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 112, + "type": "LTXVLatentUpsampler", + "pos": [ + -90, + 4030 + ], + "size": [ + 260, + 120 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 287 + }, + { + "localized_name": "upscale_model", + "name": "upscale_model", + "type": "LATENT_UPSCALE_MODEL", + "link": 288 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 289 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 366 + ] + } + ], + "title": "spatial", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVLatentUpsampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 154, + "type": "MarkdownNote", + "pos": [ + -1640, + 5050 + ], + "size": [ + 350, + 170 + ], + "flags": { + "collapsed": false + }, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Frame Rate Note", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "Please make sure the frame rate value is the same in both boxes" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 96, + "type": "LTXVAudioVAELoader", + "pos": [ + -1650, + 3970 + ], + "size": [ + 420, + 110 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 1770 + } + ], + "outputs": [ + { + "localized_name": "Audio VAE", + "name": "Audio VAE", + "type": "VAE", + "links": [ + 285, + 340 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVAudioVAELoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2-19b-dev-fp8.safetensors" + ] + }, + { + "id": 97, + "type": "LTXAVTextEncoderLoader", + "pos": [ + -1650, + 4160 + ], + "size": [ + 420, + 150 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "text_encoder", + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": 1772 + }, + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 1771 + }, + { + "localized_name": "device", + "name": "device", + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 294, + 295 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXAVTextEncoderLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + }, + { + "name": "gemma_3_12B_it_fp4_mixed.safetensors", + "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2-19b-dev-fp8.safetensors", + "default" + ] + }, + { + "id": 103, + "type": "CheckpointLoaderSimple", + "pos": [ + -1650, + 3520 + ], + "size": [ + 420, + 160 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 1768 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 325 + ] + }, + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 303, + 328, + 353, + 359 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.56", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CheckpointLoaderSimple", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2-19b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2-19b-dev-fp8.safetensors" + ] + }, + { + "id": 110, + "type": "GetImageSize", + "pos": [ + -1610, + 4630 + ], + "size": [ + 260, + 120 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 381 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": [ + 296 + ] + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": [ + 297 + ] + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": [ + 329, + 330 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "GetImageSize", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 132, + "type": "LTXVAddGuide", + "pos": [ + -600, + 4550 + ], + "size": [ + 270, + 240 + ], + "flags": {}, + "order": 32, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 313 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 314 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 328 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 357 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 348 + }, + { + "localized_name": "frame_idx", + "name": "frame_idx", + "type": "INT", + "widget": { + "name": "frame_idx" + }, + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 309, + 310 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 311, + 312 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 324 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.75", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVAddGuide", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + 1 + ] + }, + { + "id": 149, + "type": "LTXVImgToVideoInplace", + "pos": [ + -1090, + 4530 + ], + "size": [ + 270, + 180 + ], + "flags": {}, + "order": 36, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 359 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 364 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 360 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": 1758 + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 357 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.7.0", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 155, + "type": "ImageScaleBy", + "pos": [ + -1620, + 4440 + ], + "size": [ + 280, + 140 + ], + "flags": {}, + "order": 37, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 380 + }, + { + "localized_name": "upscale_method", + "name": "upscale_method", + "type": "COMBO", + "widget": { + "name": "upscale_method" + }, + "link": null + }, + { + "localized_name": "scale_by", + "name": "scale_by", + "type": "FLOAT", + "widget": { + "name": "scale_by" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 381 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ImageScaleBy", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "lanczos", + 0.5 + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -1660, + 3440, + 450, + 940 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Basic Sampling", + "bounding": [ + -700, + 3440, + 580, + 940 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + -1180, + 3440, + 450, + 940 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "Latent", + "bounding": [ + -1180, + 4420, + 1050, + 680 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 9, + "title": "Upscale Sampling(2x)", + "bounding": [ + -100, + 3440, + 1110, + 940 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Sampler", + "bounding": [ + 410, + 3480, + 590, + 880 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Model", + "bounding": [ + -90, + 3480, + 450, + 480 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 11, + "title": "Frame rate", + "bounding": [ + -1620, + 4730, + 290, + 271.6 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 326, + "origin_id": 134, + "origin_slot": 0, + "target_id": 93, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 309, + "origin_id": 132, + "origin_slot": 0, + "target_id": 93, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 311, + "origin_id": 132, + "origin_slot": 1, + "target_id": 93, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 266, + "origin_id": 122, + "origin_slot": 1, + "target_id": 101, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 280, + "origin_id": 105, + "origin_slot": 0, + "target_id": 108, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 281, + "origin_id": 104, + "origin_slot": 0, + "target_id": 108, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 282, + "origin_id": 104, + "origin_slot": 1, + "target_id": 108, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 285, + "origin_id": 96, + "origin_slot": 0, + "target_id": 111, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 329, + "origin_id": 110, + "origin_slot": 2, + "target_id": 111, + "target_slot": 1, + "type": "INT" + }, + { + "id": 260, + "origin_id": 126, + "origin_slot": 0, + "target_id": 123, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 261, + "origin_id": 93, + "origin_slot": 0, + "target_id": 123, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 262, + "origin_id": 94, + "origin_slot": 0, + "target_id": 123, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 263, + "origin_id": 95, + "origin_slot": 0, + "target_id": 123, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 323, + "origin_id": 116, + "origin_slot": 0, + "target_id": 123, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 296, + "origin_id": 110, + "origin_slot": 0, + "target_id": 115, + "target_slot": 0, + "type": "INT" + }, + { + "id": 297, + "origin_id": 110, + "origin_slot": 1, + "target_id": 115, + "target_slot": 1, + "type": "INT" + }, + { + "id": 330, + "origin_id": 110, + "origin_slot": 2, + "target_id": 115, + "target_slot": 2, + "type": "INT" + }, + { + "id": 325, + "origin_id": 103, + "origin_slot": 0, + "target_id": 134, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 292, + "origin_id": 124, + "origin_slot": 0, + "target_id": 114, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 293, + "origin_id": 119, + "origin_slot": 0, + "target_id": 114, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 294, + "origin_id": 97, + "origin_slot": 0, + "target_id": 119, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 324, + "origin_id": 132, + "origin_slot": 2, + "target_id": 116, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 300, + "origin_id": 111, + "origin_slot": 0, + "target_id": 116, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 313, + "origin_id": 114, + "origin_slot": 0, + "target_id": 132, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 314, + "origin_id": 114, + "origin_slot": 1, + "target_id": 132, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 328, + "origin_id": 103, + "origin_slot": 2, + "target_id": 132, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 272, + "origin_id": 123, + "origin_slot": 0, + "target_id": 122, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 336, + "origin_id": 107, + "origin_slot": 1, + "target_id": 138, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 339, + "origin_id": 139, + "origin_slot": 0, + "target_id": 106, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 295, + "origin_id": 97, + "origin_slot": 0, + "target_id": 124, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 303, + "origin_id": 103, + "origin_slot": 2, + "target_id": 118, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 338, + "origin_id": 138, + "origin_slot": 1, + "target_id": 139, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 340, + "origin_id": 96, + "origin_slot": 0, + "target_id": 139, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 337, + "origin_id": 138, + "origin_slot": 0, + "target_id": 113, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 291, + "origin_id": 118, + "origin_slot": 0, + "target_id": 113, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 276, + "origin_id": 108, + "origin_slot": 0, + "target_id": 107, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 277, + "origin_id": 98, + "origin_slot": 0, + "target_id": 107, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 278, + "origin_id": 99, + "origin_slot": 0, + "target_id": 107, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 279, + "origin_id": 101, + "origin_slot": 0, + "target_id": 107, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 327, + "origin_id": 134, + "origin_slot": 0, + "target_id": 105, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 310, + "origin_id": 132, + "origin_slot": 0, + "target_id": 104, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 312, + "origin_id": 132, + "origin_slot": 1, + "target_id": 104, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 270, + "origin_id": 122, + "origin_slot": 0, + "target_id": 104, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 287, + "origin_id": 104, + "origin_slot": 2, + "target_id": 112, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 288, + "origin_id": 100, + "origin_slot": 0, + "target_id": 112, + "target_slot": 1, + "type": "LATENT_UPSCALE_MODEL" + }, + { + "id": 289, + "origin_id": 118, + "origin_slot": 0, + "target_id": 112, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 322, + "origin_id": 116, + "origin_slot": 0, + "target_id": 95, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 304, + "origin_id": 106, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 345, + "origin_id": -10, + "origin_slot": 0, + "target_id": 124, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 347, + "origin_id": 187, + "origin_slot": 0, + "target_id": 107, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 348, + "origin_id": -10, + "origin_slot": 1, + "target_id": 132, + "target_slot": 4, + "type": "IMAGE" + }, + { + "id": 351, + "origin_id": 138, + "origin_slot": 0, + "target_id": 188, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 352, + "origin_id": 188, + "origin_slot": 0, + "target_id": 106, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 353, + "origin_id": 103, + "origin_slot": 2, + "target_id": 188, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 354, + "origin_id": 145, + "origin_slot": 0, + "target_id": 111, + "target_slot": 2, + "type": "INT" + }, + { + "id": 355, + "origin_id": 148, + "origin_slot": 0, + "target_id": 114, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 356, + "origin_id": 148, + "origin_slot": 0, + "target_id": 106, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 357, + "origin_id": 149, + "origin_slot": 0, + "target_id": 132, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 359, + "origin_id": 103, + "origin_slot": 2, + "target_id": 149, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 360, + "origin_id": 115, + "origin_slot": 0, + "target_id": 149, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 364, + "origin_id": -10, + "origin_slot": 2, + "target_id": 149, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 365, + "origin_id": 189, + "origin_slot": 0, + "target_id": 101, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 366, + "origin_id": 112, + "origin_slot": 0, + "target_id": 189, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 367, + "origin_id": 118, + "origin_slot": 0, + "target_id": 189, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 368, + "origin_id": -10, + "origin_slot": 4, + "target_id": 189, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 379, + "origin_id": -10, + "origin_slot": 2, + "target_id": 189, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 380, + "origin_id": -10, + "origin_slot": 1, + "target_id": 155, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 381, + "origin_id": 155, + "origin_slot": 0, + "target_id": 110, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 1758, + "origin_id": -10, + "origin_slot": 3, + "target_id": 149, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 1759, + "origin_id": -10, + "origin_slot": 3, + "target_id": 189, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 1767, + "origin_id": -10, + "origin_slot": 4, + "target_id": 126, + "target_slot": 0, + "type": "INT" + }, + { + "id": 1768, + "origin_id": -10, + "origin_slot": 5, + "target_id": 103, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 1769, + "origin_id": -10, + "origin_slot": 6, + "target_id": 134, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 1770, + "origin_id": -10, + "origin_slot": 5, + "target_id": 96, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 1771, + "origin_id": -10, + "origin_slot": 5, + "target_id": 97, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 1772, + "origin_id": -10, + "origin_slot": 7, + "target_id": 97, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 1773, + "origin_id": -10, + "origin_slot": 8, + "target_id": 105, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 1774, + "origin_id": -10, + "origin_slot": 9, + "target_id": 100, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video generation and editing/Pose to video" + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Prompt Enhance.json b/blueprints/Prompt Enhance.json index 2612f66db..5e57548ff 100644 --- a/blueprints/Prompt Enhance.json +++ b/blueprints/Prompt Enhance.json @@ -1 +1,278 @@ -{"revision": 0, "last_node_id": 15, "last_link_id": 0, "nodes": [{"id": 15, "type": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", "pos": [-1490, 2040], "size": [400, 260], "flags": {}, "order": 0, "mode": 0, "inputs": [{"name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}, {"label": "reference images", "name": "images", "type": "IMAGE", "link": null}], "outputs": [{"name": "STRING", "type": "STRING", "links": null}], "title": "Prompt Enhance", "properties": {"proxyWidgets": [["-1", "prompt"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": [""]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 15, "lastLinkId": 14, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Prompt Enhance", "inputNode": {"id": -10, "bounding": [-2170, 2110, 138.876953125, 80]}, "outputNode": {"id": -20, "bounding": [-640, 2110, 120, 60]}, "inputs": [{"id": "aeab7216-00e0-4528-a09b-bba50845c5a6", "name": "prompt", "type": "STRING", "linkIds": [11], "pos": [-2051.123046875, 2130]}, {"id": "7b73fd36-aa31-4771-9066-f6c83879994b", "name": "images", "type": "IMAGE", "linkIds": [14], "label": "reference images", "pos": [-2051.123046875, 2150]}], "outputs": [{"id": "c7b0d930-68a1-48d1-b496-0519e5837064", "name": "STRING", "type": "STRING", "linkIds": [13], "pos": [-620, 2130]}], "widgets": [], "nodes": [{"id": 11, "type": "GeminiNode", "pos": [-1560, 1990], "size": [470, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "shape": 7, "type": "IMAGE", "link": 14}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "video", "name": "video", "shape": 7, "type": "VIDEO", "link": null}, {"localized_name": "files", "name": "files", "shape": 7, "type": "GEMINI_INPUT_FILES", "link": null}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": 11}, {"localized_name": "model", "name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": null}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "system_prompt", "name": "system_prompt", "shape": 7, "type": "STRING", "widget": {"name": "system_prompt"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": [13]}], "properties": {"cnr_id": "comfy-core", "ver": "0.14.1", "Node name for S&R": "GeminiNode"}, "widgets_values": ["", "gemini-3-pro-preview", 42, "randomize", "You are an expert in prompt writing.\nBased on the input, rewrite the user's input into a detailed prompt.\nincluding camera settings, lighting, composition, and style.\nReturn the prompt only"], "color": "#432", "bgcolor": "#653"}], "groups": [], "links": [{"id": 11, "origin_id": -10, "origin_slot": 0, "target_id": 11, "target_slot": 4, "type": "STRING"}, {"id": 13, "origin_id": 11, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "STRING"}, {"id": 14, "origin_id": -10, "origin_slot": 1, "target_id": 11, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Text generation/Prompt enhance"}]}, "extra": {}} +{ + "revision": 0, + "last_node_id": 15, + "last_link_id": 0, + "nodes": [ + { + "id": 15, + "type": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", + "pos": [ + -1490, + 2040 + ], + "size": [ + 400, + 260 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + }, + { + "label": "reference images", + "name": "images", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "name": "STRING", + "type": "STRING", + "links": null + } + ], + "title": "Prompt Enhance", + "properties": { + "proxyWidgets": [ + [ + "-1", + "prompt" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.14.1" + }, + "widgets_values": [ + "" + ] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 15, + "lastLinkId": 14, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Prompt Enhance", + "inputNode": { + "id": -10, + "bounding": [ + -2170, + 2110, + 138.876953125, + 80 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + -640, + 2110, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "aeab7216-00e0-4528-a09b-bba50845c5a6", + "name": "prompt", + "type": "STRING", + "linkIds": [ + 11 + ], + "pos": [ + -2051.123046875, + 2130 + ] + }, + { + "id": "7b73fd36-aa31-4771-9066-f6c83879994b", + "name": "images", + "type": "IMAGE", + "linkIds": [ + 14 + ], + "label": "reference images", + "pos": [ + -2051.123046875, + 2150 + ] + } + ], + "outputs": [ + { + "id": "c7b0d930-68a1-48d1-b496-0519e5837064", + "name": "STRING", + "type": "STRING", + "linkIds": [ + 13 + ], + "pos": [ + -620, + 2130 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 11, + "type": "GeminiNode", + "pos": [ + -1560, + 1990 + ], + "size": [ + 470, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "shape": 7, + "type": "IMAGE", + "link": 14 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": null + }, + { + "localized_name": "video", + "name": "video", + "shape": 7, + "type": "VIDEO", + "link": null + }, + { + "localized_name": "files", + "name": "files", + "shape": 7, + "type": "GEMINI_INPUT_FILES", + "link": null + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": 11 + }, + { + "localized_name": "model", + "name": "model", + "type": "COMBO", + "widget": { + "name": "model" + }, + "link": null + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "system_prompt", + "name": "system_prompt", + "shape": 7, + "type": "STRING", + "widget": { + "name": "system_prompt" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 13 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "GeminiNode" + }, + "widgets_values": [ + "", + "gemini-3-pro-preview", + 42, + "randomize", + "You are an expert in prompt writing.\nBased on the input, rewrite the user's input into a detailed prompt.\nincluding camera settings, lighting, composition, and style.\nReturn the prompt only" + ], + "color": "#432", + "bgcolor": "#653" + } + ], + "groups": [], + "links": [ + { + "id": 11, + "origin_id": -10, + "origin_slot": 0, + "target_id": 11, + "target_slot": 4, + "type": "STRING" + }, + { + "id": 13, + "origin_id": 11, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "STRING" + }, + { + "id": 14, + "origin_id": -10, + "origin_slot": 1, + "target_id": 11, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Text generation/Prompt enhance" + } + ] + }, + "extra": {} +} diff --git a/blueprints/Sharpen.json b/blueprints/Sharpen.json index a4accaf59..f332400fd 100644 --- a/blueprints/Sharpen.json +++ b/blueprints/Sharpen.json @@ -1 +1,309 @@ -{"revision": 0, "last_node_id": 25, "last_link_id": 0, "nodes": [{"id": 25, "type": "621ba4e2-22a8-482d-a369-023753198b7b", "pos": [4610, -790], "size": [230, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "title": "Sharpen", "properties": {"proxyWidgets": [["24", "value"]]}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "621ba4e2-22a8-482d-a369-023753198b7b", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 24, "lastLinkId": 36, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Sharpen", "inputNode": {"id": -10, "bounding": [4090, -825, 120, 60]}, "outputNode": {"id": -20, "bounding": [5150, -825, 120, 60]}, "inputs": [{"id": "37011fb7-14b7-4e0e-b1a0-6a02e8da1fd7", "name": "images.image0", "type": "IMAGE", "linkIds": [34], "localized_name": "images.image0", "label": "image", "pos": [4190, -805]}], "outputs": [{"id": "e9182b3f-635c-4cd4-a152-4b4be17ae4b9", "name": "IMAGE0", "type": "IMAGE", "linkIds": [35], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [5170, -805]}], "widgets": [], "nodes": [{"id": 24, "type": "PrimitiveFloat", "pos": [4280, -1240], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "strength", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [36]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 3, "precision": 2, "step": 0.05}, "widgets_values": [0.5]}, {"id": 23, "type": "GLSLShader", "pos": [4570, -1240], "size": [370, 192], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 34}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 36}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [35]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // strength [0.0 – 2.0] typical: 0.3–1.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}", "from_input"]}], "groups": [], "links": [{"id": 36, "origin_id": 24, "origin_slot": 0, "target_id": 23, "target_slot": 2, "type": "FLOAT"}, {"id": 34, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 35, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Sharpen"}]}} +{ + "revision": 0, + "last_node_id": 25, + "last_link_id": 0, + "nodes": [ + { + "id": 25, + "type": "621ba4e2-22a8-482d-a369-023753198b7b", + "pos": [ + 4610, + -790 + ], + "size": [ + 230, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "image", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "label": "IMAGE", + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "title": "Sharpen", + "properties": { + "proxyWidgets": [ + [ + "24", + "value" + ] + ] + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "621ba4e2-22a8-482d-a369-023753198b7b", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 24, + "lastLinkId": 36, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Sharpen", + "inputNode": { + "id": -10, + "bounding": [ + 4090, + -825, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 5150, + -825, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "37011fb7-14b7-4e0e-b1a0-6a02e8da1fd7", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 34 + ], + "localized_name": "images.image0", + "label": "image", + "pos": [ + 4190, + -805 + ] + } + ], + "outputs": [ + { + "id": "e9182b3f-635c-4cd4-a152-4b4be17ae4b9", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 35 + ], + "localized_name": "IMAGE0", + "label": "IMAGE", + "pos": [ + 5170, + -805 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 24, + "type": "PrimitiveFloat", + "pos": [ + 4280, + -1240 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "strength", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 36 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 3, + "precision": 2, + "step": 0.05 + }, + "widgets_values": [ + 0.5 + ] + }, + { + "id": 23, + "type": "GLSLShader", + "pos": [ + 4570, + -1240 + ], + "size": [ + 370, + 192 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 34 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 36 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 35 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // strength [0.0 – 2.0] typical: 0.3–1.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / vec2(textureSize(u_image0, 0));\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 36, + "origin_id": 24, + "origin_slot": 0, + "target_id": 23, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 34, + "origin_id": -10, + "origin_slot": 0, + "target_id": 23, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 35, + "origin_id": 23, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Sharpen" + } + ] + } +} diff --git a/blueprints/Text to Audio (ACE-Step 1.5).json b/blueprints/Text to Audio (ACE-Step 1.5).json index 51e3bbed3..206cf16be 100644 --- a/blueprints/Text to Audio (ACE-Step 1.5).json +++ b/blueprints/Text to Audio (ACE-Step 1.5).json @@ -1 +1,1521 @@ -{"id": "67979fed-a490-450a-83f4-c7c0105d450e", "revision": 0, "last_node_id": 110, "last_link_id": 288, "nodes": [{"id": 21, "type": "510f6b52-34ee-40dd-b532-475497dee41b", "pos": [1810, -560], "size": [390, 460], "flags": {}, "order": 0, "mode": 0, "inputs": [{"name": "tags", "type": "STRING", "widget": {"name": "tags"}, "link": null}, {"name": "lyrics", "type": "STRING", "widget": {"name": "lyrics"}, "link": null}, {"name": "timesignature", "type": "COMBO", "widget": {"name": "timesignature"}, "link": null}, {"name": "language", "type": "COMBO", "widget": {"name": "language"}, "link": null}, {"name": "keyscale", "type": "COMBO", "widget": {"name": "keyscale"}, "link": null}, {"name": "generate_audio_codes", "type": "BOOLEAN", "widget": {"name": "generate_audio_codes"}, "link": null}, {"name": "cfg_scale", "type": "FLOAT", "widget": {"name": "cfg_scale"}, "link": null}, {"label": "duration", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name1", "type": "COMBO", "widget": {"name": "clip_name1"}, "link": null}, {"name": "clip_name2", "type": "COMBO", "widget": {"name": "clip_name2"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "AUDIO", "name": "AUDIO", "type": "AUDIO", "links": []}], "properties": {"proxyWidgets": [["-1", "tags"], ["-1", "lyrics"], ["-1", "language"], ["-1", "timesignature"], ["-1", "keyscale"], ["-1", "generate_audio_codes"], ["-1", "cfg_scale"], ["102", "value"], ["102", "control_after_generate"], ["-1", "unet_name"], ["-1", "clip_name1"], ["-1", "clip_name2"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.12.3", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", "", "en", "4", "E minor", true, 2, null, null, "acestep_v1.5_turbo.safetensors", "qwen_0.6b_ace15.safetensors", "qwen_4b_ace15.safetensors", "ace_1.5_vae.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "510f6b52-34ee-40dd-b532-475497dee41b", "version": 1, "state": {"lastGroupId": 3, "lastNodeId": 110, "lastLinkId": 288, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Text to Audio (ACE-Step 1.5)", "inputNode": {"id": -10, "bounding": [-660, -560, 167.458984375, 280]}, "outputNode": {"id": -20, "bounding": [1504.8375, -410, 120, 60]}, "inputs": [{"id": "ebc79d17-2e65-4e0f-855a-c9f2466a5fbf", "name": "tags", "type": "STRING", "linkIds": [264], "pos": [-512.541015625, -540]}, {"id": "230afdb4-a647-4fb7-a68c-a2204fd5d570", "name": "lyrics", "type": "STRING", "linkIds": [265], "pos": [-512.541015625, -520]}, {"id": "efdcbb48-231c-4757-b343-4458c011a283", "name": "timesignature", "type": "COMBO", "linkIds": [266], "pos": [-512.541015625, -500]}, {"id": "811579c1-2979-4721-a1e1-7d9352616e7b", "name": "language", "type": "COMBO", "linkIds": [267], "pos": [-512.541015625, -480]}, {"id": "76a68b0d-7a5f-43dc-873d-d78adf32895f", "name": "keyscale", "type": "COMBO", "linkIds": [268], "pos": [-512.541015625, -460]}, {"id": "11bb3297-272d-4c56-873a-2c974581e838", "name": "generate_audio_codes", "type": "BOOLEAN", "linkIds": [269], "pos": [-512.541015625, -440]}, {"id": "e5a30400-a8b0-422a-a0f3-21739727ab03", "name": "cfg_scale", "type": "FLOAT", "linkIds": [270], "pos": [-512.541015625, -420]}, {"id": "91a37ca5-e0d1-42c5-8248-419b850661a0", "name": "value", "type": "FLOAT", "linkIds": [284], "label": "duration", "pos": [-512.541015625, -400]}, {"id": "30f69f59-e916-48ab-9a5d-ae445b8d8a63", "name": "unet_name", "type": "COMBO", "linkIds": [285], "pos": [-512.541015625, -380]}, {"id": "1af0e8df-6fa7-4df2-b1b4-9c356a8f30a6", "name": "clip_name1", "type": "COMBO", "linkIds": [286], "pos": [-512.541015625, -360]}, {"id": "c7195505-9e83-4f87-b8d7-7747d808577d", "name": "clip_name2", "type": "COMBO", "linkIds": [287], "pos": [-512.541015625, -340]}, {"id": "ca4bd68f-e7c1-4d87-9914-cfe15c63b96e", "name": "vae_name", "type": "COMBO", "linkIds": [288], "pos": [-512.541015625, -320]}], "outputs": [{"id": "bfd748f6-f9ac-4588-81fa-41bde07a58fa", "name": "AUDIO", "type": "AUDIO", "linkIds": [263], "localized_name": "AUDIO", "pos": [1524.8375, -390]}], "widgets": [], "nodes": [{"id": 105, "type": "DualCLIPLoader", "pos": [-165, -660], "size": [380, 130], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name1", "name": "clip_name1", "type": "COMBO", "widget": {"name": "clip_name1"}, "link": 286}, {"localized_name": "clip_name2", "name": "clip_name2", "type": "COMBO", "widget": {"name": "clip_name2"}, "link": 287}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [261]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "DualCLIPLoader", "models": [{"name": "qwen_0.6b_ace15.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_0.6b_ace15.safetensors", "directory": "text_encoders"}, {"name": "qwen_4b_ace15.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_4b_ace15.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_0.6b_ace15.safetensors", "qwen_4b_ace15.safetensors", "ace", "default"]}, {"id": 106, "type": "VAELoader", "pos": [-165, -470], "size": [380, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 288}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [262]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "VAELoader", "models": [{"name": "ace_1.5_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/vae/ace_1.5_vae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ace_1.5_vae.safetensors"]}, {"id": 98, "type": "EmptyAceStep1.5LatentAudio", "pos": [-150, 10], "size": [314.90390625, 82], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "seconds", "name": "seconds", "type": "FLOAT", "widget": {"name": "seconds"}, "link": 279}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [249]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "EmptyAceStep1.5LatentAudio", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [120, 1]}, {"id": 47, "type": "ConditioningZeroOut", "pos": [670, 50], "size": [204.75, 26], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 255}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [119]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "ConditioningZeroOut", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 3, "type": "KSampler", "pos": [930, -680], "size": [329.39477481889753, 262], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 175}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 254}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 119}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 249}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": 258}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [256]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "fixed", 8, 1, "euler", "simple", 1]}, {"id": 78, "type": "ModelSamplingAuraFlow", "pos": [930, -810], "size": [329.39477481889753, 60], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 260}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [175]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "ModelSamplingAuraFlow", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}, {"id": 18, "type": "VAEDecodeAudio", "pos": [1280, -800], "size": [164.8375, 46], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 256}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 262}], "outputs": [{"localized_name": "AUDIO", "name": "AUDIO", "type": "AUDIO", "links": [263]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "VAEDecodeAudio", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 94, "type": "TextEncodeAceStepAudio1.5", "pos": [270, -790], "size": [611.9184354063266, 679.7643386829468], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 261}, {"localized_name": "tags", "name": "tags", "type": "STRING", "widget": {"name": "tags"}, "link": 264}, {"localized_name": "lyrics", "name": "lyrics", "type": "STRING", "widget": {"name": "lyrics"}, "link": 265}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": 257}, {"localized_name": "bpm", "name": "bpm", "type": "INT", "widget": {"name": "bpm"}, "link": null}, {"localized_name": "duration", "name": "duration", "type": "FLOAT", "widget": {"name": "duration"}, "link": 280}, {"localized_name": "timesignature", "name": "timesignature", "type": "COMBO", "widget": {"name": "timesignature"}, "link": 266}, {"localized_name": "language", "name": "language", "type": "COMBO", "widget": {"name": "language"}, "link": 267}, {"localized_name": "keyscale", "name": "keyscale", "type": "COMBO", "widget": {"name": "keyscale"}, "link": 268}, {"localized_name": "generate_audio_codes", "name": "generate_audio_codes", "type": "BOOLEAN", "widget": {"name": "generate_audio_codes"}, "link": 269}, {"localized_name": "cfg_scale", "name": "cfg_scale", "type": "FLOAT", "widget": {"name": "cfg_scale"}, "link": 270}, {"localized_name": "temperature", "name": "temperature", "type": "FLOAT", "widget": {"name": "temperature"}, "link": null}, {"localized_name": "top_p", "name": "top_p", "type": "FLOAT", "widget": {"name": "top_p"}, "link": null}, {"localized_name": "top_k", "name": "top_k", "type": "INT", "widget": {"name": "top_k"}, "link": null}, {"localized_name": "min_p", "name": "min_p", "type": "FLOAT", "widget": {"name": "min_p"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [254, 255]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "TextEncodeAceStepAudio1.5", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", "", 0, "fixed", 190, 120, "4", "en", "E minor", true, 2, 0.85, 0.9, 0, 0]}, {"id": 104, "type": "UNETLoader", "pos": [-170, -790], "size": [380, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 285}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [260]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.1", "Node name for S&R": "UNETLoader", "models": [{"name": "acestep_v1.5_turbo.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/diffusion_models/acestep_v1.5_turbo.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["acestep_v1.5_turbo.safetensors", "default"]}, {"id": 102, "type": "PrimitiveNode", "pos": [-120, -130], "size": [268.39945903485034, 82], "flags": {}, "order": 3, "mode": 0, "inputs": [], "outputs": [{"name": "INT", "type": "INT", "widget": {"name": "seed"}, "links": [257, 258]}], "title": "seed", "properties": {"Run widget replace on values": false}, "widgets_values": [0, "randomize"]}, {"id": 110, "type": "PrimitiveFloat", "pos": [-120, -280], "size": [270, 58], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": 284}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [279, 280]}], "title": "Song Duration", "properties": {"cnr_id": "comfy-core", "ver": "0.12.3", "Node name for S&R": "PrimitiveFloat", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [120]}], "groups": [{"id": 1, "title": "Step 1 - Load Models", "bounding": [-180, -860, 405, 461.6], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Step 2 - Duration", "bounding": [-180, -370, 400, 170], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Step3 - Prompt", "bounding": [260, -860, 640, 960], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 255, "origin_id": 94, "origin_slot": 0, "target_id": 47, "target_slot": 0, "type": "CONDITIONING"}, {"id": 175, "origin_id": 78, "origin_slot": 0, "target_id": 3, "target_slot": 0, "type": "MODEL"}, {"id": 254, "origin_id": 94, "origin_slot": 0, "target_id": 3, "target_slot": 1, "type": "CONDITIONING"}, {"id": 119, "origin_id": 47, "origin_slot": 0, "target_id": 3, "target_slot": 2, "type": "CONDITIONING"}, {"id": 249, "origin_id": 98, "origin_slot": 0, "target_id": 3, "target_slot": 3, "type": "LATENT"}, {"id": 258, "origin_id": 102, "origin_slot": 0, "target_id": 3, "target_slot": 4, "type": "INT"}, {"id": 260, "origin_id": 104, "origin_slot": 0, "target_id": 78, "target_slot": 0, "type": "MODEL"}, {"id": 256, "origin_id": 3, "origin_slot": 0, "target_id": 18, "target_slot": 0, "type": "LATENT"}, {"id": 262, "origin_id": 106, "origin_slot": 0, "target_id": 18, "target_slot": 1, "type": "VAE"}, {"id": 261, "origin_id": 105, "origin_slot": 0, "target_id": 94, "target_slot": 0, "type": "CLIP"}, {"id": 257, "origin_id": 102, "origin_slot": 0, "target_id": 94, "target_slot": 3, "type": "INT"}, {"id": 263, "origin_id": 18, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "AUDIO"}, {"id": 264, "origin_id": -10, "origin_slot": 0, "target_id": 94, "target_slot": 1, "type": "STRING"}, {"id": 265, "origin_id": -10, "origin_slot": 1, "target_id": 94, "target_slot": 2, "type": "STRING"}, {"id": 266, "origin_id": -10, "origin_slot": 2, "target_id": 94, "target_slot": 6, "type": "COMBO"}, {"id": 267, "origin_id": -10, "origin_slot": 3, "target_id": 94, "target_slot": 7, "type": "COMBO"}, {"id": 268, "origin_id": -10, "origin_slot": 4, "target_id": 94, "target_slot": 8, "type": "COMBO"}, {"id": 269, "origin_id": -10, "origin_slot": 5, "target_id": 94, "target_slot": 9, "type": "BOOLEAN"}, {"id": 270, "origin_id": -10, "origin_slot": 6, "target_id": 94, "target_slot": 10, "type": "FLOAT"}, {"id": 279, "origin_id": 110, "origin_slot": 0, "target_id": 98, "target_slot": 0, "type": "FLOAT"}, {"id": 280, "origin_id": 110, "origin_slot": 0, "target_id": 94, "target_slot": 5, "type": "FLOAT"}, {"id": 284, "origin_id": -10, "origin_slot": 7, "target_id": 110, "target_slot": 0, "type": "FLOAT"}, {"id": 285, "origin_id": -10, "origin_slot": 8, "target_id": 104, "target_slot": 0, "type": "COMBO"}, {"id": 286, "origin_id": -10, "origin_slot": 9, "target_id": 105, "target_slot": 0, "type": "COMBO"}, {"id": 287, "origin_id": -10, "origin_slot": 10, "target_id": 105, "target_slot": 1, "type": "COMBO"}, {"id": 288, "origin_id": -10, "origin_slot": 11, "target_id": 106, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Audio/Music generation"}]}, "config": {}, "extra": {"workflowRendererVersion": "LG", "ds": {"scale": 0.9575633843910519, "offset": [-950.8014851321678, 872.1540230582457]}}, "version": 0.4} +{ + "id": "67979fed-a490-450a-83f4-c7c0105d450e", + "revision": 0, + "last_node_id": 110, + "last_link_id": 288, + "nodes": [ + { + "id": 21, + "type": "510f6b52-34ee-40dd-b532-475497dee41b", + "pos": [ + 1810, + -560 + ], + "size": [ + 390, + 460 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "name": "tags", + "type": "STRING", + "widget": { + "name": "tags" + }, + "link": null + }, + { + "name": "lyrics", + "type": "STRING", + "widget": { + "name": "lyrics" + }, + "link": null + }, + { + "name": "timesignature", + "type": "COMBO", + "widget": { + "name": "timesignature" + }, + "link": null + }, + { + "name": "language", + "type": "COMBO", + "widget": { + "name": "language" + }, + "link": null + }, + { + "name": "keyscale", + "type": "COMBO", + "widget": { + "name": "keyscale" + }, + "link": null + }, + { + "name": "generate_audio_codes", + "type": "BOOLEAN", + "widget": { + "name": "generate_audio_codes" + }, + "link": null + }, + { + "name": "cfg_scale", + "type": "FLOAT", + "widget": { + "name": "cfg_scale" + }, + "link": null + }, + { + "label": "duration", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": null + }, + { + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "AUDIO", + "name": "AUDIO", + "type": "AUDIO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "tags" + ], + [ + "-1", + "lyrics" + ], + [ + "-1", + "language" + ], + [ + "-1", + "timesignature" + ], + [ + "-1", + "keyscale" + ], + [ + "-1", + "generate_audio_codes" + ], + [ + "-1", + "cfg_scale" + ], + [ + "102", + "value" + ], + [ + "102", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name1" + ], + [ + "-1", + "clip_name2" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.12.3", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "", + "", + "en", + "4", + "E minor", + true, + 2, + null, + null, + "acestep_v1.5_turbo.safetensors", + "qwen_0.6b_ace15.safetensors", + "qwen_4b_ace15.safetensors", + "ace_1.5_vae.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "510f6b52-34ee-40dd-b532-475497dee41b", + "version": 1, + "state": { + "lastGroupId": 3, + "lastNodeId": 110, + "lastLinkId": 288, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Text to Audio (ACE-Step 1.5)", + "inputNode": { + "id": -10, + "bounding": [ + -660, + -560, + 167.458984375, + 280 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1504.8375, + -410, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "ebc79d17-2e65-4e0f-855a-c9f2466a5fbf", + "name": "tags", + "type": "STRING", + "linkIds": [ + 264 + ], + "pos": [ + -512.541015625, + -540 + ] + }, + { + "id": "230afdb4-a647-4fb7-a68c-a2204fd5d570", + "name": "lyrics", + "type": "STRING", + "linkIds": [ + 265 + ], + "pos": [ + -512.541015625, + -520 + ] + }, + { + "id": "efdcbb48-231c-4757-b343-4458c011a283", + "name": "timesignature", + "type": "COMBO", + "linkIds": [ + 266 + ], + "pos": [ + -512.541015625, + -500 + ] + }, + { + "id": "811579c1-2979-4721-a1e1-7d9352616e7b", + "name": "language", + "type": "COMBO", + "linkIds": [ + 267 + ], + "pos": [ + -512.541015625, + -480 + ] + }, + { + "id": "76a68b0d-7a5f-43dc-873d-d78adf32895f", + "name": "keyscale", + "type": "COMBO", + "linkIds": [ + 268 + ], + "pos": [ + -512.541015625, + -460 + ] + }, + { + "id": "11bb3297-272d-4c56-873a-2c974581e838", + "name": "generate_audio_codes", + "type": "BOOLEAN", + "linkIds": [ + 269 + ], + "pos": [ + -512.541015625, + -440 + ] + }, + { + "id": "e5a30400-a8b0-422a-a0f3-21739727ab03", + "name": "cfg_scale", + "type": "FLOAT", + "linkIds": [ + 270 + ], + "pos": [ + -512.541015625, + -420 + ] + }, + { + "id": "91a37ca5-e0d1-42c5-8248-419b850661a0", + "name": "value", + "type": "FLOAT", + "linkIds": [ + 284 + ], + "label": "duration", + "pos": [ + -512.541015625, + -400 + ] + }, + { + "id": "30f69f59-e916-48ab-9a5d-ae445b8d8a63", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 285 + ], + "pos": [ + -512.541015625, + -380 + ] + }, + { + "id": "1af0e8df-6fa7-4df2-b1b4-9c356a8f30a6", + "name": "clip_name1", + "type": "COMBO", + "linkIds": [ + 286 + ], + "pos": [ + -512.541015625, + -360 + ] + }, + { + "id": "c7195505-9e83-4f87-b8d7-7747d808577d", + "name": "clip_name2", + "type": "COMBO", + "linkIds": [ + 287 + ], + "pos": [ + -512.541015625, + -340 + ] + }, + { + "id": "ca4bd68f-e7c1-4d87-9914-cfe15c63b96e", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 288 + ], + "pos": [ + -512.541015625, + -320 + ] + } + ], + "outputs": [ + { + "id": "bfd748f6-f9ac-4588-81fa-41bde07a58fa", + "name": "AUDIO", + "type": "AUDIO", + "linkIds": [ + 263 + ], + "localized_name": "AUDIO", + "pos": [ + 1524.8375, + -390 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 105, + "type": "DualCLIPLoader", + "pos": [ + -165, + -660 + ], + "size": [ + 380, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name1", + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": 286 + }, + { + "localized_name": "clip_name2", + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": 287 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 261 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "DualCLIPLoader", + "models": [ + { + "name": "qwen_0.6b_ace15.safetensors", + "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_0.6b_ace15.safetensors", + "directory": "text_encoders" + }, + { + "name": "qwen_4b_ace15.safetensors", + "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_4b_ace15.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_0.6b_ace15.safetensors", + "qwen_4b_ace15.safetensors", + "ace", + "default" + ] + }, + { + "id": 106, + "type": "VAELoader", + "pos": [ + -165, + -470 + ], + "size": [ + 380, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 288 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 262 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ace_1.5_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/vae/ace_1.5_vae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ace_1.5_vae.safetensors" + ] + }, + { + "id": 98, + "type": "EmptyAceStep1.5LatentAudio", + "pos": [ + -150, + 10 + ], + "size": [ + 314.90390625, + 82 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "seconds", + "name": "seconds", + "type": "FLOAT", + "widget": { + "name": "seconds" + }, + "link": 279 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 249 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "EmptyAceStep1.5LatentAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 120, + 1 + ] + }, + { + "id": 47, + "type": "ConditioningZeroOut", + "pos": [ + 670, + 50 + ], + "size": [ + 204.75, + 26 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 255 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 119 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "ConditioningZeroOut", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 930, + -680 + ], + "size": [ + 329.39477481889753, + 262 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 175 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 254 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 119 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 249 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 258 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 256 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "fixed", + 8, + 1, + "euler", + "simple", + 1 + ] + }, + { + "id": 78, + "type": "ModelSamplingAuraFlow", + "pos": [ + 930, + -810 + ], + "size": [ + 329.39477481889753, + 60 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 260 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 175 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 18, + "type": "VAEDecodeAudio", + "pos": [ + 1280, + -800 + ], + "size": [ + 164.8375, + 46 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 256 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 262 + } + ], + "outputs": [ + { + "localized_name": "AUDIO", + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 263 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "VAEDecodeAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 94, + "type": "TextEncodeAceStepAudio1.5", + "pos": [ + 270, + -790 + ], + "size": [ + 611.9184354063266, + 679.7643386829468 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 261 + }, + { + "localized_name": "tags", + "name": "tags", + "type": "STRING", + "widget": { + "name": "tags" + }, + "link": 264 + }, + { + "localized_name": "lyrics", + "name": "lyrics", + "type": "STRING", + "widget": { + "name": "lyrics" + }, + "link": 265 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 257 + }, + { + "localized_name": "bpm", + "name": "bpm", + "type": "INT", + "widget": { + "name": "bpm" + }, + "link": null + }, + { + "localized_name": "duration", + "name": "duration", + "type": "FLOAT", + "widget": { + "name": "duration" + }, + "link": 280 + }, + { + "localized_name": "timesignature", + "name": "timesignature", + "type": "COMBO", + "widget": { + "name": "timesignature" + }, + "link": 266 + }, + { + "localized_name": "language", + "name": "language", + "type": "COMBO", + "widget": { + "name": "language" + }, + "link": 267 + }, + { + "localized_name": "keyscale", + "name": "keyscale", + "type": "COMBO", + "widget": { + "name": "keyscale" + }, + "link": 268 + }, + { + "localized_name": "generate_audio_codes", + "name": "generate_audio_codes", + "type": "BOOLEAN", + "widget": { + "name": "generate_audio_codes" + }, + "link": 269 + }, + { + "localized_name": "cfg_scale", + "name": "cfg_scale", + "type": "FLOAT", + "widget": { + "name": "cfg_scale" + }, + "link": 270 + }, + { + "localized_name": "temperature", + "name": "temperature", + "type": "FLOAT", + "widget": { + "name": "temperature" + }, + "link": null + }, + { + "localized_name": "top_p", + "name": "top_p", + "type": "FLOAT", + "widget": { + "name": "top_p" + }, + "link": null + }, + { + "localized_name": "top_k", + "name": "top_k", + "type": "INT", + "widget": { + "name": "top_k" + }, + "link": null + }, + { + "localized_name": "min_p", + "name": "min_p", + "type": "FLOAT", + "widget": { + "name": "min_p" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 254, + 255 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "TextEncodeAceStepAudio1.5", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "", + "", + 0, + "fixed", + 190, + 120, + "4", + "en", + "E minor", + true, + 2, + 0.85, + 0.9, + 0, + 0 + ] + }, + { + "id": 104, + "type": "UNETLoader", + "pos": [ + -170, + -790 + ], + "size": [ + 380, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 285 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 260 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.1", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "acestep_v1.5_turbo.safetensors", + "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/diffusion_models/acestep_v1.5_turbo.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "acestep_v1.5_turbo.safetensors", + "default" + ] + }, + { + "id": 102, + "type": "PrimitiveNode", + "pos": [ + -120, + -130 + ], + "size": [ + 268.39945903485034, + 82 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "INT", + "type": "INT", + "widget": { + "name": "seed" + }, + "links": [ + 257, + 258 + ] + } + ], + "title": "seed", + "properties": { + "Run widget replace on values": false + }, + "widgets_values": [ + 0, + "randomize" + ] + }, + { + "id": 110, + "type": "PrimitiveFloat", + "pos": [ + -120, + -280 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": 284 + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 279, + 280 + ] + } + ], + "title": "Song Duration", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 120 + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Step 1 - Load Models", + "bounding": [ + -180, + -860, + 405, + 461.6 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Step 2 - Duration", + "bounding": [ + -180, + -370, + 400, + 170 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Step3 - Prompt", + "bounding": [ + 260, + -860, + 640, + 960 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 255, + "origin_id": 94, + "origin_slot": 0, + "target_id": 47, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 175, + "origin_id": 78, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 254, + "origin_id": 94, + "origin_slot": 0, + "target_id": 3, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 119, + "origin_id": 47, + "origin_slot": 0, + "target_id": 3, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 249, + "origin_id": 98, + "origin_slot": 0, + "target_id": 3, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 258, + "origin_id": 102, + "origin_slot": 0, + "target_id": 3, + "target_slot": 4, + "type": "INT" + }, + { + "id": 260, + "origin_id": 104, + "origin_slot": 0, + "target_id": 78, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 256, + "origin_id": 3, + "origin_slot": 0, + "target_id": 18, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 262, + "origin_id": 106, + "origin_slot": 0, + "target_id": 18, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 261, + "origin_id": 105, + "origin_slot": 0, + "target_id": 94, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 257, + "origin_id": 102, + "origin_slot": 0, + "target_id": 94, + "target_slot": 3, + "type": "INT" + }, + { + "id": 263, + "origin_id": 18, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "AUDIO" + }, + { + "id": 264, + "origin_id": -10, + "origin_slot": 0, + "target_id": 94, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 265, + "origin_id": -10, + "origin_slot": 1, + "target_id": 94, + "target_slot": 2, + "type": "STRING" + }, + { + "id": 266, + "origin_id": -10, + "origin_slot": 2, + "target_id": 94, + "target_slot": 6, + "type": "COMBO" + }, + { + "id": 267, + "origin_id": -10, + "origin_slot": 3, + "target_id": 94, + "target_slot": 7, + "type": "COMBO" + }, + { + "id": 268, + "origin_id": -10, + "origin_slot": 4, + "target_id": 94, + "target_slot": 8, + "type": "COMBO" + }, + { + "id": 269, + "origin_id": -10, + "origin_slot": 5, + "target_id": 94, + "target_slot": 9, + "type": "BOOLEAN" + }, + { + "id": 270, + "origin_id": -10, + "origin_slot": 6, + "target_id": 94, + "target_slot": 10, + "type": "FLOAT" + }, + { + "id": 279, + "origin_id": 110, + "origin_slot": 0, + "target_id": 98, + "target_slot": 0, + "type": "FLOAT" + }, + { + "id": 280, + "origin_id": 110, + "origin_slot": 0, + "target_id": 94, + "target_slot": 5, + "type": "FLOAT" + }, + { + "id": 284, + "origin_id": -10, + "origin_slot": 7, + "target_id": 110, + "target_slot": 0, + "type": "FLOAT" + }, + { + "id": 285, + "origin_id": -10, + "origin_slot": 8, + "target_id": 104, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 286, + "origin_id": -10, + "origin_slot": 9, + "target_id": 105, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 287, + "origin_id": -10, + "origin_slot": 10, + "target_id": 105, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 288, + "origin_id": -10, + "origin_slot": 11, + "target_id": 106, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Audio/Music generation" + } + ] + }, + "config": {}, + "extra": { + "workflowRendererVersion": "LG", + "ds": { + "scale": 0.9575633843910519, + "offset": [ + -950.8014851321678, + 872.1540230582457 + ] + } + }, + "version": 0.4 +} diff --git a/blueprints/Text to Image (Flux.1 Dev).json b/blueprints/Text to Image (Flux.1 Dev).json new file mode 100644 index 000000000..04c3cb95a --- /dev/null +++ b/blueprints/Text to Image (Flux.1 Dev).json @@ -0,0 +1,1046 @@ +{ + "revision": 0, + "last_node_id": 193, + "last_link_id": 0, + "nodes": [ + { + "id": 193, + "type": "1fd98b34-59ef-4d8d-afbf-58bdd7a1cd35", + "pos": [ + -1210, + -1770 + ], + "size": [ + 400, + 380 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": null + }, + { + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "45", + "text" + ], + [ + "27", + "width" + ], + [ + "27", + "height" + ], + [ + "31", + "seed" + ], + [ + "38", + "unet_name" + ], + [ + "40", + "clip_name1" + ], + [ + "40", + "clip_name2" + ], + [ + "39", + "vae_name" + ], + [ + "31", + "control_after_generate" + ] + ], + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1" + }, + "widgets_values": [], + "title": "Text to Image (Flux.1 Dev)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "1fd98b34-59ef-4d8d-afbf-58bdd7a1cd35", + "version": 1, + "state": { + "lastGroupId": 8, + "lastNodeId": 193, + "lastLinkId": 388, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Text to Image (Flux.1 Dev)", + "inputNode": { + "id": -10, + "bounding": [ + -1090, + 411, + 120, + 200 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 540, + 100, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "669e384e-5e26-4291-9bac-e1d1f04b4a16", + "name": "text", + "type": "STRING", + "linkIds": [ + 68 + ], + "label": "prompt", + "pos": [ + -990, + 431 + ] + }, + { + "id": "5a5c0b01-5836-4ca6-a24f-68c0a4fb9802", + "name": "width", + "type": "INT", + "linkIds": [ + 69 + ], + "pos": [ + -990, + 451 + ] + }, + { + "id": "5e01104a-ed7f-457b-aaee-934e8ecc088d", + "name": "height", + "type": "INT", + "linkIds": [ + 70 + ], + "pos": [ + -990, + 471 + ] + }, + { + "id": "ea5ea317-a484-4605-8138-8628a4b8e502", + "name": "seed", + "type": "INT", + "linkIds": [ + 382 + ], + "pos": [ + -990, + 491 + ] + }, + { + "id": "ea2332f5-bd49-4e2e-8c7a-95817dc56ed6", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 385 + ], + "pos": [ + -990, + 511 + ] + }, + { + "id": "4fca3f43-c05f-4337-bf84-2afe67e43739", + "name": "clip_name1", + "type": "COMBO", + "linkIds": [ + 386 + ], + "pos": [ + -990, + 531 + ] + }, + { + "id": "357a679f-1370-4cd5-9269-0d5ae1986b49", + "name": "clip_name2", + "type": "COMBO", + "linkIds": [ + 387 + ], + "pos": [ + -990, + 551 + ] + }, + { + "id": "924ffec5-81f8-4585-8761-5a80d5d775bc", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 388 + ], + "pos": [ + -990, + 571 + ] + } + ], + "outputs": [ + { + "id": "2185cb4d-8689-4cf8-b345-75319fb46a8e", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 9 + ], + "localized_name": "IMAGE", + "pos": [ + 560, + 120 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 39, + "type": "VAELoader", + "pos": [ + -800, + 670 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 388 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 58 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 38, + "type": "UNETLoader", + "pos": [ + -800, + 160 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 385 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 61 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "flux1-dev.safetensors", + "url": "https://huggingface.co/Comfy-Org/flux1-dev/resolve/main/flux1-dev.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "flux1-dev.safetensors", + "default" + ] + }, + { + "id": 40, + "type": "DualCLIPLoader", + "pos": [ + -800, + 380 + ], + "size": [ + 270, + 180 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name1", + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": 386 + }, + { + "localized_name": "clip_name2", + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": 387 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 64 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "DualCLIPLoader", + "models": [ + { + "name": "clip_l.safetensors", + "url": "https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors", + "directory": "text_encoders" + }, + { + "name": "t5xxl_fp16.safetensors", + "url": "https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "clip_l.safetensors", + "t5xxl_fp16.safetensors", + "flux", + "default" + ] + }, + { + "id": 27, + "type": "EmptySD3LatentImage", + "pos": [ + -420, + 640 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 69 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 70 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 51 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "EmptySD3LatentImage" + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 45, + "type": "CLIPTextEncode", + "pos": [ + -460, + 150 + ], + "size": [ + 330, + 220 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 64 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 68 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 65, + 66 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ] + }, + { + "id": 31, + "type": "KSampler", + "pos": [ + -50, + 260 + ], + "size": [ + 320, + 350 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 61 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 65 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 63 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 51 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 382 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 52 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 0, + "randomize", + 20, + 1, + "euler", + "simple", + 1 + ] + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 20, + 120 + ], + "size": [ + 230, + 100 + ], + "flags": { + "collapsed": false + }, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 52 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 58 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 9 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 42, + "type": "ConditioningZeroOut", + "pos": [ + -350, + 420 + ], + "size": [ + 230, + 80 + ], + "flags": { + "collapsed": false + }, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 66 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 63 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "ConditioningZeroOut" + } + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -820, + 70, + 320, + 750 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Image Size", + "bounding": [ + -470, + 570, + 380, + 250 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + -470, + 70, + 380, + 470 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 52, + "origin_id": 31, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 58, + "origin_id": 39, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 61, + "origin_id": 38, + "origin_slot": 0, + "target_id": 31, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 63, + "origin_id": 42, + "origin_slot": 0, + "target_id": 31, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 51, + "origin_id": 27, + "origin_slot": 0, + "target_id": 31, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 9, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 64, + "origin_id": 40, + "origin_slot": 0, + "target_id": 45, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 65, + "origin_id": 45, + "origin_slot": 0, + "target_id": 31, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 66, + "origin_id": 45, + "origin_slot": 0, + "target_id": 42, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 68, + "origin_id": -10, + "origin_slot": 0, + "target_id": 45, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 69, + "origin_id": -10, + "origin_slot": 1, + "target_id": 27, + "target_slot": 0, + "type": "INT" + }, + { + "id": 70, + "origin_id": -10, + "origin_slot": 2, + "target_id": 27, + "target_slot": 1, + "type": "INT" + }, + { + "id": 382, + "origin_id": -10, + "origin_slot": 3, + "target_id": 31, + "target_slot": 4, + "type": "INT" + }, + { + "id": 385, + "origin_id": -10, + "origin_slot": 4, + "target_id": 38, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 386, + "origin_id": -10, + "origin_slot": 5, + "target_id": 40, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 387, + "origin_id": -10, + "origin_slot": 6, + "target_id": 40, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 388, + "origin_id": -10, + "origin_slot": 7, + "target_id": 39, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Text to image" + } + ] + }, + "extra": { + "ds": { + "scale": 0.7513148009015777, + "offset": [ + 1726.1426909346173, + 146.66925047394233 + ] + }, + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Text to Image (Flux.1 Krea Dev).json b/blueprints/Text to Image (Flux.1 Krea Dev).json new file mode 100644 index 000000000..fe4db1cfc --- /dev/null +++ b/blueprints/Text to Image (Flux.1 Krea Dev).json @@ -0,0 +1,1040 @@ +{ + "revision": 0, + "last_node_id": 196, + "last_link_id": 0, + "nodes": [ + { + "id": 196, + "type": "aa0a207e-bf0e-477c-a87f-f58fcf5f7749", + "pos": [ + 1010, + 130 + ], + "size": [ + 410, + 460 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": null + }, + { + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "195", + "text" + ], + [ + "27", + "width" + ], + [ + "27", + "height" + ], + [ + "31", + "seed" + ], + [ + "38", + "unet_name" + ], + [ + "40", + "clip_name1" + ], + [ + "40", + "clip_name2" + ], + [ + "39", + "vae_name" + ] + ], + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1" + }, + "widgets_values": [], + "title": "Text to Image (Flux.1 Krea Dev)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "aa0a207e-bf0e-477c-a87f-f58fcf5f7749", + "version": 1, + "state": { + "lastGroupId": 8, + "lastNodeId": 196, + "lastLinkId": 395, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Text to Image (Flux.1 Krea Dev)", + "inputNode": { + "id": -10, + "bounding": [ + -1050, + 426, + 120, + 200 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 620, + 140, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "c2515318-6e10-4ad9-9466-e6aa855bc849", + "name": "text", + "type": "STRING", + "linkIds": [ + 71 + ], + "pos": [ + -950, + 446 + ] + }, + { + "id": "09f20672-c8a3-4180-823a-5a6af0113e4f", + "name": "width", + "type": "INT", + "linkIds": [ + 72 + ], + "pos": [ + -950, + 466 + ] + }, + { + "id": "7f54c952-896e-4356-bfb2-970e1c8f2eb7", + "name": "height", + "type": "INT", + "linkIds": [ + 73 + ], + "pos": [ + -950, + 486 + ] + }, + { + "id": "e2dc1c86-2fb4-4b80-b560-f30560af1897", + "name": "seed", + "type": "INT", + "linkIds": [ + 391 + ], + "pos": [ + -950, + 506 + ] + }, + { + "id": "34b172e7-85b2-444a-9a4d-1221f272c46e", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 392 + ], + "pos": [ + -950, + 526 + ] + }, + { + "id": "073b7440-d943-4a2f-a3a1-fbdb8fcda9f9", + "name": "clip_name1", + "type": "COMBO", + "linkIds": [ + 393 + ], + "pos": [ + -950, + 546 + ] + }, + { + "id": "55c1286a-4aca-41fc-b967-ae3d3fa7bc85", + "name": "clip_name2", + "type": "COMBO", + "linkIds": [ + 394 + ], + "pos": [ + -950, + 566 + ] + }, + { + "id": "2241e4fc-9219-4be7-bf6d-3493b579ab5a", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 395 + ], + "pos": [ + -950, + 586 + ] + } + ], + "outputs": [ + { + "id": "5310184a-f0a2-405f-9917-dd2a352a4fac", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 9 + ], + "localized_name": "IMAGE", + "pos": [ + 640, + 160 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 40, + "type": "DualCLIPLoader", + "pos": [ + -780, + 360 + ], + "size": [ + 270, + 180 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name1", + "name": "clip_name1", + "type": "COMBO", + "widget": { + "name": "clip_name1" + }, + "link": 393 + }, + { + "localized_name": "clip_name2", + "name": "clip_name2", + "type": "COMBO", + "widget": { + "name": "clip_name2" + }, + "link": 394 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 64 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "DualCLIPLoader", + "models": [ + { + "name": "clip_l.safetensors", + "url": "https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors", + "directory": "text_encoders" + }, + { + "name": "t5xxl_fp16.safetensors", + "url": "https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "clip_l.safetensors", + "t5xxl_fp16.safetensors", + "flux", + "default" + ] + }, + { + "id": 39, + "type": "VAELoader", + "pos": [ + -770, + 630 + ], + "size": [ + 240, + 110 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 395 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 58 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 38, + "type": "UNETLoader", + "pos": [ + -780, + 170 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 392 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 61 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "flux1-krea-dev_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/FLUX.1-Krea-dev_ComfyUI/resolve/main/split_files/diffusion_models/flux1-krea-dev_fp8_scaled.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "flux1-krea-dev_fp8_scaled.safetensors", + "default" + ] + }, + { + "id": 195, + "type": "CLIPTextEncode", + "pos": [ + -440, + 180 + ], + "size": [ + 330, + 210 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 64 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 71 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 65, + 66 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.47", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ] + }, + { + "id": 27, + "type": "EmptySD3LatentImage", + "pos": [ + -390, + 650 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 72 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 73 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 51 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "EmptySD3LatentImage" + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 31, + "type": "KSampler", + "pos": [ + 0, + 130 + ], + "size": [ + 320, + 350 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 61 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 65 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 63 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 51 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 391 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 52 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 0, + "randomize", + 20, + 1, + "euler", + "simple", + 1 + ] + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 340, + 140 + ], + "size": [ + 230, + 100 + ], + "flags": { + "collapsed": false + }, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 52 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 58 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 9 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 42, + "type": "ConditioningZeroOut", + "pos": [ + -340, + 430 + ], + "size": [ + 230, + 80 + ], + "flags": { + "collapsed": false + }, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 66 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 63 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "ConditioningZeroOut" + } + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -800, + 90, + 310, + 750 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Image Size", + "bounding": [ + -460, + 560, + 400, + 280 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + -460, + 90, + 400, + 440 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 66, + "origin_id": 195, + "origin_slot": 0, + "target_id": 42, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 52, + "origin_id": 31, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 58, + "origin_id": 39, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 61, + "origin_id": 38, + "origin_slot": 0, + "target_id": 31, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 65, + "origin_id": 195, + "origin_slot": 0, + "target_id": 31, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 63, + "origin_id": 42, + "origin_slot": 0, + "target_id": 31, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 51, + "origin_id": 27, + "origin_slot": 0, + "target_id": 31, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 64, + "origin_id": 40, + "origin_slot": 0, + "target_id": 195, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 9, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 71, + "origin_id": -10, + "origin_slot": 0, + "target_id": 195, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 72, + "origin_id": -10, + "origin_slot": 1, + "target_id": 27, + "target_slot": 0, + "type": "INT" + }, + { + "id": 73, + "origin_id": -10, + "origin_slot": 2, + "target_id": 27, + "target_slot": 1, + "type": "INT" + }, + { + "id": 391, + "origin_id": -10, + "origin_slot": 3, + "target_id": 31, + "target_slot": 4, + "type": "INT" + }, + { + "id": 392, + "origin_id": -10, + "origin_slot": 4, + "target_id": 38, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 393, + "origin_id": -10, + "origin_slot": 5, + "target_id": 40, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 394, + "origin_id": -10, + "origin_slot": 6, + "target_id": 40, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 395, + "origin_id": -10, + "origin_slot": 7, + "target_id": 39, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Text to image" + } + ] + }, + "extra": { + "ds": { + "scale": 0.735584459955559, + "offset": [ + 1936.5815687336737, + 303.78330847702625 + ] + }, + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Text to Image (NetaYume Lumina).json b/blueprints/Text to Image (NetaYume Lumina).json new file mode 100644 index 000000000..394ad1608 --- /dev/null +++ b/blueprints/Text to Image (NetaYume Lumina).json @@ -0,0 +1,1468 @@ +{ + "revision": 0, + "last_node_id": 219, + "last_link_id": 0, + "nodes": [ + { + "id": 219, + "type": "fc9485c9-2acd-482e-94f1-b5fa702f2536", + "pos": [ + -1900, + 2330 + ], + "size": [ + 400, + 540 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "62", + "value" + ], + [ + "53", + "width" + ], + [ + "53", + "height" + ], + [ + "55", + "seed" + ], + [ + "56", + "ckpt_name" + ], + [ + "55", + "control_after_generate" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [], + "title": "Text to Image (NetaYume Lumina)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "fc9485c9-2acd-482e-94f1-b5fa702f2536", + "version": 1, + "state": { + "lastGroupId": 8, + "lastNodeId": 219, + "lastLinkId": 395, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Text to Image (NetaYume Lumina)", + "inputNode": { + "id": -10, + "bounding": [ + -600, + 90, + 120, + 140 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1740.333330193419, + 286.3333328495138, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "b80a1e0c-e8a6-4c4f-8eb1-825cb7e4fdcf", + "name": "value", + "type": "STRING", + "linkIds": [ + 36 + ], + "pos": [ + -500, + 110 + ] + }, + { + "id": "6583bb32-7cff-4921-a771-1f0dcdf779e6", + "name": "width", + "type": "INT", + "linkIds": [ + 39 + ], + "pos": [ + -500, + 130 + ] + }, + { + "id": "c486937a-46c0-431b-8775-057897843cbd", + "name": "height", + "type": "INT", + "linkIds": [ + 40 + ], + "pos": [ + -500, + 150 + ] + }, + { + "id": "9c85c0cc-c906-405a-a4d9-43b93c47cb53", + "name": "seed", + "type": "INT", + "linkIds": [ + 42 + ], + "pos": [ + -500, + 170 + ] + }, + { + "id": "f7e288ec-fa1f-4a1d-b721-6b605de9cb51", + "name": "ckpt_name", + "type": "COMBO", + "linkIds": [ + 43 + ], + "pos": [ + -500, + 190 + ] + } + ], + "outputs": [ + { + "id": "ea4b872b-a294-4cbf-99a9-70e55c0f8b3e", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 16 + ], + "localized_name": "IMAGE", + "pos": [ + 1760.333330193419, + 306.3333328495138 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 53, + "type": "EmptySD3LatentImage", + "pos": [ + -220, + 370 + ], + "size": [ + 320, + 170 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 39 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 40 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 17 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "EmptySD3LatentImage" + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 54, + "type": "ModelSamplingAuraFlow", + "pos": [ + 650, + 40 + ], + "size": [ + 310, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 12 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 13 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ModelSamplingAuraFlow" + }, + "widgets_values": [ + 4 + ] + }, + { + "id": 55, + "type": "KSampler", + "pos": [ + 650, + 200 + ], + "size": [ + 320, + 350 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 13 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 32 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 23 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 17 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 42 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 14 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 0, + "randomize", + 30, + 4, + "res_multistep", + "simple", + 1 + ] + }, + { + "id": 56, + "type": "CheckpointLoaderSimple", + "pos": [ + -220, + 70 + ], + "size": [ + 320, + 160 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 43 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 12 + ] + }, + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 1, + "links": [ + 22, + 35 + ] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 2, + "links": [ + 8 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CheckpointLoaderSimple", + "models": [ + { + "name": "NetaYumev35_pretrained_all_in_one.safetensors", + "url": "https://huggingface.co/duongve/NetaYume-Lumina-Image-2.0/resolve/main/NetaYumev35_pretrained_all_in_one.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "NetaYumev35_pretrained_all_in_one.safetensors" + ] + }, + { + "id": 57, + "type": "a07fdf06-1bda-4dac-bdbd-63ee8ebca1c9", + "pos": [ + 180, + 360 + ], + "size": [ + 400, + 140 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 22 + }, + { + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 23 + ] + } + ], + "properties": { + "proxyWidgets": [ + [ + "218", + "value" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [], + "color": "#223", + "bgcolor": "#335" + }, + { + "id": 217, + "type": "VAEDecode", + "pos": [ + 1040, + 210 + ], + "size": [ + 230, + 100 + ], + "flags": { + "collapsed": false + }, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 14 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 8 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 16 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 59, + "type": "MarkdownNote", + "pos": [ + 640, + -390 + ], + "size": [ + 370, + 280 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: Prompt", + "properties": {}, + "widgets_values": [ + "Check the prompt book [here](https://nieta-art.feishu.cn/wiki/RY3GwpT59icIQlkWXEfcCqIMnQd)\n\nYou should keep the prefix part fixed until the **Prompt Start** tag\n\n@whatever in the prompt is for artist tags, such as @comfyanonymous\n\nYou can find more artist tags [here](https://gumgum10.github.io/gumgum.github.io/)\n" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 60, + "type": "StringConcatenate", + "pos": [ + 170, + -370 + ], + "size": [ + 400, + 250 + ], + "flags": { + "collapsed": true + }, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "string_a", + "name": "string_a", + "type": "STRING", + "widget": { + "name": "string_a" + }, + "link": 30 + }, + { + "localized_name": "string_b", + "name": "string_b", + "type": "STRING", + "widget": { + "name": "string_b" + }, + "link": 31 + }, + { + "localized_name": "delimiter", + "name": "delimiter", + "type": "STRING", + "widget": { + "name": "delimiter" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 34 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.70", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "StringConcatenate" + }, + "widgets_values": [ + "", + "", + "" + ] + }, + { + "id": 61, + "type": "CLIPTextEncode", + "pos": [ + 170, + 60 + ], + "size": [ + 430, + 190 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 35 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 34 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 32 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 62, + "type": "PrimitiveStringMultiline", + "pos": [ + -240, + -210 + ], + "size": [ + 370, + 140 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": 36 + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 31 + ] + } + ], + "title": "Prompt", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.70", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveStringMultiline" + }, + "widgets_values": [ + "" + ] + }, + { + "id": 63, + "type": "PrimitiveStringMultiline", + "pos": [ + -240, + -390 + ], + "size": [ + 370, + 140 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 30 + ] + } + ], + "title": "System prompt", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.70", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveStringMultiline" + }, + "widgets_values": [ + "You are an assistant designed to generate high quality anime images based on textual prompts. " + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -250, + -30, + 370, + 280 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Image Size", + "bounding": [ + -250, + 280, + 370, + 290 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + 150, + -30, + 460, + 600 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 4, + "title": "Prompt Builder", + "bounding": [ + -250, + -460, + 840, + 400 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 12, + "origin_id": 56, + "origin_slot": 0, + "target_id": 54, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 13, + "origin_id": 54, + "origin_slot": 0, + "target_id": 55, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 23, + "origin_id": 57, + "origin_slot": 0, + "target_id": 55, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 17, + "origin_id": 53, + "origin_slot": 0, + "target_id": 55, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 14, + "origin_id": 55, + "origin_slot": 0, + "target_id": 217, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 8, + "origin_id": 56, + "origin_slot": 2, + "target_id": 217, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 22, + "origin_id": 56, + "origin_slot": 1, + "target_id": 57, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 16, + "origin_id": 217, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 30, + "origin_id": 63, + "origin_slot": 0, + "target_id": 60, + "target_slot": 0, + "type": "STRING" + }, + { + "id": 31, + "origin_id": 62, + "origin_slot": 0, + "target_id": 60, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 32, + "origin_id": 61, + "origin_slot": 0, + "target_id": 55, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 34, + "origin_id": 60, + "origin_slot": 0, + "target_id": 61, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 35, + "origin_id": 56, + "origin_slot": 1, + "target_id": 61, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 36, + "origin_id": -10, + "origin_slot": 0, + "target_id": 62, + "target_slot": 0, + "type": "STRING" + }, + { + "id": 39, + "origin_id": -10, + "origin_slot": 1, + "target_id": 53, + "target_slot": 0, + "type": "INT" + }, + { + "id": 40, + "origin_id": -10, + "origin_slot": 2, + "target_id": 53, + "target_slot": 1, + "type": "INT" + }, + { + "id": 42, + "origin_id": -10, + "origin_slot": 3, + "target_id": 55, + "target_slot": 4, + "type": "INT" + }, + { + "id": 43, + "origin_id": -10, + "origin_slot": 4, + "target_id": 56, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Text to image" + }, + { + "id": "a07fdf06-1bda-4dac-bdbd-63ee8ebca1c9", + "version": 1, + "state": { + "lastGroupId": 8, + "lastNodeId": 219, + "lastLinkId": 395, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "CLIP Text Encode (Negative Prompt)", + "inputNode": { + "id": -10, + "bounding": [ + -150, + 675, + 120, + 80 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 905.2780151367188, + 675, + 128.6640625, + 60 + ] + }, + "inputs": [ + { + "id": "47264a97-6fc9-454d-920f-b8a43fee0489", + "name": "clip", + "type": "CLIP", + "linkIds": [ + 5 + ], + "localized_name": "clip", + "pos": [ + -50, + 695 + ] + }, + { + "id": "7cdb7919-1dad-4bd2-928d-c543c3fd712e", + "name": "value", + "type": "STRING", + "linkIds": [ + 22 + ], + "pos": [ + -50, + 715 + ] + } + ], + "outputs": [ + { + "id": "c3f17ad9-6954-4333-bf8e-e1cf886c351b", + "name": "CONDITIONING", + "type": "CONDITIONING", + "linkIds": [ + 6 + ], + "localized_name": "CONDITIONING", + "pos": [ + 925.2780151367188, + 695 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 64, + "type": "StringConcatenate", + "pos": [ + 420, + 720 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "string_a", + "name": "string_a", + "type": "STRING", + "widget": { + "name": "string_a" + }, + "link": 19 + }, + { + "localized_name": "string_b", + "name": "string_b", + "type": "STRING", + "widget": { + "name": "string_b" + }, + "link": 20 + }, + { + "localized_name": "delimiter", + "name": "delimiter", + "type": "STRING", + "widget": { + "name": "delimiter" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 21 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.70", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "StringConcatenate" + }, + "widgets_values": [ + "", + "", + "" + ] + }, + { + "id": 65, + "type": "PrimitiveStringMultiline", + "pos": [ + 30, + 720 + ], + "size": [ + 370, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 19 + ] + } + ], + "title": "System prompt", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.70", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveStringMultiline" + }, + "widgets_values": [ + "You are an assistant designed to generate low-quality images based on textual prompts " + ] + }, + { + "id": 218, + "type": "PrimitiveStringMultiline", + "pos": [ + 30, + 900 + ], + "size": [ + 370, + 130 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": 22 + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 20 + ] + } + ], + "title": "System prompt", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.70", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveStringMultiline" + }, + "widgets_values": [ + "blurry, worst quality, low quality, jpeg artifacts, signature, watermark, username, error, deformed hands, bad anatomy, extra limbs, poorly drawn hands, poorly drawn face, mutation, deformed, extra eyes, extra arms, extra legs, malformed limbs, fused fingers, too many fingers, long neck, cross-eyed, bad proportions, missing arms, missing legs, extra digit, fewer digits, cropped" + ] + }, + { + "id": 67, + "type": "CLIPTextEncode", + "pos": [ + 420, + 410 + ], + "size": [ + 430, + 190 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 5 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 21 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 6 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "You are an assistant designed to generate low-quality images based on textual prompts blurry, worst quality, low quality, jpeg artifacts, signature, watermark, username, error, deformed hands, bad anatomy, extra limbs, poorly drawn hands, poorly drawn face, mutation, deformed, extra eyes, extra arms, extra legs, malformed limbs, fused fingers, too many fingers, long neck, cross-eyed, bad proportions, missing arms, missing legs, extra digit, fewer digits, cropped" + ], + "color": "#223", + "bgcolor": "#335" + } + ], + "groups": [], + "links": [ + { + "id": 19, + "origin_id": 65, + "origin_slot": 0, + "target_id": 64, + "target_slot": 0, + "type": "STRING" + }, + { + "id": 20, + "origin_id": 218, + "origin_slot": 0, + "target_id": 64, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 21, + "origin_id": 64, + "origin_slot": 0, + "target_id": 67, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 5, + "origin_id": -10, + "origin_slot": 0, + "target_id": 67, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 6, + "origin_id": 67, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 22, + "origin_id": -10, + "origin_slot": 1, + "target_id": 218, + "target_slot": 0, + "type": "STRING" + } + ], + "extra": { + "workflowRendererVersion": "LG" + } + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Text to Image (Qwen-Image 2512).json b/blueprints/Text to Image (Qwen-Image 2512).json new file mode 100644 index 000000000..f52ea2ef2 --- /dev/null +++ b/blueprints/Text to Image (Qwen-Image 2512).json @@ -0,0 +1,1951 @@ +{ + "revision": 0, + "last_node_id": 263, + "last_link_id": 0, + "nodes": [ + { + "id": 263, + "type": "fd6ee5f8-a0a9-487a-8b44-8cb65957532a", + "pos": [ + 750, + 760 + ], + "size": [ + 400, + 0 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "label": "enable_turbo_mode", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "249", + "text" + ], + [ + "252", + "width" + ], + [ + "252", + "height" + ], + [ + "256", + "value" + ], + [ + "253", + "seed" + ], + [ + "248", + "unet_name" + ], + [ + "245", + "clip_name" + ], + [ + "246", + "vae_name" + ], + [ + "259", + "lora_name" + ] + ], + "ue_properties": { + "widget_ue_connectable": { + "value": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.4", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [], + "title": "Text to Image (Qwen-Image 2512)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "fd6ee5f8-a0a9-487a-8b44-8cb65957532a", + "version": 1, + "state": { + "lastGroupId": 7, + "lastNodeId": 263, + "lastLinkId": 375, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Text to Image (Qwen-Image 2512)", + "inputNode": { + "id": -10, + "bounding": [ + -1080, + 1480, + 151.744140625, + 220 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1550, + 1460, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "74d26021-a723-4a90-8e33-5d805a7e5deb", + "name": "text", + "type": "STRING", + "linkIds": [ + 360 + ], + "pos": [ + -948.255859375, + 1500 + ] + }, + { + "id": "b55f69e6-c7cb-4641-9e1f-2cb1c1942ed0", + "name": "width", + "type": "INT", + "linkIds": [ + 361 + ], + "pos": [ + -948.255859375, + 1520 + ] + }, + { + "id": "3e80284d-aba3-43cd-ab7b-ac2a619ef18c", + "name": "height", + "type": "INT", + "linkIds": [ + 362 + ], + "pos": [ + -948.255859375, + 1540 + ] + }, + { + "id": "de06e137-6cec-4cb3-a6bb-737022310a7b", + "name": "value", + "type": "BOOLEAN", + "linkIds": [ + 370 + ], + "label": "enable_turbo_mode", + "pos": [ + -948.255859375, + 1560 + ] + }, + { + "id": "9e500dee-a5b9-481b-ac46-64bab4bd3530", + "name": "seed", + "type": "INT", + "linkIds": [ + 371 + ], + "pos": [ + -948.255859375, + 1580 + ] + }, + { + "id": "33422b12-24e5-41c6-96fc-f9a8dadd5d94", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 372 + ], + "pos": [ + -948.255859375, + 1600 + ] + }, + { + "id": "5cf753e4-236e-468e-9a06-6b8e238badc8", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 373 + ], + "pos": [ + -948.255859375, + 1620 + ] + }, + { + "id": "790e775c-a639-4e5f-9007-e2ee6764dc5e", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 374 + ], + "pos": [ + -948.255859375, + 1640 + ] + }, + { + "id": "3ebed521-3fe9-4922-ae26-2483e03d9305", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 375 + ], + "pos": [ + -948.255859375, + 1660 + ] + } + ], + "outputs": [ + { + "id": "7db1f9e2-40ee-4f9f-bb24-a0db7b96d45e", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 333 + ], + "localized_name": "IMAGE", + "pos": [ + 1570, + 1480 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 245, + "type": "CLIPLoader", + "pos": [ + -590, + 1370 + ], + "size": [ + 280, + 150 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 373 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 314, + 315 + ] + } + ], + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "CLIPLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + }, + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image", + "default" + ] + }, + { + "id": 246, + "type": "VAELoader", + "pos": [ + -580, + 1620 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 374 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 323 + ] + } + ], + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "VAELoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "qwen_image_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", + "directory": "vae" + }, + { + "name": "qwen_image_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "qwen_image_vae.safetensors" + ] + }, + { + "id": 247, + "type": "ModelSamplingAuraFlow", + "pos": [ + 1040, + 1110 + ], + "size": [ + 250, + 110 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 367 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 316 + ] + } + ], + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3.1000000000000005 + ] + }, + { + "id": 248, + "type": "UNETLoader", + "pos": [ + -590, + 1140 + ], + "size": [ + 280, + 130 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 372 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 312, + 324 + ] + } + ], + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "UNETLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "qwen_image_2512_fp8_e4m3fn.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_2512_fp8_e4m3fn.safetensors", + "directory": "diffusion_models" + }, + { + "name": "qwen_image_2512_fp8_e4m3fn.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_2512_fp8_e4m3fn.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "qwen_image_2512_fp8_e4m3fn.safetensors", + "default" + ] + }, + { + "id": 249, + "type": "CLIPTextEncode", + "pos": [ + -200, + 1140 + ], + "size": [ + 360, + 420 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 314 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 360 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 317 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 250, + "type": "CLIPTextEncode", + "pos": [ + -200, + 1610 + ], + "size": [ + 370, + 170 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 315 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 318 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "低分辨率，低画质，肢体畸形，手指畸形，画面过饱和，蜡像感，人脸无细节，过度光滑，画面具有AI感。构图混乱。文字模糊，扭曲" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 251, + "type": "VAEDecode", + "pos": [ + 1320, + 1120 + ], + "size": [ + 230, + 100 + ], + "flags": { + "collapsed": false + }, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 322 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 323 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 333 + ] + } + ], + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 252, + "type": "EmptySD3LatentImage", + "pos": [ + -550, + 1930 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 361 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 362 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 319 + ] + } + ], + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "EmptySD3LatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1328, + 1328, + 1 + ] + }, + { + "id": 253, + "type": "KSampler", + "pos": [ + 1040, + 1250 + ], + "size": [ + 250, + 350 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 316 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 317 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 318 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 319 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 371 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": 368 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": 369 + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 322 + ] + } + ], + "properties": { + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.48", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 464857551335368, + "randomize", + 50, + 4, + "euler", + "simple", + 1 + ] + }, + { + "id": 254, + "type": "PrimitiveInt", + "pos": [ + 300, + 1150 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 355 + ] + } + ], + "title": "Int (Steps)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 50, + "fixed" + ] + }, + { + "id": 255, + "type": "PrimitiveFloat", + "pos": [ + 300, + 1290 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 357 + ] + } + ], + "title": "Float (CFG)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 4 + ] + }, + { + "id": 256, + "type": "PrimitiveBoolean", + "pos": [ + 300, + 2060 + ], + "size": [ + 230, + 100 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": 370 + } + ], + "outputs": [ + { + "localized_name": "BOOLEAN", + "name": "BOOLEAN", + "type": "BOOLEAN", + "links": [ + 326, + 358, + 359 + ] + } + ], + "title": "Enable 4 Steps LoRA?", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "PrimitiveBoolean", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 257, + "type": "PrimitiveInt", + "pos": [ + 290, + 1540 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 347, + 354 + ] + } + ], + "title": "Int (Steps)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 4, + "fixed" + ] + }, + { + "id": 258, + "type": "PrimitiveFloat", + "pos": [ + 290, + 1670 + ], + "size": [ + 230, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 356 + ] + } + ], + "title": "Float (CFG)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "PrimitiveFloat", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 259, + "type": "LoraLoaderModelOnly", + "pos": [ + 240, + 1820 + ], + "size": [ + 330, + 140 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 312 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 375 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 325 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.49", + "Node name for S&R": "LoraLoaderModelOnly", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "Qwen-Image-2512-Lightning-4steps-V1.0-fp32.safetensors", + "url": "https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning/resolve/main/Qwen-Image-2512-Lightning-4steps-V1.0-fp32.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "Qwen-Image-2512-Lightning-4steps-V1.0-fp32.safetensors", + 1 + ] + }, + { + "id": 260, + "type": "ComfySwitchNode", + "pos": [ + 710, + 1170 + ], + "size": [ + 230, + 130 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 324 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 325 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 326 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 367 + ] + } + ], + "title": "Switch (model)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "ComfySwitchNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 261, + "type": "ComfySwitchNode", + "pos": [ + 710, + 1420 + ], + "size": [ + 230, + 130 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 355 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 354 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 359 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 368 + ] + } + ], + "title": "Switch (steps)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "ComfySwitchNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + }, + { + "id": 262, + "type": "ComfySwitchNode", + "pos": [ + 710, + 1660 + ], + "size": [ + 230, + 130 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 357 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 356 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 358 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 369 + ] + } + ], + "title": "Switch (cfg)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.12.3", + "Node name for S&R": "ComfySwitchNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + false + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + -640, + 1060, + 390, + 740 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Image size", + "bounding": [ + -630, + 1830, + 380, + 290 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + -220, + 1060, + 400, + 740 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "4-steps LoRA", + "bounding": [ + 210, + 1460, + 410, + 550 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Original Settings", + "bounding": [ + 210, + 1060, + 420, + 370 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Swtich", + "bounding": [ + 660, + 1060, + 320, + 750 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 312, + "origin_id": 248, + "origin_slot": 0, + "target_id": 259, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 314, + "origin_id": 245, + "origin_slot": 0, + "target_id": 249, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 315, + "origin_id": 245, + "origin_slot": 0, + "target_id": 250, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 322, + "origin_id": 253, + "origin_slot": 0, + "target_id": 251, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 323, + "origin_id": 246, + "origin_slot": 0, + "target_id": 251, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 316, + "origin_id": 247, + "origin_slot": 0, + "target_id": 253, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 317, + "origin_id": 249, + "origin_slot": 0, + "target_id": 253, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 318, + "origin_id": 250, + "origin_slot": 0, + "target_id": 253, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 319, + "origin_id": 252, + "origin_slot": 0, + "target_id": 253, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 324, + "origin_id": 248, + "origin_slot": 0, + "target_id": 260, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 325, + "origin_id": 259, + "origin_slot": 0, + "target_id": 260, + "target_slot": 1, + "type": "MODEL" + }, + { + "id": 326, + "origin_id": 256, + "origin_slot": 0, + "target_id": 260, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 333, + "origin_id": 251, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 347, + "origin_id": 257, + "origin_slot": 0, + "target_id": 253, + "target_slot": 4, + "type": "INT" + }, + { + "id": 354, + "origin_id": 257, + "origin_slot": 0, + "target_id": 261, + "target_slot": 1, + "type": "INT" + }, + { + "id": 355, + "origin_id": 254, + "origin_slot": 0, + "target_id": 261, + "target_slot": 0, + "type": "INT" + }, + { + "id": 356, + "origin_id": 258, + "origin_slot": 0, + "target_id": 262, + "target_slot": 1, + "type": "FLOAT" + }, + { + "id": 357, + "origin_id": 255, + "origin_slot": 0, + "target_id": 262, + "target_slot": 0, + "type": "FLOAT" + }, + { + "id": 358, + "origin_id": 256, + "origin_slot": 0, + "target_id": 262, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 359, + "origin_id": 256, + "origin_slot": 0, + "target_id": 261, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 360, + "origin_id": -10, + "origin_slot": 0, + "target_id": 249, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 361, + "origin_id": -10, + "origin_slot": 1, + "target_id": 252, + "target_slot": 0, + "type": "INT" + }, + { + "id": 362, + "origin_id": -10, + "origin_slot": 2, + "target_id": 252, + "target_slot": 1, + "type": "INT" + }, + { + "id": 367, + "origin_id": 260, + "origin_slot": 0, + "target_id": 247, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 368, + "origin_id": 261, + "origin_slot": 0, + "target_id": 253, + "target_slot": 5, + "type": "INT" + }, + { + "id": 369, + "origin_id": 262, + "origin_slot": 0, + "target_id": 253, + "target_slot": 6, + "type": "FLOAT" + }, + { + "id": 370, + "origin_id": -10, + "origin_slot": 3, + "target_id": 256, + "target_slot": 0, + "type": "BOOLEAN" + }, + { + "id": 371, + "origin_id": -10, + "origin_slot": 4, + "target_id": 253, + "target_slot": 4, + "type": "INT" + }, + { + "id": 372, + "origin_id": -10, + "origin_slot": 5, + "target_id": 248, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 373, + "origin_id": -10, + "origin_slot": 6, + "target_id": 245, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 374, + "origin_id": -10, + "origin_slot": 7, + "target_id": 246, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 375, + "origin_id": -10, + "origin_slot": 8, + "target_id": 259, + "target_slot": 1, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "Vue-corrected" + }, + "category": "Image generation and editing/Text to image" + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Text to Image (Qwen-Image).json b/blueprints/Text to Image (Qwen-Image).json new file mode 100644 index 000000000..70b4b44b3 --- /dev/null +++ b/blueprints/Text to Image (Qwen-Image).json @@ -0,0 +1,1881 @@ +{ + "revision": 0, + "last_node_id": 76, + "last_link_id": 0, + "nodes": [ + { + "id": 76, + "type": "e5cfe5ba-2ae0-4bc4-869f-ab2228cb44d3", + "pos": [ + 30, + 10 + ], + "size": [ + 470, + 660 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + }, + { + "label": "lightning_lora", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "label": "enable_turbo_mode", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "6", + "text" + ], + [ + "58", + "width" + ], + [ + "58", + "height" + ], + [ + "3", + "seed" + ], + [ + "37", + "unet_name" + ], + [ + "38", + "clip_name" + ], + [ + "39", + "vae_name" + ], + [ + "73", + "lora_name" + ], + [ + "86", + "value" + ], + [ + "3", + "control_after_generate" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": { + "text": true, + "lora_name": true, + "value": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [], + "title": "Text to Image (Qwen-Image)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "e5cfe5ba-2ae0-4bc4-869f-ab2228cb44d3", + "version": 1, + "state": { + "lastGroupId": 5, + "lastNodeId": 87, + "lastLinkId": 153, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Text to Image (Qwen-Image)", + "inputNode": { + "id": -10, + "bounding": [ + -810, + 290, + 151.744140625, + 220 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 2580, + 340, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "846fd1a5-9f4a-4e83-af40-27cafe99e5c6", + "name": "text", + "type": "STRING", + "linkIds": [ + 132 + ], + "label": "prompt", + "pos": [ + -678.255859375, + 310 + ] + }, + { + "id": "e941d29f-bb7f-4001-a956-90a9b29ae9f9", + "name": "width", + "type": "INT", + "linkIds": [ + 134 + ], + "pos": [ + -678.255859375, + 330 + ] + }, + { + "id": "df798f50-87ba-481b-b847-ca8b7c7efff3", + "name": "height", + "type": "INT", + "linkIds": [ + 135 + ], + "pos": [ + -678.255859375, + 350 + ] + }, + { + "id": "3fcf7667-f697-43ee-bdee-0d3fed39e777", + "name": "seed", + "type": "INT", + "linkIds": [ + 136 + ], + "pos": [ + -678.255859375, + 370 + ] + }, + { + "id": "e8d70f26-d9f5-4633-a39e-0bf6cf93d566", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 137 + ], + "pos": [ + -678.255859375, + 390 + ] + }, + { + "id": "8c9b537a-c6c9-4365-96ad-dbbb82d917e0", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 138 + ], + "pos": [ + -678.255859375, + 410 + ] + }, + { + "id": "7cc2f92b-6e2f-4e4e-a316-b61f58ed1442", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 139 + ], + "pos": [ + -678.255859375, + 430 + ] + }, + { + "id": "3cb1ba7c-583c-4f92-afc1-71463161e2a4", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 140 + ], + "label": "lightning_lora", + "pos": [ + -678.255859375, + 450 + ] + }, + { + "id": "4278102d-766c-4c6b-af2e-0fb9f26bbb27", + "name": "value", + "type": "BOOLEAN", + "linkIds": [ + 153 + ], + "label": "enable_turbo_mode", + "pos": [ + -678.255859375, + 470 + ] + } + ], + "outputs": [ + { + "id": "2af20250-dc7a-4643-bc84-0a180d9ca62b", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 110 + ], + "localized_name": "IMAGE", + "pos": [ + 2600, + 360 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 39, + "type": "VAELoader", + "pos": [ + -260, + 510 + ], + "size": [ + 330, + 110 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 139 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 76 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "qwen_image_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_image_vae.safetensors" + ] + }, + { + "id": 38, + "type": "CLIPLoader", + "pos": [ + -260, + 280 + ], + "size": [ + 330, + 150 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 138 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 74, + 75 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_2.5_vl_7b_fp8_scaled.safetensors", + "qwen_image", + "default" + ] + }, + { + "id": 58, + "type": "EmptySD3LatentImage", + "pos": [ + -240, + 810 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 134 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 135 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 107 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "EmptySD3LatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1328, + 1328, + 1 + ] + }, + { + "id": 66, + "type": "ModelSamplingAuraFlow", + "pos": [ + 1780, + 180 + ], + "size": [ + 300, + 110 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 147 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 125 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3.1000000000000005 + ] + }, + { + "id": 37, + "type": "UNETLoader", + "pos": [ + -260, + 80 + ], + "size": [ + 330, + 110 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 137 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 129, + 142 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "qwen_image_fp8_e4m3fn.safetensors", + "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_image_fp8_e4m3fn.safetensors", + "default" + ] + }, + { + "id": 6, + "type": "CLIPTextEncode", + "pos": [ + 120, + 60 + ], + "size": [ + 440, + 340 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 74 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 132 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 46 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 7, + "type": "CLIPTextEncode", + "pos": [ + 130, + 480 + ], + "size": [ + 430, + 180 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 75 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 52 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 2190, + 350 + ], + "size": [ + 230, + 100 + ], + "flags": { + "collapsed": false + }, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 128 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 76 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 110 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 73, + "type": "LoraLoaderModelOnly", + "pos": [ + 670, + 500 + ], + "size": [ + 400, + 140 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 129 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 140 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 141 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.49", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "Qwen-Image-Lightning-8steps-V1.0.safetensors", + "url": "https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-8steps-V1.0.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "Qwen-Image-Lightning-8steps-V1.0.safetensors", + 1 + ] + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 1780, + 330 + ], + "size": [ + 300, + 480 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 125 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 46 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 52 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 107 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": 136 + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": 148 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": 149 + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 128 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.48", + "ue_properties": { + "version": "7.7", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 50347169638278, + "randomize", + 8, + 1, + "euler", + "simple", + 1 + ] + }, + { + "id": 78, + "type": "ComfySwitchNode", + "pos": [ + 1320, + 180 + ], + "size": [ + 270, + 130 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 142 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 141 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 150 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 147 + ] + } + ], + "title": "Switch (Model)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ComfySwitchNode" + }, + "widgets_values": [ + false + ] + }, + { + "id": 79, + "type": "PrimitiveInt", + "pos": [ + 680, + 710 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 143 + ] + } + ], + "title": "Steps", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveInt" + }, + "widgets_values": [ + 8, + "fixed" + ] + }, + { + "id": 81, + "type": "PrimitiveFloat", + "pos": [ + 680, + 870 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 144 + ] + } + ], + "title": "CFG", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveFloat" + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 82, + "type": "ComfySwitchNode", + "pos": [ + 1320, + 400 + ], + "size": [ + 270, + 130 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 146 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 143 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 151 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 148 + ] + } + ], + "title": "Switch (Steps)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ComfySwitchNode" + }, + "widgets_values": [ + false + ] + }, + { + "id": 83, + "type": "ComfySwitchNode", + "pos": [ + 1320, + 600 + ], + "size": [ + 270, + 130 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "on_false", + "name": "on_false", + "type": "*", + "link": 145 + }, + { + "localized_name": "on_true", + "name": "on_true", + "type": "*", + "link": 144 + }, + { + "localized_name": "switch", + "name": "switch", + "type": "BOOLEAN", + "widget": { + "name": "switch" + }, + "link": 152 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "*", + "links": [ + 149 + ] + } + ], + "title": "Switch (CFG)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "ComfySwitchNode" + }, + "widgets_values": [ + false + ] + }, + { + "id": 84, + "type": "PrimitiveInt", + "pos": [ + 680, + 60 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 146 + ] + } + ], + "title": "Steps", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveInt" + }, + "widgets_values": [ + 20, + "fixed" + ] + }, + { + "id": 85, + "type": "PrimitiveFloat", + "pos": [ + 680, + 230 + ], + "size": [ + 270, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 145 + ] + } + ], + "title": "CFG", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveFloat" + }, + "widgets_values": [ + 4 + ] + }, + { + "id": 86, + "type": "PrimitiveBoolean", + "pos": [ + 710, + 1070 + ], + "size": [ + 270, + 100 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": 153 + } + ], + "outputs": [ + { + "localized_name": "BOOLEAN", + "name": "BOOLEAN", + "type": "BOOLEAN", + "links": [ + 150, + 151, + 152 + ] + } + ], + "title": "Enable Lightning LoRA", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.18.1", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "Node name for S&R": "PrimitiveBoolean" + }, + "widgets_values": [ + false + ] + }, + { + "id": 87, + "type": "MarkdownNote", + "pos": [ + 620, + -160 + ], + "size": [ + 500, + 120 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "Try 50 steps, if you want original the [qwen image](https://huggingface.co/Qwen/Qwen-Image)'s setting, but it will takes longer" + ], + "color": "#222", + "bgcolor": "#000" + } + ], + "groups": [ + { + "id": 1, + "title": "Step1 - Load models", + "bounding": [ + -280, + -20, + 360, + 700 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Step2 - Image size", + "bounding": [ + -280, + 710, + 360, + 300 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Step3 - Prompt", + "bounding": [ + 110, + -20, + 470, + 700 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 4, + "title": "Lightx2v 8steps LoRA", + "bounding": [ + 610, + 390, + 520, + 620 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "Original Settings", + "bounding": [ + 610, + -20, + 520, + 380 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 74, + "origin_id": 38, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 75, + "origin_id": 38, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 129, + "origin_id": 37, + "origin_slot": 0, + "target_id": 73, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 128, + "origin_id": 3, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 76, + "origin_id": 39, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 125, + "origin_id": 66, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 46, + "origin_id": 6, + "origin_slot": 0, + "target_id": 3, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 52, + "origin_id": 7, + "origin_slot": 0, + "target_id": 3, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 107, + "origin_id": 58, + "origin_slot": 0, + "target_id": 3, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 110, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 132, + "origin_id": -10, + "origin_slot": 0, + "target_id": 6, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 134, + "origin_id": -10, + "origin_slot": 1, + "target_id": 58, + "target_slot": 0, + "type": "INT" + }, + { + "id": 135, + "origin_id": -10, + "origin_slot": 2, + "target_id": 58, + "target_slot": 1, + "type": "INT" + }, + { + "id": 136, + "origin_id": -10, + "origin_slot": 3, + "target_id": 3, + "target_slot": 4, + "type": "INT" + }, + { + "id": 137, + "origin_id": -10, + "origin_slot": 4, + "target_id": 37, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 138, + "origin_id": -10, + "origin_slot": 5, + "target_id": 38, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 139, + "origin_id": -10, + "origin_slot": 6, + "target_id": 39, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 140, + "origin_id": -10, + "origin_slot": 7, + "target_id": 73, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 141, + "origin_id": 73, + "origin_slot": 0, + "target_id": 78, + "target_slot": 1, + "type": "MODEL" + }, + { + "id": 142, + "origin_id": 37, + "origin_slot": 0, + "target_id": 78, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 143, + "origin_id": 79, + "origin_slot": 0, + "target_id": 82, + "target_slot": 1, + "type": "INT" + }, + { + "id": 144, + "origin_id": 81, + "origin_slot": 0, + "target_id": 83, + "target_slot": 1, + "type": "FLOAT" + }, + { + "id": 145, + "origin_id": 85, + "origin_slot": 0, + "target_id": 83, + "target_slot": 0, + "type": "FLOAT" + }, + { + "id": 146, + "origin_id": 84, + "origin_slot": 0, + "target_id": 82, + "target_slot": 0, + "type": "INT" + }, + { + "id": 147, + "origin_id": 78, + "origin_slot": 0, + "target_id": 66, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 148, + "origin_id": 82, + "origin_slot": 0, + "target_id": 3, + "target_slot": 5, + "type": "INT" + }, + { + "id": 149, + "origin_id": 83, + "origin_slot": 0, + "target_id": 3, + "target_slot": 6, + "type": "FLOAT" + }, + { + "id": 150, + "origin_id": 86, + "origin_slot": 0, + "target_id": 78, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 151, + "origin_id": 86, + "origin_slot": 0, + "target_id": 82, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 152, + "origin_id": 86, + "origin_slot": 0, + "target_id": 83, + "target_slot": 2, + "type": "BOOLEAN" + }, + { + "id": 153, + "origin_id": -10, + "origin_slot": 8, + "target_id": 86, + "target_slot": 0, + "type": "BOOLEAN" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Text to image" + } + ] + }, + "extra": {} +} \ No newline at end of file diff --git a/blueprints/Text to Image (Z-Image-Turbo).json b/blueprints/Text to Image (Z-Image-Turbo).json index ce25ce1df..6aa80e327 100644 --- a/blueprints/Text to Image (Z-Image-Turbo).json +++ b/blueprints/Text to Image (Z-Image-Turbo).json @@ -1 +1,1078 @@ -{"id": "1c3eaa76-5cfa-4dc7-8571-97a570324e01", "revision": 0, "last_node_id": 34, "last_link_id": 40, "nodes": [{"id": 5, "type": "dfe9eb32-97c0-43a5-90d5-4fd37768d91b", "pos": [-2.5766491043910378e-05, 1229.999928629805], "size": [400, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "width", "type": "INT", "widget": {"name": "width"}, "link": null}, {"name": "height", "type": "INT", "widget": {"name": "height"}, "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": []}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "width"], ["-1", "height"], ["3", "seed"], ["3", "control_after_generate"], ["-1", "unet_name"], ["-1", "clip_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.3.73", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["", 1024, 1024, null, null, "z_image_turbo_bf16.safetensors", "qwen_3_4b.safetensors", "ae.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "dfe9eb32-97c0-43a5-90d5-4fd37768d91b", "version": 1, "state": {"lastGroupId": 4, "lastNodeId": 34, "lastLinkId": 40, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Text to Image (Z-Image-Turbo)", "inputNode": {"id": -10, "bounding": [-80, 425, 120, 160]}, "outputNode": {"id": -20, "bounding": [1490, 415, 120, 60]}, "inputs": [{"id": "fb178669-e742-4a53-8a69-7df59834dfd8", "name": "text", "type": "STRING", "linkIds": [34], "label": "prompt", "pos": [20, 445]}, {"id": "dd780b3c-23e9-46ff-8469-156008f42e5a", "name": "width", "type": "INT", "linkIds": [35], "pos": [20, 465]}, {"id": "7b08d546-6bb0-4ef9-82e9-ffae5e1ee6bc", "name": "height", "type": "INT", "linkIds": [36], "pos": [20, 485]}, {"id": "23087d15-8412-4fbd-b71e-9b6d7ef76de1", "name": "unet_name", "type": "COMBO", "linkIds": [38], "pos": [20, 505]}, {"id": "0677f5c3-2a3f-43d4-98ac-a4c56d5efdc0", "name": "clip_name", "type": "COMBO", "linkIds": [39], "pos": [20, 525]}, {"id": "c85c0445-2641-48b1-bbca-95057edf2fcf", "name": "vae_name", "type": "COMBO", "linkIds": [40], "pos": [20, 545]}], "outputs": [{"id": "1fa72a21-ce00-4952-814e-1f2ffbe87d1d", "name": "IMAGE", "type": "IMAGE", "linkIds": [16], "localized_name": "IMAGE", "pos": [1510, 435]}], "widgets": [], "nodes": [{"id": 30, "type": "CLIPLoader", "pos": [109.99997264844609, 329.99999029608756], "size": [269.9869791666667, 106], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 39}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [28]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPLoader", "models": [{"name": "qwen_3_4b.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["qwen_3_4b.safetensors", "lumina2", "default"]}, {"id": 29, "type": "VAELoader", "pos": [109.99997264844609, 479.9999847172637], "size": [269.9869791666667, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 40}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [27]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "VAELoader", "models": [{"name": "ae.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["ae.safetensors"]}, {"id": 33, "type": "ConditioningZeroOut", "pos": [639.9999103333332, 620.0000271257795], "size": [204.134765625, 26], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING", "link": 32}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [33]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "ConditioningZeroOut", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 8, "type": "VAEDecode", "pos": [1219.9999088104782, 160.00009184959066], "size": [209.98697916666669, 46], "flags": {}, "order": 5, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 14}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 27}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [16]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": []}, {"id": 28, "type": "UNETLoader", "pos": [109.99997264844609, 200.0000502647102], "size": [269.9869791666667, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 38}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [26]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "UNETLoader", "models": [{"name": "z_image_turbo_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": ["z_image_turbo_bf16.safetensors", "default"]}, {"id": 27, "type": "CLIPTextEncode", "pos": [429.99997828947767, 200.0000502647102], "size": [409.9869791666667, 319.9869791666667], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 28}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 34}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [30, 32]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.73", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [""]}, {"id": 13, "type": "EmptySD3LatentImage", "pos": [109.99997264844609, 629.9999791384399], "size": [259.9869791666667, 106], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 35}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 36}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [17]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "EmptySD3LatentImage", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [1024, 1024, 1]}, {"id": 3, "type": "KSampler", "pos": [879.9999615530063, 269.9999774911694], "size": [314.9869791666667, 262], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 13}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 30}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 33}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 17}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [14]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [0, "randomize", 4, 1, "res_multistep", "simple", 1]}, {"id": 11, "type": "ModelSamplingAuraFlow", "pos": [879.9999615530063, 160.00009184959066], "size": [309.9869791666667, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 26}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [13]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.64", "Node name for S&R": "ModelSamplingAuraFlow", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65}, "widgets_values": [3]}], "groups": [{"id": 2, "title": "Image size", "bounding": [100, 560, 290, 200], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Prompt", "bounding": [410, 130, 450, 540], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 4, "title": "Models", "bounding": [100, 130, 290, 413.6], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 32, "origin_id": 27, "origin_slot": 0, "target_id": 33, "target_slot": 0, "type": "CONDITIONING"}, {"id": 26, "origin_id": 28, "origin_slot": 0, "target_id": 11, "target_slot": 0, "type": "MODEL"}, {"id": 14, "origin_id": 3, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 27, "origin_id": 29, "origin_slot": 0, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 13, "origin_id": 11, "origin_slot": 0, "target_id": 3, "target_slot": 0, "type": "MODEL"}, {"id": 30, "origin_id": 27, "origin_slot": 0, "target_id": 3, "target_slot": 1, "type": "CONDITIONING"}, {"id": 33, "origin_id": 33, "origin_slot": 0, "target_id": 3, "target_slot": 2, "type": "CONDITIONING"}, {"id": 17, "origin_id": 13, "origin_slot": 0, "target_id": 3, "target_slot": 3, "type": "LATENT"}, {"id": 28, "origin_id": 30, "origin_slot": 0, "target_id": 27, "target_slot": 0, "type": "CLIP"}, {"id": 16, "origin_id": 8, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 34, "origin_id": -10, "origin_slot": 0, "target_id": 27, "target_slot": 1, "type": "STRING"}, {"id": 35, "origin_id": -10, "origin_slot": 1, "target_id": 13, "target_slot": 0, "type": "INT"}, {"id": 36, "origin_id": -10, "origin_slot": 2, "target_id": 13, "target_slot": 1, "type": "INT"}, {"id": 38, "origin_id": -10, "origin_slot": 3, "target_id": 28, "target_slot": 0, "type": "COMBO"}, {"id": 39, "origin_id": -10, "origin_slot": 4, "target_id": 30, "target_slot": 0, "type": "COMBO"}, {"id": 40, "origin_id": -10, "origin_slot": 5, "target_id": 29, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image generation and editing/Text to image"}]}, "config": {}, "extra": {"frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true, "ds": {"scale": 0.8401370345180755, "offset": [940.0587067393087, -830.7121087564725]}}, "version": 0.4} +{ + "id": "1c3eaa76-5cfa-4dc7-8571-97a570324e01", + "revision": 0, + "last_node_id": 34, + "last_link_id": 40, + "nodes": [ + { + "id": 5, + "type": "dfe9eb32-97c0-43a5-90d5-4fd37768d91b", + "pos": [ + -2.5766491043910378e-05, + 1229.999928629805 + ], + "size": [ + 400, + 470 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "width" + ], + [ + "-1", + "height" + ], + [ + "3", + "seed" + ], + [ + "3", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.3.73", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "", + 1024, + 1024, + null, + null, + "z_image_turbo_bf16.safetensors", + "qwen_3_4b.safetensors", + "ae.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "dfe9eb32-97c0-43a5-90d5-4fd37768d91b", + "version": 1, + "state": { + "lastGroupId": 4, + "lastNodeId": 34, + "lastLinkId": 40, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Text to Image (Z-Image-Turbo)", + "inputNode": { + "id": -10, + "bounding": [ + -80, + 425, + 120, + 160 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1490, + 415, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "fb178669-e742-4a53-8a69-7df59834dfd8", + "name": "text", + "type": "STRING", + "linkIds": [ + 34 + ], + "label": "prompt", + "pos": [ + 20, + 445 + ] + }, + { + "id": "dd780b3c-23e9-46ff-8469-156008f42e5a", + "name": "width", + "type": "INT", + "linkIds": [ + 35 + ], + "pos": [ + 20, + 465 + ] + }, + { + "id": "7b08d546-6bb0-4ef9-82e9-ffae5e1ee6bc", + "name": "height", + "type": "INT", + "linkIds": [ + 36 + ], + "pos": [ + 20, + 485 + ] + }, + { + "id": "23087d15-8412-4fbd-b71e-9b6d7ef76de1", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 38 + ], + "pos": [ + 20, + 505 + ] + }, + { + "id": "0677f5c3-2a3f-43d4-98ac-a4c56d5efdc0", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 39 + ], + "pos": [ + 20, + 525 + ] + }, + { + "id": "c85c0445-2641-48b1-bbca-95057edf2fcf", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 40 + ], + "pos": [ + 20, + 545 + ] + } + ], + "outputs": [ + { + "id": "1fa72a21-ce00-4952-814e-1f2ffbe87d1d", + "name": "IMAGE", + "type": "IMAGE", + "linkIds": [ + 16 + ], + "localized_name": "IMAGE", + "pos": [ + 1510, + 435 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 30, + "type": "CLIPLoader", + "pos": [ + 109.99997264844609, + 329.99999029608756 + ], + "size": [ + 269.9869791666667, + 106 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 39 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 28 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "qwen_3_4b.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "qwen_3_4b.safetensors", + "lumina2", + "default" + ] + }, + { + "id": 29, + "type": "VAELoader", + "pos": [ + 109.99997264844609, + 479.9999847172637 + ], + "size": [ + 269.9869791666667, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 40 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 27 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "ae.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 33, + "type": "ConditioningZeroOut", + "pos": [ + 639.9999103333332, + 620.0000271257795 + ], + "size": [ + 204.134765625, + 26 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "conditioning", + "name": "conditioning", + "type": "CONDITIONING", + "link": 32 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 33 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "ConditioningZeroOut", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 1219.9999088104782, + 160.00009184959066 + ], + "size": [ + 209.98697916666669, + 46 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 14 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 27 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 16 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [] + }, + { + "id": 28, + "type": "UNETLoader", + "pos": [ + 109.99997264844609, + 200.0000502647102 + ], + "size": [ + 269.9869791666667, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 38 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 26 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "z_image_turbo_bf16.safetensors", + "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "z_image_turbo_bf16.safetensors", + "default" + ] + }, + { + "id": 27, + "type": "CLIPTextEncode", + "pos": [ + 429.99997828947767, + 200.0000502647102 + ], + "size": [ + 409.9869791666667, + 319.9869791666667 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 28 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 34 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 30, + 32 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.73", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ] + }, + { + "id": 13, + "type": "EmptySD3LatentImage", + "pos": [ + 109.99997264844609, + 629.9999791384399 + ], + "size": [ + 259.9869791666667, + 106 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 35 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 36 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 17 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "EmptySD3LatentImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 879.9999615530063, + 269.9999774911694 + ], + "size": [ + 314.9869791666667, + 262 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 13 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 30 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 33 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 17 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 14 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0, + "randomize", + 4, + 1, + "res_multistep", + "simple", + 1 + ] + }, + { + "id": 11, + "type": "ModelSamplingAuraFlow", + "pos": [ + 879.9999615530063, + 160.00009184959066 + ], + "size": [ + 309.9869791666667, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 26 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 13 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "ModelSamplingAuraFlow", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 3 + ] + } + ], + "groups": [ + { + "id": 2, + "title": "Image size", + "bounding": [ + 100, + 560, + 290, + 200 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + 410, + 130, + 450, + 540 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 4, + "title": "Models", + "bounding": [ + 100, + 130, + 290, + 413.6 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 32, + "origin_id": 27, + "origin_slot": 0, + "target_id": 33, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 26, + "origin_id": 28, + "origin_slot": 0, + "target_id": 11, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 14, + "origin_id": 3, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 27, + "origin_id": 29, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 13, + "origin_id": 11, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 30, + "origin_id": 27, + "origin_slot": 0, + "target_id": 3, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 33, + "origin_id": 33, + "origin_slot": 0, + "target_id": 3, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 17, + "origin_id": 13, + "origin_slot": 0, + "target_id": 3, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 28, + "origin_id": 30, + "origin_slot": 0, + "target_id": 27, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 16, + "origin_id": 8, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 34, + "origin_id": -10, + "origin_slot": 0, + "target_id": 27, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 35, + "origin_id": -10, + "origin_slot": 1, + "target_id": 13, + "target_slot": 0, + "type": "INT" + }, + { + "id": 36, + "origin_id": -10, + "origin_slot": 2, + "target_id": 13, + "target_slot": 1, + "type": "INT" + }, + { + "id": 38, + "origin_id": -10, + "origin_slot": 3, + "target_id": 28, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 39, + "origin_id": -10, + "origin_slot": 4, + "target_id": 30, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 40, + "origin_id": -10, + "origin_slot": 5, + "target_id": 29, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image generation and editing/Text to image" + } + ] + }, + "config": {}, + "extra": { + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ds": { + "scale": 0.8401370345180755, + "offset": [ + 940.0587067393087, + -830.7121087564725 + ] + } + }, + "version": 0.4 +} diff --git a/blueprints/Text to Video (LTX-2.3).json b/blueprints/Text to Video (LTX-2.3).json new file mode 100644 index 000000000..ff9bc6ccf --- /dev/null +++ b/blueprints/Text to Video (LTX-2.3).json @@ -0,0 +1,4296 @@ +{ + "revision": 0, + "last_node_id": 324, + "last_link_id": 0, + "nodes": [ + { + "id": 324, + "type": "871cf29d-2726-43a5-b61e-01fa939d699d", + "pos": [ + -300, + 4290 + ], + "size": [ + 400, + 170 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": null + }, + { + "label": "width", + "name": "value_2", + "type": "INT", + "widget": { + "name": "value_2" + }, + "link": null + }, + { + "label": "height", + "name": "value_3", + "type": "INT", + "widget": { + "name": "value_3" + }, + "link": null + }, + { + "label": "duration", + "name": "value_4", + "type": "INT", + "widget": { + "name": "value_4" + }, + "link": null + }, + { + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": null + }, + { + "label": "distilled_lora", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": null + }, + { + "label": "latent_upscale_model", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": null + }, + { + "label": "fps", + "name": "value_1", + "type": "INT", + "widget": { + "name": "value_1" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "320", + "value" + ], + [ + "314", + "value" + ], + [ + "301", + "value" + ], + [ + "303", + "value" + ], + [ + "318", + "ckpt_name" + ], + [ + "287", + "lora_name" + ], + [ + "319", + "text_encoder" + ], + [ + "313", + "model_name" + ], + [ + "302", + "value" + ], + [ + "279", + "noise_seed" + ], + [ + "279", + "control_after_generate" + ] + ], + "ue_properties": { + "widget_ue_connectable": { + "value_1": true, + "value_2": true, + "value_3": true, + "value_4": true, + "lora_name": true, + "model_name": true + }, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [], + "title": "Text to Video (LTX-2.3)" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "871cf29d-2726-43a5-b61e-01fa939d699d", + "version": 1, + "state": { + "lastGroupId": 26, + "lastNodeId": 324, + "lastLinkId": 631, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Text to Video (LTX-2.3)", + "inputNode": { + "id": -10, + "bounding": [ + 720, + 4240, + 162.162109375, + 220 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 6100, + 4160, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "9494c550-4172-49c6-930e-5b508f775e77", + "name": "value", + "type": "STRING", + "linkIds": [ + 595 + ], + "pos": [ + 862.162109375, + 4260 + ] + }, + { + "id": "58dbb3f6-f924-4548-96ef-e0e34610bd4e", + "name": "value_2", + "type": "INT", + "linkIds": [ + 597 + ], + "label": "width", + "pos": [ + 862.162109375, + 4280 + ] + }, + { + "id": "6086d5b8-2586-448c-a641-dd14d76dd102", + "name": "value_3", + "type": "INT", + "linkIds": [ + 598 + ], + "label": "height", + "pos": [ + 862.162109375, + 4300 + ] + }, + { + "id": "feb8c2eb-ae48-4fa8-bc24-929552d656c3", + "name": "value_4", + "type": "INT", + "linkIds": [ + 599 + ], + "label": "duration", + "pos": [ + 862.162109375, + 4320 + ] + }, + { + "id": "d7255058-319a-4880-8f9a-7e542c8f3c3c", + "name": "ckpt_name", + "type": "COMBO", + "linkIds": [ + 601, + 604, + 605 + ], + "pos": [ + 862.162109375, + 4340 + ] + }, + { + "id": "4afce68d-8f65-4342-9d6d-ae0a7688c3e3", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 602 + ], + "label": "distilled_lora", + "pos": [ + 862.162109375, + 4360 + ] + }, + { + "id": "ab842b4b-c977-4679-b421-424722785b57", + "name": "text_encoder", + "type": "COMBO", + "linkIds": [ + 606 + ], + "pos": [ + 862.162109375, + 4380 + ] + }, + { + "id": "9e47372d-28d9-4311-91e9-e90d03f4eb43", + "name": "model_name", + "type": "COMBO", + "linkIds": [ + 607 + ], + "label": "latent_upscale_model", + "pos": [ + 862.162109375, + 4400 + ] + }, + { + "id": "7951b137-465e-4844-b05f-88b89f0e1ba8", + "name": "value_1", + "type": "INT", + "linkIds": [ + 627 + ], + "label": "fps", + "pos": [ + 862.162109375, + 4420 + ] + } + ], + "outputs": [ + { + "id": "954ef307-c897-4eea-8b5c-5c6ce15a5357", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 536 + ], + "localized_name": "VIDEO", + "pos": [ + 6120, + 4180 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 278, + "type": "RandomNoise", + "pos": [ + 4720, + 3750 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 490 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 42, + "fixed" + ] + }, + { + "id": 279, + "type": "RandomNoise", + "pos": [ + 3200, + 3900 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "NOISE", + "name": "NOISE", + "type": "NOISE", + "links": [ + 483 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "RandomNoise", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 343011291748534, + "randomize" + ] + }, + { + "id": 280, + "type": "LTXVConcatAVLatent", + "pos": [ + 4730, + 4520 + ], + "size": [ + 280, + 100 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 512 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 513 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 494 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 281, + "type": "LTXVAudioVAELoader", + "pos": [ + 1660, + 4140 + ], + "size": [ + 430, + 110 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 604 + } + ], + "outputs": [ + { + "localized_name": "Audio VAE", + "name": "Audio VAE", + "type": "VAE", + "links": [ + 481, + 496 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVAudioVAELoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-dev-fp8.safetensors" + ] + }, + { + "id": 282, + "type": "KSamplerSelect", + "pos": [ + 4720, + 4160 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 492 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler_cfg_pp" + ] + }, + { + "id": 283, + "type": "ManualSigmas", + "pos": [ + 4720, + 4340 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 493 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "0.85, 0.7250, 0.4219, 0.0" + ] + }, + { + "id": 284, + "type": "CFGGuider", + "pos": [ + 4720, + 3930 + ], + "size": [ + 280, + 160 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 478 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 479 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 480 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 491 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.71", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 285, + "type": "SamplerCustomAdvanced", + "pos": [ + 3620, + 3990 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 483 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 484 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 485 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 544 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 487 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 488 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 286, + "type": "LTXVCropGuides", + "pos": [ + 3900, + 3700 + ], + "size": [ + 250, + 120 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 475 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 476 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 477 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 479 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 480 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "slot_index": 2, + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVCropGuides", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 287, + "type": "LoraLoaderModelOnly", + "pos": [ + 1660, + 3910 + ], + "size": [ + 430, + 140 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 520 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 602 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 478, + 541 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "LoraLoaderModelOnly", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-distilled-lora-384.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-22b-distilled-lora-384.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-distilled-lora-384.safetensors", + 0.5 + ] + }, + { + "id": 288, + "type": "ResizeImagesByLongerEdge", + "pos": [ + 2120, + 5040 + ], + "size": [ + 310, + 110 + ], + "flags": { + "collapsed": false + }, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 523 + }, + { + "localized_name": "longer_edge", + "name": "longer_edge", + "type": "INT", + "widget": { + "name": "longer_edge" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "links": [ + 505 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "ResizeImagesByLongerEdge", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1536 + ] + }, + { + "id": 289, + "type": "LTXVLatentUpsampler", + "pos": [ + 4270, + 3910 + ], + "size": [ + 330, + 120 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 547 + }, + { + "localized_name": "upscale_model", + "name": "upscale_model", + "type": "LATENT_UPSCALE_MODEL", + "link": 545 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 554 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 548 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "LTXVLatentUpsampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 290, + "type": "LTXVImgToVideoInplace", + "pos": [ + 4280, + 4150 + ], + "size": [ + 300, + 180 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 552 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 515 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 548 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 543 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 512 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1, + false + ] + }, + { + "id": 291, + "type": "LTXVPreprocess", + "pos": [ + 2130, + 5190 + ], + "size": [ + 290, + 110 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 505 + }, + { + "localized_name": "img_compression", + "name": "img_compression", + "type": "INT", + "widget": { + "name": "img_compression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "output_image", + "name": "output_image", + "type": "IMAGE", + "links": [ + 510, + 515 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVPreprocess", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 18 + ] + }, + { + "id": 292, + "type": "ResizeImageMaskNode", + "pos": [ + 1670, + 5040 + ], + "size": [ + 300, + 160 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "input", + "name": "input", + "type": "IMAGE,MASK", + "link": 626 + }, + { + "localized_name": "resize_type", + "name": "resize_type", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "resize_type" + }, + "link": null + }, + { + "localized_name": "width", + "name": "resize_type.width", + "type": "INT", + "widget": { + "name": "resize_type.width" + }, + "link": 558 + }, + { + "localized_name": "height", + "name": "resize_type.height", + "type": "INT", + "widget": { + "name": "resize_type.height" + }, + "link": 559 + }, + { + "localized_name": "crop", + "name": "resize_type.crop", + "type": "COMBO", + "widget": { + "name": "resize_type.crop" + }, + "link": null + }, + { + "localized_name": "scale_method", + "name": "scale_method", + "type": "COMBO", + "widget": { + "name": "scale_method" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "resized", + "name": "resized", + "type": "*", + "links": [ + 523 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "ResizeImageMaskNode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "scale dimensions", + 1920, + 1088, + "center", + "lanczos" + ] + }, + { + "id": 293, + "type": "KSamplerSelect", + "pos": [ + 3200, + 4350 + ], + "size": [ + 280, + 110 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SAMPLER", + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 485 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "KSamplerSelect", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "euler_ancestral_cfg_pp" + ] + }, + { + "id": 294, + "type": "ComfyMathExpression", + "pos": [ + 2530, + 5070 + ], + "size": [ + 230, + 170 + ], + "flags": { + "collapsed": true + }, + "order": 19, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 560 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 561 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "ComfyMathExpression", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "a/2" + ] + }, + { + "id": 295, + "type": "Reroute", + "pos": [ + 3930, + 4090 + ], + "size": [ + 80, + 30 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 557 + } + ], + "outputs": [ + { + "name": "", + "type": "VAE", + "links": [ + 552, + 553, + 554 + ] + } + ], + "properties": { + "showOutputText": false, + "horizontal": false, + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + } + } + }, + { + "id": 296, + "type": "ComfyMathExpression", + "pos": [ + 2530, + 5130 + ], + "size": [ + 230, + 170 + ], + "flags": { + "collapsed": true + }, + "order": 21, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 562 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 563 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "ComfyMathExpression", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "a/2" + ] + }, + { + "id": 297, + "type": "EmptyLTXVLatentVideo", + "pos": [ + 2980, + 5200 + ], + "size": [ + 280, + 200 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 561 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 563 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 631 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 511 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.60", + "Node name for S&R": "EmptyLTXVLatentVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 512, + 97, + 1 + ] + }, + { + "id": 298, + "type": "LTXVImgToVideoInplace", + "pos": [ + 3420, + 4990 + ], + "size": [ + 280, + 180 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 556 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 510 + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "link": 511 + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + }, + { + "localized_name": "bypass", + "name": "bypass", + "type": "BOOLEAN", + "widget": { + "name": "bypass" + }, + "link": 542 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 497 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVImgToVideoInplace", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 0.7, + false + ] + }, + { + "id": 299, + "type": "LTXVAudioVAEDecode", + "pos": [ + 5770, + 3940 + ], + "size": [ + 270, + 100 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 495 + }, + { + "label": "Audio VAE", + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 496 + } + ], + "outputs": [ + { + "localized_name": "Audio", + "name": "Audio", + "type": "AUDIO", + "links": [ + 534 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVAudioVAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 300, + "type": "ComfyMathExpression", + "pos": [ + 2530, + 5270 + ], + "size": [ + 230, + 170 + ], + "flags": { + "collapsed": true + }, + "order": 25, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 564 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 566, + 591 + ] + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 565 + ] + } + ], + "title": "Math Expression (fps)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "ComfyMathExpression", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "a" + ] + }, + { + "id": 301, + "type": "PrimitiveInt", + "pos": [ + 1160, + 4530 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 598 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 559, + 562 + ] + } + ], + "title": "Height", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 720, + "fixed" + ] + }, + { + "id": 302, + "type": "PrimitiveInt", + "pos": [ + 1160, + 4680 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 627 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 564, + 629 + ] + } + ], + "title": "Frame Rate", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 25, + "fixed" + ] + }, + { + "id": 303, + "type": "PrimitiveInt", + "pos": [ + 1160, + 4230 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 28, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 599 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 628 + ] + } + ], + "title": "Duration", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 5, + "fixed" + ] + }, + { + "id": 304, + "type": "PrimitiveBoolean", + "pos": [ + 1170, + 4080 + ], + "size": [ + 370, + 100 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "BOOLEAN", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "BOOLEAN", + "name": "BOOLEAN", + "type": "BOOLEAN", + "links": [ + 542, + 543 + ] + } + ], + "title": "Switch to Text to Video?", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.0", + "Node name for S&R": "PrimitiveBoolean", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + true + ] + }, + { + "id": 305, + "type": "CLIPTextEncode", + "pos": [ + 2170, + 3640 + ], + "size": [ + 550, + 740 + ], + "flags": {}, + "order": 29, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 615 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 623 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 526 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 306, + "type": "LTXVConditioning", + "pos": [ + 2790, + 3670 + ], + "size": [ + 280, + 130 + ], + "flags": {}, + "order": 30, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 526 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 527 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "FLOAT", + "widget": { + "name": "frame_rate" + }, + "link": 566 + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 475, + 518 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 476, + 519 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "LTXVConditioning", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 307, + "type": "LTXVEmptyLatentAudio", + "pos": [ + 2970, + 4970 + ], + "size": [ + 280, + 170 + ], + "flags": {}, + "order": 31, + "mode": 0, + "inputs": [ + { + "localized_name": "audio_vae", + "name": "audio_vae", + "type": "VAE", + "link": 481 + }, + { + "localized_name": "frames_number", + "name": "frames_number", + "type": "INT", + "widget": { + "name": "frames_number" + }, + "link": 630 + }, + { + "localized_name": "frame_rate", + "name": "frame_rate", + "type": "INT", + "widget": { + "name": "frame_rate" + }, + "link": 565 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "Latent", + "name": "Latent", + "type": "LATENT", + "links": [ + 498 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LTXVEmptyLatentAudio", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 97, + 25, + 1 + ] + }, + { + "id": 308, + "type": "ManualSigmas", + "pos": [ + 3200, + 4550 + ], + "size": [ + 500, + 110 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "STRING", + "widget": { + "name": "sigmas" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "SIGMAS", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 544 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "ManualSigmas", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "1.0, 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0" + ] + }, + { + "id": 309, + "type": "LTXVSeparateAVLatent", + "pos": [ + 3890, + 3910 + ], + "size": [ + 250, + 100 + ], + "flags": {}, + "order": 32, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 488 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 477, + 547 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 513 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 310, + "type": "SamplerCustomAdvanced", + "pos": [ + 5070, + 3750 + ], + "size": [ + 230, + 170 + ], + "flags": {}, + "order": 33, + "mode": 0, + "inputs": [ + { + "localized_name": "noise", + "name": "noise", + "type": "NOISE", + "link": 490 + }, + { + "localized_name": "guider", + "name": "guider", + "type": "GUIDER", + "link": 491 + }, + { + "localized_name": "sampler", + "name": "sampler", + "type": "SAMPLER", + "link": 492 + }, + { + "localized_name": "sigmas", + "name": "sigmas", + "type": "SIGMAS", + "link": 493 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 494 + } + ], + "outputs": [ + { + "localized_name": "output", + "name": "output", + "type": "LATENT", + "links": [ + 578 + ] + }, + { + "localized_name": "denoised_output", + "name": "denoised_output", + "type": "LATENT", + "links": [] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.75", + "Node name for S&R": "SamplerCustomAdvanced", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 311, + "type": "LTXVSeparateAVLatent", + "pos": [ + 5410, + 3750 + ], + "size": [ + 230, + 100 + ], + "flags": {}, + "order": 34, + "mode": 0, + "inputs": [ + { + "localized_name": "av_latent", + "name": "av_latent", + "type": "LATENT", + "link": 578 + } + ], + "outputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "links": [ + 539 + ] + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "links": [ + 495 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "LTXVSeparateAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 312, + "type": "CreateVideo", + "pos": [ + 5740, + 4610 + ], + "size": [ + 280, + 130 + ], + "flags": {}, + "order": 35, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 538 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 534 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 591 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 536 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "CreateVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 24 + ] + }, + { + "id": 313, + "type": "LatentUpscaleModelLoader", + "pos": [ + 1670, + 4600 + ], + "size": [ + 400, + 110 + ], + "flags": {}, + "order": 36, + "mode": 0, + "inputs": [ + { + "localized_name": "model_name", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": 607 + } + ], + "outputs": [ + { + "localized_name": "LATENT_UPSCALE_MODEL", + "name": "LATENT_UPSCALE_MODEL", + "type": "LATENT_UPSCALE_MODEL", + "links": [ + 545 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LatentUpscaleModelLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-spatial-upscaler-x2-1.1.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors", + "directory": "latent_upscale_models" + } + ] + }, + "widgets_values": [ + "ltx-2.3-spatial-upscaler-x2-1.1.safetensors" + ] + }, + { + "id": 314, + "type": "PrimitiveInt", + "pos": [ + 1160, + 4380 + ], + "size": [ + 370, + 110 + ], + "flags": {}, + "order": 37, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "INT", + "widget": { + "name": "value" + }, + "link": 597 + } + ], + "outputs": [ + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 558, + 560 + ] + } + ], + "title": "Width", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveInt", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1280, + "fixed" + ] + }, + { + "id": 315, + "type": "CLIPTextEncode", + "pos": [ + 2180, + 4480 + ], + "size": [ + 530, + 240 + ], + "flags": {}, + "order": 38, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 625 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 527 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "pc game, console game, video game, cartoon, childish, ugly" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 316, + "type": "CFGGuider", + "pos": [ + 3200, + 4100 + ], + "size": [ + 280, + 160 + ], + "flags": {}, + "order": 39, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 541 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 518 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 519 + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "GUIDER", + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 484 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.64", + "Node name for S&R": "CFGGuider", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 317, + "type": "VAEDecodeTiled", + "pos": [ + 5760, + 3650 + ], + "size": [ + 280, + 200 + ], + "flags": {}, + "order": 40, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 539 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 553 + }, + { + "localized_name": "tile_size", + "name": "tile_size", + "type": "INT", + "widget": { + "name": "tile_size" + }, + "link": null + }, + { + "localized_name": "overlap", + "name": "overlap", + "type": "INT", + "widget": { + "name": "overlap" + }, + "link": null + }, + { + "localized_name": "temporal_size", + "name": "temporal_size", + "type": "INT", + "widget": { + "name": "temporal_size" + }, + "link": null + }, + { + "localized_name": "temporal_overlap", + "name": "temporal_overlap", + "type": "INT", + "widget": { + "name": "temporal_overlap" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 538 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.14.1", + "Node name for S&R": "VAEDecodeTiled", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + 768, + 64, + 4096, + 4 + ] + }, + { + "id": 318, + "type": "CheckpointLoaderSimple", + "pos": [ + 1660, + 3660 + ], + "size": [ + 430, + 160 + ], + "flags": {}, + "order": 41, + "mode": 0, + "inputs": [ + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 601 + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 520 + ] + }, + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [] + }, + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "links": [ + 556, + 557 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.3.56", + "Node name for S&R": "CheckpointLoaderSimple", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors", + "directory": "checkpoints" + } + ] + }, + "widgets_values": [ + "ltx-2.3-22b-dev-fp8.safetensors" + ] + }, + { + "id": 319, + "type": "LTXAVTextEncoderLoader", + "pos": [ + 1660, + 4340 + ], + "size": [ + 430, + 170 + ], + "flags": {}, + "order": 42, + "mode": 0, + "inputs": [ + { + "localized_name": "text_encoder", + "name": "text_encoder", + "type": "COMBO", + "widget": { + "name": "text_encoder" + }, + "link": 606 + }, + { + "localized_name": "ckpt_name", + "name": "ckpt_name", + "type": "COMBO", + "widget": { + "name": "ckpt_name" + }, + "link": 605 + }, + { + "localized_name": "device", + "name": "device", + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 615, + 625 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXAVTextEncoderLoader", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "models": [ + { + "name": "ltx-2.3-22b-dev-fp8.safetensors", + "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors", + "directory": "checkpoints" + }, + { + "name": "gemma_3_12B_it_fp4_mixed.safetensors", + "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "gemma_3_12B_it_fp4_mixed.safetensors", + "ltx-2.3-22b-dev-fp8.safetensors", + "default" + ] + }, + { + "id": 320, + "type": "PrimitiveStringMultiline", + "pos": [ + 1160, + 3680 + ], + "size": [ + 370, + 350 + ], + "flags": {}, + "order": 43, + "mode": 0, + "inputs": [ + { + "localized_name": "value", + "name": "value", + "type": "STRING", + "widget": { + "name": "value" + }, + "link": 595 + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 623 + ] + } + ], + "title": "Prompt", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "PrimitiveStringMultiline", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "" + ] + }, + { + "id": 321, + "type": "LTXVConcatAVLatent", + "pos": [ + 3820, + 4990 + ], + "size": [ + 240, + 100 + ], + "flags": {}, + "order": 44, + "mode": 0, + "inputs": [ + { + "localized_name": "video_latent", + "name": "video_latent", + "type": "LATENT", + "link": 497 + }, + { + "localized_name": "audio_latent", + "name": "audio_latent", + "type": "LATENT", + "link": 498 + } + ], + "outputs": [ + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 487 + ] + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.7.0", + "Node name for S&R": "LTXVConcatAVLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + } + }, + { + "id": 322, + "type": "LoadImage", + "pos": [ + 1150, + 4940 + ], + "size": [ + 400, + 480 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "COMBO", + "widget": { + "name": "image" + }, + "link": null + }, + { + "localized_name": "choose file to upload", + "name": "upload", + "type": "IMAGEUPLOAD", + "widget": { + "name": "upload" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 626 + ] + }, + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.7", + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.16.3", + "Node name for S&R": "LoadImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65 + }, + "widgets_values": [ + "example.png", + "image" + ] + }, + { + "id": 323, + "type": "ComfyMathExpression", + "pos": [ + 2540, + 5370 + ], + "size": [ + 260, + 190 + ], + "flags": { + "collapsed": true + }, + "order": 45, + "mode": 0, + "inputs": [ + { + "label": "a", + "localized_name": "values.a", + "name": "values.a", + "type": "FLOAT,INT", + "link": 628 + }, + { + "label": "b", + "localized_name": "values.b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT", + "link": 629 + }, + { + "label": "c", + "localized_name": "values.c", + "name": "values.c", + "shape": 7, + "type": "FLOAT,INT", + "link": null + }, + { + "localized_name": "expression", + "name": "expression", + "type": "STRING", + "widget": { + "name": "expression" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "localized_name": "INT", + "name": "INT", + "type": "INT", + "links": [ + 630, + 631 + ] + } + ], + "title": "Math Expression (length)", + "properties": { + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + }, + "cnr_id": "comfy-core", + "ver": "0.18.1", + "Node name for S&R": "ComfyMathExpression" + }, + "widgets_values": [ + "a * b + 1" + ] + } + ], + "groups": [ + { + "id": 1, + "title": "Model", + "bounding": [ + 1630, + 3550, + 480, + 1270 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Generate Low Resolution", + "bounding": [ + 3150, + 3550, + 1020, + 1270 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Prompt", + "bounding": [ + 2140, + 3550, + 980, + 1270 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Generate High Resolution", + "bounding": [ + 4690, + 3550, + 960, + 1270 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Lantent Upscale", + "bounding": [ + 4200, + 3550, + 460, + 1270 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 19, + "title": "Video Settings", + "bounding": [ + 1110, + 3550, + 490, + 1270 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 20, + "title": "Image Preprocess", + "bounding": [ + 1630, + 4850, + 830, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 21, + "title": "Empty Latent", + "bounding": [ + 2830, + 4850, + 1340, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 22, + "title": "Number conversion", + "bounding": [ + 2490, + 4850, + 320, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 26, + "title": "Image will not affect the video", + "bounding": [ + 1110, + 4850, + 490, + 610 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 512, + "origin_id": 290, + "origin_slot": 0, + "target_id": 280, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 513, + "origin_id": 309, + "origin_slot": 1, + "target_id": 280, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 478, + "origin_id": 287, + "origin_slot": 0, + "target_id": 284, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 479, + "origin_id": 286, + "origin_slot": 0, + "target_id": 284, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 480, + "origin_id": 286, + "origin_slot": 1, + "target_id": 284, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 541, + "origin_id": 287, + "origin_slot": 0, + "target_id": 316, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 518, + "origin_id": 306, + "origin_slot": 0, + "target_id": 316, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 519, + "origin_id": 306, + "origin_slot": 1, + "target_id": 316, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 483, + "origin_id": 279, + "origin_slot": 0, + "target_id": 285, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 484, + "origin_id": 316, + "origin_slot": 0, + "target_id": 285, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 485, + "origin_id": 293, + "origin_slot": 0, + "target_id": 285, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 544, + "origin_id": 308, + "origin_slot": 0, + "target_id": 285, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 487, + "origin_id": 321, + "origin_slot": 0, + "target_id": 285, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 475, + "origin_id": 306, + "origin_slot": 0, + "target_id": 286, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 476, + "origin_id": 306, + "origin_slot": 1, + "target_id": 286, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 477, + "origin_id": 309, + "origin_slot": 0, + "target_id": 286, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 520, + "origin_id": 318, + "origin_slot": 0, + "target_id": 287, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 523, + "origin_id": 292, + "origin_slot": 0, + "target_id": 288, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 547, + "origin_id": 309, + "origin_slot": 0, + "target_id": 289, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 545, + "origin_id": 313, + "origin_slot": 0, + "target_id": 289, + "target_slot": 1, + "type": "LATENT_UPSCALE_MODEL" + }, + { + "id": 554, + "origin_id": 295, + "origin_slot": 0, + "target_id": 289, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 552, + "origin_id": 295, + "origin_slot": 0, + "target_id": 290, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 515, + "origin_id": 291, + "origin_slot": 0, + "target_id": 290, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 548, + "origin_id": 289, + "origin_slot": 0, + "target_id": 290, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 543, + "origin_id": 304, + "origin_slot": 0, + "target_id": 290, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 505, + "origin_id": 288, + "origin_slot": 0, + "target_id": 291, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 558, + "origin_id": 314, + "origin_slot": 0, + "target_id": 292, + "target_slot": 2, + "type": "INT" + }, + { + "id": 559, + "origin_id": 301, + "origin_slot": 0, + "target_id": 292, + "target_slot": 3, + "type": "INT" + }, + { + "id": 560, + "origin_id": 314, + "origin_slot": 0, + "target_id": 294, + "target_slot": 0, + "type": "INT" + }, + { + "id": 557, + "origin_id": 318, + "origin_slot": 2, + "target_id": 295, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 562, + "origin_id": 301, + "origin_slot": 0, + "target_id": 296, + "target_slot": 0, + "type": "INT" + }, + { + "id": 561, + "origin_id": 294, + "origin_slot": 1, + "target_id": 297, + "target_slot": 0, + "type": "INT" + }, + { + "id": 563, + "origin_id": 296, + "origin_slot": 1, + "target_id": 297, + "target_slot": 1, + "type": "INT" + }, + { + "id": 556, + "origin_id": 318, + "origin_slot": 2, + "target_id": 298, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 510, + "origin_id": 291, + "origin_slot": 0, + "target_id": 298, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 511, + "origin_id": 297, + "origin_slot": 0, + "target_id": 298, + "target_slot": 2, + "type": "LATENT" + }, + { + "id": 542, + "origin_id": 304, + "origin_slot": 0, + "target_id": 298, + "target_slot": 4, + "type": "BOOLEAN" + }, + { + "id": 495, + "origin_id": 311, + "origin_slot": 1, + "target_id": 299, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 496, + "origin_id": 281, + "origin_slot": 0, + "target_id": 299, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 564, + "origin_id": 302, + "origin_slot": 0, + "target_id": 300, + "target_slot": 0, + "type": "INT" + }, + { + "id": 526, + "origin_id": 305, + "origin_slot": 0, + "target_id": 306, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 527, + "origin_id": 315, + "origin_slot": 0, + "target_id": 306, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 566, + "origin_id": 300, + "origin_slot": 0, + "target_id": 306, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 497, + "origin_id": 298, + "origin_slot": 0, + "target_id": 321, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 498, + "origin_id": 307, + "origin_slot": 0, + "target_id": 321, + "target_slot": 1, + "type": "LATENT" + }, + { + "id": 481, + "origin_id": 281, + "origin_slot": 0, + "target_id": 307, + "target_slot": 0, + "type": "VAE" + }, + { + "id": 565, + "origin_id": 300, + "origin_slot": 1, + "target_id": 307, + "target_slot": 2, + "type": "INT" + }, + { + "id": 488, + "origin_id": 285, + "origin_slot": 0, + "target_id": 309, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 490, + "origin_id": 278, + "origin_slot": 0, + "target_id": 310, + "target_slot": 0, + "type": "NOISE" + }, + { + "id": 491, + "origin_id": 284, + "origin_slot": 0, + "target_id": 310, + "target_slot": 1, + "type": "GUIDER" + }, + { + "id": 492, + "origin_id": 282, + "origin_slot": 0, + "target_id": 310, + "target_slot": 2, + "type": "SAMPLER" + }, + { + "id": 493, + "origin_id": 283, + "origin_slot": 0, + "target_id": 310, + "target_slot": 3, + "type": "SIGMAS" + }, + { + "id": 494, + "origin_id": 280, + "origin_slot": 0, + "target_id": 310, + "target_slot": 4, + "type": "LATENT" + }, + { + "id": 578, + "origin_id": 310, + "origin_slot": 0, + "target_id": 311, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 539, + "origin_id": 311, + "origin_slot": 0, + "target_id": 317, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 553, + "origin_id": 295, + "origin_slot": 0, + "target_id": 317, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 538, + "origin_id": 317, + "origin_slot": 0, + "target_id": 312, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 534, + "origin_id": 299, + "origin_slot": 0, + "target_id": 312, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 591, + "origin_id": 300, + "origin_slot": 0, + "target_id": 312, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 536, + "origin_id": 312, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 595, + "origin_id": -10, + "origin_slot": 0, + "target_id": 320, + "target_slot": 0, + "type": "STRING" + }, + { + "id": 597, + "origin_id": -10, + "origin_slot": 1, + "target_id": 314, + "target_slot": 0, + "type": "INT" + }, + { + "id": 598, + "origin_id": -10, + "origin_slot": 2, + "target_id": 301, + "target_slot": 0, + "type": "INT" + }, + { + "id": 599, + "origin_id": -10, + "origin_slot": 3, + "target_id": 303, + "target_slot": 0, + "type": "INT" + }, + { + "id": 601, + "origin_id": -10, + "origin_slot": 4, + "target_id": 318, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 602, + "origin_id": -10, + "origin_slot": 5, + "target_id": 287, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 604, + "origin_id": -10, + "origin_slot": 4, + "target_id": 281, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 605, + "origin_id": -10, + "origin_slot": 4, + "target_id": 319, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 606, + "origin_id": -10, + "origin_slot": 6, + "target_id": 319, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 607, + "origin_id": -10, + "origin_slot": 7, + "target_id": 313, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 615, + "origin_id": 319, + "origin_slot": 0, + "target_id": 305, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 623, + "origin_id": 320, + "origin_slot": 0, + "target_id": 305, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 625, + "origin_id": 319, + "origin_slot": 0, + "target_id": 315, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 626, + "origin_id": 322, + "origin_slot": 0, + "target_id": 292, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 627, + "origin_id": -10, + "origin_slot": 8, + "target_id": 302, + "target_slot": 0, + "type": "INT" + }, + { + "id": 628, + "origin_id": 303, + "origin_slot": 0, + "target_id": 323, + "target_slot": 0, + "type": "INT" + }, + { + "id": 629, + "origin_id": 302, + "origin_slot": 0, + "target_id": 323, + "target_slot": 1, + "type": "INT" + }, + { + "id": 630, + "origin_id": 323, + "origin_slot": 1, + "target_id": 307, + "target_slot": 1, + "type": "INT" + }, + { + "id": 631, + "origin_id": 323, + "origin_slot": 1, + "target_id": 297, + "target_slot": 2, + "type": "INT" + } + ], + "extra": { + "workflowRendererVersion": "Vue-corrected" + }, + "category": "Video generation and editing/Text to video" + } + ] + }, + "extra": { + "ue_links": [] + } +} \ No newline at end of file diff --git a/blueprints/Text to Video (Wan 2.2).json b/blueprints/Text to Video (Wan 2.2).json index 9f1b69669..0ce485b67 100644 --- a/blueprints/Text to Video (Wan 2.2).json +++ b/blueprints/Text to Video (Wan 2.2).json @@ -1 +1,1589 @@ -{"id": "ec7da562-7e21-4dac-a0d2-f4441e1efd3b", "revision": 0, "last_node_id": 116, "last_link_id": 188, "nodes": [{"id": 114, "type": "59b2f9c7-af11-45c8-a22b-871166f816c0", "pos": [900.0000142553818, 629.999938027585], "size": [400, 394.97395833333337], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "prompt", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}, {"name": "length", "type": "INT", "widget": {"name": "length"}, "link": null}, {"name": "width", "type": "INT", "widget": {"name": "width"}, "link": null}, {"name": "height", "type": "INT", "widget": {"name": "height"}, "link": null}], "outputs": [{"name": "VIDEO", "type": "VIDEO", "links": null}], "properties": {"proxyWidgets": [["-1", "text"], ["-1", "length"], ["-1", "width"], ["-1", "height"], ["81", "noise_seed"], ["81", "control_after_generate"]], "cnr_id": "comfy-core", "ver": "0.11.0"}, "widgets_values": ["", 81, 640, 640]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "59b2f9c7-af11-45c8-a22b-871166f816c0", "version": 1, "state": {"lastGroupId": 15, "lastNodeId": 114, "lastLinkId": 196, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Text to Video (Wan 2.2)", "inputNode": {"id": -10, "bounding": [-99.66668418897854, 621.3333300391974, 120, 120]}, "outputNode": {"id": -20, "bounding": [1661.9927561248032, 500.2133490758798, 120, 60]}, "inputs": [{"id": "3a15ef44-456f-4a3a-ade7-7a0840166830", "name": "text", "type": "STRING", "linkIds": [189], "label": "prompt", "pos": [0.333315811021464, 641.3333300391974]}, {"id": "ec76f1bf-b130-4dc9-a50c-0b10002725d6", "name": "length", "type": "INT", "linkIds": [190], "pos": [0.333315811021464, 661.3333300391974]}, {"id": "1abb6b00-a8b4-4e72-9d87-53f1fc5d281e", "name": "width", "type": "INT", "linkIds": [191], "pos": [0.333315811021464, 681.3333300391974]}, {"id": "0af36ab5-ee95-4ce5-9ad9-26436319a0d2", "name": "height", "type": "INT", "linkIds": [192], "pos": [0.333315811021464, 701.3333300391974]}], "outputs": [{"id": "6bdfda51-5568-48bf-8985-dbad1e11b3d8", "name": "VIDEO", "type": "VIDEO", "linkIds": [196], "pos": [1681.9927561248032, 520.2133490758798]}], "widgets": [], "nodes": [{"id": 71, "type": "CLIPLoader", "pos": [50.33329119280961, 51.33334121884377], "size": [346.38020833333337, 98], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "slot_index": 0, "links": [141, 160]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "CLIPLoader", "models": [{"name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors", "directory": "text_encoders"}]}, "widgets_values": ["umt5_xxl_fp8_e4m3fn_scaled.safetensors", "wan", "default"]}, {"id": 73, "type": "VAELoader", "pos": [50.33329119280961, 211.33336855035554], "size": [344.7135416666667, 50], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [158]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "VAELoader", "models": [{"name": "wan_2.1_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors", "directory": "vae"}]}, "widgets_values": ["wan_2.1_vae.safetensors"]}, {"id": 76, "type": "UNETLoader", "pos": [50.33329119280961, -78.66666636275716], "size": [346.7447916666667, 74], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [155]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "UNETLoader", "models": [{"name": "wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors", "directory": "diffusion_models"}]}, "widgets_values": ["wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors", "default"]}, {"id": 75, "type": "UNETLoader", "pos": [50.33329119280961, -208.66667394435814], "size": [346.7447916666667, 74], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [153]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "UNETLoader", "models": [{"name": "wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors", "directory": "diffusion_models"}]}, "widgets_values": ["wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors", "default"]}, {"id": 83, "type": "LoraLoaderModelOnly", "pos": [450.3332425195698, -198.66662836038148], "size": [279.9869791666667, 74], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 153}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [152]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.49", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors", "directory": "loras"}]}, "widgets_values": ["wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors", 1.0000000000000002]}, {"id": 85, "type": "LoraLoaderModelOnly", "pos": [450.3332425195698, -58.66669219682302], "size": [279.9869791666667, 74], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 155}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [156]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.49", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors", "directory": "loras"}]}, "widgets_values": ["wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors", 1.0000000000000002]}, {"id": 86, "type": "ModelSamplingSD3", "pos": [740.3332774326827, -58.66669219682302], "size": [210, 50], "flags": {"collapsed": false}, "order": 9, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 156}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [183]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "ModelSamplingSD3"}, "widgets_values": [5.000000000000001]}, {"id": 82, "type": "ModelSamplingSD3", "pos": [740.3332774326827, -198.66662836038148], "size": [210, 50], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 152}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [181]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "ModelSamplingSD3"}, "widgets_values": [5.000000000000001]}, {"id": 81, "type": "KSamplerAdvanced", "pos": [990.3333640139272, -248.66668077723608], "size": [300, 440.98958333333337], "flags": {}, "order": 13, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 181}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 149}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 150}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 151}, {"localized_name": "add_noise", "name": "add_noise", "type": "COMBO", "widget": {"name": "add_noise"}, "link": null}, {"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "start_at_step", "name": "start_at_step", "type": "INT", "widget": {"name": "start_at_step"}, "link": null}, {"localized_name": "end_at_step", "name": "end_at_step", "type": "INT", "widget": {"name": "end_at_step"}, "link": null}, {"localized_name": "return_with_leftover_noise", "name": "return_with_leftover_noise", "type": "COMBO", "widget": {"name": "return_with_leftover_noise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [145]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "KSamplerAdvanced"}, "widgets_values": ["enable", 0, "randomize", 4, 1, "euler", "simple", 0, 2, "enable"]}, {"id": 74, "type": "EmptyHunyuanLatentVideo", "pos": [70.33326535874369, 381.33332446382485], "size": [314.9869791666667, 122], "flags": {}, "order": 11, "mode": 0, "inputs": [{"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 191}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 192}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": 190}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [151]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "EmptyHunyuanLatentVideo"}, "widgets_values": [640, 640, 81, 1]}, {"id": 78, "type": "KSamplerAdvanced", "pos": [1310.3334186769505, -248.66668077723608], "size": [304.73958333333337, 440.98958333333337], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 183}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 143}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 144}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 145}, {"localized_name": "add_noise", "name": "add_noise", "type": "COMBO", "widget": {"name": "add_noise"}, "link": null}, {"localized_name": "noise_seed", "name": "noise_seed", "type": "INT", "widget": {"name": "noise_seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "start_at_step", "name": "start_at_step", "type": "INT", "widget": {"name": "start_at_step"}, "link": null}, {"localized_name": "end_at_step", "name": "end_at_step", "type": "INT", "widget": {"name": "end_at_step"}, "link": null}, {"localized_name": "return_with_leftover_noise", "name": "return_with_leftover_noise", "type": "COMBO", "widget": {"name": "return_with_leftover_noise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [157]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "KSamplerAdvanced"}, "widgets_values": ["disable", 0, "fixed", 4, 1, "euler", "simple", 2, 4, "disable"]}, {"id": 114, "type": "CreateVideo", "pos": [1320.333347258908, 441.33336396364655], "size": [269.9869791666667, 70], "flags": {}, "order": 16, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 195}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [196]}], "properties": {"cnr_id": "comfy-core", "ver": "0.11.0", "Node name for S&R": "CreateVideo"}, "widgets_values": [16]}, {"id": 112, "type": "Note", "pos": [30.33320002485607, -428.6666237736725], "size": [359.9869791666667, 52], "flags": {}, "order": 4, "mode": 0, "inputs": [], "outputs": [], "title": "About 4 Steps LoRA", "properties": {}, "widgets_values": ["Using the Wan2.2 Lighting LoRA will result in the loss of video dynamics, but it will reduce the generation time. This template provides two workflows, and you can enable one as needed."], "color": "#222", "bgcolor": "#000"}, {"id": 62, "type": "MarkdownNote", "pos": [-489.666771800538, -278.666700527147], "size": [479.9869791666667, 542.1354166666667], "flags": {}, "order": 5, "mode": 0, "inputs": [], "outputs": [], "title": "Model Links", "properties": {}, "widgets_values": ["[Tutorial](https://docs.comfy.org/tutorials/video/wan/wan2_2\n) | [教程](https://docs.comfy.org/zh-CN/tutorials/video/wan/wan2_2\n)\n\n**Diffusion Model** \n- [wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors)\n- [wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors)\n\n**LoRA**\n\n- [wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors)\n- [wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors)\n\n**VAE**\n- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)\n\n**Text Encoder** \n- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)\n\n\nFile save location\n\n```\nComfyUI/\n├───📂 models/\n│ ├───📂 diffusion_models/\n│ │ ├─── wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors\n│ │ └─── wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors\n│ ├───📂 loras/\n│ │ ├───wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors\n│ │ └───wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors\n│ ├───📂 text_encoders/\n│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors \n│ └───📂 vae/\n│ └── wan_2.1_vae.safetensors\n```\n"], "color": "#222", "bgcolor": "#000"}, {"id": 87, "type": "VAEDecode", "pos": [1020.3331497597994, 471.3333837135574], "size": [210, 46], "flags": {"collapsed": false}, "order": 14, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 157}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 158}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [195]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "VAEDecode"}, "widgets_values": []}, {"id": 72, "type": "CLIPTextEncode", "pos": [440.3333139376125, 331.3333305479798], "size": [500, 170], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 141}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [144, 150]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "CLIPTextEncode"}, "widgets_values": ["色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走，裸露，NSFW"], "color": "#322", "bgcolor": "#533"}, {"id": 89, "type": "CLIPTextEncode", "pos": [440.3333139376125, 131.33323788258042], "size": [510, 170], "flags": {}, "order": 15, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 160}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": 189}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [143, 149]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.45", "Node name for S&R": "CLIPTextEncode"}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}], "groups": [{"id": 13, "title": "Wan2.2 T2V fp8_scaled + 4 steps LoRA", "bounding": [31.999982477688036, -317.00000329413615, 1610, 880], "color": "#444", "font_size": 24, "flags": {}}, {"id": 6, "title": "Step3 Prompt", "bounding": [431.99998247768815, 57.99999670586385, 530, 460], "color": "#444", "font_size": 24, "flags": {}}, {"id": 7, "title": "Lightx2v 4steps LoRA", "bounding": [431.99998247768815, -275.33333662746946, 530, 320], "color": "#444", "font_size": 24, "flags": {}}, {"id": 11, "title": "Step 1 - Load models", "bounding": [40.33331581102152, -275.33333662746946, 366.7470703125, 563.5814208984375], "color": "#444", "font_size": 24, "flags": {}}, {"id": 12, "title": "Step 2 - Video size", "bounding": [40.33331581102152, 299.6666633725306, 370, 230], "color": "#444", "font_size": 24, "flags": {}}], "links": [{"id": 153, "origin_id": 75, "origin_slot": 0, "target_id": 83, "target_slot": 0, "type": "MODEL"}, {"id": 155, "origin_id": 76, "origin_slot": 0, "target_id": 85, "target_slot": 0, "type": "MODEL"}, {"id": 156, "origin_id": 85, "origin_slot": 0, "target_id": 86, "target_slot": 0, "type": "MODEL"}, {"id": 152, "origin_id": 83, "origin_slot": 0, "target_id": 82, "target_slot": 0, "type": "MODEL"}, {"id": 160, "origin_id": 71, "origin_slot": 0, "target_id": 89, "target_slot": 0, "type": "CLIP"}, {"id": 181, "origin_id": 82, "origin_slot": 0, "target_id": 81, "target_slot": 0, "type": "MODEL"}, {"id": 149, "origin_id": 89, "origin_slot": 0, "target_id": 81, "target_slot": 1, "type": "CONDITIONING"}, {"id": 150, "origin_id": 72, "origin_slot": 0, "target_id": 81, "target_slot": 2, "type": "CONDITIONING"}, {"id": 151, "origin_id": 74, "origin_slot": 0, "target_id": 81, "target_slot": 3, "type": "LATENT"}, {"id": 157, "origin_id": 78, "origin_slot": 0, "target_id": 87, "target_slot": 0, "type": "LATENT"}, {"id": 158, "origin_id": 73, "origin_slot": 0, "target_id": 87, "target_slot": 1, "type": "VAE"}, {"id": 141, "origin_id": 71, "origin_slot": 0, "target_id": 72, "target_slot": 0, "type": "CLIP"}, {"id": 183, "origin_id": 86, "origin_slot": 0, "target_id": 78, "target_slot": 0, "type": "MODEL"}, {"id": 143, "origin_id": 89, "origin_slot": 0, "target_id": 78, "target_slot": 1, "type": "CONDITIONING"}, {"id": 144, "origin_id": 72, "origin_slot": 0, "target_id": 78, "target_slot": 2, "type": "CONDITIONING"}, {"id": 145, "origin_id": 81, "origin_slot": 0, "target_id": 78, "target_slot": 3, "type": "LATENT"}, {"id": 189, "origin_id": -10, "origin_slot": 0, "target_id": 89, "target_slot": 1, "type": "STRING"}, {"id": 190, "origin_id": -10, "origin_slot": 1, "target_id": 74, "target_slot": 2, "type": "INT"}, {"id": 191, "origin_id": -10, "origin_slot": 2, "target_id": 74, "target_slot": 0, "type": "INT"}, {"id": 192, "origin_id": -10, "origin_slot": 3, "target_id": 74, "target_slot": 1, "type": "INT"}, {"id": 195, "origin_id": 87, "origin_slot": 0, "target_id": 114, "target_slot": 0, "type": "IMAGE"}, {"id": 196, "origin_id": 114, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Text to video"}]}, "config": {}, "extra": {"frontendVersion": "1.37.10", "workflowRendererVersion": "LG", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true}, "version": 0.4} +{ + "id": "ec7da562-7e21-4dac-a0d2-f4441e1efd3b", + "revision": 0, + "last_node_id": 116, + "last_link_id": 188, + "nodes": [ + { + "id": 114, + "type": "59b2f9c7-af11-45c8-a22b-871166f816c0", + "pos": [ + 900.0000142553818, + 629.999938027585 + ], + "size": [ + 400, + 394.97395833333337 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "prompt", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + }, + { + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + } + ], + "outputs": [ + { + "name": "VIDEO", + "type": "VIDEO", + "links": null + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "text" + ], + [ + "-1", + "length" + ], + [ + "-1", + "width" + ], + [ + "-1", + "height" + ], + [ + "81", + "noise_seed" + ], + [ + "81", + "control_after_generate" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.11.0" + }, + "widgets_values": [ + "", + 81, + 640, + 640 + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "59b2f9c7-af11-45c8-a22b-871166f816c0", + "version": 1, + "state": { + "lastGroupId": 15, + "lastNodeId": 114, + "lastLinkId": 196, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Text to Video (Wan 2.2)", + "inputNode": { + "id": -10, + "bounding": [ + -99.66668418897854, + 621.3333300391974, + 120, + 120 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1661.9927561248032, + 500.2133490758798, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "3a15ef44-456f-4a3a-ade7-7a0840166830", + "name": "text", + "type": "STRING", + "linkIds": [ + 189 + ], + "label": "prompt", + "pos": [ + 0.333315811021464, + 641.3333300391974 + ] + }, + { + "id": "ec76f1bf-b130-4dc9-a50c-0b10002725d6", + "name": "length", + "type": "INT", + "linkIds": [ + 190 + ], + "pos": [ + 0.333315811021464, + 661.3333300391974 + ] + }, + { + "id": "1abb6b00-a8b4-4e72-9d87-53f1fc5d281e", + "name": "width", + "type": "INT", + "linkIds": [ + 191 + ], + "pos": [ + 0.333315811021464, + 681.3333300391974 + ] + }, + { + "id": "0af36ab5-ee95-4ce5-9ad9-26436319a0d2", + "name": "height", + "type": "INT", + "linkIds": [ + 192 + ], + "pos": [ + 0.333315811021464, + 701.3333300391974 + ] + } + ], + "outputs": [ + { + "id": "6bdfda51-5568-48bf-8985-dbad1e11b3d8", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 196 + ], + "pos": [ + 1681.9927561248032, + 520.2133490758798 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 71, + "type": "CLIPLoader", + "pos": [ + 50.33329119280961, + 51.33334121884377 + ], + "size": [ + 346.38020833333337, + 98 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 141, + 160 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "directory": "text_encoders" + } + ] + }, + "widgets_values": [ + "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "wan", + "default" + ] + }, + { + "id": 73, + "type": "VAELoader", + "pos": [ + 50.33329119280961, + 211.33336855035554 + ], + "size": [ + 344.7135416666667, + 50 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 158 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "wan_2.1_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors", + "directory": "vae" + } + ] + }, + "widgets_values": [ + "wan_2.1_vae.safetensors" + ] + }, + { + "id": 76, + "type": "UNETLoader", + "pos": [ + 50.33329119280961, + -78.66666636275716 + ], + "size": [ + 346.7447916666667, + 74 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 155 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors", + "default" + ] + }, + { + "id": 75, + "type": "UNETLoader", + "pos": [ + 50.33329119280961, + -208.66667394435814 + ], + "size": [ + 346.7447916666667, + 74 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 153 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors", + "directory": "diffusion_models" + } + ] + }, + "widgets_values": [ + "wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors", + "default" + ] + }, + { + "id": 83, + "type": "LoraLoaderModelOnly", + "pos": [ + 450.3332425195698, + -198.66662836038148 + ], + "size": [ + 279.9869791666667, + 74 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 153 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 152 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.49", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors", + 1.0000000000000002 + ] + }, + { + "id": 85, + "type": "LoraLoaderModelOnly", + "pos": [ + 450.3332425195698, + -58.66669219682302 + ], + "size": [ + 279.9869791666667, + 74 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 155 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 156 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.49", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors", + "directory": "loras" + } + ] + }, + "widgets_values": [ + "wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors", + 1.0000000000000002 + ] + }, + { + "id": 86, + "type": "ModelSamplingSD3", + "pos": [ + 740.3332774326827, + -58.66669219682302 + ], + "size": [ + 210, + 50 + ], + "flags": { + "collapsed": false + }, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 156 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 183 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "ModelSamplingSD3" + }, + "widgets_values": [ + 5.000000000000001 + ] + }, + { + "id": 82, + "type": "ModelSamplingSD3", + "pos": [ + 740.3332774326827, + -198.66662836038148 + ], + "size": [ + 210, + 50 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 152 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 181 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "ModelSamplingSD3" + }, + "widgets_values": [ + 5.000000000000001 + ] + }, + { + "id": 81, + "type": "KSamplerAdvanced", + "pos": [ + 990.3333640139272, + -248.66668077723608 + ], + "size": [ + 300, + 440.98958333333337 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 181 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 149 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 150 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 151 + }, + { + "localized_name": "add_noise", + "name": "add_noise", + "type": "COMBO", + "widget": { + "name": "add_noise" + }, + "link": null + }, + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "start_at_step", + "name": "start_at_step", + "type": "INT", + "widget": { + "name": "start_at_step" + }, + "link": null + }, + { + "localized_name": "end_at_step", + "name": "end_at_step", + "type": "INT", + "widget": { + "name": "end_at_step" + }, + "link": null + }, + { + "localized_name": "return_with_leftover_noise", + "name": "return_with_leftover_noise", + "type": "COMBO", + "widget": { + "name": "return_with_leftover_noise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 145 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "KSamplerAdvanced" + }, + "widgets_values": [ + "enable", + 0, + "randomize", + 4, + 1, + "euler", + "simple", + 0, + 2, + "enable" + ] + }, + { + "id": 74, + "type": "EmptyHunyuanLatentVideo", + "pos": [ + 70.33326535874369, + 381.33332446382485 + ], + "size": [ + 314.9869791666667, + 122 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 191 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 192 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 190 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 151 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "EmptyHunyuanLatentVideo" + }, + "widgets_values": [ + 640, + 640, + 81, + 1 + ] + }, + { + "id": 78, + "type": "KSamplerAdvanced", + "pos": [ + 1310.3334186769505, + -248.66668077723608 + ], + "size": [ + 304.73958333333337, + 440.98958333333337 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 183 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 143 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 144 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 145 + }, + { + "localized_name": "add_noise", + "name": "add_noise", + "type": "COMBO", + "widget": { + "name": "add_noise" + }, + "link": null + }, + { + "localized_name": "noise_seed", + "name": "noise_seed", + "type": "INT", + "widget": { + "name": "noise_seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "start_at_step", + "name": "start_at_step", + "type": "INT", + "widget": { + "name": "start_at_step" + }, + "link": null + }, + { + "localized_name": "end_at_step", + "name": "end_at_step", + "type": "INT", + "widget": { + "name": "end_at_step" + }, + "link": null + }, + { + "localized_name": "return_with_leftover_noise", + "name": "return_with_leftover_noise", + "type": "COMBO", + "widget": { + "name": "return_with_leftover_noise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 157 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "KSamplerAdvanced" + }, + "widgets_values": [ + "disable", + 0, + "fixed", + 4, + 1, + "euler", + "simple", + 2, + 4, + "disable" + ] + }, + { + "id": 114, + "type": "CreateVideo", + "pos": [ + 1320.333347258908, + 441.33336396364655 + ], + "size": [ + 269.9869791666667, + 70 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 195 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": null + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 196 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.11.0", + "Node name for S&R": "CreateVideo" + }, + "widgets_values": [ + 16 + ] + }, + { + "id": 112, + "type": "Note", + "pos": [ + 30.33320002485607, + -428.6666237736725 + ], + "size": [ + 359.9869791666667, + 52 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "About 4 Steps LoRA", + "properties": {}, + "widgets_values": [ + "Using the Wan2.2 Lighting LoRA will result in the loss of video dynamics, but it will reduce the generation time. This template provides two workflows, and you can enable one as needed." + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 62, + "type": "MarkdownNote", + "pos": [ + -489.666771800538, + -278.666700527147 + ], + "size": [ + 479.9869791666667, + 542.1354166666667 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Model Links", + "properties": {}, + "widgets_values": [ + "[Tutorial](https://docs.comfy.org/tutorials/video/wan/wan2_2\n) | [教程](https://docs.comfy.org/zh-CN/tutorials/video/wan/wan2_2\n)\n\n**Diffusion Model** \n- [wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors)\n- [wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors)\n\n**LoRA**\n\n- [wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors)\n- [wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors)\n\n**VAE**\n- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)\n\n**Text Encoder** \n- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)\n\n\nFile save location\n\n```\nComfyUI/\n├───📂 models/\n│ ├───📂 diffusion_models/\n│ │ ├─── wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors\n│ │ └─── wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors\n│ ├───📂 loras/\n│ │ ├───wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors\n│ │ └───wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors\n│ ├───📂 text_encoders/\n│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors \n│ └───📂 vae/\n│ └── wan_2.1_vae.safetensors\n```\n" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 87, + "type": "VAEDecode", + "pos": [ + 1020.3331497597994, + 471.3333837135574 + ], + "size": [ + 210, + 46 + ], + "flags": { + "collapsed": false + }, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 157 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 158 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 195 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "VAEDecode" + }, + "widgets_values": [] + }, + { + "id": 72, + "type": "CLIPTextEncode", + "pos": [ + 440.3333139376125, + 331.3333305479798 + ], + "size": [ + 500, + 170 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 141 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 144, + 150 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走，裸露，NSFW" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 89, + "type": "CLIPTextEncode", + "pos": [ + 440.3333139376125, + 131.33323788258042 + ], + "size": [ + 510, + 170 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 160 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": 189 + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 143, + 149 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.45", + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + } + ], + "groups": [ + { + "id": 13, + "title": "Wan2.2 T2V fp8_scaled + 4 steps LoRA", + "bounding": [ + 31.999982477688036, + -317.00000329413615, + 1610, + 880 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 6, + "title": "Step3 Prompt", + "bounding": [ + 431.99998247768815, + 57.99999670586385, + 530, + 460 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 7, + "title": "Lightx2v 4steps LoRA", + "bounding": [ + 431.99998247768815, + -275.33333662746946, + 530, + 320 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 11, + "title": "Step 1 - Load models", + "bounding": [ + 40.33331581102152, + -275.33333662746946, + 366.7470703125, + 563.5814208984375 + ], + "color": "#444", + "font_size": 24, + "flags": {} + }, + { + "id": 12, + "title": "Step 2 - Video size", + "bounding": [ + 40.33331581102152, + 299.6666633725306, + 370, + 230 + ], + "color": "#444", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 153, + "origin_id": 75, + "origin_slot": 0, + "target_id": 83, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 155, + "origin_id": 76, + "origin_slot": 0, + "target_id": 85, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 156, + "origin_id": 85, + "origin_slot": 0, + "target_id": 86, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 152, + "origin_id": 83, + "origin_slot": 0, + "target_id": 82, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 160, + "origin_id": 71, + "origin_slot": 0, + "target_id": 89, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 181, + "origin_id": 82, + "origin_slot": 0, + "target_id": 81, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 149, + "origin_id": 89, + "origin_slot": 0, + "target_id": 81, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 150, + "origin_id": 72, + "origin_slot": 0, + "target_id": 81, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 151, + "origin_id": 74, + "origin_slot": 0, + "target_id": 81, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 157, + "origin_id": 78, + "origin_slot": 0, + "target_id": 87, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 158, + "origin_id": 73, + "origin_slot": 0, + "target_id": 87, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 141, + "origin_id": 71, + "origin_slot": 0, + "target_id": 72, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 183, + "origin_id": 86, + "origin_slot": 0, + "target_id": 78, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 143, + "origin_id": 89, + "origin_slot": 0, + "target_id": 78, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 144, + "origin_id": 72, + "origin_slot": 0, + "target_id": 78, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 145, + "origin_id": 81, + "origin_slot": 0, + "target_id": 78, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 189, + "origin_id": -10, + "origin_slot": 0, + "target_id": 89, + "target_slot": 1, + "type": "STRING" + }, + { + "id": 190, + "origin_id": -10, + "origin_slot": 1, + "target_id": 74, + "target_slot": 2, + "type": "INT" + }, + { + "id": 191, + "origin_id": -10, + "origin_slot": 2, + "target_id": 74, + "target_slot": 0, + "type": "INT" + }, + { + "id": 192, + "origin_id": -10, + "origin_slot": 3, + "target_id": 74, + "target_slot": 1, + "type": "INT" + }, + { + "id": 195, + "origin_id": 87, + "origin_slot": 0, + "target_id": 114, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 196, + "origin_id": 114, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video generation and editing/Text to video" + } + ] + }, + "config": {}, + "extra": { + "frontendVersion": "1.37.10", + "workflowRendererVersion": "LG", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "version": 0.4 +} diff --git a/blueprints/Unsharp Mask.json b/blueprints/Unsharp Mask.json index 9363037ef..137acaa43 100644 --- a/blueprints/Unsharp Mask.json +++ b/blueprints/Unsharp Mask.json @@ -1 +1,441 @@ -{"revision": 0, "last_node_id": 30, "last_link_id": 0, "nodes": [{"id": 30, "type": "d99ba3f5-8a56-4365-8e45-3f3ea7c572a1", "pos": [4420, -370], "size": [210, 106], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "title": "Unsharp Mask", "properties": {"proxyWidgets": [["27", "value"], ["28", "value"], ["29", "value"]]}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "d99ba3f5-8a56-4365-8e45-3f3ea7c572a1", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 29, "lastLinkId": 43, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Unsharp Mask", "inputNode": {"id": -10, "bounding": [3920, -405, 120, 60]}, "outputNode": {"id": -20, "bounding": [4930, -405, 120, 60]}, "inputs": [{"id": "75354555-d2f3-46b9-a3dd-b076dcfca561", "name": "images.image0", "type": "IMAGE", "linkIds": [39], "localized_name": "images.image0", "label": "image0", "pos": [4020, -385]}], "outputs": [{"id": "04368b94-2a96-46ff-8c07-d0ce3235b40d", "name": "IMAGE0", "type": "IMAGE", "linkIds": [40], "localized_name": "IMAGE0", "pos": [4950, -385]}], "widgets": [], "nodes": [{"id": 27, "type": "PrimitiveFloat", "pos": [4100, -540], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "amount", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [41]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 3, "precision": 2, "step": 0.05}, "widgets_values": [1]}, {"id": 28, "type": "PrimitiveFloat", "pos": [4100, -430], "size": [270, 58], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "radius", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [42]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 10, "precision": 1, "step": 0.5}, "widgets_values": [3]}, {"id": 29, "type": "PrimitiveFloat", "pos": [4100, -320], "size": [270, 58], "flags": {}, "order": 2, "mode": 0, "inputs": [{"label": "threshold", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [43]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 1, "precision": 2, "step": 0.05}, "widgets_values": [0]}, {"id": 26, "type": "GLSLShader", "pos": [4470, -580], "size": [400, 232], "flags": {}, "order": 3, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 39}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 41}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": 42}, {"label": "u_float2", "localized_name": "floats.u_float2", "name": "floats.u_float2", "shape": 7, "type": "FLOAT", "link": 43}, {"label": "u_float3", "localized_name": "floats.u_float3", "name": "floats.u_float3", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [40]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // amount [0.0 - 3.0] typical: 0.5-1.5\nuniform float u_float1; // radius [0.5 - 10.0] blur radius in pixels\nuniform float u_float2; // threshold [0.0 - 0.1] min difference to sharpen\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nfloat getLuminance(vec3 color) {\n return dot(color, vec3(0.2126, 0.7152, 0.0722));\n}\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n float radius = max(u_float1, 0.5);\n float amount = u_float0;\n float threshold = u_float2;\n\n vec4 original = texture(u_image0, v_texCoord);\n\n // Gaussian blur for the \"unsharp\" mask\n int samples = int(ceil(radius));\n float sigma = radius / 2.0;\n\n vec4 blurred = vec4(0.0);\n float totalWeight = 0.0;\n\n for (int x = -samples; x <= samples; x++) {\n for (int y = -samples; y <= samples; y++) {\n vec2 offset = vec2(float(x), float(y)) * texel;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float dist = length(vec2(float(x), float(y)));\n float weight = gaussian(dist, sigma);\n blurred += sample_color * weight;\n totalWeight += weight;\n }\n }\n blurred /= totalWeight;\n\n // Unsharp mask = original - blurred\n vec3 mask = original.rgb - blurred.rgb;\n\n // Luminance-based threshold with smooth falloff\n float lumaDelta = abs(getLuminance(original.rgb) - getLuminance(blurred.rgb));\n float thresholdScale = smoothstep(0.0, threshold, lumaDelta);\n mask *= thresholdScale;\n\n // Sharpen: original + mask * amount\n vec3 sharpened = original.rgb + mask * amount;\n\n fragColor0 = vec4(clamp(sharpened, 0.0, 1.0), original.a);\n}\n", "from_input"]}], "groups": [], "links": [{"id": 41, "origin_id": 27, "origin_slot": 0, "target_id": 26, "target_slot": 2, "type": "FLOAT"}, {"id": 42, "origin_id": 28, "origin_slot": 0, "target_id": 26, "target_slot": 3, "type": "FLOAT"}, {"id": 43, "origin_id": 29, "origin_slot": 0, "target_id": 26, "target_slot": 4, "type": "FLOAT"}, {"id": 39, "origin_id": -10, "origin_slot": 0, "target_id": 26, "target_slot": 0, "type": "IMAGE"}, {"id": 40, "origin_id": 26, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Sharpen"}]}} +{ + "revision": 0, + "last_node_id": 30, + "last_link_id": 0, + "nodes": [ + { + "id": 30, + "type": "d99ba3f5-8a56-4365-8e45-3f3ea7c572a1", + "pos": [ + 4420, + -370 + ], + "size": [ + 210, + 106 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [] + } + ], + "title": "Unsharp Mask", + "properties": { + "proxyWidgets": [ + [ + "27", + "value" + ], + [ + "28", + "value" + ], + [ + "29", + "value" + ] + ] + }, + "widgets_values": [] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "d99ba3f5-8a56-4365-8e45-3f3ea7c572a1", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 29, + "lastLinkId": 43, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Unsharp Mask", + "inputNode": { + "id": -10, + "bounding": [ + 3920, + -405, + 120, + 60 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 4930, + -405, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "75354555-d2f3-46b9-a3dd-b076dcfca561", + "name": "images.image0", + "type": "IMAGE", + "linkIds": [ + 39 + ], + "localized_name": "images.image0", + "label": "image0", + "pos": [ + 4020, + -385 + ] + } + ], + "outputs": [ + { + "id": "04368b94-2a96-46ff-8c07-d0ce3235b40d", + "name": "IMAGE0", + "type": "IMAGE", + "linkIds": [ + 40 + ], + "localized_name": "IMAGE0", + "pos": [ + 4950, + -385 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 27, + "type": "PrimitiveFloat", + "pos": [ + 4100, + -540 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "amount", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 41 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 3, + "precision": 2, + "step": 0.05 + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 28, + "type": "PrimitiveFloat", + "pos": [ + 4100, + -430 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "label": "radius", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 42 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 10, + "precision": 1, + "step": 0.5 + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 29, + "type": "PrimitiveFloat", + "pos": [ + 4100, + -320 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "label": "threshold", + "localized_name": "value", + "name": "value", + "type": "FLOAT", + "widget": { + "name": "value" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 43 + ] + } + ], + "properties": { + "Node name for S&R": "PrimitiveFloat", + "min": 0, + "max": 1, + "precision": 2, + "step": 0.05 + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 26, + "type": "GLSLShader", + "pos": [ + 4470, + -580 + ], + "size": [ + 400, + 232 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "label": "image0", + "localized_name": "images.image0", + "name": "images.image0", + "type": "IMAGE", + "link": 39 + }, + { + "label": "image1", + "localized_name": "images.image1", + "name": "images.image1", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "label": "u_float0", + "localized_name": "floats.u_float0", + "name": "floats.u_float0", + "shape": 7, + "type": "FLOAT", + "link": 41 + }, + { + "label": "u_float1", + "localized_name": "floats.u_float1", + "name": "floats.u_float1", + "shape": 7, + "type": "FLOAT", + "link": 42 + }, + { + "label": "u_float2", + "localized_name": "floats.u_float2", + "name": "floats.u_float2", + "shape": 7, + "type": "FLOAT", + "link": 43 + }, + { + "label": "u_float3", + "localized_name": "floats.u_float3", + "name": "floats.u_float3", + "shape": 7, + "type": "FLOAT", + "link": null + }, + { + "label": "u_int0", + "localized_name": "ints.u_int0", + "name": "ints.u_int0", + "shape": 7, + "type": "INT", + "link": null + }, + { + "localized_name": "fragment_shader", + "name": "fragment_shader", + "type": "STRING", + "widget": { + "name": "fragment_shader" + }, + "link": null + }, + { + "localized_name": "size_mode", + "name": "size_mode", + "type": "COMFY_DYNAMICCOMBO_V3", + "widget": { + "name": "size_mode" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE0", + "name": "IMAGE0", + "type": "IMAGE", + "links": [ + 40 + ] + }, + { + "localized_name": "IMAGE1", + "name": "IMAGE1", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE2", + "name": "IMAGE2", + "type": "IMAGE", + "links": null + }, + { + "localized_name": "IMAGE3", + "name": "IMAGE3", + "type": "IMAGE", + "links": null + } + ], + "properties": { + "Node name for S&R": "GLSLShader" + }, + "widgets_values": [ + "#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // amount [0.0 - 3.0] typical: 0.5-1.5\nuniform float u_float1; // radius [0.5 - 10.0] blur radius in pixels\nuniform float u_float2; // threshold [0.0 - 0.1] min difference to sharpen\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nfloat getLuminance(vec3 color) {\n return dot(color, vec3(0.2126, 0.7152, 0.0722));\n}\n\nvoid main() {\n vec2 texel = 1.0 / vec2(textureSize(u_image0, 0));\n float radius = max(u_float1, 0.5);\n float amount = u_float0;\n float threshold = u_float2;\n\n vec4 original = texture(u_image0, v_texCoord);\n\n // Gaussian blur for the \"unsharp\" mask\n int samples = int(ceil(radius));\n float sigma = radius / 2.0;\n\n vec4 blurred = vec4(0.0);\n float totalWeight = 0.0;\n\n for (int x = -samples; x <= samples; x++) {\n for (int y = -samples; y <= samples; y++) {\n vec2 offset = vec2(float(x), float(y)) * texel;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float dist = length(vec2(float(x), float(y)));\n float weight = gaussian(dist, sigma);\n blurred += sample_color * weight;\n totalWeight += weight;\n }\n }\n blurred /= totalWeight;\n\n // Unsharp mask = original - blurred\n vec3 mask = original.rgb - blurred.rgb;\n\n // Luminance-based threshold with smooth falloff\n float lumaDelta = abs(getLuminance(original.rgb) - getLuminance(blurred.rgb));\n float thresholdScale = smoothstep(0.0, threshold, lumaDelta);\n mask *= thresholdScale;\n\n // Sharpen: original + mask * amount\n vec3 sharpened = original.rgb + mask * amount;\n\n fragColor0 = vec4(clamp(sharpened, 0.0, 1.0), original.a);\n}\n", + "from_input" + ] + } + ], + "groups": [], + "links": [ + { + "id": 41, + "origin_id": 27, + "origin_slot": 0, + "target_id": 26, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 42, + "origin_id": 28, + "origin_slot": 0, + "target_id": 26, + "target_slot": 3, + "type": "FLOAT" + }, + { + "id": 43, + "origin_id": 29, + "origin_slot": 0, + "target_id": 26, + "target_slot": 4, + "type": "FLOAT" + }, + { + "id": 39, + "origin_id": -10, + "origin_slot": 0, + "target_id": 26, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 40, + "origin_id": 26, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "IMAGE" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Image Tools/Sharpen" + } + ] + } +} diff --git a/blueprints/Video Captioning (Gemini).json b/blueprints/Video Captioning (Gemini).json index 1d72718a1..ea6dc8bee 100644 --- a/blueprints/Video Captioning (Gemini).json +++ b/blueprints/Video Captioning (Gemini).json @@ -1 +1,314 @@ -{"revision": 0, "last_node_id": 233, "last_link_id": 0, "nodes": [{"id": 233, "type": "dcf32045-0ee4-4efc-9aca-9f26f3a157be", "pos": [0, 1140], "size": [400, 260], "flags": {}, "order": 7, "mode": 0, "inputs": [{"name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}, {"name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": null}, {"name": "video", "type": "VIDEO", "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": []}], "title": "Video Captioning(Gemini)", "properties": {"proxyWidgets": [["-1", "prompt"], ["-1", "model"], ["1", "seed"]], "cnr_id": "comfy-core", "ver": "0.13.0"}, "widgets_values": ["Describe this video", "gemini-2.5-pro"]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "dcf32045-0ee4-4efc-9aca-9f26f3a157be", "version": 1, "state": {"lastGroupId": 1, "lastNodeId": 16, "lastLinkId": 17, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Video Captioning(Gemini)", "inputNode": {"id": -10, "bounding": [-6870, 2530, 120, 100]}, "outputNode": {"id": -20, "bounding": [-6240, 2530, 120, 60]}, "inputs": [{"id": "d8cbd7eb-636a-4d7b-8ff6-b22f1755e26c", "name": "prompt", "type": "STRING", "linkIds": [15], "pos": [-6770, 2550]}, {"id": "b034e26a-d114-4604-aec2-32783e86aa6b", "name": "model", "type": "COMBO", "linkIds": [16], "pos": [-6770, 2570]}, {"id": "f7363f60-a106-4e06-90af-df5f53355b98", "name": "video", "type": "VIDEO", "linkIds": [17], "pos": [-6770, 2590]}], "outputs": [{"id": "e12c6e80-5210-4328-a581-bc8924c53070", "name": "STRING", "type": "STRING", "linkIds": [6], "localized_name": "STRING", "pos": [-6220, 2550]}], "widgets": [], "nodes": [{"id": 1, "type": "GeminiNode", "pos": [-6690, 2360], "size": [390, 430], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "shape": 7, "type": "IMAGE", "link": null}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "video", "name": "video", "shape": 7, "type": "VIDEO", "link": 17}, {"localized_name": "files", "name": "files", "shape": 7, "type": "GEMINI_INPUT_FILES", "link": null}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": 15}, {"localized_name": "model", "name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": 16}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "system_prompt", "name": "system_prompt", "shape": 7, "type": "STRING", "widget": {"name": "system_prompt"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": [6]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "GeminiNode"}, "widgets_values": ["Describe this video", "gemini-2.5-pro", 511865409297955, "randomize", "- Role: AI Video Analysis and Description Specialist\n- Background: The user requires a prompt that enables AI to analyze videos (including frame sequences, dynamic movements, audio-visual elements) and generate detailed, structured descriptions. These descriptions must be directly usable as video generation prompts to create similar videos, serving core tasks such as video content creation, creative inspiration extraction, and artistic style exploration.\n- Profile: As an AI Video Analysis and Description Specialist, you possess expertise in computer vision, video temporal sequence processing, motion analysis, and multi-modal natural language generation. You excel at interpreting dynamic visual data (frame-by-frame features + continuous motion) and translating it into precise descriptive text that fully guides the creation of new videos with matching style, rhythm, and content.\n- Skills: Proficiency in video frame feature extraction, motion trajectory recognition, temporal rhythm analysis, scene/shot segmentation, color grading detection, camera movement identification (pan/tilt/zoom/dolly), audio-visual element correlation analysis, and descriptive language generation that captures both static visual features and dynamic temporal characteristics. Mastery of artistic elements in video: composition (per frame + dynamic framing), color palette (consistent + transitional), texture (surface details + motion blur), pacing (frame rate, shot duration), and sound style (background music, ambient sound cues).\n- Goals: To analyze the provided video comprehensively, generate a detailed, structured description that captures all key video elements (static visual features + dynamic motion/temporal characteristics + audio-visual style), and ensure this description can directly serve as a high-quality prompt for creating similar videos.\n- Constraints: \n 1. The description must be clear, structured, and specific enough to guide end-to-end video creation (including frame rate, shot duration, camera movement, motion speed, color transitions).\n 2. Avoid ambiguity; focus on the most salient static (per-frame) and dynamic (temporal) features of the video.\n 3. Prioritize video-specific elements: motion trajectory, shot types (close-up/wide shot/etc.), camera movement, frame rate, scene transitions, rhythm/pacing, and temporal color changes.\n 4. The output must only contain the video generation prompt (no extra explanations).\n- OutputFormat: A detailed, hierarchical text description of the video, structured as follows:\n 1. Core Content & Narrative: Brief overview of the video's subject and temporal progression\n 2. Visual Style (Static): Per-frame key elements (objects, colors, composition, lighting, texture)\n 3. Dynamic Elements (Temporal): Motion details (speed, trajectory, direction), camera movement (type, speed, direction), shot duration/frame rate, scene transitions\n 4. Audio-Visual Style: Color grading (consistent/transitional), rhythm/pacing, and implied audio style (if discernible)\n- Workflow:\n 1. Analyze the video to segment shots/scenes, identify frame-by-frame static visual elements (objects, colors, composition) and cross-frame dynamic elements (motion, camera movement, temporal changes).\n 2. Extract video-specific technical features: frame rate, shot duration, scene transition types, motion speed/rhythm.\n 3. Generate a structured, detailed description that captures the essence of the video (static + dynamic + temporal characteristics), ensuring specificity and actionability for video generation.\n 4. Refine the description for clarity, conciseness, and alignment with video generation prompt norms (e.g., including frame rate, camera movement terms, motion speed descriptors)."], "color": "#432", "bgcolor": "#653"}], "groups": [], "links": [{"id": 6, "origin_id": 1, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "*"}, {"id": 15, "origin_id": -10, "origin_slot": 0, "target_id": 1, "target_slot": 4, "type": "STRING"}, {"id": 16, "origin_id": -10, "origin_slot": 1, "target_id": 1, "target_slot": 5, "type": "COMBO"}, {"id": 17, "origin_id": -10, "origin_slot": 2, "target_id": 1, "target_slot": 2, "type": "VIDEO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Text generation/Video Captioning"}]}} +{ + "revision": 0, + "last_node_id": 233, + "last_link_id": 0, + "nodes": [ + { + "id": 233, + "type": "dcf32045-0ee4-4efc-9aca-9f26f3a157be", + "pos": [ + 0, + 1140 + ], + "size": [ + 400, + 260 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": null + }, + { + "name": "model", + "type": "COMBO", + "widget": { + "name": "model" + }, + "link": null + }, + { + "name": "video", + "type": "VIDEO", + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [] + } + ], + "title": "Video Captioning(Gemini)", + "properties": { + "proxyWidgets": [ + [ + "-1", + "prompt" + ], + [ + "-1", + "model" + ], + [ + "1", + "seed" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.13.0" + }, + "widgets_values": [ + "Describe this video", + "gemini-2.5-pro" + ] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "dcf32045-0ee4-4efc-9aca-9f26f3a157be", + "version": 1, + "state": { + "lastGroupId": 1, + "lastNodeId": 16, + "lastLinkId": 17, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Video Captioning(Gemini)", + "inputNode": { + "id": -10, + "bounding": [ + -6870, + 2530, + 120, + 100 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + -6240, + 2530, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "d8cbd7eb-636a-4d7b-8ff6-b22f1755e26c", + "name": "prompt", + "type": "STRING", + "linkIds": [ + 15 + ], + "pos": [ + -6770, + 2550 + ] + }, + { + "id": "b034e26a-d114-4604-aec2-32783e86aa6b", + "name": "model", + "type": "COMBO", + "linkIds": [ + 16 + ], + "pos": [ + -6770, + 2570 + ] + }, + { + "id": "f7363f60-a106-4e06-90af-df5f53355b98", + "name": "video", + "type": "VIDEO", + "linkIds": [ + 17 + ], + "pos": [ + -6770, + 2590 + ] + } + ], + "outputs": [ + { + "id": "e12c6e80-5210-4328-a581-bc8924c53070", + "name": "STRING", + "type": "STRING", + "linkIds": [ + 6 + ], + "localized_name": "STRING", + "pos": [ + -6220, + 2550 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 1, + "type": "GeminiNode", + "pos": [ + -6690, + 2360 + ], + "size": [ + 390, + 430 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": null + }, + { + "localized_name": "video", + "name": "video", + "shape": 7, + "type": "VIDEO", + "link": 17 + }, + { + "localized_name": "files", + "name": "files", + "shape": 7, + "type": "GEMINI_INPUT_FILES", + "link": null + }, + { + "localized_name": "prompt", + "name": "prompt", + "type": "STRING", + "widget": { + "name": "prompt" + }, + "link": 15 + }, + { + "localized_name": "model", + "name": "model", + "type": "COMBO", + "widget": { + "name": "model" + }, + "link": 16 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "system_prompt", + "name": "system_prompt", + "shape": 7, + "type": "STRING", + "widget": { + "name": "system_prompt" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "STRING", + "name": "STRING", + "type": "STRING", + "links": [ + 6 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.5.1", + "Node name for S&R": "GeminiNode" + }, + "widgets_values": [ + "Describe this video", + "gemini-2.5-pro", + 511865409297955, + "randomize", + "- Role: AI Video Analysis and Description Specialist\n- Background: The user requires a prompt that enables AI to analyze videos (including frame sequences, dynamic movements, audio-visual elements) and generate detailed, structured descriptions. These descriptions must be directly usable as video generation prompts to create similar videos, serving core tasks such as video content creation, creative inspiration extraction, and artistic style exploration.\n- Profile: As an AI Video Analysis and Description Specialist, you possess expertise in computer vision, video temporal sequence processing, motion analysis, and multi-modal natural language generation. You excel at interpreting dynamic visual data (frame-by-frame features + continuous motion) and translating it into precise descriptive text that fully guides the creation of new videos with matching style, rhythm, and content.\n- Skills: Proficiency in video frame feature extraction, motion trajectory recognition, temporal rhythm analysis, scene/shot segmentation, color grading detection, camera movement identification (pan/tilt/zoom/dolly), audio-visual element correlation analysis, and descriptive language generation that captures both static visual features and dynamic temporal characteristics. Mastery of artistic elements in video: composition (per frame + dynamic framing), color palette (consistent + transitional), texture (surface details + motion blur), pacing (frame rate, shot duration), and sound style (background music, ambient sound cues).\n- Goals: To analyze the provided video comprehensively, generate a detailed, structured description that captures all key video elements (static visual features + dynamic motion/temporal characteristics + audio-visual style), and ensure this description can directly serve as a high-quality prompt for creating similar videos.\n- Constraints: \n 1. The description must be clear, structured, and specific enough to guide end-to-end video creation (including frame rate, shot duration, camera movement, motion speed, color transitions).\n 2. Avoid ambiguity; focus on the most salient static (per-frame) and dynamic (temporal) features of the video.\n 3. Prioritize video-specific elements: motion trajectory, shot types (close-up/wide shot/etc.), camera movement, frame rate, scene transitions, rhythm/pacing, and temporal color changes.\n 4. The output must only contain the video generation prompt (no extra explanations).\n- OutputFormat: A detailed, hierarchical text description of the video, structured as follows:\n 1. Core Content & Narrative: Brief overview of the video's subject and temporal progression\n 2. Visual Style (Static): Per-frame key elements (objects, colors, composition, lighting, texture)\n 3. Dynamic Elements (Temporal): Motion details (speed, trajectory, direction), camera movement (type, speed, direction), shot duration/frame rate, scene transitions\n 4. Audio-Visual Style: Color grading (consistent/transitional), rhythm/pacing, and implied audio style (if discernible)\n- Workflow:\n 1. Analyze the video to segment shots/scenes, identify frame-by-frame static visual elements (objects, colors, composition) and cross-frame dynamic elements (motion, camera movement, temporal changes).\n 2. Extract video-specific technical features: frame rate, shot duration, scene transition types, motion speed/rhythm.\n 3. Generate a structured, detailed description that captures the essence of the video (static + dynamic + temporal characteristics), ensuring specificity and actionability for video generation.\n 4. Refine the description for clarity, conciseness, and alignment with video generation prompt norms (e.g., including frame rate, camera movement terms, motion speed descriptors)." + ], + "color": "#432", + "bgcolor": "#653" + } + ], + "groups": [], + "links": [ + { + "id": 6, + "origin_id": 1, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "*" + }, + { + "id": 15, + "origin_id": -10, + "origin_slot": 0, + "target_id": 1, + "target_slot": 4, + "type": "STRING" + }, + { + "id": 16, + "origin_id": -10, + "origin_slot": 1, + "target_id": 1, + "target_slot": 5, + "type": "COMBO" + }, + { + "id": 17, + "origin_id": -10, + "origin_slot": 2, + "target_id": 1, + "target_slot": 2, + "type": "VIDEO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Text generation/Video Captioning" + } + ] + } +} diff --git a/blueprints/Video Inpaint(Wan2.1 VACE).json b/blueprints/Video Inpaint(Wan2.1 VACE).json index a7c6db003..f404e6773 100644 --- a/blueprints/Video Inpaint(Wan2.1 VACE).json +++ b/blueprints/Video Inpaint(Wan2.1 VACE).json @@ -1 +1,2387 @@ -{"id": "2f429c60-2e03-4117-908b-31e1fab04bba", "revision": 0, "last_node_id": 229, "last_link_id": 366, "nodes": [{"id": 229, "type": "53a657f3-c9eb-40f2-9ebd-1ed77d25ed67", "pos": [-230, 160], "size": [400, 480], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "video mask", "localized_name": "mask", "name": "mask", "type": "MASK", "link": null}, {"localized_name": "video", "name": "video", "type": "VIDEO", "link": null}, {"name": "width", "type": "INT", "widget": {"name": "width"}, "link": null}, {"name": "height", "type": "INT", "widget": {"name": "height"}, "link": null}, {"label": "reference image", "name": "reference_image_1", "type": "IMAGE", "link": null}, {"name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": null}, {"name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": null}, {"name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": null}, {"name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "properties": {"proxyWidgets": [["6", "text"], ["-1", "width"], ["-1", "height"], ["3", "seed"], ["3", "control_after_generate"], ["-1", "unet_name"], ["-1", "lora_name"], ["-1", "clip_name"], ["-1", "vae_name"]], "cnr_id": "comfy-core", "ver": "0.13.0"}, "widgets_values": [null, 720, 720, null, null, "wan2.1_vace_14B_fp16.safetensors", "Wan21_CausVid_14B_T2V_lora_rank32.safetensors", "umt5_xxl_fp8_e4m3fn_scaled.safetensors", "wan_2.1_vae.safetensors"]}], "links": [], "groups": [], "definitions": {"subgraphs": [{"id": "53a657f3-c9eb-40f2-9ebd-1ed77d25ed67", "version": 1, "state": {"lastGroupId": 25, "lastNodeId": 229, "lastLinkId": 366, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "local-Video Inpaint(Wan2.1 VACE)", "inputNode": {"id": -10, "bounding": [-970, 800, 132.54296875, 220]}, "outputNode": {"id": -20, "bounding": [1480, 535, 120, 60]}, "inputs": [{"id": "9fdda38d-6aa7-48ad-b425-f493d8aa585c", "name": "mask", "type": "MASK", "linkIds": [351, 335, 345], "localized_name": "mask", "label": "video mask", "pos": [-857.45703125, 820]}, {"id": "8b1788cc-46d2-4f40-8b33-70fd56b4cb24", "name": "video", "type": "VIDEO", "linkIds": [336], "localized_name": "video", "pos": [-857.45703125, 840]}, {"id": "09393f21-257e-4476-bb02-54899a8252b8", "name": "width", "type": "INT", "linkIds": [355], "pos": [-857.45703125, 860]}, {"id": "07a030f7-7eac-4b3f-b8f3-f00ee87b191d", "name": "height", "type": "INT", "linkIds": [356], "pos": [-857.45703125, 880]}, {"id": "255908d3-6cc9-48fc-b76b-ab9fb72695bc", "name": "reference_image_1", "type": "IMAGE", "linkIds": [361], "label": "reference image", "pos": [-857.45703125, 900]}, {"id": "18a5d241-523c-433d-ae05-25b6e69d1e29", "name": "unet_name", "type": "COMBO", "linkIds": [363], "pos": [-857.45703125, 920]}, {"id": "d7576e1b-da5f-402f-81b2-d37f838b1f8f", "name": "lora_name", "type": "COMBO", "linkIds": [364], "pos": [-857.45703125, 940]}, {"id": "41676a3e-c710-4723-821e-f651ad3784b1", "name": "clip_name", "type": "COMBO", "linkIds": [365], "pos": [-857.45703125, 960]}, {"id": "41fc878c-9aa6-4c12-bef3-ceda6b094b7c", "name": "vae_name", "type": "COMBO", "linkIds": [366], "pos": [-857.45703125, 980]}], "outputs": [{"id": "d4861f39-1011-49dc-80fd-ee318b614a8d", "name": "VIDEO", "type": "VIDEO", "linkIds": [129], "localized_name": "VIDEO", "pos": [1500, 555]}], "widgets": [], "nodes": [{"id": 58, "type": "TrimVideoLatent", "pos": [760, 390], "size": [315, 60], "flags": {"collapsed": false}, "order": 13, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 116}, {"localized_name": "trim_amount", "name": "trim_amount", "type": "INT", "widget": {"name": "trim_amount"}, "link": 115}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [117]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "TrimVideoLatent", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {"trim_amount": true}}, "widgets_values": [0]}, {"id": 8, "type": "VAEDecode", "pos": [770, 500], "size": [315, 46], "flags": {"collapsed": false}, "order": 11, "mode": 0, "inputs": [{"localized_name": "samples", "name": "samples", "type": "LATENT", "link": 117}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 76}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "slot_index": 0, "links": [139]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAEDecode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 48, "type": "ModelSamplingSD3", "pos": [400, 50], "size": [315, 58], "flags": {}, "order": 9, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 279}, {"localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": {"name": "shift"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [280]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "ModelSamplingSD3", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": [5]}, {"id": 219, "type": "InvertMask", "pos": [400, 990], "size": [140, 26], "flags": {}, "order": 24, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 351}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [352]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.40", "Node name for S&R": "InvertMask"}, "widgets_values": []}, {"id": 216, "type": "MaskToImage", "pos": [560, 990], "size": [193.2779296875, 26], "flags": {}, "order": 23, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 352}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [334]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.40", "Node name for S&R": "MaskToImage"}, "widgets_values": []}, {"id": 213, "type": "RebatchImages", "pos": [410, 690], "size": [230, 60], "flags": {}, "order": 21, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 360}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": 340}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "shape": 6, "type": "IMAGE", "links": [333]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.40", "Node name for S&R": "RebatchImages"}, "widgets_values": [1]}, {"id": 68, "type": "CreateVideo", "pos": [1150, 50], "size": [270, 78], "flags": {"collapsed": false}, "order": 14, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 139}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 362}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 353}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [129]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "CreateVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": [16]}, {"id": 208, "type": "ImageCompositeMasked", "pos": [410, 790], "size": [230, 146], "flags": {}, "order": 18, "mode": 0, "inputs": [{"localized_name": "destination", "name": "destination", "type": "IMAGE", "link": 333}, {"localized_name": "source", "name": "source", "type": "IMAGE", "link": 334}, {"localized_name": "mask", "name": "mask", "shape": 7, "type": "MASK", "link": 335}, {"localized_name": "x", "name": "x", "type": "INT", "widget": {"name": "x"}, "link": null}, {"localized_name": "y", "name": "y", "type": "INT", "widget": {"name": "y"}, "link": null}, {"localized_name": "resize_source", "name": "resize_source", "type": "BOOLEAN", "widget": {"name": "resize_source"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [341, 344]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.40", "Node name for S&R": "ImageCompositeMasked"}, "widgets_values": [0, 0, true]}, {"id": 214, "type": "PreviewImage", "pos": [760, 690], "size": [300, 300], "flags": {}, "order": 22, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 341}], "outputs": [], "properties": {"cnr_id": "comfy-core", "ver": "0.3.40", "Node name for S&R": "PreviewImage"}, "widgets_values": []}, {"id": 111, "type": "MaskToImage", "pos": [20, 1270], "size": [240, 26], "flags": {}, "order": 15, "mode": 0, "inputs": [{"localized_name": "mask", "name": "mask", "type": "MASK", "link": 345}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [201]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "MaskToImage", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": []}, {"id": 129, "type": "RepeatImageBatch", "pos": [20, 1160], "size": [240, 60], "flags": {}, "order": 16, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 201}, {"localized_name": "amount", "name": "amount", "type": "INT", "widget": {"name": "amount"}, "link": 346}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [202]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "RepeatImageBatch", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {"amount": true}}, "widgets_values": [17]}, {"id": 130, "type": "ImageToMask", "pos": [20, 1050], "size": [240, 60], "flags": {}, "order": 17, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 202}, {"localized_name": "channel", "name": "channel", "type": "COMBO", "widget": {"name": "channel"}, "link": null}], "outputs": [{"localized_name": "MASK", "name": "MASK", "type": "MASK", "links": [349]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "ImageToMask", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["red"]}, {"id": 3, "type": "KSampler", "pos": [770, 50], "size": [315, 262], "flags": {}, "order": 10, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 280}, {"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 98}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 99}, {"localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 160}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "steps", "name": "steps", "type": "INT", "widget": {"name": "steps"}, "link": null}, {"localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": {"name": "cfg"}, "link": null}, {"localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": {"name": "sampler_name"}, "link": null}, {"localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": {"name": "scheduler"}, "link": null}, {"localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": {"name": "denoise"}, "link": null}], "outputs": [{"localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "slot_index": 0, "links": [116]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "KSampler", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": [584027519362099, "randomize", 4, 1, "uni_pc", "simple", 1]}, {"id": 224, "type": "MarkdownNote", "pos": [420, -160], "size": [310, 110], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [], "title": "About Video Size", "properties": {}, "widgets_values": ["| Model | 480P | 720P |\n| ------------------------------------------------------------ | ---- | ---- |\n| [VACE-1.3B](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B) | ✅ | ❌ |\n| [VACE-14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B) | ✅ | ✅ |"], "color": "#432", "bgcolor": "#000"}, {"id": 223, "type": "MarkdownNote", "pos": [770, -210], "size": [303.90106201171875, 158.5415802001953], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [], "title": "KSampler Setting", "properties": {}, "widgets_values": ["## Default\n\n- steps:20\n- cfg:6.0\n\n## For CausVid LoRA\n\n- steps: 2-4\n- cfg: 1.0\n\n"], "color": "#432", "bgcolor": "#000"}, {"id": 6, "type": "CLIPTextEncode", "pos": [-80, 60], "size": [420, 280], "flags": {}, "order": 7, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 74}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [96]}], "title": "CLIP Text Encode (Positive Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": [""], "color": "#232", "bgcolor": "#353"}, {"id": 140, "type": "UNETLoader", "pos": [-505.8336486816406, 88.22794342041016], "size": [360, 82], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": {"name": "unet_name"}, "link": 363}, {"localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": {"name": "weight_dtype"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "slot_index": 0, "links": [248]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "UNETLoader", "models": [{"name": "wan2.1_vace_14B_fp16.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_vace_14B_fp16.safetensors", "directory": "diffusion_models"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["wan2.1_vace_14B_fp16.safetensors", "fp8_e4m3fn_fast"]}, {"id": 154, "type": "LoraLoaderModelOnly", "pos": [-505.8336486816406, 228.2279510498047], "size": [360, 85.11004638671875], "flags": {}, "order": 6, "mode": 0, "inputs": [{"localized_name": "model", "name": "model", "type": "MODEL", "link": 248}, {"localized_name": "lora_name", "name": "lora_name", "type": "COMBO", "widget": {"name": "lora_name"}, "link": 364}, {"localized_name": "strength_model", "name": "strength_model", "type": "FLOAT", "widget": {"name": "strength_model"}, "link": null}], "outputs": [{"localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [279]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "Wan21_CausVid_14B_T2V_lora_rank32.safetensors", "url": "https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Wan21_CausVid_14B_T2V_lora_rank32.safetensors", "directory": "loras"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["Wan21_CausVid_14B_T2V_lora_rank32.safetensors", 0.30000000000000004]}, {"id": 38, "type": "CLIPLoader", "pos": [-499.14141845703125, 368.0911865234375], "size": [360, 106], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": {"name": "clip_name"}, "link": 365}, {"localized_name": "type", "name": "type", "type": "COMBO", "widget": {"name": "type"}, "link": null}, {"localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": {"name": "device"}, "link": null}], "outputs": [{"localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "slot_index": 0, "links": [74, 75]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "CLIPLoader", "models": [{"name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors?download=true", "directory": "text_encoders"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["umt5_xxl_fp8_e4m3fn_scaled.safetensors", "wan", "default"]}, {"id": 39, "type": "VAELoader", "pos": [-498.5298156738281, 517.2576293945312], "size": [360, 60], "flags": {}, "order": 4, "mode": 0, "inputs": [{"localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": {"name": "vae_name"}, "link": 366}], "outputs": [{"localized_name": "VAE", "name": "VAE", "type": "VAE", "slot_index": 0, "links": [76, 101]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "VAELoader", "models": [{"name": "wan_2.1_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors", "directory": "vae"}], "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["wan_2.1_vae.safetensors"]}, {"id": 221, "type": "MarkdownNote", "pos": [380, 1090], "size": [480, 170], "flags": {}, "order": 5, "mode": 0, "inputs": [], "outputs": [], "title": "[EN] About video mask", "properties": {"widget_ue_connectable": {}}, "widgets_values": ["Currently, it's difficult to perfectly draw dynamic masks for different frames using only core nodes. However, to avoid requiring users to install additional custom nodes, our templates only use core nodes. You can refer to this implementation idea to achieve video inpainting.\n\nYou can use KJNode’s Points Editor and Sam2Segmentation to create some dynamic mask functions.\n\nCustom node links:\n- [ComfyUI-KJNodes](https://github.com/kijai/ComfyUI-KJNodes)\n- [ComfyUI-segment-anything-2](https://github.com/kijai/ComfyUI-segment-anything-2)"], "color": "#432", "bgcolor": "#000"}, {"id": 7, "type": "CLIPTextEncode", "pos": [-80, 390], "size": [425.27801513671875, 180.6060791015625], "flags": {}, "order": 8, "mode": 0, "inputs": [{"localized_name": "clip", "name": "clip", "type": "CLIP", "link": 75}, {"localized_name": "text", "name": "text", "type": "STRING", "widget": {"name": "text"}, "link": null}], "outputs": [{"localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "slot_index": 0, "links": [97]}], "title": "CLIP Text Encode (Negative Prompt)", "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "CLIPTextEncode", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {}}, "widgets_values": ["过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走,过曝，"], "color": "#223", "bgcolor": "#335"}, {"id": 229, "type": "ImageFromBatch", "pos": [-510, 800], "size": [270, 82], "flags": {}, "order": 25, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 358}, {"localized_name": "batch_index", "name": "batch_index", "type": "INT", "widget": {"name": "batch_index"}, "link": null}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": null}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [359, 360]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "ImageFromBatch"}, "widgets_values": [0, 81]}, {"id": 49, "type": "WanVaceToVideo", "pos": [400, 200], "size": [315, 254], "flags": {}, "order": 12, "mode": 0, "inputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 96}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 97}, {"localized_name": "vae", "name": "vae", "type": "VAE", "link": 101}, {"localized_name": "control_video", "name": "control_video", "shape": 7, "type": "IMAGE", "link": 344}, {"localized_name": "control_masks", "name": "control_masks", "shape": 7, "type": "MASK", "link": 349}, {"localized_name": "reference_image", "name": "reference_image", "shape": 7, "type": "IMAGE", "link": 361}, {"localized_name": "width", "name": "width", "type": "INT", "widget": {"name": "width"}, "link": 355}, {"localized_name": "height", "name": "height", "type": "INT", "widget": {"name": "height"}, "link": 356}, {"localized_name": "length", "name": "length", "type": "INT", "widget": {"name": "length"}, "link": null}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": {"name": "batch_size"}, "link": null}, {"localized_name": "strength", "name": "strength", "type": "FLOAT", "widget": {"name": "strength"}, "link": null}], "outputs": [{"localized_name": "positive", "name": "positive", "type": "CONDITIONING", "links": [98]}, {"localized_name": "negative", "name": "negative", "type": "CONDITIONING", "links": [99]}, {"localized_name": "latent", "name": "latent", "type": "LATENT", "links": [160]}, {"localized_name": "trim_latent", "name": "trim_latent", "type": "INT", "links": [115]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.34", "Node name for S&R": "WanVaceToVideo", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "widget_ue_connectable": {"width": true, "height": true, "length": true}}, "widgets_values": [720, 720, 81, 1, 1]}, {"id": 211, "type": "GetImageSize", "pos": [70, 800], "size": [190, 66], "flags": {"collapsed": false}, "order": 20, "mode": 0, "inputs": [{"localized_name": "image", "name": "image", "type": "IMAGE", "link": 359}], "outputs": [{"localized_name": "width", "name": "width", "type": "INT", "links": null}, {"localized_name": "height", "name": "height", "type": "INT", "links": null}, {"localized_name": "batch_size", "name": "batch_size", "type": "INT", "links": [340, 346]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.40", "Node name for S&R": "GetImageSize"}, "widgets_values": []}, {"id": 210, "type": "GetVideoComponents", "pos": [-510, 690], "size": [193.530859375, 66], "flags": {}, "order": 19, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": 336}], "outputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "links": [358]}, {"localized_name": "audio", "name": "audio", "type": "AUDIO", "links": [362]}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "links": [353]}], "properties": {"cnr_id": "comfy-core", "ver": "0.3.40", "Node name for S&R": "GetVideoComponents"}, "widgets_values": []}], "groups": [{"id": 1, "title": "Step1 - Load models here", "bounding": [-540, -30, 430, 620], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 2, "title": "Prompt", "bounding": [-90, -30, 450, 620], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 3, "title": "Sampling & Decoding", "bounding": [380, -30, 720, 620], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 10, "title": "Repeat Mask Batch", "bounding": [-90, 910, 450, 460], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 21, "title": "Get video info", "bounding": [-540, 610, 900, 290], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 22, "title": "Composite video & masks", "bounding": [380, 610, 720, 420], "color": "#3f789e", "font_size": 24, "flags": {}}, {"id": 23, "title": "Step4 - Set video size & length", "bounding": [390, 130, 360, 340], "color": "#A88", "font_size": 24, "flags": {}}, {"id": 25, "title": "14B", "bounding": [-520, 10, 380, 308.7100524902344], "color": "#3f789e", "font_size": 24, "flags": {}}], "links": [{"id": 116, "origin_id": 3, "origin_slot": 0, "target_id": 58, "target_slot": 0, "type": "LATENT"}, {"id": 115, "origin_id": 49, "origin_slot": 3, "target_id": 58, "target_slot": 1, "type": "INT"}, {"id": 117, "origin_id": 58, "origin_slot": 0, "target_id": 8, "target_slot": 0, "type": "LATENT"}, {"id": 76, "origin_id": 39, "origin_slot": 0, "target_id": 8, "target_slot": 1, "type": "VAE"}, {"id": 279, "origin_id": 154, "origin_slot": 0, "target_id": 48, "target_slot": 0, "type": "MODEL"}, {"id": 352, "origin_id": 219, "origin_slot": 0, "target_id": 216, "target_slot": 0, "type": "MASK"}, {"id": 340, "origin_id": 211, "origin_slot": 2, "target_id": 213, "target_slot": 1, "type": "INT"}, {"id": 96, "origin_id": 6, "origin_slot": 0, "target_id": 49, "target_slot": 0, "type": "CONDITIONING"}, {"id": 97, "origin_id": 7, "origin_slot": 0, "target_id": 49, "target_slot": 1, "type": "CONDITIONING"}, {"id": 101, "origin_id": 39, "origin_slot": 0, "target_id": 49, "target_slot": 2, "type": "VAE"}, {"id": 344, "origin_id": 208, "origin_slot": 0, "target_id": 49, "target_slot": 3, "type": "IMAGE"}, {"id": 349, "origin_id": 130, "origin_slot": 0, "target_id": 49, "target_slot": 4, "type": "MASK"}, {"id": 139, "origin_id": 8, "origin_slot": 0, "target_id": 68, "target_slot": 0, "type": "IMAGE"}, {"id": 353, "origin_id": 210, "origin_slot": 2, "target_id": 68, "target_slot": 2, "type": "FLOAT"}, {"id": 333, "origin_id": 213, "origin_slot": 0, "target_id": 208, "target_slot": 0, "type": "IMAGE"}, {"id": 334, "origin_id": 216, "origin_slot": 0, "target_id": 208, "target_slot": 1, "type": "IMAGE"}, {"id": 341, "origin_id": 208, "origin_slot": 0, "target_id": 214, "target_slot": 0, "type": "IMAGE"}, {"id": 201, "origin_id": 111, "origin_slot": 0, "target_id": 129, "target_slot": 0, "type": "IMAGE"}, {"id": 346, "origin_id": 211, "origin_slot": 2, "target_id": 129, "target_slot": 1, "type": "INT"}, {"id": 202, "origin_id": 129, "origin_slot": 0, "target_id": 130, "target_slot": 0, "type": "IMAGE"}, {"id": 280, "origin_id": 48, "origin_slot": 0, "target_id": 3, "target_slot": 0, "type": "MODEL"}, {"id": 98, "origin_id": 49, "origin_slot": 0, "target_id": 3, "target_slot": 1, "type": "CONDITIONING"}, {"id": 99, "origin_id": 49, "origin_slot": 1, "target_id": 3, "target_slot": 2, "type": "CONDITIONING"}, {"id": 160, "origin_id": 49, "origin_slot": 2, "target_id": 3, "target_slot": 3, "type": "LATENT"}, {"id": 74, "origin_id": 38, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "CLIP"}, {"id": 248, "origin_id": 140, "origin_slot": 0, "target_id": 154, "target_slot": 0, "type": "MODEL"}, {"id": 75, "origin_id": 38, "origin_slot": 0, "target_id": 7, "target_slot": 0, "type": "CLIP"}, {"id": 351, "origin_id": -10, "origin_slot": 0, "target_id": 219, "target_slot": 0, "type": "MASK"}, {"id": 335, "origin_id": -10, "origin_slot": 0, "target_id": 208, "target_slot": 2, "type": "MASK"}, {"id": 345, "origin_id": -10, "origin_slot": 0, "target_id": 111, "target_slot": 0, "type": "MASK"}, {"id": 336, "origin_id": -10, "origin_slot": 1, "target_id": 210, "target_slot": 0, "type": "VIDEO"}, {"id": 129, "origin_id": 68, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 355, "origin_id": -10, "origin_slot": 2, "target_id": 49, "target_slot": 6, "type": "INT"}, {"id": 356, "origin_id": -10, "origin_slot": 3, "target_id": 49, "target_slot": 7, "type": "INT"}, {"id": 358, "origin_id": 210, "origin_slot": 0, "target_id": 229, "target_slot": 0, "type": "IMAGE"}, {"id": 359, "origin_id": 229, "origin_slot": 0, "target_id": 211, "target_slot": 0, "type": "IMAGE"}, {"id": 360, "origin_id": 229, "origin_slot": 0, "target_id": 213, "target_slot": 0, "type": "IMAGE"}, {"id": 361, "origin_id": -10, "origin_slot": 4, "target_id": 49, "target_slot": 5, "type": "IMAGE"}, {"id": 362, "origin_id": 210, "origin_slot": 1, "target_id": 68, "target_slot": 1, "type": "AUDIO"}, {"id": 363, "origin_id": -10, "origin_slot": 5, "target_id": 140, "target_slot": 0, "type": "COMBO"}, {"id": 364, "origin_id": -10, "origin_slot": 6, "target_id": 154, "target_slot": 1, "type": "COMBO"}, {"id": 365, "origin_id": -10, "origin_slot": 7, "target_id": 38, "target_slot": 0, "type": "COMBO"}, {"id": 366, "origin_id": -10, "origin_slot": 8, "target_id": 39, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Inpaint video"}]}, "config": {}, "extra": {"workflowRendererVersion": "LG", "ds": {"scale": 0.8183828377358485, "offset": [1215.8643989712405, 178.87024992690183]}}, "version": 0.4} +{ + "id": "2f429c60-2e03-4117-908b-31e1fab04bba", + "revision": 0, + "last_node_id": 229, + "last_link_id": 366, + "nodes": [ + { + "id": 229, + "type": "53a657f3-c9eb-40f2-9ebd-1ed77d25ed67", + "pos": [ + -230, + 160 + ], + "size": [ + 400, + 480 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "video mask", + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": null + }, + { + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": null + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": null + }, + { + "label": "reference image", + "name": "reference_image_1", + "type": "IMAGE", + "link": null + }, + { + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": null + }, + { + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": null + }, + { + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": null + }, + { + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "6", + "text" + ], + [ + "-1", + "width" + ], + [ + "-1", + "height" + ], + [ + "3", + "seed" + ], + [ + "3", + "control_after_generate" + ], + [ + "-1", + "unet_name" + ], + [ + "-1", + "lora_name" + ], + [ + "-1", + "clip_name" + ], + [ + "-1", + "vae_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.13.0" + }, + "widgets_values": [ + null, + 720, + 720, + null, + null, + "wan2.1_vace_14B_fp16.safetensors", + "Wan21_CausVid_14B_T2V_lora_rank32.safetensors", + "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "wan_2.1_vae.safetensors" + ] + } + ], + "links": [], + "groups": [], + "definitions": { + "subgraphs": [ + { + "id": "53a657f3-c9eb-40f2-9ebd-1ed77d25ed67", + "version": 1, + "state": { + "lastGroupId": 25, + "lastNodeId": 229, + "lastLinkId": 366, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "local-Video Inpaint(Wan2.1 VACE)", + "inputNode": { + "id": -10, + "bounding": [ + -970, + 800, + 132.54296875, + 220 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1480, + 535, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "9fdda38d-6aa7-48ad-b425-f493d8aa585c", + "name": "mask", + "type": "MASK", + "linkIds": [ + 351, + 335, + 345 + ], + "localized_name": "mask", + "label": "video mask", + "pos": [ + -857.45703125, + 820 + ] + }, + { + "id": "8b1788cc-46d2-4f40-8b33-70fd56b4cb24", + "name": "video", + "type": "VIDEO", + "linkIds": [ + 336 + ], + "localized_name": "video", + "pos": [ + -857.45703125, + 840 + ] + }, + { + "id": "09393f21-257e-4476-bb02-54899a8252b8", + "name": "width", + "type": "INT", + "linkIds": [ + 355 + ], + "pos": [ + -857.45703125, + 860 + ] + }, + { + "id": "07a030f7-7eac-4b3f-b8f3-f00ee87b191d", + "name": "height", + "type": "INT", + "linkIds": [ + 356 + ], + "pos": [ + -857.45703125, + 880 + ] + }, + { + "id": "255908d3-6cc9-48fc-b76b-ab9fb72695bc", + "name": "reference_image_1", + "type": "IMAGE", + "linkIds": [ + 361 + ], + "label": "reference image", + "pos": [ + -857.45703125, + 900 + ] + }, + { + "id": "18a5d241-523c-433d-ae05-25b6e69d1e29", + "name": "unet_name", + "type": "COMBO", + "linkIds": [ + 363 + ], + "pos": [ + -857.45703125, + 920 + ] + }, + { + "id": "d7576e1b-da5f-402f-81b2-d37f838b1f8f", + "name": "lora_name", + "type": "COMBO", + "linkIds": [ + 364 + ], + "pos": [ + -857.45703125, + 940 + ] + }, + { + "id": "41676a3e-c710-4723-821e-f651ad3784b1", + "name": "clip_name", + "type": "COMBO", + "linkIds": [ + 365 + ], + "pos": [ + -857.45703125, + 960 + ] + }, + { + "id": "41fc878c-9aa6-4c12-bef3-ceda6b094b7c", + "name": "vae_name", + "type": "COMBO", + "linkIds": [ + 366 + ], + "pos": [ + -857.45703125, + 980 + ] + } + ], + "outputs": [ + { + "id": "d4861f39-1011-49dc-80fd-ee318b614a8d", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 129 + ], + "localized_name": "VIDEO", + "pos": [ + 1500, + 555 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 58, + "type": "TrimVideoLatent", + "pos": [ + 760, + 390 + ], + "size": [ + 315, + 60 + ], + "flags": { + "collapsed": false + }, + "order": 13, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 116 + }, + { + "localized_name": "trim_amount", + "name": "trim_amount", + "type": "INT", + "widget": { + "name": "trim_amount" + }, + "link": 115 + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "links": [ + 117 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "TrimVideoLatent", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": { + "trim_amount": true + } + }, + "widgets_values": [ + 0 + ] + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 770, + 500 + ], + "size": [ + 315, + 46 + ], + "flags": { + "collapsed": false + }, + "order": 11, + "mode": 0, + "inputs": [ + { + "localized_name": "samples", + "name": "samples", + "type": "LATENT", + "link": 117 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 76 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 139 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAEDecode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 48, + "type": "ModelSamplingSD3", + "pos": [ + 400, + 50 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 279 + }, + { + "localized_name": "shift", + "name": "shift", + "type": "FLOAT", + "widget": { + "name": "shift" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 280 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "ModelSamplingSD3", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + 5 + ] + }, + { + "id": 219, + "type": "InvertMask", + "pos": [ + 400, + 990 + ], + "size": [ + 140, + 26 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 351 + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 352 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "InvertMask" + }, + "widgets_values": [] + }, + { + "id": 216, + "type": "MaskToImage", + "pos": [ + 560, + 990 + ], + "size": [ + 193.2779296875, + 26 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 352 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 334 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "MaskToImage" + }, + "widgets_values": [] + }, + { + "id": 213, + "type": "RebatchImages", + "pos": [ + 410, + 690 + ], + "size": [ + 230, + 60 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 360 + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": 340 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "shape": 6, + "type": "IMAGE", + "links": [ + 333 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "RebatchImages" + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 68, + "type": "CreateVideo", + "pos": [ + 1150, + 50 + ], + "size": [ + 270, + 78 + ], + "flags": { + "collapsed": false + }, + "order": 14, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 139 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 362 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 353 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 129 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "CreateVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + 16 + ] + }, + { + "id": 208, + "type": "ImageCompositeMasked", + "pos": [ + 410, + 790 + ], + "size": [ + 230, + 146 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "localized_name": "destination", + "name": "destination", + "type": "IMAGE", + "link": 333 + }, + { + "localized_name": "source", + "name": "source", + "type": "IMAGE", + "link": 334 + }, + { + "localized_name": "mask", + "name": "mask", + "shape": 7, + "type": "MASK", + "link": 335 + }, + { + "localized_name": "x", + "name": "x", + "type": "INT", + "widget": { + "name": "x" + }, + "link": null + }, + { + "localized_name": "y", + "name": "y", + "type": "INT", + "widget": { + "name": "y" + }, + "link": null + }, + { + "localized_name": "resize_source", + "name": "resize_source", + "type": "BOOLEAN", + "widget": { + "name": "resize_source" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 341, + 344 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "ImageCompositeMasked" + }, + "widgets_values": [ + 0, + 0, + true + ] + }, + { + "id": 214, + "type": "PreviewImage", + "pos": [ + 760, + 690 + ], + "size": [ + 300, + 300 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 341 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "PreviewImage" + }, + "widgets_values": [] + }, + { + "id": 111, + "type": "MaskToImage", + "pos": [ + 20, + 1270 + ], + "size": [ + 240, + 26 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "localized_name": "mask", + "name": "mask", + "type": "MASK", + "link": 345 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 201 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "MaskToImage", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 129, + "type": "RepeatImageBatch", + "pos": [ + 20, + 1160 + ], + "size": [ + 240, + 60 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 201 + }, + { + "localized_name": "amount", + "name": "amount", + "type": "INT", + "widget": { + "name": "amount" + }, + "link": 346 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 202 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "RepeatImageBatch", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": { + "amount": true + } + }, + "widgets_values": [ + 17 + ] + }, + { + "id": 130, + "type": "ImageToMask", + "pos": [ + 20, + 1050 + ], + "size": [ + 240, + 60 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 202 + }, + { + "localized_name": "channel", + "name": "channel", + "type": "COMBO", + "widget": { + "name": "channel" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MASK", + "name": "MASK", + "type": "MASK", + "links": [ + 349 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "ImageToMask", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "red" + ] + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 770, + 50 + ], + "size": [ + 315, + 262 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 280 + }, + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 98 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 99 + }, + { + "localized_name": "latent_image", + "name": "latent_image", + "type": "LATENT", + "link": 160 + }, + { + "localized_name": "seed", + "name": "seed", + "type": "INT", + "widget": { + "name": "seed" + }, + "link": null + }, + { + "localized_name": "steps", + "name": "steps", + "type": "INT", + "widget": { + "name": "steps" + }, + "link": null + }, + { + "localized_name": "cfg", + "name": "cfg", + "type": "FLOAT", + "widget": { + "name": "cfg" + }, + "link": null + }, + { + "localized_name": "sampler_name", + "name": "sampler_name", + "type": "COMBO", + "widget": { + "name": "sampler_name" + }, + "link": null + }, + { + "localized_name": "scheduler", + "name": "scheduler", + "type": "COMBO", + "widget": { + "name": "scheduler" + }, + "link": null + }, + { + "localized_name": "denoise", + "name": "denoise", + "type": "FLOAT", + "widget": { + "name": "denoise" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "LATENT", + "name": "LATENT", + "type": "LATENT", + "slot_index": 0, + "links": [ + 116 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "KSampler", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + 584027519362099, + "randomize", + 4, + 1, + "uni_pc", + "simple", + 1 + ] + }, + { + "id": 224, + "type": "MarkdownNote", + "pos": [ + 420, + -160 + ], + "size": [ + 310, + 110 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "About Video Size", + "properties": {}, + "widgets_values": [ + "| Model | 480P | 720P |\n| ------------------------------------------------------------ | ---- | ---- |\n| [VACE-1.3B](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B) | ✅ | ❌ |\n| [VACE-14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B) | ✅ | ✅ |" + ], + "color": "#432", + "bgcolor": "#000" + }, + { + "id": 223, + "type": "MarkdownNote", + "pos": [ + 770, + -210 + ], + "size": [ + 303.90106201171875, + 158.5415802001953 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "KSampler Setting", + "properties": {}, + "widgets_values": [ + "## Default\n\n- steps:20\n- cfg:6.0\n\n## For CausVid LoRA\n\n- steps: 2-4\n- cfg: 1.0\n\n" + ], + "color": "#432", + "bgcolor": "#000" + }, + { + "id": 6, + "type": "CLIPTextEncode", + "pos": [ + -80, + 60 + ], + "size": [ + 420, + 280 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 74 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 96 + ] + } + ], + "title": "CLIP Text Encode (Positive Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "" + ], + "color": "#232", + "bgcolor": "#353" + }, + { + "id": 140, + "type": "UNETLoader", + "pos": [ + -505.8336486816406, + 88.22794342041016 + ], + "size": [ + 360, + 82 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "unet_name", + "name": "unet_name", + "type": "COMBO", + "widget": { + "name": "unet_name" + }, + "link": 363 + }, + { + "localized_name": "weight_dtype", + "name": "weight_dtype", + "type": "COMBO", + "widget": { + "name": "weight_dtype" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "slot_index": 0, + "links": [ + 248 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "UNETLoader", + "models": [ + { + "name": "wan2.1_vace_14B_fp16.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_vace_14B_fp16.safetensors", + "directory": "diffusion_models" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "wan2.1_vace_14B_fp16.safetensors", + "fp8_e4m3fn_fast" + ] + }, + { + "id": 154, + "type": "LoraLoaderModelOnly", + "pos": [ + -505.8336486816406, + 228.2279510498047 + ], + "size": [ + 360, + 85.11004638671875 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "localized_name": "model", + "name": "model", + "type": "MODEL", + "link": 248 + }, + { + "localized_name": "lora_name", + "name": "lora_name", + "type": "COMBO", + "widget": { + "name": "lora_name" + }, + "link": 364 + }, + { + "localized_name": "strength_model", + "name": "strength_model", + "type": "FLOAT", + "widget": { + "name": "strength_model" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "MODEL", + "name": "MODEL", + "type": "MODEL", + "links": [ + 279 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "LoraLoaderModelOnly", + "models": [ + { + "name": "Wan21_CausVid_14B_T2V_lora_rank32.safetensors", + "url": "https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Wan21_CausVid_14B_T2V_lora_rank32.safetensors", + "directory": "loras" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "Wan21_CausVid_14B_T2V_lora_rank32.safetensors", + 0.30000000000000004 + ] + }, + { + "id": 38, + "type": "CLIPLoader", + "pos": [ + -499.14141845703125, + 368.0911865234375 + ], + "size": [ + 360, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "clip_name", + "name": "clip_name", + "type": "COMBO", + "widget": { + "name": "clip_name" + }, + "link": 365 + }, + { + "localized_name": "type", + "name": "type", + "type": "COMBO", + "widget": { + "name": "type" + }, + "link": null + }, + { + "localized_name": "device", + "name": "device", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "device" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CLIP", + "name": "CLIP", + "type": "CLIP", + "slot_index": 0, + "links": [ + 74, + 75 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "CLIPLoader", + "models": [ + { + "name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors?download=true", + "directory": "text_encoders" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "umt5_xxl_fp8_e4m3fn_scaled.safetensors", + "wan", + "default" + ] + }, + { + "id": 39, + "type": "VAELoader", + "pos": [ + -498.5298156738281, + 517.2576293945312 + ], + "size": [ + 360, + 60 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "localized_name": "vae_name", + "name": "vae_name", + "type": "COMBO", + "widget": { + "name": "vae_name" + }, + "link": 366 + } + ], + "outputs": [ + { + "localized_name": "VAE", + "name": "VAE", + "type": "VAE", + "slot_index": 0, + "links": [ + 76, + 101 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "VAELoader", + "models": [ + { + "name": "wan_2.1_vae.safetensors", + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors", + "directory": "vae" + } + ], + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "wan_2.1_vae.safetensors" + ] + }, + { + "id": 221, + "type": "MarkdownNote", + "pos": [ + 380, + 1090 + ], + "size": [ + 480, + 170 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "[EN] About video mask", + "properties": { + "widget_ue_connectable": {} + }, + "widgets_values": [ + "Currently, it's difficult to perfectly draw dynamic masks for different frames using only core nodes. However, to avoid requiring users to install additional custom nodes, our templates only use core nodes. You can refer to this implementation idea to achieve video inpainting.\n\nYou can use KJNode’s Points Editor and Sam2Segmentation to create some dynamic mask functions.\n\nCustom node links:\n- [ComfyUI-KJNodes](https://github.com/kijai/ComfyUI-KJNodes)\n- [ComfyUI-segment-anything-2](https://github.com/kijai/ComfyUI-segment-anything-2)" + ], + "color": "#432", + "bgcolor": "#000" + }, + { + "id": 7, + "type": "CLIPTextEncode", + "pos": [ + -80, + 390 + ], + "size": [ + 425.27801513671875, + 180.6060791015625 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "localized_name": "clip", + "name": "clip", + "type": "CLIP", + "link": 75 + }, + { + "localized_name": "text", + "name": "text", + "type": "STRING", + "widget": { + "name": "text" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "CONDITIONING", + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 97 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "CLIPTextEncode", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": {} + }, + "widgets_values": [ + "过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走,过曝，" + ], + "color": "#223", + "bgcolor": "#335" + }, + { + "id": 229, + "type": "ImageFromBatch", + "pos": [ + -510, + 800 + ], + "size": [ + 270, + 82 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 358 + }, + { + "localized_name": "batch_index", + "name": "batch_index", + "type": "INT", + "widget": { + "name": "batch_index" + }, + "link": null + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 359, + 360 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "ImageFromBatch" + }, + "widgets_values": [ + 0, + 81 + ] + }, + { + "id": 49, + "type": "WanVaceToVideo", + "pos": [ + 400, + 200 + ], + "size": [ + 315, + 254 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "link": 96 + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "link": 97 + }, + { + "localized_name": "vae", + "name": "vae", + "type": "VAE", + "link": 101 + }, + { + "localized_name": "control_video", + "name": "control_video", + "shape": 7, + "type": "IMAGE", + "link": 344 + }, + { + "localized_name": "control_masks", + "name": "control_masks", + "shape": 7, + "type": "MASK", + "link": 349 + }, + { + "localized_name": "reference_image", + "name": "reference_image", + "shape": 7, + "type": "IMAGE", + "link": 361 + }, + { + "localized_name": "width", + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 355 + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 356 + }, + { + "localized_name": "length", + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": null + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "widget": { + "name": "batch_size" + }, + "link": null + }, + { + "localized_name": "strength", + "name": "strength", + "type": "FLOAT", + "widget": { + "name": "strength" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "positive", + "name": "positive", + "type": "CONDITIONING", + "links": [ + 98 + ] + }, + { + "localized_name": "negative", + "name": "negative", + "type": "CONDITIONING", + "links": [ + 99 + ] + }, + { + "localized_name": "latent", + "name": "latent", + "type": "LATENT", + "links": [ + 160 + ] + }, + { + "localized_name": "trim_latent", + "name": "trim_latent", + "type": "INT", + "links": [ + 115 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.34", + "Node name for S&R": "WanVaceToVideo", + "enableTabs": false, + "tabWidth": 65, + "tabXOffset": 10, + "hasSecondTab": false, + "secondTabText": "Send Back", + "secondTabOffset": 80, + "secondTabWidth": 65, + "widget_ue_connectable": { + "width": true, + "height": true, + "length": true + } + }, + "widgets_values": [ + 720, + 720, + 81, + 1, + 1 + ] + }, + { + "id": 211, + "type": "GetImageSize", + "pos": [ + 70, + 800 + ], + "size": [ + 190, + 66 + ], + "flags": { + "collapsed": false + }, + "order": 20, + "mode": 0, + "inputs": [ + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 359 + } + ], + "outputs": [ + { + "localized_name": "width", + "name": "width", + "type": "INT", + "links": null + }, + { + "localized_name": "height", + "name": "height", + "type": "INT", + "links": null + }, + { + "localized_name": "batch_size", + "name": "batch_size", + "type": "INT", + "links": [ + 340, + 346 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "GetImageSize" + }, + "widgets_values": [] + }, + { + "id": 210, + "type": "GetVideoComponents", + "pos": [ + -510, + 690 + ], + "size": [ + 193.530859375, + 66 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": 336 + } + ], + "outputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "links": [ + 358 + ] + }, + { + "localized_name": "audio", + "name": "audio", + "type": "AUDIO", + "links": [ + 362 + ] + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "links": [ + 353 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.40", + "Node name for S&R": "GetVideoComponents" + }, + "widgets_values": [] + } + ], + "groups": [ + { + "id": 1, + "title": "Step1 - Load models here", + "bounding": [ + -540, + -30, + 430, + 620 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Prompt", + "bounding": [ + -90, + -30, + 450, + 620 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "Sampling & Decoding", + "bounding": [ + 380, + -30, + 720, + 620 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 10, + "title": "Repeat Mask Batch", + "bounding": [ + -90, + 910, + 450, + 460 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 21, + "title": "Get video info", + "bounding": [ + -540, + 610, + 900, + 290 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 22, + "title": "Composite video & masks", + "bounding": [ + 380, + 610, + 720, + 420 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 23, + "title": "Step4 - Set video size & length", + "bounding": [ + 390, + 130, + 360, + 340 + ], + "color": "#A88", + "font_size": 24, + "flags": {} + }, + { + "id": 25, + "title": "14B", + "bounding": [ + -520, + 10, + 380, + 308.7100524902344 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "links": [ + { + "id": 116, + "origin_id": 3, + "origin_slot": 0, + "target_id": 58, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 115, + "origin_id": 49, + "origin_slot": 3, + "target_id": 58, + "target_slot": 1, + "type": "INT" + }, + { + "id": 117, + "origin_id": 58, + "origin_slot": 0, + "target_id": 8, + "target_slot": 0, + "type": "LATENT" + }, + { + "id": 76, + "origin_id": 39, + "origin_slot": 0, + "target_id": 8, + "target_slot": 1, + "type": "VAE" + }, + { + "id": 279, + "origin_id": 154, + "origin_slot": 0, + "target_id": 48, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 352, + "origin_id": 219, + "origin_slot": 0, + "target_id": 216, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 340, + "origin_id": 211, + "origin_slot": 2, + "target_id": 213, + "target_slot": 1, + "type": "INT" + }, + { + "id": 96, + "origin_id": 6, + "origin_slot": 0, + "target_id": 49, + "target_slot": 0, + "type": "CONDITIONING" + }, + { + "id": 97, + "origin_id": 7, + "origin_slot": 0, + "target_id": 49, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 101, + "origin_id": 39, + "origin_slot": 0, + "target_id": 49, + "target_slot": 2, + "type": "VAE" + }, + { + "id": 344, + "origin_id": 208, + "origin_slot": 0, + "target_id": 49, + "target_slot": 3, + "type": "IMAGE" + }, + { + "id": 349, + "origin_id": 130, + "origin_slot": 0, + "target_id": 49, + "target_slot": 4, + "type": "MASK" + }, + { + "id": 139, + "origin_id": 8, + "origin_slot": 0, + "target_id": 68, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 353, + "origin_id": 210, + "origin_slot": 2, + "target_id": 68, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 333, + "origin_id": 213, + "origin_slot": 0, + "target_id": 208, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 334, + "origin_id": 216, + "origin_slot": 0, + "target_id": 208, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 341, + "origin_id": 208, + "origin_slot": 0, + "target_id": 214, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 201, + "origin_id": 111, + "origin_slot": 0, + "target_id": 129, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 346, + "origin_id": 211, + "origin_slot": 2, + "target_id": 129, + "target_slot": 1, + "type": "INT" + }, + { + "id": 202, + "origin_id": 129, + "origin_slot": 0, + "target_id": 130, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 280, + "origin_id": 48, + "origin_slot": 0, + "target_id": 3, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 98, + "origin_id": 49, + "origin_slot": 0, + "target_id": 3, + "target_slot": 1, + "type": "CONDITIONING" + }, + { + "id": 99, + "origin_id": 49, + "origin_slot": 1, + "target_id": 3, + "target_slot": 2, + "type": "CONDITIONING" + }, + { + "id": 160, + "origin_id": 49, + "origin_slot": 2, + "target_id": 3, + "target_slot": 3, + "type": "LATENT" + }, + { + "id": 74, + "origin_id": 38, + "origin_slot": 0, + "target_id": 6, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 248, + "origin_id": 140, + "origin_slot": 0, + "target_id": 154, + "target_slot": 0, + "type": "MODEL" + }, + { + "id": 75, + "origin_id": 38, + "origin_slot": 0, + "target_id": 7, + "target_slot": 0, + "type": "CLIP" + }, + { + "id": 351, + "origin_id": -10, + "origin_slot": 0, + "target_id": 219, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 335, + "origin_id": -10, + "origin_slot": 0, + "target_id": 208, + "target_slot": 2, + "type": "MASK" + }, + { + "id": 345, + "origin_id": -10, + "origin_slot": 0, + "target_id": 111, + "target_slot": 0, + "type": "MASK" + }, + { + "id": 336, + "origin_id": -10, + "origin_slot": 1, + "target_id": 210, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 129, + "origin_id": 68, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 355, + "origin_id": -10, + "origin_slot": 2, + "target_id": 49, + "target_slot": 6, + "type": "INT" + }, + { + "id": 356, + "origin_id": -10, + "origin_slot": 3, + "target_id": 49, + "target_slot": 7, + "type": "INT" + }, + { + "id": 358, + "origin_id": 210, + "origin_slot": 0, + "target_id": 229, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 359, + "origin_id": 229, + "origin_slot": 0, + "target_id": 211, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 360, + "origin_id": 229, + "origin_slot": 0, + "target_id": 213, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 361, + "origin_id": -10, + "origin_slot": 4, + "target_id": 49, + "target_slot": 5, + "type": "IMAGE" + }, + { + "id": 362, + "origin_id": 210, + "origin_slot": 1, + "target_id": 68, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 363, + "origin_id": -10, + "origin_slot": 5, + "target_id": 140, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 364, + "origin_id": -10, + "origin_slot": 6, + "target_id": 154, + "target_slot": 1, + "type": "COMBO" + }, + { + "id": 365, + "origin_id": -10, + "origin_slot": 7, + "target_id": 38, + "target_slot": 0, + "type": "COMBO" + }, + { + "id": 366, + "origin_id": -10, + "origin_slot": 8, + "target_id": 39, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video generation and editing/Inpaint video" + } + ] + }, + "config": {}, + "extra": { + "workflowRendererVersion": "LG", + "ds": { + "scale": 0.8183828377358485, + "offset": [ + 1215.8643989712405, + 178.87024992690183 + ] + } + }, + "version": 0.4 +} diff --git a/blueprints/Video Stitch.json b/blueprints/Video Stitch.json index 11bcf6b7d..020896d78 100644 --- a/blueprints/Video Stitch.json +++ b/blueprints/Video Stitch.json @@ -1 +1,591 @@ -{"revision": 0, "last_node_id": 84, "last_link_id": 0, "nodes": [{"id": 84, "type": "8e8aa94a-647e-436d-8440-8ee4691864de", "pos": [-6100, 2620], "size": [290, 160], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "Before Video", "localized_name": "video", "name": "video", "type": "VIDEO", "link": null}, {"label": "After Video", "localized_name": "video_1", "name": "video_1", "type": "VIDEO", "link": null}, {"name": "direction", "type": "COMBO", "widget": {"name": "direction"}, "link": null}, {"name": "match_image_size", "type": "BOOLEAN", "widget": {"name": "match_image_size"}, "link": null}, {"name": "spacing_width", "type": "INT", "widget": {"name": "spacing_width"}, "link": null}, {"name": "spacing_color", "type": "COMBO", "widget": {"name": "spacing_color"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "properties": {"proxyWidgets": [["-1", "direction"], ["-1", "match_image_size"], ["-1", "spacing_width"], ["-1", "spacing_color"]], "cnr_id": "comfy-core", "ver": "0.13.0"}, "widgets_values": ["right", true, 0, "white"], "title": "Video Stitch"}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "8e8aa94a-647e-436d-8440-8ee4691864de", "version": 1, "state": {"lastGroupId": 1, "lastNodeId": 84, "lastLinkId": 262, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Video Stitch", "inputNode": {"id": -10, "bounding": [-6580, 2649, 143.55859375, 160]}, "outputNode": {"id": -20, "bounding": [-5720, 2659, 120, 60]}, "inputs": [{"id": "85555afe-c7a1-4f6e-b073-7c37f7bace7f", "name": "video", "type": "VIDEO", "linkIds": [253], "localized_name": "video", "label": "Before Video", "pos": [-6456.44140625, 2669]}, {"id": "022773ee-6b4f-4e3d-bead-68b3e75e2d20", "name": "video_1", "type": "VIDEO", "linkIds": [254], "localized_name": "video_1", "label": "After Video", "pos": [-6456.44140625, 2689]}, {"id": "7bcd7cbc-e918-472a-a0cf-2e0900545372", "name": "direction", "type": "COMBO", "linkIds": [259], "pos": [-6456.44140625, 2709]}, {"id": "9a00389d-c1c8-40d5-87fe-f41019b61fbc", "name": "match_image_size", "type": "BOOLEAN", "linkIds": [260], "pos": [-6456.44140625, 2729]}, {"id": "b95e0440-3ea8-4ae0-887e-12e75701042a", "name": "spacing_width", "type": "INT", "linkIds": [261], "pos": [-6456.44140625, 2749]}, {"id": "83ab9382-0a70-4169-b26a-66ab026b43c4", "name": "spacing_color", "type": "COMBO", "linkIds": [262], "pos": [-6456.44140625, 2769]}], "outputs": [{"id": "09707f43-7552-4a6e-bd23-d962d31801c2", "name": "VIDEO", "type": "VIDEO", "linkIds": [255], "localized_name": "VIDEO", "pos": [-5700, 2679]}], "widgets": [], "nodes": [{"id": 78, "type": "GetVideoComponents", "pos": [-6390, 2560], "size": [193.530859375, 66], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": 254}], "outputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "links": [249]}, {"localized_name": "audio", "name": "audio", "type": "AUDIO", "links": null}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "links": null}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "GetVideoComponents"}}, {"id": 77, "type": "GetVideoComponents", "pos": [-6390, 2420], "size": [193.530859375, 66], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": 253}], "outputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "links": [248]}, {"localized_name": "audio", "name": "audio", "type": "AUDIO", "links": [251]}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "links": [252]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "GetVideoComponents"}}, {"id": 79, "type": "ImageStitch", "pos": [-6390, 2700], "size": [270, 150], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "image1", "name": "image1", "type": "IMAGE", "link": 248}, {"localized_name": "image2", "name": "image2", "shape": 7, "type": "IMAGE", "link": 249}, {"localized_name": "direction", "name": "direction", "type": "COMBO", "widget": {"name": "direction"}, "link": 259}, {"localized_name": "match_image_size", "name": "match_image_size", "type": "BOOLEAN", "widget": {"name": "match_image_size"}, "link": 260}, {"localized_name": "spacing_width", "name": "spacing_width", "type": "INT", "widget": {"name": "spacing_width"}, "link": 261}, {"localized_name": "spacing_color", "name": "spacing_color", "type": "COMBO", "widget": {"name": "spacing_color"}, "link": 262}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [250]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "ImageStitch"}, "widgets_values": ["right", true, 0, "white"]}, {"id": 80, "type": "CreateVideo", "pos": [-6040, 2610], "size": [270, 78], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 250}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 251}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 252}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [255]}], "properties": {"cnr_id": "comfy-core", "ver": "0.13.0", "Node name for S&R": "CreateVideo"}, "widgets_values": [30]}], "groups": [], "links": [{"id": 248, "origin_id": 77, "origin_slot": 0, "target_id": 79, "target_slot": 0, "type": "IMAGE"}, {"id": 249, "origin_id": 78, "origin_slot": 0, "target_id": 79, "target_slot": 1, "type": "IMAGE"}, {"id": 250, "origin_id": 79, "origin_slot": 0, "target_id": 80, "target_slot": 0, "type": "IMAGE"}, {"id": 251, "origin_id": 77, "origin_slot": 1, "target_id": 80, "target_slot": 1, "type": "AUDIO"}, {"id": 252, "origin_id": 77, "origin_slot": 2, "target_id": 80, "target_slot": 2, "type": "FLOAT"}, {"id": 253, "origin_id": -10, "origin_slot": 0, "target_id": 77, "target_slot": 0, "type": "VIDEO"}, {"id": 254, "origin_id": -10, "origin_slot": 1, "target_id": 78, "target_slot": 0, "type": "VIDEO"}, {"id": 255, "origin_id": 80, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 259, "origin_id": -10, "origin_slot": 2, "target_id": 79, "target_slot": 2, "type": "COMBO"}, {"id": 260, "origin_id": -10, "origin_slot": 3, "target_id": 79, "target_slot": 3, "type": "BOOLEAN"}, {"id": 261, "origin_id": -10, "origin_slot": 4, "target_id": 79, "target_slot": 4, "type": "INT"}, {"id": 262, "origin_id": -10, "origin_slot": 5, "target_id": 79, "target_slot": 5, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video Tools/Stitch videos"}]}} +{ + "revision": 0, + "last_node_id": 84, + "last_link_id": 0, + "nodes": [ + { + "id": 84, + "type": "8e8aa94a-647e-436d-8440-8ee4691864de", + "pos": [ + -6100, + 2620 + ], + "size": [ + 290, + 160 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "label": "Before Video", + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": null + }, + { + "label": "After Video", + "localized_name": "video_1", + "name": "video_1", + "type": "VIDEO", + "link": null + }, + { + "name": "direction", + "type": "COMBO", + "widget": { + "name": "direction" + }, + "link": null + }, + { + "name": "match_image_size", + "type": "BOOLEAN", + "widget": { + "name": "match_image_size" + }, + "link": null + }, + { + "name": "spacing_width", + "type": "INT", + "widget": { + "name": "spacing_width" + }, + "link": null + }, + { + "name": "spacing_color", + "type": "COMBO", + "widget": { + "name": "spacing_color" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "properties": { + "proxyWidgets": [ + [ + "-1", + "direction" + ], + [ + "-1", + "match_image_size" + ], + [ + "-1", + "spacing_width" + ], + [ + "-1", + "spacing_color" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.13.0" + }, + "widgets_values": [ + "right", + true, + 0, + "white" + ], + "title": "Video Stitch" + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "8e8aa94a-647e-436d-8440-8ee4691864de", + "version": 1, + "state": { + "lastGroupId": 1, + "lastNodeId": 84, + "lastLinkId": 262, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Video Stitch", + "inputNode": { + "id": -10, + "bounding": [ + -6580, + 2649, + 143.55859375, + 160 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + -5720, + 2659, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "85555afe-c7a1-4f6e-b073-7c37f7bace7f", + "name": "video", + "type": "VIDEO", + "linkIds": [ + 253 + ], + "localized_name": "video", + "label": "Before Video", + "pos": [ + -6456.44140625, + 2669 + ] + }, + { + "id": "022773ee-6b4f-4e3d-bead-68b3e75e2d20", + "name": "video_1", + "type": "VIDEO", + "linkIds": [ + 254 + ], + "localized_name": "video_1", + "label": "After Video", + "pos": [ + -6456.44140625, + 2689 + ] + }, + { + "id": "7bcd7cbc-e918-472a-a0cf-2e0900545372", + "name": "direction", + "type": "COMBO", + "linkIds": [ + 259 + ], + "pos": [ + -6456.44140625, + 2709 + ] + }, + { + "id": "9a00389d-c1c8-40d5-87fe-f41019b61fbc", + "name": "match_image_size", + "type": "BOOLEAN", + "linkIds": [ + 260 + ], + "pos": [ + -6456.44140625, + 2729 + ] + }, + { + "id": "b95e0440-3ea8-4ae0-887e-12e75701042a", + "name": "spacing_width", + "type": "INT", + "linkIds": [ + 261 + ], + "pos": [ + -6456.44140625, + 2749 + ] + }, + { + "id": "83ab9382-0a70-4169-b26a-66ab026b43c4", + "name": "spacing_color", + "type": "COMBO", + "linkIds": [ + 262 + ], + "pos": [ + -6456.44140625, + 2769 + ] + } + ], + "outputs": [ + { + "id": "09707f43-7552-4a6e-bd23-d962d31801c2", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 255 + ], + "localized_name": "VIDEO", + "pos": [ + -5700, + 2679 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 78, + "type": "GetVideoComponents", + "pos": [ + -6390, + 2560 + ], + "size": [ + 193.530859375, + 66 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": 254 + } + ], + "outputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "links": [ + 249 + ] + }, + { + "localized_name": "audio", + "name": "audio", + "type": "AUDIO", + "links": null + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "GetVideoComponents" + } + }, + { + "id": 77, + "type": "GetVideoComponents", + "pos": [ + -6390, + 2420 + ], + "size": [ + 193.530859375, + 66 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": 253 + } + ], + "outputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "links": [ + 248 + ] + }, + { + "localized_name": "audio", + "name": "audio", + "type": "AUDIO", + "links": [ + 251 + ] + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "links": [ + 252 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "GetVideoComponents" + } + }, + { + "id": 79, + "type": "ImageStitch", + "pos": [ + -6390, + 2700 + ], + "size": [ + 270, + 150 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "image1", + "name": "image1", + "type": "IMAGE", + "link": 248 + }, + { + "localized_name": "image2", + "name": "image2", + "shape": 7, + "type": "IMAGE", + "link": 249 + }, + { + "localized_name": "direction", + "name": "direction", + "type": "COMBO", + "widget": { + "name": "direction" + }, + "link": 259 + }, + { + "localized_name": "match_image_size", + "name": "match_image_size", + "type": "BOOLEAN", + "widget": { + "name": "match_image_size" + }, + "link": 260 + }, + { + "localized_name": "spacing_width", + "name": "spacing_width", + "type": "INT", + "widget": { + "name": "spacing_width" + }, + "link": 261 + }, + { + "localized_name": "spacing_color", + "name": "spacing_color", + "type": "COMBO", + "widget": { + "name": "spacing_color" + }, + "link": 262 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 250 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "ImageStitch" + }, + "widgets_values": [ + "right", + true, + 0, + "white" + ] + }, + { + "id": 80, + "type": "CreateVideo", + "pos": [ + -6040, + 2610 + ], + "size": [ + 270, + 78 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 250 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 251 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 252 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 255 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.13.0", + "Node name for S&R": "CreateVideo" + }, + "widgets_values": [ + 30 + ] + } + ], + "groups": [], + "links": [ + { + "id": 248, + "origin_id": 77, + "origin_slot": 0, + "target_id": 79, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 249, + "origin_id": 78, + "origin_slot": 0, + "target_id": 79, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 250, + "origin_id": 79, + "origin_slot": 0, + "target_id": 80, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 251, + "origin_id": 77, + "origin_slot": 1, + "target_id": 80, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 252, + "origin_id": 77, + "origin_slot": 2, + "target_id": 80, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 253, + "origin_id": -10, + "origin_slot": 0, + "target_id": 77, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 254, + "origin_id": -10, + "origin_slot": 1, + "target_id": 78, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 255, + "origin_id": 80, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 259, + "origin_id": -10, + "origin_slot": 2, + "target_id": 79, + "target_slot": 2, + "type": "COMBO" + }, + { + "id": 260, + "origin_id": -10, + "origin_slot": 3, + "target_id": 79, + "target_slot": 3, + "type": "BOOLEAN" + }, + { + "id": 261, + "origin_id": -10, + "origin_slot": 4, + "target_id": 79, + "target_slot": 4, + "type": "INT" + }, + { + "id": 262, + "origin_id": -10, + "origin_slot": 5, + "target_id": 79, + "target_slot": 5, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video Tools/Stitch videos" + } + ] + } +} diff --git a/blueprints/Video Upscale(GAN x4).json b/blueprints/Video Upscale(GAN x4).json index e80b2e229..b61dc88d7 100644 --- a/blueprints/Video Upscale(GAN x4).json +++ b/blueprints/Video Upscale(GAN x4).json @@ -1 +1,420 @@ -{"revision": 0, "last_node_id": 13, "last_link_id": 0, "nodes": [{"id": 13, "type": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", "pos": [1120, 330], "size": [240, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": null}, {"name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "title": "Video Upscale(GAN x4)", "properties": {"proxyWidgets": [["-1", "model_name"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": ["RealESRGAN_x4plus.safetensors"]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 13, "lastLinkId": 19, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Video Upscale(GAN x4)", "inputNode": {"id": -10, "bounding": [550, 460, 120, 80]}, "outputNode": {"id": -20, "bounding": [1490, 460, 120, 60]}, "inputs": [{"id": "666d633e-93e7-42dc-8d11-2b7b99b0f2a6", "name": "video", "type": "VIDEO", "linkIds": [10], "localized_name": "video", "pos": [650, 480]}, {"id": "2e23a087-caa8-4d65-99e6-662761aa905a", "name": "model_name", "type": "COMBO", "linkIds": [19], "pos": [650, 500]}], "outputs": [{"id": "0c1768ea-3ec2-412f-9af6-8e0fa36dae70", "name": "VIDEO", "type": "VIDEO", "linkIds": [15], "localized_name": "VIDEO", "pos": [1510, 480]}], "widgets": [], "nodes": [{"id": 2, "type": "ImageUpscaleWithModel", "pos": [1110, 450], "size": [320, 46], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "upscale_model", "name": "upscale_model", "type": "UPSCALE_MODEL", "link": 1}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 14}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [13]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "ImageUpscaleWithModel"}}, {"id": 11, "type": "CreateVideo", "pos": [1110, 550], "size": [320, 78], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 13}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 16}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 12}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [15]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "CreateVideo"}, "widgets_values": [30]}, {"id": 10, "type": "GetVideoComponents", "pos": [1110, 330], "size": [320, 70], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": 10}], "outputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "links": [14]}, {"localized_name": "audio", "name": "audio", "type": "AUDIO", "links": [16]}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "links": [12]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "GetVideoComponents"}}, {"id": 1, "type": "UpscaleModelLoader", "pos": [750, 450], "size": [280, 60], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": 19}], "outputs": [{"localized_name": "UPSCALE_MODEL", "name": "UPSCALE_MODEL", "type": "UPSCALE_MODEL", "links": [1]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "UpscaleModelLoader", "models": [{"name": "RealESRGAN_x4plus.safetensors", "url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors", "directory": "upscale_models"}]}, "widgets_values": ["RealESRGAN_x4plus.safetensors"]}], "groups": [], "links": [{"id": 1, "origin_id": 1, "origin_slot": 0, "target_id": 2, "target_slot": 0, "type": "UPSCALE_MODEL"}, {"id": 14, "origin_id": 10, "origin_slot": 0, "target_id": 2, "target_slot": 1, "type": "IMAGE"}, {"id": 13, "origin_id": 2, "origin_slot": 0, "target_id": 11, "target_slot": 0, "type": "IMAGE"}, {"id": 16, "origin_id": 10, "origin_slot": 1, "target_id": 11, "target_slot": 1, "type": "AUDIO"}, {"id": 12, "origin_id": 10, "origin_slot": 2, "target_id": 11, "target_slot": 2, "type": "FLOAT"}, {"id": 10, "origin_id": -10, "origin_slot": 0, "target_id": 10, "target_slot": 0, "type": "VIDEO"}, {"id": 15, "origin_id": 11, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 19, "origin_id": -10, "origin_slot": 1, "target_id": 1, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Enhance video"}]}, "extra": {}} +{ + "revision": 0, + "last_node_id": 13, + "last_link_id": 0, + "nodes": [ + { + "id": 13, + "type": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", + "pos": [ + 1120, + 330 + ], + "size": [ + 240, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": null + }, + { + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": null + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [] + } + ], + "title": "Video Upscale(GAN x4)", + "properties": { + "proxyWidgets": [ + [ + "-1", + "model_name" + ] + ], + "cnr_id": "comfy-core", + "ver": "0.14.1" + }, + "widgets_values": [ + "RealESRGAN_x4plus.safetensors" + ] + } + ], + "links": [], + "version": 0.4, + "definitions": { + "subgraphs": [ + { + "id": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", + "version": 1, + "state": { + "lastGroupId": 0, + "lastNodeId": 13, + "lastLinkId": 19, + "lastRerouteId": 0 + }, + "revision": 0, + "config": {}, + "name": "Video Upscale(GAN x4)", + "inputNode": { + "id": -10, + "bounding": [ + 550, + 460, + 120, + 80 + ] + }, + "outputNode": { + "id": -20, + "bounding": [ + 1490, + 460, + 120, + 60 + ] + }, + "inputs": [ + { + "id": "666d633e-93e7-42dc-8d11-2b7b99b0f2a6", + "name": "video", + "type": "VIDEO", + "linkIds": [ + 10 + ], + "localized_name": "video", + "pos": [ + 650, + 480 + ] + }, + { + "id": "2e23a087-caa8-4d65-99e6-662761aa905a", + "name": "model_name", + "type": "COMBO", + "linkIds": [ + 19 + ], + "pos": [ + 650, + 500 + ] + } + ], + "outputs": [ + { + "id": "0c1768ea-3ec2-412f-9af6-8e0fa36dae70", + "name": "VIDEO", + "type": "VIDEO", + "linkIds": [ + 15 + ], + "localized_name": "VIDEO", + "pos": [ + 1510, + 480 + ] + } + ], + "widgets": [], + "nodes": [ + { + "id": 2, + "type": "ImageUpscaleWithModel", + "pos": [ + 1110, + 450 + ], + "size": [ + 320, + 46 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [ + { + "localized_name": "upscale_model", + "name": "upscale_model", + "type": "UPSCALE_MODEL", + "link": 1 + }, + { + "localized_name": "image", + "name": "image", + "type": "IMAGE", + "link": 14 + } + ], + "outputs": [ + { + "localized_name": "IMAGE", + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 13 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.10.0", + "Node name for S&R": "ImageUpscaleWithModel" + } + }, + { + "id": 11, + "type": "CreateVideo", + "pos": [ + 1110, + 550 + ], + "size": [ + 320, + 78 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "link": 13 + }, + { + "localized_name": "audio", + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 16 + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "widget": { + "name": "fps" + }, + "link": 12 + } + ], + "outputs": [ + { + "localized_name": "VIDEO", + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 15 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.10.0", + "Node name for S&R": "CreateVideo" + }, + "widgets_values": [ + 30 + ] + }, + { + "id": 10, + "type": "GetVideoComponents", + "pos": [ + 1110, + 330 + ], + "size": [ + 320, + 70 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [ + { + "localized_name": "video", + "name": "video", + "type": "VIDEO", + "link": 10 + } + ], + "outputs": [ + { + "localized_name": "images", + "name": "images", + "type": "IMAGE", + "links": [ + 14 + ] + }, + { + "localized_name": "audio", + "name": "audio", + "type": "AUDIO", + "links": [ + 16 + ] + }, + { + "localized_name": "fps", + "name": "fps", + "type": "FLOAT", + "links": [ + 12 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.10.0", + "Node name for S&R": "GetVideoComponents" + } + }, + { + "id": 1, + "type": "UpscaleModelLoader", + "pos": [ + 750, + 450 + ], + "size": [ + 280, + 60 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [ + { + "localized_name": "model_name", + "name": "model_name", + "type": "COMBO", + "widget": { + "name": "model_name" + }, + "link": 19 + } + ], + "outputs": [ + { + "localized_name": "UPSCALE_MODEL", + "name": "UPSCALE_MODEL", + "type": "UPSCALE_MODEL", + "links": [ + 1 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.10.0", + "Node name for S&R": "UpscaleModelLoader", + "models": [ + { + "name": "RealESRGAN_x4plus.safetensors", + "url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors", + "directory": "upscale_models" + } + ] + }, + "widgets_values": [ + "RealESRGAN_x4plus.safetensors" + ] + } + ], + "groups": [], + "links": [ + { + "id": 1, + "origin_id": 1, + "origin_slot": 0, + "target_id": 2, + "target_slot": 0, + "type": "UPSCALE_MODEL" + }, + { + "id": 14, + "origin_id": 10, + "origin_slot": 0, + "target_id": 2, + "target_slot": 1, + "type": "IMAGE" + }, + { + "id": 13, + "origin_id": 2, + "origin_slot": 0, + "target_id": 11, + "target_slot": 0, + "type": "IMAGE" + }, + { + "id": 16, + "origin_id": 10, + "origin_slot": 1, + "target_id": 11, + "target_slot": 1, + "type": "AUDIO" + }, + { + "id": 12, + "origin_id": 10, + "origin_slot": 2, + "target_id": 11, + "target_slot": 2, + "type": "FLOAT" + }, + { + "id": 10, + "origin_id": -10, + "origin_slot": 0, + "target_id": 10, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 15, + "origin_id": 11, + "origin_slot": 0, + "target_id": -20, + "target_slot": 0, + "type": "VIDEO" + }, + { + "id": 19, + "origin_id": -10, + "origin_slot": 1, + "target_id": 1, + "target_slot": 0, + "type": "COMBO" + } + ], + "extra": { + "workflowRendererVersion": "LG" + }, + "category": "Video generation and editing/Enhance video" + } + ] + }, + "extra": {} +} diff --git a/comfy/cli_args.py b/comfy/cli_args.py index dbaadf723..cef1a5e6b 100644 --- a/comfy/cli_args.py +++ b/comfy/cli_args.py @@ -90,7 +90,6 @@ parser.add_argument("--force-channels-last", action="store_true", help="Force ch parser.add_argument("--directml", type=int, nargs="?", metavar="DIRECTML_DEVICE", const=-1, help="Use torch-directml.") parser.add_argument("--oneapi-device-selector", type=str, default=None, metavar="SELECTOR_STRING", help="Sets the oneAPI device(s) this instance will use.") -parser.add_argument("--disable-ipex-optimize", action="store_true", help="Disables ipex.optimize default when loading models with Intel's Extension for Pytorch.") parser.add_argument("--supports-fp8-compute", action="store_true", help="ComfyUI will act like if the device supports fp8 compute.") class LatentPreviewMethod(enum.Enum): diff --git a/comfy/latent_formats.py b/comfy/latent_formats.py index 6a57bca1c..3dac5be18 100644 --- a/comfy/latent_formats.py +++ b/comfy/latent_formats.py @@ -224,6 +224,7 @@ class Flux2(LatentFormat): self.latent_rgb_factors_bias = [-0.0329, -0.0718, -0.0851] self.latent_rgb_factors_reshape = lambda t: t.reshape(t.shape[0], 32, 2, 2, t.shape[-2], t.shape[-1]).permute(0, 1, 4, 2, 5, 3).reshape(t.shape[0], 32, t.shape[-2] * 2, t.shape[-1] * 2) + self.taesd_decoder_name = "taef2_decoder" def process_in(self, latent): return latent @@ -783,3 +784,10 @@ class ZImagePixelSpace(ChromaRadiance): No VAE encoding/decoding — the model operates directly on RGB pixels. """ pass + +class CogVideoX(LatentFormat): + latent_channels = 16 + latent_dimensions = 3 + + def __init__(self): + self.scale_factor = 1.15258426 diff --git a/comfy/ldm/ace/ace_step15.py b/comfy/ldm/ace/ace_step15.py index 1d7dc59a8..2ca2d26c4 100644 --- a/comfy/ldm/ace/ace_step15.py +++ b/comfy/ldm/ace/ace_step15.py @@ -611,6 +611,7 @@ class AceStepDiTModel(nn.Module): intermediate_size, patch_size, audio_acoustic_hidden_dim, + condition_dim=None, layer_types=None, sliding_window=128, rms_norm_eps=1e-6, @@ -640,7 +641,7 @@ class AceStepDiTModel(nn.Module): self.time_embed = TimestepEmbedding(256, hidden_size, dtype=dtype, device=device, operations=operations) self.time_embed_r = TimestepEmbedding(256, hidden_size, dtype=dtype, device=device, operations=operations) - self.condition_embedder = Linear(hidden_size, hidden_size, dtype=dtype, device=device) + self.condition_embedder = Linear(condition_dim, hidden_size, dtype=dtype, device=device) if layer_types is None: layer_types = ["full_attention"] * num_layers @@ -1035,6 +1036,9 @@ class AceStepConditionGenerationModel(nn.Module): fsq_dim=2048, fsq_levels=[8, 8, 8, 5, 5, 5], fsq_input_num_quantizers=1, + encoder_hidden_size=2048, + encoder_intermediate_size=6144, + encoder_num_heads=16, audio_model=None, dtype=None, device=None, @@ -1054,24 +1058,24 @@ class AceStepConditionGenerationModel(nn.Module): self.decoder = AceStepDiTModel( in_channels, hidden_size, num_dit_layers, num_heads, num_kv_heads, head_dim, - intermediate_size, patch_size, audio_acoustic_hidden_dim, + intermediate_size, patch_size, audio_acoustic_hidden_dim, condition_dim=encoder_hidden_size, layer_types=layer_types, sliding_window=sliding_window, rms_norm_eps=rms_norm_eps, dtype=dtype, device=device, operations=operations ) self.encoder = AceStepConditionEncoder( - text_hidden_dim, timbre_hidden_dim, hidden_size, num_lyric_layers, num_timbre_layers, - num_heads, num_kv_heads, head_dim, intermediate_size, rms_norm_eps, + text_hidden_dim, timbre_hidden_dim, encoder_hidden_size, num_lyric_layers, num_timbre_layers, + encoder_num_heads, num_kv_heads, head_dim, encoder_intermediate_size, rms_norm_eps, dtype=dtype, device=device, operations=operations ) self.tokenizer = AceStepAudioTokenizer( - audio_acoustic_hidden_dim, hidden_size, pool_window_size, fsq_dim=fsq_dim, fsq_levels=fsq_levels, fsq_input_num_quantizers=fsq_input_num_quantizers, num_layers=num_tokenizer_layers, head_dim=head_dim, rms_norm_eps=rms_norm_eps, + audio_acoustic_hidden_dim, encoder_hidden_size, pool_window_size, fsq_dim=fsq_dim, fsq_levels=fsq_levels, fsq_input_num_quantizers=fsq_input_num_quantizers, num_layers=num_tokenizer_layers, head_dim=head_dim, rms_norm_eps=rms_norm_eps, dtype=dtype, device=device, operations=operations ) self.detokenizer = AudioTokenDetokenizer( - hidden_size, pool_window_size, audio_acoustic_hidden_dim, num_layers=2, head_dim=head_dim, + encoder_hidden_size, pool_window_size, audio_acoustic_hidden_dim, num_layers=2, head_dim=head_dim, dtype=dtype, device=device, operations=operations ) - self.null_condition_emb = nn.Parameter(torch.empty(1, 1, hidden_size, dtype=dtype, device=device)) + self.null_condition_emb = nn.Parameter(torch.empty(1, 1, encoder_hidden_size, dtype=dtype, device=device)) def prepare_condition( self, diff --git a/comfy/ldm/cogvideo/__init__.py b/comfy/ldm/cogvideo/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/comfy/ldm/cogvideo/model.py b/comfy/ldm/cogvideo/model.py new file mode 100644 index 000000000..fb475ed53 --- /dev/null +++ b/comfy/ldm/cogvideo/model.py @@ -0,0 +1,573 @@ +# CogVideoX 3D Transformer - ported to ComfyUI native ops +# Architecture reference: diffusers CogVideoXTransformer3DModel +# Style reference: comfy/ldm/wan/model.py + +import math +import torch +import torch.nn as nn +import torch.nn.functional as F + +from comfy.ldm.modules.attention import optimized_attention +import comfy.patcher_extension +import comfy.ldm.common_dit + + +def _get_1d_rotary_pos_embed(dim, pos, theta=10000.0): + """Returns (cos, sin) each with shape [seq_len, dim]. + + Frequencies are computed at dim//2 resolution then repeat_interleaved + to full dim, matching CogVideoX's interleaved (real, imag) pair format. + """ + freqs = 1.0 / (theta ** (torch.arange(0, dim, 2, dtype=torch.float32, device=pos.device) / dim)) + angles = torch.outer(pos.float(), freqs.float()) + cos = angles.cos().repeat_interleave(2, dim=-1).float() + sin = angles.sin().repeat_interleave(2, dim=-1).float() + return (cos, sin) + + +def apply_rotary_emb(x, freqs_cos_sin): + """Apply CogVideoX rotary embedding to query or key tensor. + + x: [B, heads, seq_len, head_dim] + freqs_cos_sin: (cos, sin) each [seq_len, head_dim//2] + + Uses interleaved pair rotation (same as diffusers CogVideoX/Flux). + head_dim is reshaped to (-1, 2) pairs, rotated, then flattened back. + """ + cos, sin = freqs_cos_sin + cos = cos[None, None, :, :].to(x.device) + sin = sin[None, None, :, :].to(x.device) + + # Interleaved pairs: [B, H, S, D] -> [B, H, S, D//2, 2] -> (real, imag) + x_real, x_imag = x.reshape(*x.shape[:-1], -1, 2).unbind(-1) + x_rotated = torch.stack([-x_imag, x_real], dim=-1).flatten(3) + + return (x.float() * cos + x_rotated.float() * sin).to(x.dtype) + + +def get_timestep_embedding(timesteps, dim, flip_sin_to_cos=True, downscale_freq_shift=0, scale=1, max_period=10000): + half = dim // 2 + freqs = torch.exp(-math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32, device=timesteps.device) / half) + args = timesteps[:, None].float() * freqs[None] * scale + embedding = torch.cat([torch.sin(args), torch.cos(args)], dim=-1) + if flip_sin_to_cos: + embedding = torch.cat([embedding[:, half:], embedding[:, :half]], dim=-1) + if dim % 2: + embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1) + return embedding + + +def get_3d_sincos_pos_embed(embed_dim, spatial_size, temporal_size, spatial_interpolation_scale=1.0, temporal_interpolation_scale=1.0, device=None): + if isinstance(spatial_size, int): + spatial_size = (spatial_size, spatial_size) + + grid_w = torch.arange(spatial_size[0], dtype=torch.float32, device=device) / spatial_interpolation_scale + grid_h = torch.arange(spatial_size[1], dtype=torch.float32, device=device) / spatial_interpolation_scale + grid_t = torch.arange(temporal_size, dtype=torch.float32, device=device) / temporal_interpolation_scale + + grid_t, grid_h, grid_w = torch.meshgrid(grid_t, grid_h, grid_w, indexing="ij") + + embed_dim_spatial = 2 * (embed_dim // 3) + embed_dim_temporal = embed_dim // 3 + + pos_embed_spatial = _get_2d_sincos_pos_embed(embed_dim_spatial, grid_h, grid_w, device=device) + pos_embed_temporal = _get_1d_sincos_pos_embed(embed_dim_temporal, grid_t[:, 0, 0], device=device) + + T, H, W = grid_t.shape + pos_embed_temporal = pos_embed_temporal.unsqueeze(1).unsqueeze(1).expand(-1, H, W, -1) + pos_embed = torch.cat([pos_embed_temporal, pos_embed_spatial], dim=-1) + + return pos_embed + + +def _get_2d_sincos_pos_embed(embed_dim, grid_h, grid_w, device=None): + T, H, W = grid_h.shape + half_dim = embed_dim // 2 + pos_h = _get_1d_sincos_pos_embed(half_dim, grid_h.reshape(-1), device=device).reshape(T, H, W, half_dim) + pos_w = _get_1d_sincos_pos_embed(half_dim, grid_w.reshape(-1), device=device).reshape(T, H, W, half_dim) + return torch.cat([pos_h, pos_w], dim=-1) + + +def _get_1d_sincos_pos_embed(embed_dim, pos, device=None): + half = embed_dim // 2 + freqs = torch.exp(-math.log(10000.0) * torch.arange(start=0, end=half, dtype=torch.float32, device=device) / half) + args = pos.float().reshape(-1)[:, None] * freqs[None] + embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1) + if embed_dim % 2: + embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1) + return embedding + + + +class CogVideoXPatchEmbed(nn.Module): + def __init__(self, patch_size=2, patch_size_t=None, in_channels=16, dim=1920, + text_dim=4096, bias=True, sample_width=90, sample_height=60, + sample_frames=49, temporal_compression_ratio=4, + max_text_seq_length=226, spatial_interpolation_scale=1.875, + temporal_interpolation_scale=1.0, use_positional_embeddings=True, + use_learned_positional_embeddings=True, + device=None, dtype=None, operations=None): + super().__init__() + self.patch_size = patch_size + self.patch_size_t = patch_size_t + self.dim = dim + self.sample_height = sample_height + self.sample_width = sample_width + self.sample_frames = sample_frames + self.temporal_compression_ratio = temporal_compression_ratio + self.max_text_seq_length = max_text_seq_length + self.spatial_interpolation_scale = spatial_interpolation_scale + self.temporal_interpolation_scale = temporal_interpolation_scale + self.use_positional_embeddings = use_positional_embeddings + self.use_learned_positional_embeddings = use_learned_positional_embeddings + + if patch_size_t is None: + self.proj = operations.Conv2d(in_channels, dim, kernel_size=patch_size, stride=patch_size, bias=bias, device=device, dtype=dtype) + else: + self.proj = operations.Linear(in_channels * patch_size * patch_size * patch_size_t, dim, device=device, dtype=dtype) + + self.text_proj = operations.Linear(text_dim, dim, device=device, dtype=dtype) + + if use_positional_embeddings or use_learned_positional_embeddings: + persistent = use_learned_positional_embeddings + pos_embedding = self._get_positional_embeddings(sample_height, sample_width, sample_frames) + self.register_buffer("pos_embedding", pos_embedding, persistent=persistent) + + def _get_positional_embeddings(self, sample_height, sample_width, sample_frames, device=None): + post_patch_height = sample_height // self.patch_size + post_patch_width = sample_width // self.patch_size + post_time_compression_frames = (sample_frames - 1) // self.temporal_compression_ratio + 1 + if self.patch_size_t is not None: + post_time_compression_frames = post_time_compression_frames // self.patch_size_t + num_patches = post_patch_height * post_patch_width * post_time_compression_frames + + pos_embedding = get_3d_sincos_pos_embed( + self.dim, + (post_patch_width, post_patch_height), + post_time_compression_frames, + self.spatial_interpolation_scale, + self.temporal_interpolation_scale, + device=device, + ) + pos_embedding = pos_embedding.reshape(-1, self.dim) + joint_pos_embedding = pos_embedding.new_zeros( + 1, self.max_text_seq_length + num_patches, self.dim, requires_grad=False + ) + joint_pos_embedding.data[:, self.max_text_seq_length:].copy_(pos_embedding) + return joint_pos_embedding + + def forward(self, text_embeds, image_embeds): + input_dtype = text_embeds.dtype + text_embeds = self.text_proj(text_embeds.to(self.text_proj.weight.dtype)).to(input_dtype) + batch_size, num_frames, channels, height, width = image_embeds.shape + + proj_dtype = self.proj.weight.dtype + if self.patch_size_t is None: + image_embeds = image_embeds.reshape(-1, channels, height, width) + image_embeds = self.proj(image_embeds.to(proj_dtype)).to(input_dtype) + image_embeds = image_embeds.view(batch_size, num_frames, *image_embeds.shape[1:]) + image_embeds = image_embeds.flatten(3).transpose(2, 3) + image_embeds = image_embeds.flatten(1, 2) + else: + p = self.patch_size + p_t = self.patch_size_t + image_embeds = image_embeds.permute(0, 1, 3, 4, 2) + image_embeds = image_embeds.reshape( + batch_size, num_frames // p_t, p_t, height // p, p, width // p, p, channels + ) + image_embeds = image_embeds.permute(0, 1, 3, 5, 7, 2, 4, 6).flatten(4, 7).flatten(1, 3) + image_embeds = self.proj(image_embeds.to(proj_dtype)).to(input_dtype) + + embeds = torch.cat([text_embeds, image_embeds], dim=1).contiguous() + + if self.use_positional_embeddings or self.use_learned_positional_embeddings: + text_seq_length = text_embeds.shape[1] + num_image_patches = image_embeds.shape[1] + + if self.use_learned_positional_embeddings: + image_pos = self.pos_embedding[ + :, self.max_text_seq_length:self.max_text_seq_length + num_image_patches + ].to(device=embeds.device, dtype=embeds.dtype) + else: + image_pos = get_3d_sincos_pos_embed( + self.dim, + (width // self.patch_size, height // self.patch_size), + num_image_patches // ((height // self.patch_size) * (width // self.patch_size)), + self.spatial_interpolation_scale, + self.temporal_interpolation_scale, + device=embeds.device, + ).reshape(1, num_image_patches, self.dim).to(dtype=embeds.dtype) + + # Build joint: zeros for text + sincos for image + joint_pos = torch.zeros(1, text_seq_length + num_image_patches, self.dim, device=embeds.device, dtype=embeds.dtype) + joint_pos[:, text_seq_length:] = image_pos + embeds = embeds + joint_pos + + return embeds + + +class CogVideoXLayerNormZero(nn.Module): + def __init__(self, time_dim, dim, elementwise_affine=True, eps=1e-5, bias=True, + device=None, dtype=None, operations=None): + super().__init__() + self.silu = nn.SiLU() + self.linear = operations.Linear(time_dim, 6 * dim, bias=bias, device=device, dtype=dtype) + self.norm = operations.LayerNorm(dim, eps=eps, elementwise_affine=elementwise_affine, device=device, dtype=dtype) + + def forward(self, hidden_states, encoder_hidden_states, temb): + shift, scale, gate, enc_shift, enc_scale, enc_gate = self.linear(self.silu(temb)).chunk(6, dim=1) + hidden_states = self.norm(hidden_states) * (1 + scale)[:, None, :] + shift[:, None, :] + encoder_hidden_states = self.norm(encoder_hidden_states) * (1 + enc_scale)[:, None, :] + enc_shift[:, None, :] + return hidden_states, encoder_hidden_states, gate[:, None, :], enc_gate[:, None, :] + + +class CogVideoXAdaLayerNorm(nn.Module): + def __init__(self, time_dim, dim, elementwise_affine=True, eps=1e-5, + device=None, dtype=None, operations=None): + super().__init__() + self.silu = nn.SiLU() + self.linear = operations.Linear(time_dim, 2 * dim, device=device, dtype=dtype) + self.norm = operations.LayerNorm(dim, eps=eps, elementwise_affine=elementwise_affine, device=device, dtype=dtype) + + def forward(self, x, temb): + temb = self.linear(self.silu(temb)) + shift, scale = temb.chunk(2, dim=1) + x = self.norm(x) * (1 + scale)[:, None, :] + shift[:, None, :] + return x + + +class CogVideoXBlock(nn.Module): + def __init__(self, dim, num_heads, head_dim, time_dim, + eps=1e-5, ff_inner_dim=None, ff_bias=True, + device=None, dtype=None, operations=None): + super().__init__() + self.dim = dim + self.num_heads = num_heads + self.head_dim = head_dim + + self.norm1 = CogVideoXLayerNormZero(time_dim, dim, eps=eps, device=device, dtype=dtype, operations=operations) + + # Self-attention (joint text + latent) + self.q = operations.Linear(dim, dim, bias=True, device=device, dtype=dtype) + self.k = operations.Linear(dim, dim, bias=True, device=device, dtype=dtype) + self.v = operations.Linear(dim, dim, bias=True, device=device, dtype=dtype) + self.norm_q = operations.LayerNorm(head_dim, eps=1e-6, elementwise_affine=True, device=device, dtype=dtype) + self.norm_k = operations.LayerNorm(head_dim, eps=1e-6, elementwise_affine=True, device=device, dtype=dtype) + self.attn_out = operations.Linear(dim, dim, bias=True, device=device, dtype=dtype) + + self.norm2 = CogVideoXLayerNormZero(time_dim, dim, eps=eps, device=device, dtype=dtype, operations=operations) + + # Feed-forward (GELU approximate) + inner_dim = ff_inner_dim or dim * 4 + self.ff_proj = operations.Linear(dim, inner_dim, bias=ff_bias, device=device, dtype=dtype) + self.ff_out = operations.Linear(inner_dim, dim, bias=ff_bias, device=device, dtype=dtype) + + def forward(self, hidden_states, encoder_hidden_states, temb, image_rotary_emb=None, transformer_options=None): + if transformer_options is None: + transformer_options = {} + text_seq_length = encoder_hidden_states.size(1) + + # Norm & modulate + norm_hidden, norm_encoder, gate_msa, enc_gate_msa = self.norm1(hidden_states, encoder_hidden_states, temb) + + # Joint self-attention + qkv_input = torch.cat([norm_encoder, norm_hidden], dim=1) + b, s, _ = qkv_input.shape + n, d = self.num_heads, self.head_dim + + q = self.q(qkv_input).view(b, s, n, d) + k = self.k(qkv_input).view(b, s, n, d) + v = self.v(qkv_input) + + q = self.norm_q(q).view(b, s, n, d) + k = self.norm_k(k).view(b, s, n, d) + + # Apply rotary embeddings to image tokens only (diffusers format: [B, heads, seq, head_dim]) + if image_rotary_emb is not None: + q_img = q[:, text_seq_length:].transpose(1, 2) # [B, heads, img_seq, head_dim] + k_img = k[:, text_seq_length:].transpose(1, 2) + q_img = apply_rotary_emb(q_img, image_rotary_emb) + k_img = apply_rotary_emb(k_img, image_rotary_emb) + q = torch.cat([q[:, :text_seq_length], q_img.transpose(1, 2)], dim=1) + k = torch.cat([k[:, :text_seq_length], k_img.transpose(1, 2)], dim=1) + + attn_out = optimized_attention( + q.reshape(b, s, n * d), + k.reshape(b, s, n * d), + v, + heads=self.num_heads, + transformer_options=transformer_options, + ) + + attn_out = self.attn_out(attn_out) + + attn_encoder, attn_hidden = attn_out.split([text_seq_length, s - text_seq_length], dim=1) + + hidden_states = hidden_states + gate_msa * attn_hidden + encoder_hidden_states = encoder_hidden_states + enc_gate_msa * attn_encoder + + # Norm & modulate for FF + norm_hidden, norm_encoder, gate_ff, enc_gate_ff = self.norm2(hidden_states, encoder_hidden_states, temb) + + # Feed-forward (GELU on concatenated text + latent) + ff_input = torch.cat([norm_encoder, norm_hidden], dim=1) + ff_output = self.ff_out(F.gelu(self.ff_proj(ff_input), approximate="tanh")) + + hidden_states = hidden_states + gate_ff * ff_output[:, text_seq_length:] + encoder_hidden_states = encoder_hidden_states + enc_gate_ff * ff_output[:, :text_seq_length] + + return hidden_states, encoder_hidden_states + + +class CogVideoXTransformer3DModel(nn.Module): + def __init__(self, + num_attention_heads=30, + attention_head_dim=64, + in_channels=16, + out_channels=16, + flip_sin_to_cos=True, + freq_shift=0, + time_embed_dim=512, + ofs_embed_dim=None, + text_embed_dim=4096, + num_layers=30, + dropout=0.0, + attention_bias=True, + sample_width=90, + sample_height=60, + sample_frames=49, + patch_size=2, + patch_size_t=None, + temporal_compression_ratio=4, + max_text_seq_length=226, + spatial_interpolation_scale=1.875, + temporal_interpolation_scale=1.0, + use_rotary_positional_embeddings=False, + use_learned_positional_embeddings=False, + patch_bias=True, + image_model=None, + device=None, + dtype=None, + operations=None, + ): + super().__init__() + self.dtype = dtype + dim = num_attention_heads * attention_head_dim + self.dim = dim + self.num_attention_heads = num_attention_heads + self.attention_head_dim = attention_head_dim + self.in_channels = in_channels + self.out_channels = out_channels + self.patch_size = patch_size + self.patch_size_t = patch_size_t + self.max_text_seq_length = max_text_seq_length + self.use_rotary_positional_embeddings = use_rotary_positional_embeddings + + # 1. Patch embedding + self.patch_embed = CogVideoXPatchEmbed( + patch_size=patch_size, + patch_size_t=patch_size_t, + in_channels=in_channels, + dim=dim, + text_dim=text_embed_dim, + bias=patch_bias, + sample_width=sample_width, + sample_height=sample_height, + sample_frames=sample_frames, + temporal_compression_ratio=temporal_compression_ratio, + max_text_seq_length=max_text_seq_length, + spatial_interpolation_scale=spatial_interpolation_scale, + temporal_interpolation_scale=temporal_interpolation_scale, + use_positional_embeddings=not use_rotary_positional_embeddings, + use_learned_positional_embeddings=use_learned_positional_embeddings, + device=device, dtype=torch.float32, operations=operations, + ) + + # 2. Time embedding + self.time_proj_dim = dim + self.time_proj_flip = flip_sin_to_cos + self.time_proj_shift = freq_shift + self.time_embedding_linear_1 = operations.Linear(dim, time_embed_dim, device=device, dtype=dtype) + self.time_embedding_act = nn.SiLU() + self.time_embedding_linear_2 = operations.Linear(time_embed_dim, time_embed_dim, device=device, dtype=dtype) + + # Optional OFS embedding (CogVideoX 1.5 I2V) + self.ofs_proj_dim = ofs_embed_dim + if ofs_embed_dim: + self.ofs_embedding_linear_1 = operations.Linear(ofs_embed_dim, ofs_embed_dim, device=device, dtype=dtype) + self.ofs_embedding_act = nn.SiLU() + self.ofs_embedding_linear_2 = operations.Linear(ofs_embed_dim, ofs_embed_dim, device=device, dtype=dtype) + else: + self.ofs_embedding_linear_1 = None + + # 3. Transformer blocks + self.blocks = nn.ModuleList([ + CogVideoXBlock( + dim=dim, + num_heads=num_attention_heads, + head_dim=attention_head_dim, + time_dim=time_embed_dim, + eps=1e-5, + device=device, dtype=dtype, operations=operations, + ) + for _ in range(num_layers) + ]) + + self.norm_final = operations.LayerNorm(dim, eps=1e-5, elementwise_affine=True, device=device, dtype=dtype) + + # 4. Output + self.norm_out = CogVideoXAdaLayerNorm( + time_dim=time_embed_dim, dim=dim, eps=1e-5, + device=device, dtype=dtype, operations=operations, + ) + + if patch_size_t is None: + output_dim = patch_size * patch_size * out_channels + else: + output_dim = patch_size * patch_size * patch_size_t * out_channels + + self.proj_out = operations.Linear(dim, output_dim, device=device, dtype=dtype) + + self.spatial_interpolation_scale = spatial_interpolation_scale + self.temporal_interpolation_scale = temporal_interpolation_scale + self.temporal_compression_ratio = temporal_compression_ratio + + def forward(self, x, timestep, context, ofs=None, transformer_options=None, **kwargs): + if transformer_options is None: + transformer_options = {} + return comfy.patcher_extension.WrapperExecutor.new_class_executor( + self._forward, + self, + comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options) + ).execute(x, timestep, context, ofs, transformer_options, **kwargs) + + def _forward(self, x, timestep, context, ofs=None, transformer_options=None, **kwargs): + if transformer_options is None: + transformer_options = {} + # ComfyUI passes [B, C, T, H, W] + batch_size, channels, t, h, w = x.shape + + # Pad to patch size (temporal + spatial), same pattern as WAN + p_t = self.patch_size_t if self.patch_size_t is not None else 1 + x = comfy.ldm.common_dit.pad_to_patch_size(x, (p_t, self.patch_size, self.patch_size)) + + # CogVideoX expects [B, T, C, H, W] + x = x.permute(0, 2, 1, 3, 4) + batch_size, num_frames, channels, height, width = x.shape + + # Time embedding + t_emb = get_timestep_embedding(timestep, self.time_proj_dim, self.time_proj_flip, self.time_proj_shift) + t_emb = t_emb.to(dtype=x.dtype) + emb = self.time_embedding_linear_2(self.time_embedding_act(self.time_embedding_linear_1(t_emb))) + + if self.ofs_embedding_linear_1 is not None and ofs is not None: + ofs_emb = get_timestep_embedding(ofs, self.ofs_proj_dim, self.time_proj_flip, self.time_proj_shift) + ofs_emb = ofs_emb.to(dtype=x.dtype) + ofs_emb = self.ofs_embedding_linear_2(self.ofs_embedding_act(self.ofs_embedding_linear_1(ofs_emb))) + emb = emb + ofs_emb + + # Patch embedding + hidden_states = self.patch_embed(context, x) + + text_seq_length = context.shape[1] + encoder_hidden_states = hidden_states[:, :text_seq_length] + hidden_states = hidden_states[:, text_seq_length:] + + # Rotary embeddings (if used) + image_rotary_emb = None + if self.use_rotary_positional_embeddings: + post_patch_height = height // self.patch_size + post_patch_width = width // self.patch_size + if self.patch_size_t is None: + post_time = num_frames + else: + post_time = num_frames // self.patch_size_t + image_rotary_emb = self._get_rotary_emb(post_patch_height, post_patch_width, post_time, device=x.device) + + # Transformer blocks + for i, block in enumerate(self.blocks): + hidden_states, encoder_hidden_states = block( + hidden_states=hidden_states, + encoder_hidden_states=encoder_hidden_states, + temb=emb, + image_rotary_emb=image_rotary_emb, + transformer_options=transformer_options, + ) + + hidden_states = self.norm_final(hidden_states) + + # Output projection + hidden_states = self.norm_out(hidden_states, temb=emb) + hidden_states = self.proj_out(hidden_states) + + # Unpatchify + p = self.patch_size + p_t = self.patch_size_t + + if p_t is None: + output = hidden_states.reshape(batch_size, num_frames, height // p, width // p, -1, p, p) + output = output.permute(0, 1, 4, 2, 5, 3, 6).flatten(5, 6).flatten(3, 4) + else: + output = hidden_states.reshape( + batch_size, (num_frames + p_t - 1) // p_t, height // p, width // p, -1, p_t, p, p + ) + output = output.permute(0, 1, 5, 4, 2, 6, 3, 7).flatten(6, 7).flatten(4, 5).flatten(1, 2) + + # Back to ComfyUI format [B, C, T, H, W] and crop padding + output = output.permute(0, 2, 1, 3, 4)[:, :, :t, :h, :w] + return output + + def _get_rotary_emb(self, h, w, t, device): + """Compute CogVideoX 3D rotary positional embeddings. + + For CogVideoX 1.5 (patch_size_t != None): uses "slice" mode — grid positions + are integer arange computed at max_size, then sliced to actual size. + For CogVideoX 1.0 (patch_size_t == None): uses "linspace" mode with crop coords + scaled by spatial_interpolation_scale. + """ + d = self.attention_head_dim + dim_t = d // 4 + dim_h = d // 8 * 3 + dim_w = d // 8 * 3 + + if self.patch_size_t is not None: + # CogVideoX 1.5: "slice" mode — positions are simple integer indices + # Compute at max(sample_size, actual_size) then slice to actual + base_h = self.patch_embed.sample_height // self.patch_size + base_w = self.patch_embed.sample_width // self.patch_size + max_h = max(base_h, h) + max_w = max(base_w, w) + + grid_h = torch.arange(max_h, device=device, dtype=torch.float32) + grid_w = torch.arange(max_w, device=device, dtype=torch.float32) + grid_t = torch.arange(t, device=device, dtype=torch.float32) + else: + # CogVideoX 1.0: "linspace" mode with interpolation scale + grid_h = torch.linspace(0, h - 1, h, device=device, dtype=torch.float32) * self.spatial_interpolation_scale + grid_w = torch.linspace(0, w - 1, w, device=device, dtype=torch.float32) * self.spatial_interpolation_scale + grid_t = torch.arange(t, device=device, dtype=torch.float32) + + freqs_t = _get_1d_rotary_pos_embed(dim_t, grid_t) + freqs_h = _get_1d_rotary_pos_embed(dim_h, grid_h) + freqs_w = _get_1d_rotary_pos_embed(dim_w, grid_w) + + t_cos, t_sin = freqs_t + h_cos, h_sin = freqs_h + w_cos, w_sin = freqs_w + + # Slice to actual size (for "slice" mode where grids may be larger) + t_cos, t_sin = t_cos[:t], t_sin[:t] + h_cos, h_sin = h_cos[:h], h_sin[:h] + w_cos, w_sin = w_cos[:w], w_sin[:w] + + # Broadcast and concatenate into [T*H*W, head_dim] + t_cos = t_cos[:, None, None, :].expand(-1, h, w, -1) + t_sin = t_sin[:, None, None, :].expand(-1, h, w, -1) + h_cos = h_cos[None, :, None, :].expand(t, -1, w, -1) + h_sin = h_sin[None, :, None, :].expand(t, -1, w, -1) + w_cos = w_cos[None, None, :, :].expand(t, h, -1, -1) + w_sin = w_sin[None, None, :, :].expand(t, h, -1, -1) + + cos = torch.cat([t_cos, h_cos, w_cos], dim=-1).reshape(t * h * w, -1) + sin = torch.cat([t_sin, h_sin, w_sin], dim=-1).reshape(t * h * w, -1) + return (cos, sin) diff --git a/comfy/ldm/cogvideo/vae.py b/comfy/ldm/cogvideo/vae.py new file mode 100644 index 000000000..d4e6f321e --- /dev/null +++ b/comfy/ldm/cogvideo/vae.py @@ -0,0 +1,566 @@ +# CogVideoX VAE - ported to ComfyUI native ops +# Architecture reference: diffusers AutoencoderKLCogVideoX +# Style reference: comfy/ldm/wan/vae.py + +import numpy as np + +import torch +import torch.nn as nn +import torch.nn.functional as F + +import comfy.ops +ops = comfy.ops.disable_weight_init + + +class CausalConv3d(nn.Module): + """Causal 3D convolution with temporal padding. + + Uses comfy.ops.Conv3d with autopad='causal_zero' fast path: when input has + a single temporal frame and no cache, the 3D conv weight is sliced to act + as a 2D conv, avoiding computation on zero-padded temporal dimensions. + """ + def __init__(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, pad_mode="constant"): + super().__init__() + if isinstance(kernel_size, int): + kernel_size = (kernel_size,) * 3 + + time_kernel, height_kernel, width_kernel = kernel_size + self.time_kernel_size = time_kernel + self.pad_mode = pad_mode + + height_pad = (height_kernel - 1) // 2 + width_pad = (width_kernel - 1) // 2 + self.time_causal_padding = (width_pad, width_pad, height_pad, height_pad, time_kernel - 1, 0) + + stride = stride if isinstance(stride, tuple) else (stride, 1, 1) + dilation = (dilation, 1, 1) + self.conv = ops.Conv3d( + in_channels, out_channels, kernel_size, + stride=stride, dilation=dilation, + padding=(0, height_pad, width_pad), + ) + + def forward(self, x, conv_cache=None): + if self.pad_mode == "replicate": + x = F.pad(x, self.time_causal_padding, mode="replicate") + conv_cache = None + else: + kernel_t = self.time_kernel_size + if kernel_t > 1: + if conv_cache is None and x.shape[2] == 1: + # Fast path: single frame, no cache. All temporal padding + # frames are copies of the input (replicate-style), so the + # 3D conv reduces to a 2D conv with summed temporal kernel. + w = comfy.ops.cast_to_input(self.conv.weight, x) + b = comfy.ops.cast_to_input(self.conv.bias, x) if self.conv.bias is not None else None + w2d = w.sum(dim=2, keepdim=True) + out = F.conv3d(x, w2d, b, + self.conv.stride, self.conv.padding, + self.conv.dilation, self.conv.groups) + return out, None + cached = [conv_cache] if conv_cache is not None else [x[:, :, :1]] * (kernel_t - 1) + x = torch.cat(cached + [x], dim=2) + conv_cache = x[:, :, -self.time_kernel_size + 1:].clone() if self.time_kernel_size > 1 else None + + out = self.conv(x) + return out, conv_cache + + +def _interpolate_zq(zq, target_size): + """Interpolate latent z to target (T, H, W), matching CogVideoX's first-frame-special handling.""" + t = target_size[0] + if t > 1 and t % 2 == 1: + z_first = F.interpolate(zq[:, :, :1], size=(1, target_size[1], target_size[2])) + z_rest = F.interpolate(zq[:, :, 1:], size=(t - 1, target_size[1], target_size[2])) + return torch.cat([z_first, z_rest], dim=2) + return F.interpolate(zq, size=target_size) + + +class SpatialNorm3D(nn.Module): + """Spatially conditioned normalization.""" + def __init__(self, f_channels, zq_channels, groups=32): + super().__init__() + self.norm_layer = ops.GroupNorm(num_channels=f_channels, num_groups=groups, eps=1e-6, affine=True) + self.conv_y = CausalConv3d(zq_channels, f_channels, kernel_size=1, stride=1) + self.conv_b = CausalConv3d(zq_channels, f_channels, kernel_size=1, stride=1) + + def forward(self, f, zq, conv_cache=None): + new_cache = {} + conv_cache = conv_cache or {} + + if zq.shape[-3:] != f.shape[-3:]: + zq = _interpolate_zq(zq, f.shape[-3:]) + + conv_y, new_cache["conv_y"] = self.conv_y(zq, conv_cache=conv_cache.get("conv_y")) + conv_b, new_cache["conv_b"] = self.conv_b(zq, conv_cache=conv_cache.get("conv_b")) + + return self.norm_layer(f) * conv_y + conv_b, new_cache + + +class ResnetBlock3D(nn.Module): + """3D ResNet block with optional spatial norm.""" + def __init__(self, in_channels, out_channels=None, temb_channels=512, groups=32, + eps=1e-6, act_fn="silu", spatial_norm_dim=None, pad_mode="first"): + super().__init__() + out_channels = out_channels or in_channels + self.in_channels = in_channels + self.out_channels = out_channels + self.spatial_norm_dim = spatial_norm_dim + + if act_fn == "silu": + self.nonlinearity = nn.SiLU() + elif act_fn == "swish": + self.nonlinearity = nn.SiLU() + else: + self.nonlinearity = nn.SiLU() + + if spatial_norm_dim is None: + self.norm1 = ops.GroupNorm(num_channels=in_channels, num_groups=groups, eps=eps) + self.norm2 = ops.GroupNorm(num_channels=out_channels, num_groups=groups, eps=eps) + else: + self.norm1 = SpatialNorm3D(in_channels, spatial_norm_dim, groups=groups) + self.norm2 = SpatialNorm3D(out_channels, spatial_norm_dim, groups=groups) + + self.conv1 = CausalConv3d(in_channels, out_channels, kernel_size=3, pad_mode=pad_mode) + + if temb_channels > 0: + self.temb_proj = ops.Linear(temb_channels, out_channels) + + self.conv2 = CausalConv3d(out_channels, out_channels, kernel_size=3, pad_mode=pad_mode) + + if in_channels != out_channels: + self.conv_shortcut = ops.Conv3d(in_channels, out_channels, kernel_size=1, stride=1, padding=0) + else: + self.conv_shortcut = None + + def forward(self, x, temb=None, zq=None, conv_cache=None): + new_cache = {} + conv_cache = conv_cache or {} + residual = x + + if zq is not None: + x, new_cache["norm1"] = self.norm1(x, zq, conv_cache=conv_cache.get("norm1")) + else: + x = self.norm1(x) + + x = self.nonlinearity(x) + x, new_cache["conv1"] = self.conv1(x, conv_cache=conv_cache.get("conv1")) + + if temb is not None and hasattr(self, "temb_proj"): + x = x + self.temb_proj(self.nonlinearity(temb))[:, :, None, None, None] + + if zq is not None: + x, new_cache["norm2"] = self.norm2(x, zq, conv_cache=conv_cache.get("norm2")) + else: + x = self.norm2(x) + + x = self.nonlinearity(x) + x, new_cache["conv2"] = self.conv2(x, conv_cache=conv_cache.get("conv2")) + + if self.conv_shortcut is not None: + residual = self.conv_shortcut(residual) + + return x + residual, new_cache + + +class Downsample3D(nn.Module): + """3D downsampling with optional temporal compression.""" + def __init__(self, in_channels, out_channels, kernel_size=3, stride=2, padding=0, compress_time=False): + super().__init__() + self.conv = ops.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding) + self.compress_time = compress_time + + def forward(self, x): + if self.compress_time: + b, c, t, h, w = x.shape + x = x.permute(0, 3, 4, 1, 2).reshape(b * h * w, c, t) + if t % 2 == 1: + x_first, x_rest = x[..., 0], x[..., 1:] + if x_rest.shape[-1] > 0: + x_rest = F.avg_pool1d(x_rest, kernel_size=2, stride=2) + x = torch.cat([x_first[..., None], x_rest], dim=-1) + x = x.reshape(b, h, w, c, x.shape[-1]).permute(0, 3, 4, 1, 2) + else: + x = F.avg_pool1d(x, kernel_size=2, stride=2) + x = x.reshape(b, h, w, c, x.shape[-1]).permute(0, 3, 4, 1, 2) + + pad = (0, 1, 0, 1) + x = F.pad(x, pad, mode="constant", value=0) + b, c, t, h, w = x.shape + x = x.permute(0, 2, 1, 3, 4).reshape(b * t, c, h, w) + x = self.conv(x) + x = x.reshape(b, t, x.shape[1], x.shape[2], x.shape[3]).permute(0, 2, 1, 3, 4) + return x + + +class Upsample3D(nn.Module): + """3D upsampling with optional temporal decompression.""" + def __init__(self, in_channels, out_channels, kernel_size=3, stride=1, padding=1, compress_time=False): + super().__init__() + self.conv = ops.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding) + self.compress_time = compress_time + + def forward(self, x): + if self.compress_time: + if x.shape[2] > 1 and x.shape[2] % 2 == 1: + x_first, x_rest = x[:, :, 0], x[:, :, 1:] + x_first = F.interpolate(x_first, scale_factor=2.0) + x_rest = F.interpolate(x_rest, scale_factor=2.0) + x = torch.cat([x_first[:, :, None, :, :], x_rest], dim=2) + elif x.shape[2] > 1: + x = F.interpolate(x, scale_factor=2.0) + else: + x = x.squeeze(2) + x = F.interpolate(x, scale_factor=2.0) + x = x[:, :, None, :, :] + else: + b, c, t, h, w = x.shape + x = x.permute(0, 2, 1, 3, 4).reshape(b * t, c, h, w) + x = F.interpolate(x, scale_factor=2.0) + x = x.reshape(b, t, c, *x.shape[2:]).permute(0, 2, 1, 3, 4) + + b, c, t, h, w = x.shape + x = x.permute(0, 2, 1, 3, 4).reshape(b * t, c, h, w) + x = self.conv(x) + x = x.reshape(b, t, *x.shape[1:]).permute(0, 2, 1, 3, 4) + return x + + +class DownBlock3D(nn.Module): + def __init__(self, in_channels, out_channels, temb_channels=0, num_layers=1, + eps=1e-6, act_fn="silu", groups=32, add_downsample=True, + compress_time=False, pad_mode="first"): + super().__init__() + self.resnets = nn.ModuleList([ + ResnetBlock3D( + in_channels=in_channels if i == 0 else out_channels, + out_channels=out_channels, + temb_channels=temb_channels, + groups=groups, eps=eps, act_fn=act_fn, pad_mode=pad_mode, + ) + for i in range(num_layers) + ]) + self.downsamplers = nn.ModuleList([Downsample3D(out_channels, out_channels, compress_time=compress_time)]) if add_downsample else None + + def forward(self, x, temb=None, zq=None, conv_cache=None): + new_cache = {} + conv_cache = conv_cache or {} + for i, resnet in enumerate(self.resnets): + x, new_cache[f"resnet_{i}"] = resnet(x, temb, zq, conv_cache=conv_cache.get(f"resnet_{i}")) + if self.downsamplers is not None: + for ds in self.downsamplers: + x = ds(x) + return x, new_cache + + +class MidBlock3D(nn.Module): + def __init__(self, in_channels, temb_channels=0, num_layers=1, + eps=1e-6, act_fn="silu", groups=32, spatial_norm_dim=None, pad_mode="first"): + super().__init__() + self.resnets = nn.ModuleList([ + ResnetBlock3D( + in_channels=in_channels, out_channels=in_channels, + temb_channels=temb_channels, groups=groups, eps=eps, + act_fn=act_fn, spatial_norm_dim=spatial_norm_dim, pad_mode=pad_mode, + ) + for _ in range(num_layers) + ]) + + def forward(self, x, temb=None, zq=None, conv_cache=None): + new_cache = {} + conv_cache = conv_cache or {} + for i, resnet in enumerate(self.resnets): + x, new_cache[f"resnet_{i}"] = resnet(x, temb, zq, conv_cache=conv_cache.get(f"resnet_{i}")) + return x, new_cache + + +class UpBlock3D(nn.Module): + def __init__(self, in_channels, out_channels, temb_channels=0, num_layers=1, + eps=1e-6, act_fn="silu", groups=32, spatial_norm_dim=16, + add_upsample=True, compress_time=False, pad_mode="first"): + super().__init__() + self.resnets = nn.ModuleList([ + ResnetBlock3D( + in_channels=in_channels if i == 0 else out_channels, + out_channels=out_channels, + temb_channels=temb_channels, groups=groups, eps=eps, + act_fn=act_fn, spatial_norm_dim=spatial_norm_dim, pad_mode=pad_mode, + ) + for i in range(num_layers) + ]) + self.upsamplers = nn.ModuleList([Upsample3D(out_channels, out_channels, compress_time=compress_time)]) if add_upsample else None + + def forward(self, x, temb=None, zq=None, conv_cache=None): + new_cache = {} + conv_cache = conv_cache or {} + for i, resnet in enumerate(self.resnets): + x, new_cache[f"resnet_{i}"] = resnet(x, temb, zq, conv_cache=conv_cache.get(f"resnet_{i}")) + if self.upsamplers is not None: + for us in self.upsamplers: + x = us(x) + return x, new_cache + + +class Encoder3D(nn.Module): + def __init__(self, in_channels=3, out_channels=16, + block_out_channels=(128, 256, 256, 512), + layers_per_block=3, act_fn="silu", + eps=1e-6, groups=32, pad_mode="first", + temporal_compression_ratio=4): + super().__init__() + temporal_compress_level = int(np.log2(temporal_compression_ratio)) + + self.conv_in = CausalConv3d(in_channels, block_out_channels[0], kernel_size=3, pad_mode=pad_mode) + + self.down_blocks = nn.ModuleList() + output_channel = block_out_channels[0] + for i in range(len(block_out_channels)): + input_channel = output_channel + output_channel = block_out_channels[i] + is_final = i == len(block_out_channels) - 1 + compress_time = i < temporal_compress_level + + self.down_blocks.append(DownBlock3D( + in_channels=input_channel, out_channels=output_channel, + temb_channels=0, num_layers=layers_per_block, + eps=eps, act_fn=act_fn, groups=groups, + add_downsample=not is_final, compress_time=compress_time, + )) + + self.mid_block = MidBlock3D( + in_channels=block_out_channels[-1], temb_channels=0, + num_layers=2, eps=eps, act_fn=act_fn, groups=groups, pad_mode=pad_mode, + ) + + self.norm_out = ops.GroupNorm(groups, block_out_channels[-1], eps=1e-6) + self.conv_act = nn.SiLU() + self.conv_out = CausalConv3d(block_out_channels[-1], 2 * out_channels, kernel_size=3, pad_mode=pad_mode) + + def forward(self, x, conv_cache=None): + new_cache = {} + conv_cache = conv_cache or {} + + x, new_cache["conv_in"] = self.conv_in(x, conv_cache=conv_cache.get("conv_in")) + + for i, block in enumerate(self.down_blocks): + key = f"down_block_{i}" + x, new_cache[key] = block(x, None, None, conv_cache.get(key)) + + x, new_cache["mid_block"] = self.mid_block(x, None, None, conv_cache=conv_cache.get("mid_block")) + + x = self.norm_out(x) + x = self.conv_act(x) + x, new_cache["conv_out"] = self.conv_out(x, conv_cache=conv_cache.get("conv_out")) + + return x, new_cache + + +class Decoder3D(nn.Module): + def __init__(self, in_channels=16, out_channels=3, + block_out_channels=(128, 256, 256, 512), + layers_per_block=3, act_fn="silu", + eps=1e-6, groups=32, pad_mode="first", + temporal_compression_ratio=4): + super().__init__() + reversed_channels = list(reversed(block_out_channels)) + temporal_compress_level = int(np.log2(temporal_compression_ratio)) + + self.conv_in = CausalConv3d(in_channels, reversed_channels[0], kernel_size=3, pad_mode=pad_mode) + + self.mid_block = MidBlock3D( + in_channels=reversed_channels[0], temb_channels=0, + num_layers=2, eps=eps, act_fn=act_fn, groups=groups, + spatial_norm_dim=in_channels, pad_mode=pad_mode, + ) + + self.up_blocks = nn.ModuleList() + output_channel = reversed_channels[0] + for i in range(len(block_out_channels)): + prev_channel = output_channel + output_channel = reversed_channels[i] + is_final = i == len(block_out_channels) - 1 + compress_time = i < temporal_compress_level + + self.up_blocks.append(UpBlock3D( + in_channels=prev_channel, out_channels=output_channel, + temb_channels=0, num_layers=layers_per_block + 1, + eps=eps, act_fn=act_fn, groups=groups, + spatial_norm_dim=in_channels, + add_upsample=not is_final, compress_time=compress_time, + )) + + self.norm_out = SpatialNorm3D(reversed_channels[-1], in_channels, groups=groups) + self.conv_act = nn.SiLU() + self.conv_out = CausalConv3d(reversed_channels[-1], out_channels, kernel_size=3, pad_mode=pad_mode) + + def forward(self, sample, conv_cache=None): + new_cache = {} + conv_cache = conv_cache or {} + + x, new_cache["conv_in"] = self.conv_in(sample, conv_cache=conv_cache.get("conv_in")) + + x, new_cache["mid_block"] = self.mid_block(x, None, sample, conv_cache=conv_cache.get("mid_block")) + + for i, block in enumerate(self.up_blocks): + key = f"up_block_{i}" + x, new_cache[key] = block(x, None, sample, conv_cache=conv_cache.get(key)) + + x, new_cache["norm_out"] = self.norm_out(x, sample, conv_cache=conv_cache.get("norm_out")) + x = self.conv_act(x) + x, new_cache["conv_out"] = self.conv_out(x, conv_cache=conv_cache.get("conv_out")) + + return x, new_cache + + + +class AutoencoderKLCogVideoX(nn.Module): + """CogVideoX VAE. Spatial tiling/slicing handled by ComfyUI's VAE wrapper. + + Uses rolling temporal decode: conv_in + mid_block + temporal up_blocks run + on the full (low-res) tensor, then the expensive spatial-only up_blocks + + norm_out + conv_out are processed in small temporal chunks with conv_cache + carrying causal state between chunks. This keeps peak VRAM proportional to + chunk_size rather than total frame count. + """ + + def __init__(self, + in_channels=3, out_channels=3, + block_out_channels=(128, 256, 256, 512), + latent_channels=16, layers_per_block=3, + act_fn="silu", eps=1e-6, groups=32, + temporal_compression_ratio=4, + ): + super().__init__() + self.latent_channels = latent_channels + self.temporal_compression_ratio = temporal_compression_ratio + + self.encoder = Encoder3D( + in_channels=in_channels, out_channels=latent_channels, + block_out_channels=block_out_channels, layers_per_block=layers_per_block, + act_fn=act_fn, eps=eps, groups=groups, + temporal_compression_ratio=temporal_compression_ratio, + ) + self.decoder = Decoder3D( + in_channels=latent_channels, out_channels=out_channels, + block_out_channels=block_out_channels, layers_per_block=layers_per_block, + act_fn=act_fn, eps=eps, groups=groups, + temporal_compression_ratio=temporal_compression_ratio, + ) + + self.num_latent_frames_batch_size = 2 + self.num_sample_frames_batch_size = 8 + + def encode(self, x): + t = x.shape[2] + frame_batch = self.num_sample_frames_batch_size + remainder = t % frame_batch + conv_cache = None + enc = [] + + # Process remainder frames first so only the first chunk can have an + # odd temporal dimension — where Downsample3D's first-frame-special + # handling in temporal compression is actually correct. + if remainder > 0: + chunk, conv_cache = self.encoder(x[:, :, :remainder], conv_cache=conv_cache) + enc.append(chunk.to(x.device)) + + for start in range(remainder, t, frame_batch): + chunk, conv_cache = self.encoder(x[:, :, start:start + frame_batch], conv_cache=conv_cache) + enc.append(chunk.to(x.device)) + + enc = torch.cat(enc, dim=2) + mean, _ = enc.chunk(2, dim=1) + return mean + + def decode(self, z): + return self._decode_rolling(z) + + def _decode_batched(self, z): + """Original batched decode - processes 2 latent frames through full decoder.""" + t = z.shape[2] + frame_batch = self.num_latent_frames_batch_size + num_batches = max(t // frame_batch, 1) + conv_cache = None + dec = [] + for i in range(num_batches): + remaining = t % frame_batch + start = frame_batch * i + (0 if i == 0 else remaining) + end = frame_batch * (i + 1) + remaining + chunk, conv_cache = self.decoder(z[:, :, start:end], conv_cache=conv_cache) + dec.append(chunk.cpu()) + return torch.cat(dec, dim=2).to(z.device) + + def _decode_rolling(self, z): + """Rolling decode - processes low-res layers on full tensor, then rolls + through expensive high-res layers in temporal chunks.""" + decoder = self.decoder + device = z.device + + # Determine which up_blocks have temporal upsample vs spatial-only. + # Temporal up_blocks are cheap (low res), spatial-only are expensive. + temporal_compress_level = int(np.log2(self.temporal_compression_ratio)) + split_at = temporal_compress_level # first N up_blocks do temporal upsample + + # Phase 1: conv_in + mid_block + temporal up_blocks on full tensor (low/medium res) + x, _ = decoder.conv_in(z) + x, _ = decoder.mid_block(x, None, z) + + for i in range(split_at): + x, _ = decoder.up_blocks[i](x, None, z) + + # Phase 2: remaining spatial-only up_blocks + norm_out + conv_out in temporal chunks + remaining_blocks = list(range(split_at, len(decoder.up_blocks))) + chunk_size = 4 # pixel frames per chunk through high-res layers + t_expanded = x.shape[2] + + if t_expanded <= chunk_size or len(remaining_blocks) == 0: + # Small enough to process in one go + for i in remaining_blocks: + x, _ = decoder.up_blocks[i](x, None, z) + x, _ = decoder.norm_out(x, z) + x = decoder.conv_act(x) + x, _ = decoder.conv_out(x) + return x + + # Expand z temporally once to match Phase 2's time dimension. + # z stays at latent spatial resolution so this is small (~16 MB vs ~1.3 GB + # for the old approach of pre-interpolating to every pixel resolution). + z_time_expanded = _interpolate_zq(z, (t_expanded, z.shape[3], z.shape[4])) + + # Process in temporal chunks, interpolating spatially per-chunk to avoid + # allocating full [B, C, t_expanded, H, W] tensors at each resolution. + dec_out = [] + conv_caches = {} + + for chunk_start in range(0, t_expanded, chunk_size): + chunk_end = min(chunk_start + chunk_size, t_expanded) + x_chunk = x[:, :, chunk_start:chunk_end] + z_t_chunk = z_time_expanded[:, :, chunk_start:chunk_end] + z_spatial_cache = {} + + for i in remaining_blocks: + block = decoder.up_blocks[i] + cache_key = f"up_block_{i}" + hw_key = (x_chunk.shape[3], x_chunk.shape[4]) + if hw_key not in z_spatial_cache: + if z_t_chunk.shape[3] == hw_key[0] and z_t_chunk.shape[4] == hw_key[1]: + z_spatial_cache[hw_key] = z_t_chunk + else: + z_spatial_cache[hw_key] = F.interpolate(z_t_chunk, size=(z_t_chunk.shape[2], hw_key[0], hw_key[1])) + x_chunk, new_cache = block(x_chunk, None, z_spatial_cache[hw_key], conv_cache=conv_caches.get(cache_key)) + conv_caches[cache_key] = new_cache + + hw_key = (x_chunk.shape[3], x_chunk.shape[4]) + if hw_key not in z_spatial_cache: + z_spatial_cache[hw_key] = F.interpolate(z_t_chunk, size=(z_t_chunk.shape[2], hw_key[0], hw_key[1])) + x_chunk, new_cache = decoder.norm_out(x_chunk, z_spatial_cache[hw_key], conv_cache=conv_caches.get("norm_out")) + conv_caches["norm_out"] = new_cache + x_chunk = decoder.conv_act(x_chunk) + x_chunk, new_cache = decoder.conv_out(x_chunk, conv_cache=conv_caches.get("conv_out")) + conv_caches["conv_out"] = new_cache + + dec_out.append(x_chunk.cpu()) + del z_spatial_cache + + del x, z_time_expanded + return torch.cat(dec_out, dim=2).to(device) diff --git a/comfy/ldm/ernie/model.py b/comfy/ldm/ernie/model.py new file mode 100644 index 000000000..eba661aec --- /dev/null +++ b/comfy/ldm/ernie/model.py @@ -0,0 +1,301 @@ +import math +import torch +import torch.nn as nn +import torch.nn.functional as F + +from comfy.ldm.modules.attention import optimized_attention +import comfy.model_management + +def rope(pos: torch.Tensor, dim: int, theta: int) -> torch.Tensor: + assert dim % 2 == 0 + if not comfy.model_management.supports_fp64(pos.device): + device = torch.device("cpu") + else: + device = pos.device + + scale = torch.arange(0, dim, 2, dtype=torch.float64, device=device) / dim + omega = 1.0 / (theta**scale) + out = torch.einsum("...n,d->...nd", pos.to(device), omega) + out = torch.stack([torch.cos(out), torch.sin(out)], dim=0) + return out.to(dtype=torch.float32, device=pos.device) + +def apply_rotary_emb(x_in: torch.Tensor, freqs_cis: torch.Tensor) -> torch.Tensor: + rot_dim = freqs_cis.shape[-1] + x, x_pass = x_in[..., :rot_dim], x_in[..., rot_dim:] + cos_ = freqs_cis[0] + sin_ = freqs_cis[1] + x1, x2 = x.chunk(2, dim=-1) + x_rotated = torch.cat((-x2, x1), dim=-1) + return torch.cat((x * cos_ + x_rotated * sin_, x_pass), dim=-1) + +class ErnieImageEmbedND3(nn.Module): + def __init__(self, dim: int, theta: int, axes_dim: tuple): + super().__init__() + self.dim = dim + self.theta = theta + self.axes_dim = list(axes_dim) + + def forward(self, ids: torch.Tensor) -> torch.Tensor: + emb = torch.cat([rope(ids[..., i], self.axes_dim[i], self.theta) for i in range(3)], dim=-1) + emb = emb.unsqueeze(3) # [2, B, S, 1, head_dim//2] + return torch.stack([emb, emb], dim=-1).reshape(*emb.shape[:-1], -1) # [B, S, 1, head_dim] + +class ErnieImagePatchEmbedDynamic(nn.Module): + def __init__(self, in_channels: int, embed_dim: int, patch_size: int, operations, device=None, dtype=None): + super().__init__() + self.patch_size = patch_size + self.proj = operations.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=patch_size, bias=True, device=device, dtype=dtype) + + def forward(self, x: torch.Tensor) -> torch.Tensor: + x = self.proj(x) + batch_size, dim, height, width = x.shape + return x.reshape(batch_size, dim, height * width).transpose(1, 2).contiguous() + +class Timesteps(nn.Module): + def __init__(self, num_channels: int, flip_sin_to_cos: bool = False): + super().__init__() + self.num_channels = num_channels + self.flip_sin_to_cos = flip_sin_to_cos + + def forward(self, timesteps: torch.Tensor) -> torch.Tensor: + half_dim = self.num_channels // 2 + exponent = -math.log(10000) * torch.arange(half_dim, dtype=torch.float32, device=timesteps.device) / half_dim + emb = torch.exp(exponent) + emb = timesteps[:, None].float() * emb[None, :] + if self.flip_sin_to_cos: + emb = torch.cat([torch.cos(emb), torch.sin(emb)], dim=-1) + else: + emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=-1) + return emb + +class TimestepEmbedding(nn.Module): + def __init__(self, in_channels: int, time_embed_dim: int, operations, device=None, dtype=None): + super().__init__() + Linear = operations.Linear + self.linear_1 = Linear(in_channels, time_embed_dim, bias=True, device=device, dtype=dtype) + self.act = nn.SiLU() + self.linear_2 = Linear(time_embed_dim, time_embed_dim, bias=True, device=device, dtype=dtype) + + def forward(self, sample: torch.Tensor) -> torch.Tensor: + sample = self.linear_1(sample) + sample = self.act(sample) + sample = self.linear_2(sample) + return sample + +class ErnieImageAttention(nn.Module): + def __init__(self, query_dim: int, heads: int, dim_head: int, eps: float = 1e-6, operations=None, device=None, dtype=None): + super().__init__() + self.heads = heads + self.head_dim = dim_head + self.inner_dim = heads * dim_head + + Linear = operations.Linear + RMSNorm = operations.RMSNorm + + self.to_q = Linear(query_dim, self.inner_dim, bias=False, device=device, dtype=dtype) + self.to_k = Linear(query_dim, self.inner_dim, bias=False, device=device, dtype=dtype) + self.to_v = Linear(query_dim, self.inner_dim, bias=False, device=device, dtype=dtype) + + self.norm_q = RMSNorm(dim_head, eps=eps, elementwise_affine=True, device=device, dtype=dtype) + self.norm_k = RMSNorm(dim_head, eps=eps, elementwise_affine=True, device=device, dtype=dtype) + + self.to_out = nn.ModuleList([Linear(self.inner_dim, query_dim, bias=False, device=device, dtype=dtype)]) + + def forward(self, x: torch.Tensor, attention_mask: torch.Tensor = None, image_rotary_emb: torch.Tensor = None) -> torch.Tensor: + B, S, _ = x.shape + + q_flat = self.to_q(x) + k_flat = self.to_k(x) + v_flat = self.to_v(x) + + query = q_flat.view(B, S, self.heads, self.head_dim) + key = k_flat.view(B, S, self.heads, self.head_dim) + + query = self.norm_q(query) + key = self.norm_k(key) + + if image_rotary_emb is not None: + query = apply_rotary_emb(query, image_rotary_emb) + key = apply_rotary_emb(key, image_rotary_emb) + + q_flat = query.reshape(B, S, -1) + k_flat = key.reshape(B, S, -1) + + hidden_states = optimized_attention(q_flat, k_flat, v_flat, self.heads, mask=attention_mask) + + return self.to_out[0](hidden_states) + +class ErnieImageFeedForward(nn.Module): + def __init__(self, hidden_size: int, ffn_hidden_size: int, operations, device=None, dtype=None): + super().__init__() + Linear = operations.Linear + self.gate_proj = Linear(hidden_size, ffn_hidden_size, bias=False, device=device, dtype=dtype) + self.up_proj = Linear(hidden_size, ffn_hidden_size, bias=False, device=device, dtype=dtype) + self.linear_fc2 = Linear(ffn_hidden_size, hidden_size, bias=False, device=device, dtype=dtype) + + def forward(self, x: torch.Tensor) -> torch.Tensor: + return self.linear_fc2(self.up_proj(x) * F.gelu(self.gate_proj(x))) + +class ErnieImageSharedAdaLNBlock(nn.Module): + def __init__(self, hidden_size: int, num_heads: int, ffn_hidden_size: int, eps: float = 1e-6, operations=None, device=None, dtype=None): + super().__init__() + RMSNorm = operations.RMSNorm + + self.adaLN_sa_ln = RMSNorm(hidden_size, eps=eps, device=device, dtype=dtype) + self.self_attention = ErnieImageAttention( + query_dim=hidden_size, + dim_head=hidden_size // num_heads, + heads=num_heads, + eps=eps, + operations=operations, + device=device, + dtype=dtype + ) + self.adaLN_mlp_ln = RMSNorm(hidden_size, eps=eps, device=device, dtype=dtype) + self.mlp = ErnieImageFeedForward(hidden_size, ffn_hidden_size, operations=operations, device=device, dtype=dtype) + + def forward(self, x, rotary_pos_emb, temb, attention_mask=None): + shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = temb + + residual = x + x_norm = self.adaLN_sa_ln(x) + x_norm = x_norm * (1 + scale_msa) + shift_msa + + attn_out = self.self_attention(x_norm, attention_mask=attention_mask, image_rotary_emb=rotary_pos_emb) + x = residual + gate_msa * attn_out + + residual = x + x_norm = self.adaLN_mlp_ln(x) + x_norm = x_norm * (1 + scale_mlp) + shift_mlp + + return residual + gate_mlp * self.mlp(x_norm) + +class ErnieImageAdaLNContinuous(nn.Module): + def __init__(self, hidden_size: int, eps: float = 1e-6, operations=None, device=None, dtype=None): + super().__init__() + LayerNorm = operations.LayerNorm + Linear = operations.Linear + self.norm = LayerNorm(hidden_size, elementwise_affine=False, eps=eps, device=device, dtype=dtype) + self.linear = Linear(hidden_size, hidden_size * 2, device=device, dtype=dtype) + + def forward(self, x: torch.Tensor, conditioning: torch.Tensor) -> torch.Tensor: + scale, shift = self.linear(conditioning).chunk(2, dim=-1) + x = self.norm(x) + x = torch.addcmul(shift.unsqueeze(1), x, 1 + scale.unsqueeze(1)) + return x + +class ErnieImageModel(nn.Module): + def __init__( + self, + hidden_size: int = 4096, + num_attention_heads: int = 32, + num_layers: int = 36, + ffn_hidden_size: int = 12288, + in_channels: int = 128, + out_channels: int = 128, + patch_size: int = 1, + text_in_dim: int = 3072, + rope_theta: int = 256, + rope_axes_dim: tuple = (32, 48, 48), + eps: float = 1e-6, + qk_layernorm: bool = True, + device=None, + dtype=None, + operations=None, + **kwargs + ): + super().__init__() + self.dtype = dtype + self.hidden_size = hidden_size + self.num_heads = num_attention_heads + self.head_dim = hidden_size // num_attention_heads + self.patch_size = patch_size + self.out_channels = out_channels + + Linear = operations.Linear + + self.x_embedder = ErnieImagePatchEmbedDynamic(in_channels, hidden_size, patch_size, operations, device, dtype) + self.text_proj = Linear(text_in_dim, hidden_size, bias=False, device=device, dtype=dtype) if text_in_dim != hidden_size else None + + self.time_proj = Timesteps(hidden_size, flip_sin_to_cos=False) + self.time_embedding = TimestepEmbedding(hidden_size, hidden_size, operations, device, dtype) + + self.pos_embed = ErnieImageEmbedND3(dim=self.head_dim, theta=rope_theta, axes_dim=rope_axes_dim) + + self.adaLN_modulation = nn.Sequential( + nn.SiLU(), + Linear(hidden_size, 6 * hidden_size, device=device, dtype=dtype) + ) + + self.layers = nn.ModuleList([ + ErnieImageSharedAdaLNBlock(hidden_size, num_attention_heads, ffn_hidden_size, eps, operations, device, dtype) + for _ in range(num_layers) + ]) + + self.final_norm = ErnieImageAdaLNContinuous(hidden_size, eps, operations, device, dtype) + self.final_linear = Linear(hidden_size, patch_size * patch_size * out_channels, device=device, dtype=dtype) + + def forward(self, x, timesteps, context, **kwargs): + device, dtype = x.device, x.dtype + B, C, H, W = x.shape + p, Hp, Wp = self.patch_size, H // self.patch_size, W // self.patch_size + N_img = Hp * Wp + + img_bsh = self.x_embedder(x) + + text_bth = context + if self.text_proj is not None and text_bth.numel() > 0: + text_bth = self.text_proj(text_bth) + Tmax = text_bth.shape[1] + + hidden_states = torch.cat([img_bsh, text_bth], dim=1) + + text_ids = torch.zeros((B, Tmax, 3), device=device, dtype=torch.float32) + text_ids[:, :, 0] = torch.linspace(0, Tmax - 1, steps=Tmax, device=x.device, dtype=torch.float32) + index = float(Tmax) + + transformer_options = kwargs.get("transformer_options", {}) + rope_options = transformer_options.get("rope_options", None) + + h_len, w_len = float(Hp), float(Wp) + h_offset, w_offset = 0.0, 0.0 + + if rope_options is not None: + h_len = (h_len - 1.0) * rope_options.get("scale_y", 1.0) + 1.0 + w_len = (w_len - 1.0) * rope_options.get("scale_x", 1.0) + 1.0 + index += rope_options.get("shift_t", 0.0) + h_offset += rope_options.get("shift_y", 0.0) + w_offset += rope_options.get("shift_x", 0.0) + + image_ids = torch.zeros((Hp, Wp, 3), device=device, dtype=torch.float32) + image_ids[:, :, 0] = image_ids[:, :, 1] + index + image_ids[:, :, 1] = image_ids[:, :, 1] + torch.linspace(h_offset, h_len - 1 + h_offset, steps=Hp, device=device, dtype=torch.float32).unsqueeze(1) + image_ids[:, :, 2] = image_ids[:, :, 2] + torch.linspace(w_offset, w_len - 1 + w_offset, steps=Wp, device=device, dtype=torch.float32).unsqueeze(0) + + image_ids = image_ids.view(1, N_img, 3).expand(B, -1, -1) + + rotary_pos_emb = self.pos_embed(torch.cat([image_ids, text_ids], dim=1)).to(x.dtype) + del image_ids, text_ids + + sample = self.time_proj(timesteps).to(dtype) + c = self.time_embedding(sample) + + shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = [ + t.unsqueeze(1).contiguous() for t in self.adaLN_modulation(c).chunk(6, dim=-1) + ] + + temb = [shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp] + for layer in self.layers: + hidden_states = layer(hidden_states, rotary_pos_emb, temb) + + hidden_states = self.final_norm(hidden_states, c).type_as(hidden_states) + + patches = self.final_linear(hidden_states)[:, :N_img, :] + output = ( + patches.view(B, Hp, Wp, p, p, self.out_channels) + .permute(0, 5, 1, 3, 2, 4) + .contiguous() + .view(B, self.out_channels, H, W) + ) + + return output diff --git a/comfy/ldm/flux/math.py b/comfy/ldm/flux/math.py index 824daf5e6..6d0aed827 100644 --- a/comfy/ldm/flux/math.py +++ b/comfy/ldm/flux/math.py @@ -16,7 +16,7 @@ def attention(q: Tensor, k: Tensor, v: Tensor, pe: Tensor, mask=None, transforme def rope(pos: Tensor, dim: int, theta: int) -> Tensor: assert dim % 2 == 0 - if comfy.model_management.is_device_mps(pos.device) or comfy.model_management.is_intel_xpu() or comfy.model_management.is_directml_enabled(): + if not comfy.model_management.supports_fp64(pos.device): device = torch.device("cpu") else: device = pos.device diff --git a/comfy/ldm/lightricks/av_model.py b/comfy/ldm/lightricks/av_model.py index 6f2ba41ef..3fb87b4a3 100644 --- a/comfy/ldm/lightricks/av_model.py +++ b/comfy/ldm/lightricks/av_model.py @@ -16,6 +16,7 @@ from comfy.ldm.lightricks.model import ( from comfy.ldm.lightricks.symmetric_patchifier import AudioPatchifier from comfy.ldm.lightricks.embeddings_connector import Embeddings1DConnector import comfy.ldm.common_dit +import comfy.model_prefetch class CompressedTimestep: """Store video timestep embeddings in compressed form using per-frame indexing.""" @@ -907,9 +908,11 @@ class LTXAVModel(LTXVModel): """Process transformer blocks for LTXAV.""" patches_replace = transformer_options.get("patches_replace", {}) blocks_replace = patches_replace.get("dit", {}) + prefetch_queue = comfy.model_prefetch.make_prefetch_queue(list(self.transformer_blocks), vx.device, transformer_options) # Process transformer blocks for i, block in enumerate(self.transformer_blocks): + comfy.model_prefetch.prefetch_queue_pop(prefetch_queue, vx.device, block) if ("double_block", i) in blocks_replace: def block_wrap(args): @@ -982,6 +985,8 @@ class LTXAVModel(LTXVModel): a_prompt_timestep=a_prompt_timestep, ) + comfy.model_prefetch.prefetch_queue_pop(prefetch_queue, vx.device, None) + return [vx, ax] def _process_output(self, x, embedded_timestep, keyframe_idxs, **kwargs): diff --git a/comfy/ldm/lightricks/vae/audio_vae.py b/comfy/ldm/lightricks/vae/audio_vae.py index fa0a00748..dd5320c8f 100644 --- a/comfy/ldm/lightricks/vae/audio_vae.py +++ b/comfy/ldm/lightricks/vae/audio_vae.py @@ -4,9 +4,6 @@ import math import torch import torchaudio -import comfy.model_management -import comfy.model_patcher -import comfy.utils as utils from comfy.ldm.mmaudio.vae.distributions import DiagonalGaussianDistribution from comfy.ldm.lightricks.symmetric_patchifier import AudioPatchifier from comfy.ldm.lightricks.vae.causal_audio_autoencoder import ( @@ -43,30 +40,6 @@ class AudioVAEComponentConfig: return cls(autoencoder=audio_config, vocoder=vocoder_config) - -class ModelDeviceManager: - """Manages device placement and GPU residency for the composed model.""" - - def __init__(self, module: torch.nn.Module): - load_device = comfy.model_management.get_torch_device() - offload_device = comfy.model_management.vae_offload_device() - self.patcher = comfy.model_patcher.ModelPatcher(module, load_device, offload_device) - - def ensure_model_loaded(self) -> None: - comfy.model_management.free_memory( - self.patcher.model_size(), - self.patcher.load_device, - ) - comfy.model_management.load_model_gpu(self.patcher) - - def move_to_load_device(self, tensor: torch.Tensor) -> torch.Tensor: - return tensor.to(self.patcher.load_device) - - @property - def load_device(self): - return self.patcher.load_device - - class AudioLatentNormalizer: """Applies per-channel statistics in patch space and restores original layout.""" @@ -132,23 +105,17 @@ class AudioPreprocessor: class AudioVAE(torch.nn.Module): """High-level Audio VAE wrapper exposing encode and decode entry points.""" - def __init__(self, state_dict: dict, metadata: dict): + def __init__(self, metadata: dict): super().__init__() component_config = AudioVAEComponentConfig.from_metadata(metadata) - vae_sd = utils.state_dict_prefix_replace(state_dict, {"audio_vae.": ""}, filter_keys=True) - vocoder_sd = utils.state_dict_prefix_replace(state_dict, {"vocoder.": ""}, filter_keys=True) - self.autoencoder = CausalAudioAutoencoder(config=component_config.autoencoder) if "bwe" in component_config.vocoder: self.vocoder = VocoderWithBWE(config=component_config.vocoder) else: self.vocoder = Vocoder(config=component_config.vocoder) - self.autoencoder.load_state_dict(vae_sd, strict=False) - self.vocoder.load_state_dict(vocoder_sd, strict=False) - autoencoder_config = self.autoencoder.get_config() self.normalizer = AudioLatentNormalizer( AudioPatchifier( @@ -168,18 +135,12 @@ class AudioVAE(torch.nn.Module): n_fft=autoencoder_config["n_fft"], ) - self.device_manager = ModelDeviceManager(self) - - def encode(self, audio: dict) -> torch.Tensor: + def encode(self, audio, sample_rate=44100) -> torch.Tensor: """Encode a waveform dictionary into normalized latent tensors.""" - waveform = audio["waveform"] - waveform_sample_rate = audio["sample_rate"] + waveform = audio + waveform_sample_rate = sample_rate input_device = waveform.device - # Ensure that Audio VAE is loaded on the correct device. - self.device_manager.ensure_model_loaded() - - waveform = self.device_manager.move_to_load_device(waveform) expected_channels = self.autoencoder.encoder.in_channels if waveform.shape[1] != expected_channels: if waveform.shape[1] == 1: @@ -190,7 +151,7 @@ class AudioVAE(torch.nn.Module): ) mel_spec = self.preprocessor.waveform_to_mel( - waveform, waveform_sample_rate, device=self.device_manager.load_device + waveform, waveform_sample_rate, device=waveform.device ) latents = self.autoencoder.encode(mel_spec) @@ -204,17 +165,13 @@ class AudioVAE(torch.nn.Module): """Decode normalized latent tensors into an audio waveform.""" original_shape = latents.shape - # Ensure that Audio VAE is loaded on the correct device. - self.device_manager.ensure_model_loaded() - - latents = self.device_manager.move_to_load_device(latents) latents = self.normalizer.denormalize(latents) target_shape = self.target_shape_from_latents(original_shape) mel_spec = self.autoencoder.decode(latents, target_shape=target_shape) waveform = self.run_vocoder(mel_spec) - return self.device_manager.move_to_load_device(waveform) + return waveform def target_shape_from_latents(self, latents_shape): batch, _, time, _ = latents_shape diff --git a/comfy/ldm/models/autoencoder.py b/comfy/ldm/models/autoencoder.py index 4f50810dc..582b44e69 100644 --- a/comfy/ldm/models/autoencoder.py +++ b/comfy/ldm/models/autoencoder.py @@ -155,6 +155,7 @@ class AutoencodingEngineLegacy(AutoencodingEngine): def __init__(self, embed_dim: int, **kwargs): self.max_batch_size = kwargs.pop("max_batch_size", None) ddconfig = kwargs.pop("ddconfig") + decoder_ddconfig = kwargs.pop("decoder_ddconfig", ddconfig) super().__init__( encoder_config={ "target": "comfy.ldm.modules.diffusionmodules.model.Encoder", @@ -162,7 +163,7 @@ class AutoencodingEngineLegacy(AutoencodingEngine): }, decoder_config={ "target": "comfy.ldm.modules.diffusionmodules.model.Decoder", - "params": ddconfig, + "params": decoder_ddconfig, }, **kwargs, ) diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py index b193fe5e8..a68cb8439 100644 --- a/comfy/ldm/modules/attention.py +++ b/comfy/ldm/modules/attention.py @@ -14,6 +14,8 @@ from .sub_quadratic_attention import efficient_dot_product_attention from comfy import model_management +TORCH_HAS_GQA = model_management.torch_version_numeric >= (2, 5) + if model_management.xformers_enabled(): import xformers import xformers.ops @@ -150,7 +152,12 @@ def attention_basic(q, k, v, heads, mask=None, attn_precision=None, skip_reshape b, _, dim_head = q.shape dim_head //= heads - scale = dim_head ** -0.5 + if kwargs.get("enable_gqa", False) and q.shape[-3] != k.shape[-3]: + n_rep = q.shape[-3] // k.shape[-3] + k = k.repeat_interleave(n_rep, dim=-3) + v = v.repeat_interleave(n_rep, dim=-3) + + scale = kwargs.get("scale", dim_head ** -0.5) h = heads if skip_reshape: @@ -219,6 +226,10 @@ def attention_sub_quad(query, key, value, heads, mask=None, attn_precision=None, b, _, dim_head = query.shape dim_head //= heads + if "scale" in kwargs: + # Pre-scale query to match requested scale (cancels internal 1/sqrt(dim_head)) + query = query * (kwargs["scale"] * dim_head ** 0.5) + if skip_reshape: query = query.reshape(b * heads, -1, dim_head) value = value.reshape(b * heads, -1, dim_head) @@ -290,7 +301,7 @@ def attention_split(q, k, v, heads, mask=None, attn_precision=None, skip_reshape b, _, dim_head = q.shape dim_head //= heads - scale = dim_head ** -0.5 + scale = kwargs.get("scale", dim_head ** -0.5) if skip_reshape: q, k, v = map( @@ -500,8 +511,13 @@ def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_resha if mask.ndim == 3: mask = mask.unsqueeze(1) + # Pass through extra SDPA kwargs (scale, enable_gqa) if provided + # enable_gqa requires PyTorch 2.5+; older versions use manual KV expansion above + sdpa_keys = ("scale", "enable_gqa") if TORCH_HAS_GQA else ("scale",) + sdpa_extra = {k: v for k, v in kwargs.items() if k in sdpa_keys} + if SDP_BATCH_LIMIT >= b: - out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False) + out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False, **sdpa_extra) if not skip_output_reshape: out = ( out.transpose(1, 2).reshape(b, -1, heads * dim_head) @@ -519,7 +535,7 @@ def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_resha k[i : i + SDP_BATCH_LIMIT], v[i : i + SDP_BATCH_LIMIT], attn_mask=m, - dropout_p=0.0, is_causal=False + dropout_p=0.0, is_causal=False, **sdpa_extra ).transpose(1, 2).reshape(-1, q.shape[2], heads * dim_head) return out diff --git a/comfy/ldm/modules/diffusionmodules/openaimodel.py b/comfy/ldm/modules/diffusionmodules/openaimodel.py index 295310df6..4b92c44cf 100644 --- a/comfy/ldm/modules/diffusionmodules/openaimodel.py +++ b/comfy/ldm/modules/diffusionmodules/openaimodel.py @@ -34,6 +34,16 @@ class TimestepBlock(nn.Module): #This is needed because accelerate makes a copy of transformer_options which breaks "transformer_index" def forward_timestep_embed(ts, x, emb, context=None, transformer_options={}, output_shape=None, time_context=None, num_video_frames=None, image_only_indicator=None): for layer in ts: + if "patches" in transformer_options and "forward_timestep_embed_patch" in transformer_options["patches"]: + found_patched = False + for class_type, handler in transformer_options["patches"]["forward_timestep_embed_patch"]: + if isinstance(layer, class_type): + x = handler(layer, x, emb, context, transformer_options, output_shape, time_context, num_video_frames, image_only_indicator) + found_patched = True + break + if found_patched: + continue + if isinstance(layer, VideoResBlock): x = layer(x, emb, num_video_frames, image_only_indicator) elif isinstance(layer, TimestepBlock): @@ -49,15 +59,6 @@ def forward_timestep_embed(ts, x, emb, context=None, transformer_options={}, out elif isinstance(layer, Upsample): x = layer(x, output_shape=output_shape) else: - if "patches" in transformer_options and "forward_timestep_embed_patch" in transformer_options["patches"]: - found_patched = False - for class_type, handler in transformer_options["patches"]["forward_timestep_embed_patch"]: - if isinstance(layer, class_type): - x = handler(layer, x, emb, context, transformer_options, output_shape, time_context, num_video_frames, image_only_indicator) - found_patched = True - break - if found_patched: - continue x = layer(x) return x @@ -894,6 +895,12 @@ class UNetModel(nn.Module): h = forward_timestep_embed(self.middle_block, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator) h = apply_control(h, control, 'middle') + if "middle_block_after_patch" in transformer_patches: + patch = transformer_patches["middle_block_after_patch"] + for p in patch: + out = p({"h": h, "x": x, "emb": emb, "context": context, "y": y, + "timesteps": timesteps, "transformer_options": transformer_options}) + h = out["h"] for id, module in enumerate(self.output_blocks): transformer_options["block"] = ("output", id) @@ -905,8 +912,9 @@ class UNetModel(nn.Module): for p in patch: h, hsp = p(h, hsp, transformer_options) - h = th.cat([h, hsp], dim=1) - del hsp + if hsp is not None: + h = th.cat([h, hsp], dim=1) + del hsp if len(hs) > 0: output_shape = hs[-1].shape else: diff --git a/comfy/ldm/modules/encoders/noise_aug_modules.py b/comfy/ldm/modules/encoders/noise_aug_modules.py index a5d866030..c853e4298 100644 --- a/comfy/ldm/modules/encoders/noise_aug_modules.py +++ b/comfy/ldm/modules/encoders/noise_aug_modules.py @@ -3,12 +3,9 @@ from ..diffusionmodules.openaimodel import Timestep import torch class CLIPEmbeddingNoiseAugmentation(ImageConcatWithNoiseAugmentation): - def __init__(self, *args, clip_stats_path=None, timestep_dim=256, **kwargs): + def __init__(self, *args, timestep_dim=256, **kwargs): super().__init__(*args, **kwargs) - if clip_stats_path is None: - clip_mean, clip_std = torch.zeros(timestep_dim), torch.ones(timestep_dim) - else: - clip_mean, clip_std = torch.load(clip_stats_path, map_location="cpu") + clip_mean, clip_std = torch.zeros(timestep_dim), torch.ones(timestep_dim) self.register_buffer("data_mean", clip_mean[None, :], persistent=False) self.register_buffer("data_std", clip_std[None, :], persistent=False) self.time_embed = Timestep(timestep_dim) diff --git a/comfy/ldm/modules/sdpose.py b/comfy/ldm/modules/sdpose.py index d67b60b76..1a9585fc2 100644 --- a/comfy/ldm/modules/sdpose.py +++ b/comfy/ldm/modules/sdpose.py @@ -90,7 +90,7 @@ class HeatmapHead(torch.nn.Module): origin_max = np.max(hm[k]) dr = np.zeros((H + 2 * border, W + 2 * border), dtype=np.float32) dr[border:-border, border:-border] = hm[k].copy() - dr = gaussian_filter(dr, sigma=2.0) + dr = gaussian_filter(dr, sigma=2.0, truncate=2.5) hm[k] = dr[border:-border, border:-border].copy() cur_max = np.max(hm[k]) if cur_max > 0: diff --git a/comfy/ldm/sam3/detector.py b/comfy/ldm/sam3/detector.py new file mode 100644 index 000000000..12d3a01ab --- /dev/null +++ b/comfy/ldm/sam3/detector.py @@ -0,0 +1,596 @@ +# SAM3 detector: transformer encoder-decoder, segmentation head, geometry encoder, scoring. + +import math + +import torch +import torch.nn as nn +import torch.nn.functional as F +from torchvision.ops import roi_align + +from comfy.ldm.modules.attention import optimized_attention +from comfy.ldm.sam3.tracker import SAM3Tracker, SAM31Tracker +from comfy.ldm.sam3.sam import SAM3VisionBackbone # noqa: used in __init__ +from comfy.ldm.sam3.sam import MLP, PositionEmbeddingSine + +TRACKER_CLASSES = {"SAM3": SAM3Tracker, "SAM31": SAM31Tracker} +from comfy.ops import cast_to_input + + +def box_cxcywh_to_xyxy(x): + cx, cy, w, h = x.unbind(-1) + return torch.stack([cx - 0.5 * w, cy - 0.5 * h, cx + 0.5 * w, cy + 0.5 * h], dim=-1) + + +def gen_sineembed_for_position(pos_tensor, num_feats=256): + """Per-coordinate sinusoidal embedding: (..., N) -> (..., N * num_feats).""" + assert num_feats % 2 == 0 + hdim = num_feats // 2 + freqs = 10000.0 ** (2 * (torch.arange(hdim, dtype=torch.float32, device=pos_tensor.device) // 2) / hdim) + embeds = [] + for c in range(pos_tensor.shape[-1]): + raw = (pos_tensor[..., c].float() * 2 * math.pi).unsqueeze(-1) / freqs + embeds.append(torch.stack([raw[..., 0::2].sin(), raw[..., 1::2].cos()], dim=-1).flatten(-2)) + return torch.cat(embeds, dim=-1).to(pos_tensor.dtype) + + +class SplitMHA(nn.Module): + """Multi-head attention with separate Q/K/V projections (split from fused in_proj_weight).""" + def __init__(self, d_model, num_heads=8, device=None, dtype=None, operations=None): + super().__init__() + self.num_heads = num_heads + self.q_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.k_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.v_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.out_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + + def forward(self, q_input, k_input=None, v_input=None, mask=None): + q = self.q_proj(q_input) + if k_input is None: + k = self.k_proj(q_input) + v = self.v_proj(q_input) + else: + k = self.k_proj(k_input) + v = self.v_proj(v_input if v_input is not None else k_input) + if mask is not None and mask.ndim == 2: + mask = mask[:, None, None, :] # [B, T] -> [B, 1, 1, T] for SDPA broadcast + dtype = q.dtype # manual_cast may produce mixed dtypes + out = optimized_attention(q, k.to(dtype), v.to(dtype), self.num_heads, mask=mask, low_precision_attention=False) + return self.out_proj(out) + + +class MLPWithNorm(nn.Module): + """MLP with residual connection and output LayerNorm.""" + def __init__(self, input_dim, hidden_dim, output_dim, num_layers, residual=True, device=None, dtype=None, operations=None): + super().__init__() + dims = [input_dim] + [hidden_dim] * (num_layers - 1) + [output_dim] + self.layers = nn.ModuleList([ + operations.Linear(dims[i], dims[i + 1], device=device, dtype=dtype) + for i in range(num_layers) + ]) + self.out_norm = operations.LayerNorm(output_dim, device=device, dtype=dtype) + self.residual = residual and (input_dim == output_dim) + + def forward(self, x): + orig = x + for i, layer in enumerate(self.layers): + x = layer(x) + if i < len(self.layers) - 1: + x = F.relu(x) + if self.residual: + x = x + orig + return self.out_norm(x) + + +class EncoderLayer(nn.Module): + def __init__(self, d_model=256, num_heads=8, dim_ff=2048, device=None, dtype=None, operations=None): + super().__init__() + self.self_attn = SplitMHA(d_model, num_heads, device=device, dtype=dtype, operations=operations) + self.cross_attn_image = SplitMHA(d_model, num_heads, device=device, dtype=dtype, operations=operations) + self.linear1 = operations.Linear(d_model, dim_ff, device=device, dtype=dtype) + self.linear2 = operations.Linear(dim_ff, d_model, device=device, dtype=dtype) + self.norm1 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm2 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm3 = operations.LayerNorm(d_model, device=device, dtype=dtype) + + def forward(self, x, pos, text_memory=None, text_mask=None): + normed = self.norm1(x) + q_k = normed + pos + x = x + self.self_attn(q_k, q_k, normed) + if text_memory is not None: + normed = self.norm2(x) + x = x + self.cross_attn_image(normed, text_memory, text_memory, mask=text_mask) + normed = self.norm3(x) + x = x + self.linear2(F.relu(self.linear1(normed))) + return x + + +class TransformerEncoder(nn.Module): + """Checkpoint: transformer.encoder.layers.N.*""" + def __init__(self, d_model=256, num_heads=8, dim_ff=2048, num_layers=6, device=None, dtype=None, operations=None): + super().__init__() + self.layers = nn.ModuleList([ + EncoderLayer(d_model, num_heads, dim_ff, device=device, dtype=dtype, operations=operations) + for _ in range(num_layers) + ]) + + def forward(self, x, pos, text_memory=None, text_mask=None): + for layer in self.layers: + x = layer(x, pos, text_memory, text_mask) + return x + + +class DecoderLayer(nn.Module): + def __init__(self, d_model=256, num_heads=8, dim_ff=2048, device=None, dtype=None, operations=None): + super().__init__() + self.self_attn = SplitMHA(d_model, num_heads, device=device, dtype=dtype, operations=operations) + self.cross_attn = SplitMHA(d_model, num_heads, device=device, dtype=dtype, operations=operations) + self.ca_text = SplitMHA(d_model, num_heads, device=device, dtype=dtype, operations=operations) + self.norm1 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm2 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm3 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.catext_norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.linear1 = operations.Linear(d_model, dim_ff, device=device, dtype=dtype) + self.linear2 = operations.Linear(dim_ff, d_model, device=device, dtype=dtype) + + def forward(self, x, memory, x_pos, memory_pos, text_memory=None, text_mask=None, cross_attn_bias=None): + q_k = x + x_pos + x = self.norm2(x + self.self_attn(q_k, q_k, x)) + if text_memory is not None: + x = self.catext_norm(x + self.ca_text(x + x_pos, text_memory, text_memory, mask=text_mask)) + x = self.norm1(x + self.cross_attn(x + x_pos, memory + memory_pos, memory, mask=cross_attn_bias)) + x = self.norm3(x + self.linear2(F.relu(self.linear1(x)))) + return x + + +class TransformerDecoder(nn.Module): + def __init__(self, d_model=256, num_heads=8, dim_ff=2048, num_layers=6, + num_queries=200, device=None, dtype=None, operations=None): + super().__init__() + self.d_model = d_model + self.num_queries = num_queries + + self.layers = nn.ModuleList([ + DecoderLayer(d_model, num_heads, dim_ff, device=device, dtype=dtype, operations=operations) + for _ in range(num_layers) + ]) + self.norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.query_embed = operations.Embedding(num_queries, d_model, device=device, dtype=dtype) + self.reference_points = operations.Embedding(num_queries, 4, device=device, dtype=dtype) # Reference points: Embedding(num_queries, 4) — learned anchor boxes + self.ref_point_head = MLP(d_model * 2, d_model, d_model, 2, device=device, dtype=dtype, operations=operations) # ref_point_head input: 512 (4 coords * 128 sine features each) + self.bbox_embed = MLP(d_model, d_model, 4, 3, device=device, dtype=dtype, operations=operations) + + self.boxRPB_embed_x = MLP(2, d_model, num_heads, 2, device=device, dtype=dtype, operations=operations) + self.boxRPB_embed_y = MLP(2, d_model, num_heads, 2, device=device, dtype=dtype, operations=operations) + + self.presence_token = operations.Embedding(1, d_model, device=device, dtype=dtype) + self.presence_token_head = MLP(d_model, d_model, 1, 3, device=device, dtype=dtype, operations=operations) + self.presence_token_out_norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + + @staticmethod + def _inverse_sigmoid(x): + return torch.log(x / (1 - x + 1e-6) + 1e-6) + + def _compute_box_rpb(self, ref_points, H, W): + """Box rotary position bias: (B, Q, 4) cxcywh -> (B, n_heads, Q+1, H*W) bias.""" + boxes_xyxy = box_cxcywh_to_xyxy(ref_points) + B, Q, _ = boxes_xyxy.shape + coords_h = torch.arange(H, device=ref_points.device, dtype=torch.float32) / H + coords_w = torch.arange(W, device=ref_points.device, dtype=torch.float32) / W + deltas_x = coords_w.view(1, 1, -1, 1) - boxes_xyxy[:, :, None, 0:3:2] + deltas_y = coords_h.view(1, 1, -1, 1) - boxes_xyxy[:, :, None, 1:4:2] + + log2_8 = float(math.log2(8)) + def log_scale(d): + return torch.sign(d * 8) * torch.log2(torch.abs(d * 8) + 1.0) / log2_8 + + rpb_x = self.boxRPB_embed_x(log_scale(deltas_x).to(ref_points.dtype)) + rpb_y = self.boxRPB_embed_y(log_scale(deltas_y).to(ref_points.dtype)) + + bias = (rpb_y.unsqueeze(3) + rpb_x.unsqueeze(2)).flatten(2, 3).permute(0, 3, 1, 2) + pres_bias = torch.zeros(B, bias.shape[1], 1, bias.shape[3], device=bias.device, dtype=bias.dtype) + return torch.cat([pres_bias, bias], dim=2) + + def forward(self, memory, memory_pos, text_memory=None, text_mask=None, H=72, W=72): + B = memory.shape[0] + tgt = cast_to_input(self.query_embed.weight, memory).unsqueeze(0).expand(B, -1, -1) + presence_out = cast_to_input(self.presence_token.weight, memory)[None].expand(B, -1, -1) + ref_points = cast_to_input(self.reference_points.weight, memory).unsqueeze(0).expand(B, -1, -1).sigmoid() + + for layer_idx, layer in enumerate(self.layers): + query_pos = self.ref_point_head(gen_sineembed_for_position(ref_points, self.d_model)) + tgt_with_pres = torch.cat([presence_out, tgt], dim=1) + pos_with_pres = torch.cat([torch.zeros_like(presence_out), query_pos], dim=1) + tgt_with_pres = layer(tgt_with_pres, memory, pos_with_pres, memory_pos, + text_memory, text_mask, self._compute_box_rpb(ref_points, H, W)) + presence_out, tgt = tgt_with_pres[:, :1], tgt_with_pres[:, 1:] + if layer_idx < len(self.layers) - 1: + ref_inv = self._inverse_sigmoid(ref_points) + ref_points = (ref_inv + self.bbox_embed(self.norm(tgt))).sigmoid().detach() + + query_out = self.norm(tgt) + ref_inv = self._inverse_sigmoid(ref_points) + boxes = (ref_inv + self.bbox_embed(query_out)).sigmoid() + presence = self.presence_token_head(self.presence_token_out_norm(presence_out)).squeeze(-1) + return {"decoder_output": query_out, "pred_boxes": boxes, "presence": presence} + + +class Transformer(nn.Module): + def __init__(self, d_model=256, num_heads=8, dim_ff=2048, enc_layers=6, dec_layers=6, + num_queries=200, device=None, dtype=None, operations=None): + super().__init__() + self.encoder = TransformerEncoder(d_model, num_heads, dim_ff, enc_layers, device=device, dtype=dtype, operations=operations) + self.decoder = TransformerDecoder(d_model, num_heads, dim_ff, dec_layers, num_queries, device=device, dtype=dtype, operations=operations) + + +class GeometryEncoder(nn.Module): + def __init__(self, d_model=256, num_heads=8, num_layers=3, roi_size=7, device=None, dtype=None, operations=None): + super().__init__() + self.d_model = d_model + self.roi_size = roi_size + self.pos_enc = PositionEmbeddingSine(num_pos_feats=d_model, normalize=True) + self.points_direct_project = operations.Linear(2, d_model, device=device, dtype=dtype) + self.points_pool_project = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.points_pos_enc_project = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.boxes_direct_project = operations.Linear(4, d_model, device=device, dtype=dtype) + self.boxes_pool_project = operations.Conv2d(d_model, d_model, kernel_size=roi_size, device=device, dtype=dtype) + self.boxes_pos_enc_project = operations.Linear(d_model + 2, d_model, device=device, dtype=dtype) + self.label_embed = operations.Embedding(2, d_model, device=device, dtype=dtype) + self.cls_embed = operations.Embedding(1, d_model, device=device, dtype=dtype) + self.norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.img_pre_norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.encode = nn.ModuleList([ + EncoderLayer(d_model, num_heads, 2048, device=device, dtype=dtype, operations=operations) + for _ in range(num_layers) + ]) + self.encode_norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.final_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + + def _encode_points(self, coords, labels, img_feat_2d): + """Encode point prompts: direct + pool + pos_enc + label. coords: [B, N, 2] normalized.""" + B, N, _ = coords.shape + embed = self.points_direct_project(coords) + # Pool features from backbone at point locations via grid_sample + grid = (coords * 2 - 1).unsqueeze(2) # [B, N, 1, 2] in [-1, 1] + sampled = F.grid_sample(img_feat_2d, grid, align_corners=False) # [B, C, N, 1] + embed = embed + self.points_pool_project(sampled.squeeze(-1).permute(0, 2, 1)) # [B, N, C] + # Positional encoding of coordinates + x, y = coords[:, :, 0], coords[:, :, 1] # [B, N] + pos_x, pos_y = self.pos_enc._encode_xy(x.flatten(), y.flatten()) + enc = torch.cat([pos_x, pos_y], dim=-1).view(B, N, -1) + embed = embed + self.points_pos_enc_project(cast_to_input(enc, embed)) + embed = embed + cast_to_input(self.label_embed(labels.long()), embed) + return embed + + def _encode_boxes(self, boxes, labels, img_feat_2d): + """Encode box prompts: direct + pool + pos_enc + label. boxes: [B, N, 4] normalized cxcywh.""" + B, N, _ = boxes.shape + embed = self.boxes_direct_project(boxes) + # ROI align from backbone at box regions + H, W = img_feat_2d.shape[-2:] + boxes_xyxy = box_cxcywh_to_xyxy(boxes) + scale = torch.tensor([W, H, W, H], dtype=boxes_xyxy.dtype, device=boxes_xyxy.device) + boxes_scaled = boxes_xyxy * scale + sampled = roi_align(img_feat_2d, boxes_scaled.view(-1, 4).split(N), self.roi_size) + proj = self.boxes_pool_project(sampled).view(B, N, -1) # Conv2d(roi_size) -> [B*N, C, 1, 1] -> [B, N, C] + embed = embed + proj + # Positional encoding of box center + size + cx, cy, w, h = boxes[:, :, 0], boxes[:, :, 1], boxes[:, :, 2], boxes[:, :, 3] + enc = self.pos_enc.encode_boxes(cx.flatten(), cy.flatten(), w.flatten(), h.flatten()) + enc = enc.view(B, N, -1) + embed = embed + self.boxes_pos_enc_project(cast_to_input(enc, embed)) + embed = embed + cast_to_input(self.label_embed(labels.long()), embed) + return embed + + def forward(self, points=None, boxes=None, image_features=None): + """Encode geometry prompts. image_features: [B, HW, C] flattened backbone features.""" + # Prepare 2D image features for pooling + img_feat_2d = None + if image_features is not None: + B = image_features.shape[0] + HW, C = image_features.shape[1], image_features.shape[2] + hw = int(math.sqrt(HW)) + img_normed = self.img_pre_norm(image_features) + img_feat_2d = img_normed.permute(0, 2, 1).view(B, C, hw, hw) + + embeddings = [] + if points is not None: + coords, labels = points + embeddings.append(self._encode_points(coords, labels, img_feat_2d)) + if boxes is not None: + B = boxes.shape[0] + box_labels = torch.ones(B, boxes.shape[1], dtype=torch.long, device=boxes.device) + embeddings.append(self._encode_boxes(boxes, box_labels, img_feat_2d)) + if not embeddings: + return None + geo = torch.cat(embeddings, dim=1) + geo = self.norm(geo) + if image_features is not None: + for layer in self.encode: + geo = layer(geo, torch.zeros_like(geo), image_features) + geo = self.encode_norm(geo) + return self.final_proj(geo) + + +class PixelDecoder(nn.Module): + """Top-down FPN pixel decoder with GroupNorm + ReLU + nearest interpolation.""" + def __init__(self, d_model=256, num_stages=3, device=None, dtype=None, operations=None): + super().__init__() + self.conv_layers = nn.ModuleList([operations.Conv2d(d_model, d_model, kernel_size=3, padding=1, device=device, dtype=dtype) for _ in range(num_stages)]) + self.norms = nn.ModuleList([operations.GroupNorm(8, d_model, device=device, dtype=dtype) for _ in range(num_stages)]) + + def forward(self, backbone_features): + prev = backbone_features[-1] + for i, feat in enumerate(backbone_features[:-1][::-1]): + prev = F.relu(self.norms[i](self.conv_layers[i](feat + F.interpolate(prev, size=feat.shape[-2:], mode="nearest")))) + return prev + + +class MaskPredictor(nn.Module): + def __init__(self, d_model=256, device=None, dtype=None, operations=None): + super().__init__() + self.mask_embed = MLP(d_model, d_model, d_model, 3, device=device, dtype=dtype, operations=operations) + + def forward(self, query_embeddings, pixel_features): + mask_embed = self.mask_embed(query_embeddings) + return torch.einsum("bqc,bchw->bqhw", mask_embed, pixel_features) + + +class SegmentationHead(nn.Module): + def __init__(self, d_model=256, num_heads=8, device=None, dtype=None, operations=None): + super().__init__() + self.d_model = d_model + self.pixel_decoder = PixelDecoder(d_model, 3, device=device, dtype=dtype, operations=operations) + self.mask_predictor = MaskPredictor(d_model, device=device, dtype=dtype, operations=operations) + self.cross_attend_prompt = SplitMHA(d_model, num_heads, device=device, dtype=dtype, operations=operations) + self.cross_attn_norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.instance_seg_head = operations.Conv2d(d_model, d_model, kernel_size=1, device=device, dtype=dtype) + self.semantic_seg_head = operations.Conv2d(d_model, 1, kernel_size=1, device=device, dtype=dtype) + + def forward(self, query_embeddings, backbone_features, encoder_hidden_states=None, prompt=None, prompt_mask=None): + if encoder_hidden_states is not None and prompt is not None: + enc_normed = self.cross_attn_norm(encoder_hidden_states) + enc_cross = self.cross_attend_prompt(enc_normed, prompt, prompt, mask=prompt_mask) + encoder_hidden_states = enc_cross + encoder_hidden_states + + if encoder_hidden_states is not None: + B, H, W = encoder_hidden_states.shape[0], backbone_features[-1].shape[-2], backbone_features[-1].shape[-1] + encoder_visual = encoder_hidden_states[:, :H * W].permute(0, 2, 1).view(B, self.d_model, H, W) + backbone_features = list(backbone_features) + backbone_features[-1] = encoder_visual + + pixel_features = self.pixel_decoder(backbone_features) + instance_features = self.instance_seg_head(pixel_features) + masks = self.mask_predictor(query_embeddings, instance_features) + return masks + + +class DotProductScoring(nn.Module): + def __init__(self, d_model=256, device=None, dtype=None, operations=None): + super().__init__() + self.hs_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.prompt_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.prompt_mlp = MLPWithNorm(d_model, 2048, d_model, 2, device=device, dtype=dtype, operations=operations) + self.scale = 1.0 / (d_model ** 0.5) + + def forward(self, query_embeddings, prompt_embeddings, prompt_mask=None): + prompt = self.prompt_mlp(prompt_embeddings) + if prompt_mask is not None: + weight = prompt_mask.unsqueeze(-1).to(dtype=prompt.dtype) + pooled = (prompt * weight).sum(dim=1) / weight.sum(dim=1).clamp(min=1) + else: + pooled = prompt.mean(dim=1) + hs = self.hs_proj(query_embeddings) + pp = self.prompt_proj(pooled).unsqueeze(-1).to(hs.dtype) + scores = torch.matmul(hs, pp) + return (scores * self.scale).clamp(-12.0, 12.0).squeeze(-1) + + +class SAM3Detector(nn.Module): + def __init__(self, d_model=256, embed_dim=1024, num_queries=200, device=None, dtype=None, operations=None, **kwargs): + super().__init__() + image_model = kwargs.pop("image_model", "SAM3") + for k in ("num_heads", "num_head_channels"): + kwargs.pop(k, None) + multiplex = image_model == "SAM31" + # SAM3: 4 FPN levels, drop last (scalp=1); SAM3.1: 3 levels, use all (scalp=0) + self.scalp = 0 if multiplex else 1 + self.backbone = nn.ModuleDict({ + "vision_backbone": SAM3VisionBackbone(embed_dim=embed_dim, d_model=d_model, multiplex=multiplex, device=device, dtype=dtype, operations=operations, **kwargs), + "language_backbone": nn.ModuleDict({"resizer": operations.Linear(embed_dim, d_model, device=device, dtype=dtype)}), + }) + self.transformer = Transformer(d_model=d_model, num_queries=num_queries, device=device, dtype=dtype, operations=operations) + self.segmentation_head = SegmentationHead(d_model=d_model, device=device, dtype=dtype, operations=operations) + self.geometry_encoder = GeometryEncoder(d_model=d_model, device=device, dtype=dtype, operations=operations) + self.dot_prod_scoring = DotProductScoring(d_model=d_model, device=device, dtype=dtype, operations=operations) + + def _get_backbone_features(self, images): + """Run backbone and return (detector_features, detector_positions, tracker_features, tracker_positions).""" + bb = self.backbone["vision_backbone"] + if bb.multiplex: + all_f, all_p, tf, tp = bb(images, tracker_mode="propagation") + else: + all_f, all_p, tf, tp = bb(images, need_tracker=True) + return all_f, all_p, tf, tp + + @staticmethod + def _run_geo_layer(layer, x, memory, memory_pos): + x = x + layer.self_attn(layer.norm1(x)) + x = x + layer.cross_attn_image(layer.norm2(x), memory + memory_pos, memory) + x = x + layer.linear2(F.relu(layer.linear1(layer.norm3(x)))) + return x + + def _detect(self, features, positions, text_embeddings=None, text_mask=None, + points=None, boxes=None): + """Shared detection: geometry encoding, transformer, scoring, segmentation.""" + B = features[0].shape[0] + # Scalp for encoder (use top-level feature), but keep all levels for segmentation head + seg_features = features + if self.scalp > 0: + features = features[:-self.scalp] + positions = positions[:-self.scalp] + enc_feat, enc_pos = features[-1], positions[-1] + _, _, H, W = enc_feat.shape + img_flat = enc_feat.flatten(2).permute(0, 2, 1) + pos_flat = enc_pos.flatten(2).permute(0, 2, 1) + + has_prompts = text_embeddings is not None or points is not None or boxes is not None + if has_prompts: + geo_enc = self.geometry_encoder + geo_prompts = geo_enc(points=points, boxes=boxes, image_features=img_flat) + geo_cls = geo_enc.norm(geo_enc.final_proj(cast_to_input(geo_enc.cls_embed.weight, img_flat).view(1, 1, -1).expand(B, -1, -1))) + for layer in geo_enc.encode: + geo_cls = self._run_geo_layer(layer, geo_cls, img_flat, pos_flat) + geo_cls = geo_enc.encode_norm(geo_cls) + if text_embeddings is not None and text_embeddings.shape[0] != B: + text_embeddings = text_embeddings.expand(B, -1, -1) + if text_mask is not None and text_mask.shape[0] != B: + text_mask = text_mask.expand(B, -1) + parts = [t for t in [text_embeddings, geo_prompts, geo_cls] if t is not None] + text_embeddings = torch.cat(parts, dim=1) + n_new = text_embeddings.shape[1] - (text_mask.shape[1] if text_mask is not None else 0) + if text_mask is not None: + text_mask = torch.cat([text_mask, torch.ones(B, n_new, dtype=torch.bool, device=text_mask.device)], dim=1) + else: + text_mask = torch.ones(B, text_embeddings.shape[1], dtype=torch.bool, device=text_embeddings.device) + + memory = self.transformer.encoder(img_flat, pos_flat, text_embeddings, text_mask) + dec_out = self.transformer.decoder(memory, pos_flat, text_embeddings, text_mask, H, W) + query_out, pred_boxes = dec_out["decoder_output"], dec_out["pred_boxes"] + + if text_embeddings is not None: + scores = self.dot_prod_scoring(query_out, text_embeddings, text_mask) + else: + scores = torch.zeros(B, query_out.shape[1], device=query_out.device) + + masks = self.segmentation_head(query_out, seg_features, encoder_hidden_states=memory, prompt=text_embeddings, prompt_mask=text_mask) + return box_cxcywh_to_xyxy(pred_boxes), scores, masks, dec_out + + def forward(self, images, text_embeddings=None, text_mask=None, points=None, boxes=None, threshold=0.3, orig_size=None): + features, positions, _, _ = self._get_backbone_features(images) + + if text_embeddings is not None: + text_embeddings = self.backbone["language_backbone"]["resizer"](text_embeddings) + if text_mask is not None: + text_mask = text_mask.bool() + + boxes_xyxy, scores, masks, dec_out = self._detect( + features, positions, text_embeddings, text_mask, points, boxes) + + if orig_size is not None: + oh, ow = orig_size + boxes_xyxy = boxes_xyxy * torch.tensor([ow, oh, ow, oh], device=boxes_xyxy.device, dtype=boxes_xyxy.dtype) + masks = F.interpolate(masks, size=orig_size, mode="bilinear", align_corners=False) + + return { + "boxes": boxes_xyxy, + "scores": scores, + "masks": masks, + "presence": dec_out.get("presence"), + } + + def forward_from_trunk(self, trunk_out, text_embeddings, text_mask): + """Run detection using a pre-computed ViTDet trunk output. + + text_embeddings must already be resized through language_backbone.resizer. + Returns dict with boxes (normalized xyxy), scores, masks at detector resolution. + """ + bb = self.backbone["vision_backbone"] + features = [conv(trunk_out) for conv in bb.convs] + positions = [cast_to_input(bb.position_encoding(f), f) for f in features] + + if text_mask is not None: + text_mask = text_mask.bool() + + boxes_xyxy, scores, masks, _ = self._detect(features, positions, text_embeddings, text_mask) + return {"boxes": boxes_xyxy, "scores": scores, "masks": masks} + + +class SAM3Model(nn.Module): + def __init__(self, device=None, dtype=None, operations=None, **kwargs): + super().__init__() + self.dtype = dtype + image_model = kwargs.get("image_model", "SAM3") + tracker_cls = TRACKER_CLASSES[image_model] + self.detector = SAM3Detector(device=device, dtype=dtype, operations=operations, **kwargs) + self.tracker = tracker_cls(device=device, dtype=dtype, operations=operations, **kwargs) + + def forward(self, images, **kwargs): + return self.detector(images, **kwargs) + + def forward_segment(self, images, point_inputs=None, box_inputs=None, mask_inputs=None): + """Interactive segmentation using SAM decoder with point/box/mask prompts. + + Args: + images: [B, 3, 1008, 1008] preprocessed images + point_inputs: {"point_coords": [B, N, 2], "point_labels": [B, N]} in 1008x1008 pixel space + box_inputs: [B, 2, 2] box corners (top-left, bottom-right) in 1008x1008 pixel space + mask_inputs: [B, 1, H, W] coarse mask logits to refine + Returns: + [B, 1, image_size, image_size] high-res mask logits + """ + bb = self.detector.backbone["vision_backbone"] + if bb.multiplex: + _, _, tracker_features, tracker_positions = bb(images, tracker_mode="interactive") + else: + _, _, tracker_features, tracker_positions = bb(images, need_tracker=True) + if self.detector.scalp > 0: + tracker_features = tracker_features[:-self.detector.scalp] + tracker_positions = tracker_positions[:-self.detector.scalp] + + high_res = list(tracker_features[:-1]) + backbone_feat = tracker_features[-1] + B, C, H, W = backbone_feat.shape + # Add no-memory embedding (init frame path) + no_mem = getattr(self.tracker, 'interactivity_no_mem_embed', None) + if no_mem is None: + no_mem = getattr(self.tracker, 'no_mem_embed', None) + if no_mem is not None: + feat_flat = backbone_feat.flatten(2).permute(0, 2, 1) + feat_flat = feat_flat + cast_to_input(no_mem, feat_flat) + backbone_feat = feat_flat.view(B, H, W, C).permute(0, 3, 1, 2) + + num_pts = 0 if point_inputs is None else point_inputs["point_labels"].size(1) + _, high_res_masks, _, _ = self.tracker._forward_sam_heads( + backbone_features=backbone_feat, + point_inputs=point_inputs, + mask_inputs=mask_inputs, + box_inputs=box_inputs, + high_res_features=high_res, + multimask_output=(0 < num_pts <= 1), + ) + return high_res_masks + + def forward_video(self, images, initial_masks, pbar=None, text_prompts=None, + new_det_thresh=0.5, max_objects=0, detect_interval=1): + """Track video with optional per-frame text-prompted detection.""" + bb = self.detector.backbone["vision_backbone"] + + def backbone_fn(frame, frame_idx=None): + trunk_out = bb.trunk(frame) + if bb.multiplex: + _, _, tf, tp = bb(frame, tracker_mode="propagation", cached_trunk=trunk_out, tracker_only=True) + else: + _, _, tf, tp = bb(frame, need_tracker=True, cached_trunk=trunk_out, tracker_only=True) + return tf, tp, trunk_out + + detect_fn = None + if text_prompts: + resizer = self.detector.backbone["language_backbone"]["resizer"] + resized = [(resizer(emb), m.bool() if m is not None else None) for emb, m in text_prompts] + def detect_fn(trunk_out): + all_scores, all_masks = [], [] + for emb, mask in resized: + det = self.detector.forward_from_trunk(trunk_out, emb, mask) + all_scores.append(det["scores"]) + all_masks.append(det["masks"]) + return {"scores": torch.cat(all_scores, dim=1), "masks": torch.cat(all_masks, dim=1)} + + if hasattr(self.tracker, 'track_video_with_detection'): + return self.tracker.track_video_with_detection( + backbone_fn, images, initial_masks, detect_fn, + new_det_thresh=new_det_thresh, max_objects=max_objects, + detect_interval=detect_interval, backbone_obj=bb, pbar=pbar) + # SAM3 (non-multiplex) — no detection support, requires initial masks + if initial_masks is None: + raise ValueError("SAM3 (non-multiplex) requires initial_mask for video tracking") + return self.tracker.track_video(backbone_fn, images, initial_masks, pbar=pbar, backbone_obj=bb) diff --git a/comfy/ldm/sam3/sam.py b/comfy/ldm/sam3/sam.py new file mode 100644 index 000000000..75cb457cf --- /dev/null +++ b/comfy/ldm/sam3/sam.py @@ -0,0 +1,425 @@ +# SAM3 shared components: primitives, ViTDet backbone, FPN neck, position encodings. + +import math + +import torch +import torch.nn as nn +import torch.nn.functional as F + +from comfy.ldm.modules.attention import optimized_attention +from comfy.ldm.flux.math import apply_rope +from comfy.ldm.flux.layers import EmbedND +from comfy.ops import cast_to_input + + +class MLP(nn.Module): + def __init__(self, input_dim, hidden_dim, output_dim, num_layers, sigmoid_output=False, device=None, dtype=None, operations=None): + super().__init__() + dims = [input_dim] + [hidden_dim] * (num_layers - 1) + [output_dim] + self.layers = nn.ModuleList([operations.Linear(dims[i], dims[i + 1], device=device, dtype=dtype) for i in range(num_layers)]) + self.sigmoid_output = sigmoid_output + + def forward(self, x): + for i, layer in enumerate(self.layers): + x = F.relu(layer(x)) if i < len(self.layers) - 1 else layer(x) + return torch.sigmoid(x) if self.sigmoid_output else x + + +class SAMAttention(nn.Module): + def __init__(self, embedding_dim, num_heads, downsample_rate=1, kv_in_dim=None, device=None, dtype=None, operations=None): + super().__init__() + self.num_heads = num_heads + internal_dim = embedding_dim // downsample_rate + kv_dim = kv_in_dim if kv_in_dim is not None else embedding_dim + self.q_proj = operations.Linear(embedding_dim, internal_dim, device=device, dtype=dtype) + self.k_proj = operations.Linear(kv_dim, internal_dim, device=device, dtype=dtype) + self.v_proj = operations.Linear(kv_dim, internal_dim, device=device, dtype=dtype) + self.out_proj = operations.Linear(internal_dim, embedding_dim, device=device, dtype=dtype) + + def forward(self, q, k, v): + q = self.q_proj(q) + k = self.k_proj(k) + v = self.v_proj(v) + return self.out_proj(optimized_attention(q, k, v, self.num_heads, low_precision_attention=False)) + + +class TwoWayAttentionBlock(nn.Module): + def __init__(self, embedding_dim, num_heads, mlp_dim=2048, attention_downsample_rate=2, skip_first_layer_pe=False, device=None, dtype=None, operations=None): + super().__init__() + self.skip_first_layer_pe = skip_first_layer_pe + self.self_attn = SAMAttention(embedding_dim, num_heads, device=device, dtype=dtype, operations=operations) + self.cross_attn_token_to_image = SAMAttention(embedding_dim, num_heads, downsample_rate=attention_downsample_rate, device=device, dtype=dtype, operations=operations) + self.cross_attn_image_to_token = SAMAttention(embedding_dim, num_heads, downsample_rate=attention_downsample_rate, device=device, dtype=dtype, operations=operations) + self.mlp = nn.Sequential(operations.Linear(embedding_dim, mlp_dim, device=device, dtype=dtype), nn.ReLU(), operations.Linear(mlp_dim, embedding_dim, device=device, dtype=dtype)) + self.norm1 = operations.LayerNorm(embedding_dim, device=device, dtype=dtype) + self.norm2 = operations.LayerNorm(embedding_dim, device=device, dtype=dtype) + self.norm3 = operations.LayerNorm(embedding_dim, device=device, dtype=dtype) + self.norm4 = operations.LayerNorm(embedding_dim, device=device, dtype=dtype) + + def forward(self, queries, keys, query_pe, key_pe): + if self.skip_first_layer_pe: + queries = self.norm1(self.self_attn(queries, queries, queries)) + else: + q = queries + query_pe + queries = self.norm1(queries + self.self_attn(q, q, queries)) + q, k = queries + query_pe, keys + key_pe + queries = self.norm2(queries + self.cross_attn_token_to_image(q, k, keys)) + queries = self.norm3(queries + self.mlp(queries)) + q, k = queries + query_pe, keys + key_pe + keys = self.norm4(keys + self.cross_attn_image_to_token(k, q, queries)) + return queries, keys + + +class TwoWayTransformer(nn.Module): + def __init__(self, depth=2, embedding_dim=256, num_heads=8, mlp_dim=2048, attention_downsample_rate=2, device=None, dtype=None, operations=None): + super().__init__() + self.layers = nn.ModuleList([ + TwoWayAttentionBlock(embedding_dim, num_heads, mlp_dim, attention_downsample_rate, + skip_first_layer_pe=(i == 0), device=device, dtype=dtype, operations=operations) + for i in range(depth) + ]) + self.final_attn_token_to_image = SAMAttention(embedding_dim, num_heads, downsample_rate=attention_downsample_rate, device=device, dtype=dtype, operations=operations) + self.norm_final = operations.LayerNorm(embedding_dim, device=device, dtype=dtype) + + def forward(self, image_embedding, image_pe, point_embedding): + queries, keys = point_embedding, image_embedding + for layer in self.layers: + queries, keys = layer(queries, keys, point_embedding, image_pe) + q, k = queries + point_embedding, keys + image_pe + queries = self.norm_final(queries + self.final_attn_token_to_image(q, k, keys)) + return queries, keys + + +class PositionEmbeddingRandom(nn.Module): + """Fourier feature positional encoding with random gaussian projection.""" + def __init__(self, num_pos_feats=64, scale=None): + super().__init__() + self.register_buffer("positional_encoding_gaussian_matrix", (scale or 1.0) * torch.randn(2, num_pos_feats)) + + def _encode(self, normalized_coords): + """Map normalized [0,1] coordinates to fourier features via random projection. Computes in fp32.""" + orig_dtype = normalized_coords.dtype + proj_matrix = self.positional_encoding_gaussian_matrix.to(device=normalized_coords.device, dtype=torch.float32) + projected = 2 * math.pi * (2 * normalized_coords.float() - 1) @ proj_matrix + return torch.cat([projected.sin(), projected.cos()], dim=-1).to(orig_dtype) + + def forward(self, size, device=None): + h, w = size + dev = device if device is not None else self.positional_encoding_gaussian_matrix.device + ones = torch.ones((h, w), device=dev, dtype=torch.float32) + norm_xy = torch.stack([(ones.cumsum(1) - 0.5) / w, (ones.cumsum(0) - 0.5) / h], dim=-1) + return self._encode(norm_xy).permute(2, 0, 1).unsqueeze(0) + + def forward_with_coords(self, pixel_coords, image_size): + norm = pixel_coords.clone() + norm[:, :, 0] /= image_size[1] + norm[:, :, 1] /= image_size[0] + return self._encode(norm) + + +# ViTDet backbone + FPN neck + +def window_partition(x: torch.Tensor, window_size: int): + B, H, W, C = x.shape + pad_h = (window_size - H % window_size) % window_size + pad_w = (window_size - W % window_size) % window_size + if pad_h > 0 or pad_w > 0: + x = F.pad(x, (0, 0, 0, pad_w, 0, pad_h)) + Hp, Wp = H + pad_h, W + pad_w + x = x.view(B, Hp // window_size, window_size, Wp // window_size, window_size, C) + windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C) + return windows, (Hp, Wp) + + +def window_unpartition(windows: torch.Tensor, window_size: int, pad_hw, hw): + Hp, Wp = pad_hw + H, W = hw + B = windows.shape[0] // (Hp * Wp // window_size // window_size) + x = windows.view(B, Hp // window_size, Wp // window_size, window_size, window_size, -1) + x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, Hp, Wp, -1) + if Hp > H or Wp > W: + x = x[:, :H, :W, :].contiguous() + return x + + +def rope_2d(end_x: int, end_y: int, dim: int, theta: float = 10000.0, scale_pos: float = 1.0): + """Generate 2D axial RoPE using flux EmbedND. Returns [1, 1, HW, dim//2, 2, 2].""" + t = torch.arange(end_x * end_y, dtype=torch.float32) + ids = torch.stack([(t % end_x) * scale_pos, + torch.div(t, end_x, rounding_mode="floor") * scale_pos], dim=-1) + return EmbedND(dim=dim, theta=theta, axes_dim=[dim // 2, dim // 2])(ids.unsqueeze(0)) + + +class _ViTMLP(nn.Module): + def __init__(self, dim, mlp_ratio=4.0, device=None, dtype=None, operations=None): + super().__init__() + hidden = int(dim * mlp_ratio) + self.fc1 = operations.Linear(dim, hidden, device=device, dtype=dtype) + self.act = nn.GELU() + self.fc2 = operations.Linear(hidden, dim, device=device, dtype=dtype) + + def forward(self, x): + return self.fc2(self.act(self.fc1(x))) + + +class Attention(nn.Module): + """ViTDet multi-head attention with fused QKV projection.""" + + def __init__(self, dim, num_heads=8, qkv_bias=True, use_rope=False, device=None, dtype=None, operations=None): + super().__init__() + self.num_heads = num_heads + self.head_dim = dim // num_heads + self.use_rope = use_rope + self.qkv = operations.Linear(dim, dim * 3, bias=qkv_bias, device=device, dtype=dtype) + self.proj = operations.Linear(dim, dim, device=device, dtype=dtype) + + def forward(self, x, freqs_cis=None): + B, N, C = x.shape + qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, self.head_dim) + q, k, v = qkv.permute(2, 0, 3, 1, 4).unbind(dim=0) + if self.use_rope and freqs_cis is not None: + q, k = apply_rope(q, k, freqs_cis) + return self.proj(optimized_attention(q, k, v, self.num_heads, skip_reshape=True, low_precision_attention=False)) + + +class Block(nn.Module): + def __init__(self, dim, num_heads, mlp_ratio=4.0, qkv_bias=True, window_size=0, use_rope=False, device=None, dtype=None, operations=None): + super().__init__() + self.window_size = window_size + self.norm1 = operations.LayerNorm(dim, device=device, dtype=dtype) + self.attn = Attention(dim, num_heads, qkv_bias, use_rope, device=device, dtype=dtype, operations=operations) + self.norm2 = operations.LayerNorm(dim, device=device, dtype=dtype) + self.mlp = _ViTMLP(dim, mlp_ratio, device=device, dtype=dtype, operations=operations) + + def forward(self, x, freqs_cis=None): + shortcut = x + x = self.norm1(x) + if self.window_size > 0: + H, W = x.shape[1], x.shape[2] + x, pad_hw = window_partition(x, self.window_size) + x = x.view(x.shape[0], self.window_size * self.window_size, -1) + x = self.attn(x, freqs_cis=freqs_cis) + x = x.view(-1, self.window_size, self.window_size, x.shape[-1]) + x = window_unpartition(x, self.window_size, pad_hw, (H, W)) + else: + B, H, W, C = x.shape + x = x.view(B, H * W, C) + x = self.attn(x, freqs_cis=freqs_cis) + x = x.view(B, H, W, C) + x = shortcut + x + x = x + self.mlp(self.norm2(x)) + return x + + +class PatchEmbed(nn.Module): + def __init__(self, patch_size=14, in_chans=3, embed_dim=1024, device=None, dtype=None, operations=None): + super().__init__() + self.proj = operations.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size, bias=False, device=device, dtype=dtype) + + def forward(self, x): + return self.proj(x) + + +class ViTDet(nn.Module): + def __init__(self, img_size=1008, patch_size=14, embed_dim=1024, depth=32, num_heads=16, mlp_ratio=4.625, qkv_bias=True, window_size=24, + global_att_blocks=(7, 15, 23, 31), use_rope=True, pretrain_img_size=336, device=None, dtype=None, operations=None, **kwargs): + super().__init__() + self.img_size = img_size + self.patch_size = patch_size + self.embed_dim = embed_dim + self.num_heads = num_heads + self.global_att_blocks = set(global_att_blocks) + + self.patch_embed = PatchEmbed(patch_size, 3, embed_dim, device=device, dtype=dtype, operations=operations) + + num_patches = (pretrain_img_size // patch_size) ** 2 + 1 # +1 for cls token + self.pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim, device=device, dtype=dtype)) + + self.ln_pre = operations.LayerNorm(embed_dim, device=device, dtype=dtype) + + grid_size = img_size // patch_size + pretrain_grid = pretrain_img_size // patch_size + + self.blocks = nn.ModuleList() + for i in range(depth): + is_global = i in self.global_att_blocks + self.blocks.append(Block( + embed_dim, num_heads, mlp_ratio, qkv_bias, + window_size=0 if is_global else window_size, + use_rope=use_rope, + device=device, dtype=dtype, operations=operations, + )) + + if use_rope: + rope_scale = pretrain_grid / grid_size + self.register_buffer("freqs_cis", rope_2d(grid_size, grid_size, embed_dim // num_heads, scale_pos=rope_scale), persistent=False) + self.register_buffer("freqs_cis_window", rope_2d(window_size, window_size, embed_dim // num_heads), persistent=False) + else: + self.freqs_cis = None + self.freqs_cis_window = None + + def _get_pos_embed(self, num_tokens): + pos = self.pos_embed + if pos.shape[1] == num_tokens: + return pos + cls_pos = pos[:, :1] + spatial_pos = pos[:, 1:] + old_size = int(math.sqrt(spatial_pos.shape[1])) + new_size = int(math.sqrt(num_tokens - 1)) if num_tokens > 1 else old_size + spatial_2d = spatial_pos.reshape(1, old_size, old_size, -1).permute(0, 3, 1, 2) + tiles_h = new_size // old_size + 1 + tiles_w = new_size // old_size + 1 + tiled = spatial_2d.tile([1, 1, tiles_h, tiles_w])[:, :, :new_size, :new_size] + tiled = tiled.permute(0, 2, 3, 1).reshape(1, new_size * new_size, -1) + return torch.cat([cls_pos, tiled], dim=1) + + def forward(self, x): + x = self.patch_embed(x) + B, C, Hp, Wp = x.shape + x = x.permute(0, 2, 3, 1).reshape(B, Hp * Wp, C) + + pos = cast_to_input(self._get_pos_embed(Hp * Wp + 1), x) + x = x + pos[:, 1:Hp * Wp + 1] + + x = x.view(B, Hp, Wp, C) + x = self.ln_pre(x) + + freqs_cis_global = self.freqs_cis + freqs_cis_win = self.freqs_cis_window + if freqs_cis_global is not None: + freqs_cis_global = cast_to_input(freqs_cis_global, x) + if freqs_cis_win is not None: + freqs_cis_win = cast_to_input(freqs_cis_win, x) + + for block in self.blocks: + fc = freqs_cis_win if block.window_size > 0 else freqs_cis_global + x = block(x, freqs_cis=fc) + + return x.permute(0, 3, 1, 2) + + +class FPNScaleConv(nn.Module): + def __init__(self, in_dim, out_dim, scale, device=None, dtype=None, operations=None): + super().__init__() + if scale == 4.0: + self.dconv_2x2_0 = operations.ConvTranspose2d(in_dim, in_dim // 2, kernel_size=2, stride=2, device=device, dtype=dtype) + self.dconv_2x2_1 = operations.ConvTranspose2d(in_dim // 2, in_dim // 4, kernel_size=2, stride=2, device=device, dtype=dtype) + proj_in = in_dim // 4 + elif scale == 2.0: + self.dconv_2x2 = operations.ConvTranspose2d(in_dim, in_dim // 2, kernel_size=2, stride=2, device=device, dtype=dtype) + proj_in = in_dim // 2 + elif scale == 1.0: + proj_in = in_dim + elif scale == 0.5: + self.pool = nn.MaxPool2d(kernel_size=2, stride=2) + proj_in = in_dim + self.scale = scale + self.conv_1x1 = operations.Conv2d(proj_in, out_dim, kernel_size=1, device=device, dtype=dtype) + self.conv_3x3 = operations.Conv2d(out_dim, out_dim, kernel_size=3, padding=1, device=device, dtype=dtype) + + def forward(self, x): + if self.scale == 4.0: + x = F.gelu(self.dconv_2x2_0(x)) + x = self.dconv_2x2_1(x) + elif self.scale == 2.0: + x = self.dconv_2x2(x) + elif self.scale == 0.5: + x = self.pool(x) + x = self.conv_1x1(x) + x = self.conv_3x3(x) + return x + + +class PositionEmbeddingSine(nn.Module): + """2D sinusoidal position encoding (DETR-style) with result caching.""" + def __init__(self, num_pos_feats=256, temperature=10000.0, normalize=True, scale=None): + super().__init__() + assert num_pos_feats % 2 == 0 + self.half_dim = num_pos_feats // 2 + self.temperature = temperature + self.normalize = normalize + self.scale = scale if scale is not None else 2 * math.pi + self._cache = {} + + def _sincos(self, vals): + """Encode 1D values to interleaved sin/cos features.""" + freqs = self.temperature ** (2 * (torch.arange(self.half_dim, dtype=torch.float32, device=vals.device) // 2) / self.half_dim) + raw = vals[..., None] * self.scale / freqs + return torch.stack((raw[..., 0::2].sin(), raw[..., 1::2].cos()), dim=-1).flatten(-2) + + def _encode_xy(self, x, y): + """Encode normalized x, y coordinates to sinusoidal features. Returns (pos_x, pos_y) each [N, half_dim].""" + dim_t = self.temperature ** (2 * (torch.arange(self.half_dim, dtype=torch.float32, device=x.device) // 2) / self.half_dim) + pos_x = x[:, None] * self.scale / dim_t + pos_y = y[:, None] * self.scale / dim_t + pos_x = torch.stack((pos_x[:, 0::2].sin(), pos_x[:, 1::2].cos()), dim=2).flatten(1) + pos_y = torch.stack((pos_y[:, 0::2].sin(), pos_y[:, 1::2].cos()), dim=2).flatten(1) + return pos_x, pos_y + + def encode_boxes(self, cx, cy, w, h): + """Encode box center + size to [N, d_model+2] features.""" + pos_x, pos_y = self._encode_xy(cx, cy) + return torch.cat((pos_y, pos_x, h[:, None], w[:, None]), dim=1) + + def forward(self, x): + B, C, H, W = x.shape + key = (H, W, x.device) + if key not in self._cache: + gy = torch.arange(H, dtype=torch.float32, device=x.device) + gx = torch.arange(W, dtype=torch.float32, device=x.device) + if self.normalize: + gy, gx = gy / (H - 1 + 1e-6), gx / (W - 1 + 1e-6) + yy, xx = torch.meshgrid(gy, gx, indexing="ij") + self._cache[key] = torch.cat((self._sincos(yy), self._sincos(xx)), dim=-1).permute(2, 0, 1).unsqueeze(0) + return self._cache[key].expand(B, -1, -1, -1) + + +class SAM3VisionBackbone(nn.Module): + def __init__(self, embed_dim=1024, d_model=256, multiplex=False, device=None, dtype=None, operations=None, **kwargs): + super().__init__() + self.trunk = ViTDet(embed_dim=embed_dim, device=device, dtype=dtype, operations=operations, **kwargs) + self.position_encoding = PositionEmbeddingSine(num_pos_feats=d_model, normalize=True) + self.multiplex = multiplex + + fpn_args = dict(device=device, dtype=dtype, operations=operations) + if multiplex: + scales = [4.0, 2.0, 1.0] + self.convs = nn.ModuleList([FPNScaleConv(embed_dim, d_model, s, **fpn_args) for s in scales]) + self.propagation_convs = nn.ModuleList([FPNScaleConv(embed_dim, d_model, s, **fpn_args) for s in scales]) + self.interactive_convs = nn.ModuleList([FPNScaleConv(embed_dim, d_model, s, **fpn_args) for s in scales]) + else: + scales = [4.0, 2.0, 1.0, 0.5] + self.convs = nn.ModuleList([FPNScaleConv(embed_dim, d_model, s, **fpn_args) for s in scales]) + self.sam2_convs = nn.ModuleList([FPNScaleConv(embed_dim, d_model, s, **fpn_args) for s in scales]) + + def forward(self, images, need_tracker=False, tracker_mode=None, cached_trunk=None, tracker_only=False): + backbone_out = cached_trunk if cached_trunk is not None else self.trunk(images) + + if tracker_only: + # Skip detector FPN when only tracker features are needed (video tracking) + if self.multiplex: + tracker_convs = self.propagation_convs if tracker_mode == "propagation" else self.interactive_convs + else: + tracker_convs = self.sam2_convs + tracker_features = [conv(backbone_out) for conv in tracker_convs] + tracker_positions = [cast_to_input(self.position_encoding(f), f) for f in tracker_features] + return None, None, tracker_features, tracker_positions + + features = [conv(backbone_out) for conv in self.convs] + positions = [cast_to_input(self.position_encoding(f), f) for f in features] + + if self.multiplex: + if tracker_mode == "propagation": + tracker_convs = self.propagation_convs + elif tracker_mode == "interactive": + tracker_convs = self.interactive_convs + else: + return features, positions, None, None + elif need_tracker: + tracker_convs = self.sam2_convs + else: + return features, positions, None, None + + tracker_features = [conv(backbone_out) for conv in tracker_convs] + tracker_positions = [cast_to_input(self.position_encoding(f), f) for f in tracker_features] + return features, positions, tracker_features, tracker_positions diff --git a/comfy/ldm/sam3/tracker.py b/comfy/ldm/sam3/tracker.py new file mode 100644 index 000000000..8f7481003 --- /dev/null +++ b/comfy/ldm/sam3/tracker.py @@ -0,0 +1,1785 @@ +# SAM3 video tracker: memory encoder, memory attention, SAM mask decoder/prompt encoder. + +import numpy as np +import torch +import torch.nn as nn +import torch.nn.functional as F +from tqdm import tqdm + +try: + import cv2 + _HAS_CV2 = True +except ImportError: + from scipy import ndimage + _HAS_CV2 = False + +import comfy.model_management +from comfy.ldm.modules.attention import optimized_attention +from comfy.ldm.sam3.sam import rope_2d, PositionEmbeddingSine +from comfy.ops import cast_to_input +from comfy.ldm.flux.math import apply_rope1 +from comfy.ldm.cascade.common import LayerNorm2d_op +from comfy.ldm.sam3.sam import MLP, PositionEmbeddingRandom +from comfy.ldm.sam3.sam import TwoWayTransformer as SAMTwoWayTransformer + +NO_OBJ_SCORE = -1024.0 + + +def to_spatial(x, H, W): + """Reshape (B, H*W, C) → (B, C, H, W).""" + return x.view(x.shape[0], H, W, -1).permute(0, 3, 1, 2) + +class MultiplexState: + """Tracks object-to-slot assignments for multiplex tracking. Provides mux/demux operations.""" + + def __init__(self, num_objects, multiplex_count, device, dtype): + self.multiplex_count = multiplex_count + self.device = device + self.dtype = dtype + self._build(num_objects) + + def mux(self, x): + """[N_obj, ...] -> [num_buckets, multiplex_count, ...]""" + out_shape = (self.num_buckets, self.multiplex_count) + x.shape[1:] + return (self.mux_matrix.to(device=x.device, dtype=x.dtype) @ x.reshape(self.total_valid_entries, -1)).view(out_shape) + + def demux(self, x): + """[num_buckets, multiplex_count, ...] -> [N_obj, ...]""" + out_shape = (self.total_valid_entries,) + x.shape[2:] + flat = x.reshape(self.num_buckets * self.multiplex_count, -1) + return (self.demux_matrix.to(device=x.device, dtype=x.dtype) @ flat).view(out_shape) + + def get_valid_object_mask(self): + """[num_buckets, multiplex_count] bool tensor, True for valid slots.""" + return (self.mux_matrix.sum(dim=1) > 0).reshape(self.num_buckets, self.multiplex_count) + + def _build(self, num_objects): + M = self.multiplex_count + self.num_buckets = (num_objects + M - 1) // M + self.total_valid_entries = num_objects + total_slots = self.num_buckets * M + self.mux_matrix = torch.zeros(total_slots, num_objects, device=self.device, dtype=self.dtype) + self.demux_matrix = torch.zeros(num_objects, total_slots, device=self.device, dtype=self.dtype) + oids = torch.arange(num_objects, device=self.device) + slots = (oids // M) * M + (oids % M) + self.mux_matrix[slots, oids] = 1.0 + self.demux_matrix[oids, slots] = 1.0 + + def add_objects(self, n_new): + """Grow multiplex state for n_new additional objects.""" + self._build(self.total_valid_entries + n_new) + +def _compute_mask_overlap(masks_a, masks_b): + """Max of IoU and IoM (intersection over minimum area). More robust to size differences.""" + a_flat = (masks_a > 0).float().flatten(1) + b_flat = (masks_b > 0).float().flatten(1) + intersection = a_flat @ b_flat.T + area_a = a_flat.sum(1, keepdim=True) + area_b = b_flat.sum(1, keepdim=True).T + iou = intersection / (area_a + area_b - intersection).clamp(min=1) + iom = intersection / torch.min(area_a.expand_as(iou), area_b.expand_as(iou)).clamp(min=1) + return torch.max(iou, iom) + + +def _nms_masks(masks, scores, thresh=0.5): + """Mask-based NMS using IoU+IoM overlap. Returns (filtered_masks, filtered_scores).""" + order = scores.argsort(descending=True) + masks, scores = masks[order], scores[order] + keep = [] + for i in range(masks.shape[0]): + if keep: + if _compute_mask_overlap(masks[i:i+1], masks[torch.tensor(keep, device=masks.device)]).max() >= thresh: + continue + keep.append(i) + return masks[keep], scores[keep] + + +def _get_connected_components(mask_bin): + """Get connected component labels and areas. mask_bin: [B, 1, H, W] uint8.""" + labels_list, areas_list = [], [] + for i in range(mask_bin.shape[0]): + m = mask_bin[i, 0].cpu().numpy() + if _HAS_CV2: + _, labeled, stats, _ = cv2.connectedComponentsWithStats(m, connectivity=8) + areas = stats[labeled, cv2.CC_STAT_AREA].astype('int32') + else: + labeled, num_features = ndimage.label(m) + areas = np.zeros_like(m, dtype=np.int32) + for c in range(1, num_features + 1): + component = labeled == c + areas[component] = component.sum() + labels_list.append(torch.from_numpy(labeled).to(mask_bin.device)) + areas_list.append(torch.from_numpy(areas).to(device=mask_bin.device, dtype=torch.int32)) + return torch.stack(labels_list).unsqueeze(1), torch.stack(areas_list).unsqueeze(1) + + +def fill_holes_in_mask_scores(mask, max_area=0): + """Remove small foreground sprinkles and fill small background holes using connected components.""" + if max_area <= 0: + return mask + + # Fill holes: small connected components in background → foreground + mask_bg = (mask <= 0).to(torch.uint8) + _, areas_bg = _get_connected_components(mask_bg) + small_bg = mask_bg.bool() & (areas_bg <= max_area) + mask = torch.where(small_bg, 0.1, mask) + + # Remove sprinkles: small connected components in foreground → background + # Only remove if area < min(max_area, half of total foreground area) + mask_fg = (mask > 0).to(torch.uint8) + fg_area_thresh = mask_fg.sum(dim=(2, 3), keepdim=True, dtype=torch.int32) + fg_area_thresh.floor_divide_(2).clamp_(max=max_area) + _, areas_fg = _get_connected_components(mask_fg) + small_fg = mask_fg.bool() & (areas_fg <= fg_area_thresh) + mask = torch.where(small_fg, -0.1, mask) + + return mask + + +def apply_rope_memory(q, k, freqs, num_heads, num_k_exclude_rope=0): + """Apply 2D axial RoPE to memory attention using flux rope format. + + Args: + q: [B, Nq, C] projected queries (current frame features) + k: [B, Nk, C] projected keys (memory tokens) + freqs: [1, Nq, dim//2, 2, 2] flux-format rotation matrices for one frame + num_heads: number of attention heads + num_k_exclude_rope: number of trailing k tokens to skip RoPE (object pointers) + """ + B, Nq, C = q.shape + head_dim = C // num_heads + + # freqs shape: [1, 1, Nq, dim//2, 2, 2] (heads broadcast dim already included) + q_h = q.view(B, Nq, num_heads, head_dim).transpose(1, 2) + q_h = apply_rope1(q_h, freqs) + q = q_h.transpose(1, 2).reshape(B, Nq, C) + + # Apply RoPE to k (excluding last num_k_exclude_rope tokens) + Nk = k.shape[1] + num_k_rope = Nk - num_k_exclude_rope + if num_k_rope > 0: + # Repeat freqs for multiple frames of spatial memory + Nf = freqs.shape[2] # spatial positions in one frame + if num_k_rope > Nf: + r = (num_k_rope + Nf - 1) // Nf + pe_k = freqs.repeat(1, 1, r, 1, 1, 1)[:, :, :num_k_rope] + else: + pe_k = freqs[:, :, :num_k_rope] + + k_h = k[:, :num_k_rope].view(B, num_k_rope, num_heads, head_dim).transpose(1, 2) + k_h = apply_rope1(k_h, pe_k) + k = k.clone() + k[:, :num_k_rope] = k_h.transpose(1, 2).reshape(B, num_k_rope, C) + + return q, k + + +def get_1d_sine_pe(pos_inds, dim, temperature=10000): + """1D sinusoidal positional encoding for temporal positions.""" + pe_dim = dim // 2 + dim_t = torch.arange(pe_dim, dtype=torch.float32, device=pos_inds.device) + dim_t = temperature ** (2 * (dim_t // 2) / pe_dim) + pos_embed = pos_inds.unsqueeze(-1) / dim_t + return torch.cat([pos_embed.sin(), pos_embed.cos()], dim=-1) + + +def _pad_to_buckets(tensor, target_buckets): + """Pad a [num_buckets, ...] tensor to target_buckets along dim 0 if needed.""" + if tensor.shape[0] >= target_buckets: + return tensor + pad_shape = (target_buckets - tensor.shape[0],) + tensor.shape[1:] + return torch.cat([tensor, torch.zeros(pad_shape, device=tensor.device, dtype=tensor.dtype)], dim=0) + + +def pack_masks(masks): + """Pack binary masks [*, H, W] to bit-packed [*, H, W//8] uint8. W must be divisible by 8.""" + binary = masks > 0 + shifts = torch.arange(8, device=masks.device) + return (binary.view(*masks.shape[:-1], -1, 8) * (1 << shifts)).sum(-1).byte() + + +def unpack_masks(packed): + """Unpack bit-packed [*, H, W//8] uint8 to bool [*, H, W*8].""" + shifts = torch.arange(8, device=packed.device) + return ((packed.unsqueeze(-1) >> shifts) & 1).view(*packed.shape[:-1], -1).bool() + + +def _compute_backbone(backbone_fn, frame, frame_idx=None): + """Compute backbone features for a single frame. Returns (vision_feats, vision_pos, feat_sizes, features, trunk_out).""" + features, positions, trunk_out = backbone_fn(frame, frame_idx=frame_idx) + feat_sizes = [(x.shape[-2], x.shape[-1]) for x in features] + vision_feats = [x.flatten(2).permute(0, 2, 1) for x in features] + vision_pos = [x.flatten(2).permute(0, 2, 1) for x in positions] + return vision_feats, vision_pos, feat_sizes, features, trunk_out + + +def collect_memory_tokens(output_dict, frame_idx, num_maskmem, maskmem_tpos_enc, device, + collect_image_feats=False, tpos_v2=False, num_buckets=None): + """Collect spatial memory, position encodings, and optionally image features from past frames.""" + to_cat_memory, to_cat_memory_pos = [], [] + to_cat_image_feat, to_cat_image_pos = [], [] + + def _append(out, tpos_idx): + feats = out["maskmem_features"].to(device) + if num_buckets is not None: + feats = _pad_to_buckets(feats, num_buckets) + to_cat_memory.append(feats.flatten(2).permute(0, 2, 1)) + enc = out["maskmem_pos_enc"][-1].to(device).flatten(2).permute(0, 2, 1) + if num_buckets is not None: + enc = _pad_to_buckets(enc, num_buckets) + tpos = cast_to_input(maskmem_tpos_enc[tpos_idx], enc) + to_cat_memory_pos.append(enc + tpos) + if collect_image_feats and "image_features" in out: + to_cat_image_feat.append(out["image_features"].to(device)) + to_cat_image_pos.append(out["image_pos_enc"].to(device) + tpos) + + cond_outputs = output_dict["cond_frame_outputs"] + for t, out in cond_outputs.items(): + if tpos_v2: + t_pos = frame_idx - t + tpos_idx = num_maskmem - t_pos - 1 if 0 < t_pos < num_maskmem else num_maskmem - 1 + else: + tpos_idx = num_maskmem - 1 + _append(out, tpos_idx) + + for t_pos in range(1, num_maskmem): + out = output_dict["non_cond_frame_outputs"].get(frame_idx - (num_maskmem - t_pos), None) + if out is None or out.get("maskmem_features") is None: + continue + _append(out, num_maskmem - t_pos - 1) + + return to_cat_memory, to_cat_memory_pos, to_cat_image_feat, to_cat_image_pos, cond_outputs + + +def compute_tpos_enc(rel_pos_list, device, d_model, proj_layer, dtype=None, max_abs_pos=None): + """Temporal position encoding for object pointers.""" + pos_enc = torch.tensor(rel_pos_list, dtype=torch.float32, device=device) / max((max_abs_pos or 2) - 1, 1) + pos_enc = get_1d_sine_pe(pos_enc, dim=d_model) + if dtype is not None: + pos_enc = pos_enc.to(dtype) + return proj_layer(pos_enc) + + +def forward_sam_heads(backbone_features, prompt_encoder, mask_decoder, obj_ptr_proj, no_obj_fn, + image_size, point_inputs=None, mask_inputs=None, box_inputs=None, + high_res_features=None, multimask_output=False): + """Shared SAM prompt encoder + mask decoder forward for both SAM3 and SAM3.1 trackers.""" + device = backbone_features.device + # Batch size from inputs (mask_inputs may have N_obj > 1 while backbone is batch 1) + if mask_inputs is not None: + B = mask_inputs.shape[0] + elif box_inputs is not None: + B = box_inputs.shape[0] + elif point_inputs is not None: + B = point_inputs["point_coords"].shape[0] + else: + B = backbone_features.shape[0] + + if point_inputs is not None: + sam_point_coords = point_inputs["point_coords"] + sam_point_labels = point_inputs["point_labels"] + else: + sam_point_coords = torch.zeros(B, 1, 2, device=device) + sam_point_labels = -torch.ones(B, 1, dtype=torch.int32, device=device) + + if mask_inputs is not None: + prompt_size = (prompt_encoder.image_embedding_size[0] * 4, prompt_encoder.image_embedding_size[1] * 4) + if mask_inputs.shape[-2:] != prompt_size: + sam_mask_prompt = F.interpolate(mask_inputs, size=prompt_size, mode="bilinear", align_corners=False, antialias=True) + else: + sam_mask_prompt = mask_inputs + else: + sam_mask_prompt = None + + sparse, dense = prompt_encoder(points=(sam_point_coords, sam_point_labels), boxes=box_inputs, masks=sam_mask_prompt) + sparse = cast_to_input(sparse, backbone_features) + dense = cast_to_input(dense, backbone_features) + image_pe = cast_to_input(prompt_encoder.get_dense_pe(), backbone_features) + + low_res_multimasks, ious, sam_output_tokens, object_score_logits = mask_decoder( + image_embeddings=backbone_features, image_pe=image_pe, + sparse_prompt_embeddings=sparse, dense_prompt_embeddings=dense, + high_res_features=high_res_features, multimask_output=multimask_output, return_all=True, + ) + + is_obj_appearing = object_score_logits > 0 + low_res_multimasks = torch.where(is_obj_appearing[:, None, None], low_res_multimasks, + torch.tensor(NO_OBJ_SCORE, device=device, dtype=low_res_multimasks.dtype)) + high_res_multimasks = F.interpolate(low_res_multimasks, size=(image_size, image_size), mode="bilinear", align_corners=False) + + sam_output_token = sam_output_tokens[:, 0] + if multimask_output: + best_iou_inds = torch.argmax(ious, dim=-1) + batch_inds = torch.arange(B, device=device) + low_res_masks = low_res_multimasks[batch_inds, best_iou_inds].unsqueeze(1) + high_res_masks = high_res_multimasks[batch_inds, best_iou_inds].unsqueeze(1) + if sam_output_tokens.size(1) > 1: + sam_output_token = sam_output_tokens[batch_inds, best_iou_inds] + else: + low_res_masks, high_res_masks = low_res_multimasks, high_res_multimasks + + obj_ptr = obj_ptr_proj(sam_output_token) + obj_ptr = no_obj_fn(obj_ptr, is_obj_appearing) + + return low_res_masks, high_res_masks, obj_ptr, object_score_logits + + +def use_mask_as_output(backbone_features, high_res_features, mask_inputs, mask_downsample, + prompt_encoder, mask_decoder, obj_ptr_proj, no_obj_fn, image_size, backbone_stride): + """Shared mask-as-output for both SAM3 and SAM3.1 trackers.""" + out_scale, out_bias = 20.0, -10.0 + mask_inputs_float = cast_to_input(mask_inputs, backbone_features) + high_res_masks = mask_inputs_float * out_scale + out_bias + low_res_masks = F.interpolate(high_res_masks, size=(image_size // backbone_stride * 4,) * 2, + mode="bilinear", align_corners=False, antialias=True) + _, _, obj_ptr, _ = forward_sam_heads( + backbone_features, prompt_encoder, mask_decoder, obj_ptr_proj, no_obj_fn, + image_size, mask_inputs=mask_downsample(mask_inputs_float), high_res_features=high_res_features, + ) + is_obj_appearing = torch.any(mask_inputs.flatten(1) > 0.0, dim=1)[..., None] + alpha = is_obj_appearing.to(obj_ptr.dtype) + object_score_logits = out_scale * alpha + out_bias + return low_res_masks, high_res_masks, obj_ptr, object_score_logits + + +# Split attention with configurable input dims (for asymmetric cross-attention) +class SplitAttn(nn.Module): + def __init__(self, embed_dim, num_heads=1, kv_dim=None, internal_dim=None, device=None, dtype=None, operations=None): + super().__init__() + self.num_heads = num_heads + kv_dim = kv_dim or embed_dim + internal_dim = internal_dim or embed_dim + self.q_proj = operations.Linear(embed_dim, internal_dim, device=device, dtype=dtype) + self.k_proj = operations.Linear(kv_dim, internal_dim, device=device, dtype=dtype) + self.v_proj = operations.Linear(kv_dim, internal_dim, device=device, dtype=dtype) + self.out_proj = operations.Linear(internal_dim, embed_dim, device=device, dtype=dtype) + + def forward(self, q, k=None, v=None, rope=None, num_k_exclude_rope=0): + if k is None: + k = q + if v is None: + v = k + q = self.q_proj(q) + k = self.k_proj(k) + v = self.v_proj(v) + if rope is not None: + q, k = apply_rope_memory(q, k, rope, self.num_heads, num_k_exclude_rope) + out = optimized_attention(q, k, v, self.num_heads, low_precision_attention=False) + return self.out_proj(out) + + +class MemoryAttnLayer(nn.Module): + def __init__(self, d_model=256, num_heads=1, kv_dim=64, dim_ff=2048, device=None, dtype=None, operations=None): + super().__init__() + self.num_heads = num_heads + self.self_attn = SplitAttn(d_model, num_heads, device=device, dtype=dtype, operations=operations) + self.cross_attn_image = SplitAttn(d_model, num_heads, kv_dim=kv_dim, device=device, dtype=dtype, operations=operations) + self.linear1 = operations.Linear(d_model, dim_ff, device=device, dtype=dtype) + self.linear2 = operations.Linear(dim_ff, d_model, device=device, dtype=dtype) + self.norm1 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm2 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm3 = operations.LayerNorm(d_model, device=device, dtype=dtype) + + def forward(self, x, memory, memory_pos=None, rope=None, num_k_exclude_rope=0): + x = x + self.self_attn(self.norm1(x), rope=rope) + mem_k = memory + memory_pos if memory_pos is not None else memory + x = x + self.cross_attn_image(self.norm2(x), mem_k, memory, rope=rope, num_k_exclude_rope=num_k_exclude_rope) + normed = self.norm3(x) + x = x + self.linear2(F.relu(self.linear1(normed))) + return x + + +class MemoryAttnEncoder(nn.Module): + def __init__(self, d_model=256, num_heads=1, kv_dim=64, dim_ff=2048, num_layers=4, image_size=1008, patch_size=14, + device=None, dtype=None, operations=None): + super().__init__() + self.layers = nn.ModuleList([ + MemoryAttnLayer(d_model, num_heads, kv_dim, dim_ff, device=device, dtype=dtype, operations=operations) + for _ in range(num_layers) + ]) + self.norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + hw = image_size // patch_size + self.register_buffer("_rope", rope_2d(hw, hw, d_model // num_heads), persistent=False) + + def forward(self, x, memory, src_pos=None, memory_pos=None, num_k_exclude_rope=0): + if src_pos is not None: + x = x + 0.1 * src_pos + + rope = self._rope.to(device=x.device) + for layer in self.layers: + x = layer(x, memory, memory_pos=memory_pos, rope=rope, num_k_exclude_rope=num_k_exclude_rope) + return self.norm(x) + + +class MemoryTransformer(nn.Module): + def __init__(self, d_model=256, num_heads=1, kv_dim=64, dim_ff=2048, num_layers=4, device=None, dtype=None, operations=None): + super().__init__() + self.encoder = MemoryAttnEncoder(d_model, num_heads, kv_dim, dim_ff, num_layers, device=device, dtype=dtype, operations=operations) + + +def _upscale_masks(output_upscaling, conv_s0, conv_s1, src_out, high_res_features): + """Shared upscaling for SAM mask decoders: deconv + high-res feature integration.""" + dc1, ln1, act1, dc2, act2 = output_upscaling + if high_res_features is not None: + upscaled = act1(ln1(dc1(src_out) + conv_s1(high_res_features[1]))) + upscaled = act2(dc2(upscaled) + conv_s0(high_res_features[0])) + else: + upscaled = act2(dc2(act1(ln1(dc1(src_out))))) + return upscaled + + +class SAMMaskDecoder(nn.Module): + def __init__(self, d_model=256, num_multimask_outputs=3, device=None, dtype=None, operations=None): + super().__init__() + self.num_mask_tokens = num_multimask_outputs + 1 + + self.transformer = SAMTwoWayTransformer(depth=2, embedding_dim=d_model, num_heads=8, mlp_dim=2048, device=device, dtype=dtype, operations=operations) + + self.iou_token = operations.Embedding(1, d_model, device=device, dtype=dtype) + self.mask_tokens = operations.Embedding(self.num_mask_tokens, d_model, device=device, dtype=dtype) + self.obj_score_token = operations.Embedding(1, d_model, device=device, dtype=dtype) + + # Output upscaling: d_model -> d_model//4 -> d_model//8 at 4x resolution + LN2d = LayerNorm2d_op(operations) + self.output_upscaling = nn.Sequential( + operations.ConvTranspose2d(d_model, d_model // 4, kernel_size=2, stride=2, device=device, dtype=dtype), LN2d(d_model // 4, device=device, dtype=dtype), nn.GELU(), + operations.ConvTranspose2d(d_model // 4, d_model // 8, kernel_size=2, stride=2, device=device, dtype=dtype), nn.GELU(), + ) + + # High-res feature integration + self.conv_s0 = operations.Conv2d(d_model, d_model // 8, kernel_size=1, device=device, dtype=dtype) + self.conv_s1 = operations.Conv2d(d_model, d_model // 4, kernel_size=1, device=device, dtype=dtype) + + # Per-mask hypernetwork MLPs + self.output_hypernetworks_mlps = nn.ModuleList([ + MLP(d_model, d_model, d_model // 8, 3, device=device, dtype=dtype, operations=operations) + for _ in range(self.num_mask_tokens) + ]) + + self.iou_prediction_head = MLP(d_model, d_model, self.num_mask_tokens, 3, device=device, dtype=dtype, operations=operations) + self.pred_obj_score_head = MLP(d_model, d_model, 1, 3, device=device, dtype=dtype, operations=operations) + + def forward(self, image_embeddings, image_pe, sparse_prompt_embeddings, dense_prompt_embeddings, + high_res_features=None, multimask_output=False, return_all=False): + B = sparse_prompt_embeddings.shape[0] + ref = sparse_prompt_embeddings + # Token order: [obj_score(1), iou(1), mask(num_mask_tokens)] + tokens = torch.cat([cast_to_input(self.obj_score_token.weight, ref), + cast_to_input(self.iou_token.weight, ref), + cast_to_input(self.mask_tokens.weight, ref)], dim=0) + tokens = torch.cat([tokens.unsqueeze(0).expand(B, -1, -1), sparse_prompt_embeddings], dim=1) + + src = image_embeddings + if src.shape[0] != B: + src = src.expand(B, -1, -1, -1) + src = src + dense_prompt_embeddings + pos_src = image_pe.expand(B, -1, -1, -1) + + b, c, h, w = src.shape + src_flat = src.flatten(2).permute(0, 2, 1) + pos_flat = pos_src.flatten(2).permute(0, 2, 1) + + hs, src_out = self.transformer(src_flat, pos_flat, tokens) + + obj_score_token_out = hs[:, 0, :] + iou_token_out = hs[:, 1, :] + mask_tokens_out = hs[:, 2:2 + self.num_mask_tokens, :] + + src_out = src_out.permute(0, 2, 1).view(b, c, h, w) + upscaled = _upscale_masks(self.output_upscaling, self.conv_s0, self.conv_s1, src_out, high_res_features) + + hyper_in = torch.stack([ + mlp(mask_tokens_out[:, i, :]) for i, mlp in enumerate(self.output_hypernetworks_mlps) + ], dim=1) + + masks = (hyper_in @ upscaled.flatten(2)).view(B, self.num_mask_tokens, upscaled.shape[2], upscaled.shape[3]) + iou_pred = self.iou_prediction_head(iou_token_out) + object_score_logits = self.pred_obj_score_head(obj_score_token_out) + + if multimask_output: + out_masks = masks[:, 1:] + out_iou = iou_pred[:, 1:] + out_tokens = mask_tokens_out[:, 1:] + else: + out_masks = masks[:, 0:1] + out_iou = iou_pred[:, 0:1] + out_tokens = mask_tokens_out[:, 0:1] + + if return_all: + return out_masks, out_iou, out_tokens, object_score_logits + return out_masks, out_iou + + +class SAMPromptEncoder(nn.Module): + def __init__(self, d_model=256, image_embedding_size=(72, 72), input_image_size=(1008, 1008), device=None, dtype=None, operations=None): + super().__init__() + self.embed_dim = d_model + self.image_embedding_size = image_embedding_size + self.input_image_size = input_image_size + + self.pe_layer = PositionEmbeddingRandom(d_model // 2) + self.point_embeddings = nn.ModuleList([ + operations.Embedding(1, d_model, device=device, dtype=dtype) for _ in range(4) + ]) + self.not_a_point_embed = operations.Embedding(1, d_model, device=device, dtype=dtype) + + LN2d = LayerNorm2d_op(operations) + self.mask_downscaling = nn.Sequential( + operations.Conv2d(1, 4, kernel_size=2, stride=2, device=device, dtype=dtype), + LN2d(4, device=device, dtype=dtype), nn.GELU(), + operations.Conv2d(4, 16, kernel_size=2, stride=2, device=device, dtype=dtype), + LN2d(16, device=device, dtype=dtype), nn.GELU(), + operations.Conv2d(16, d_model, kernel_size=1, device=device, dtype=dtype), + ) + self.no_mask_embed = operations.Embedding(1, d_model, device=device, dtype=dtype) + + def get_dense_pe(self): + return self.pe_layer(self.image_embedding_size) + + def forward(self, points=None, boxes=None, masks=None): + ref = points[0] if points is not None else boxes if boxes is not None else masks + B = 1 + sparse = torch.empty((B, 0, self.embed_dim), device=ref.device, dtype=ref.dtype) + + if points is not None: + coords, labels = points + B = coords.shape[0] + # Pad with an extra point (label=-1) when no boxes are provided (matching reference) + if boxes is None: + coords = torch.cat([coords, torch.zeros(B, 1, 2, device=coords.device, dtype=coords.dtype)], dim=1) + labels = torch.cat([labels, -torch.ones(B, 1, device=labels.device, dtype=labels.dtype)], dim=1) + pe = self.pe_layer.forward_with_coords(coords + 0.5, self.input_image_size) + for i in range(4): + pe[labels == i] += cast_to_input(self.point_embeddings[i].weight, ref) + invalid = (labels == -1) + pe[invalid] = 0.0 + pe[invalid] += cast_to_input(self.not_a_point_embed.weight, ref) + sparse = torch.cat([sparse.expand(B, -1, -1), pe], dim=1) + + if boxes is not None: + B = boxes.shape[0] + corners = self.pe_layer.forward_with_coords((boxes.reshape(-1, 2, 2) + 0.5), self.input_image_size) + corners[:, 0] += cast_to_input(self.point_embeddings[2].weight, ref) + corners[:, 1] += cast_to_input(self.point_embeddings[3].weight, ref) + sparse = torch.cat([sparse.expand(B, -1, -1), corners], dim=1) + + if masks is not None: + dense = self.mask_downscaling(masks) + else: + dense = cast_to_input(self.no_mask_embed.weight, ref).reshape(1, -1, 1, 1).expand( + B, -1, self.image_embedding_size[0], self.image_embedding_size[1]) + + return sparse, dense + + +class CXBlock(nn.Module): + def __init__(self, dim=256, kernel_size=7, device=None, dtype=None, operations=None): + super().__init__() + self.dwconv = operations.Conv2d(dim, dim, kernel_size=kernel_size, padding=kernel_size // 2, groups=dim, device=device, dtype=dtype) + self.norm = operations.LayerNorm(dim, device=device, dtype=dtype) + self.pwconv1 = operations.Linear(dim, 4 * dim, device=device, dtype=dtype) + self.pwconv2 = operations.Linear(4 * dim, dim, device=device, dtype=dtype) + self.gamma = nn.Parameter(torch.ones(dim, device=device, dtype=dtype)) + + def forward(self, x): + residual = x + x = self.dwconv(x).permute(0, 2, 3, 1) + x = self.pwconv2(F.gelu(self.pwconv1(self.norm(x)))) + x.mul_(cast_to_input(self.gamma, x)) + return residual + x.permute(0, 3, 1, 2) + + +class MaskDownSampler(nn.Module): + def __init__(self, out_dim=256, in_chans=1, channels=None, interpol_size=(1152, 1152), device=None, dtype=None, operations=None): + super().__init__() + self.interpol_size = list(interpol_size) if interpol_size else None + if channels is None: + channels = [4, 16, 64, out_dim] # SAM3 default + LN2d = LayerNorm2d_op(operations) + layers = [] + prev = in_chans + for ch in channels: + layers += [operations.Conv2d(prev, ch, kernel_size=3, stride=2, padding=1, device=device, dtype=dtype), + LN2d(ch, device=device, dtype=dtype), nn.GELU()] + prev = ch + layers.append(operations.Conv2d(prev, out_dim, kernel_size=1, device=device, dtype=dtype)) + self.encoder = nn.Sequential(*layers) + + def forward(self, x): + if self.interpol_size is not None and list(x.shape[-2:]) != self.interpol_size: + x = F.interpolate(x, size=self.interpol_size, mode="bilinear", align_corners=False, antialias=True) + return self.encoder(x) + + +class Fuser(nn.Module): + def __init__(self, dim=256, num_layers=2, device=None, dtype=None, operations=None): + super().__init__() + self.layers = nn.Sequential(*[CXBlock(dim, device=device, dtype=dtype, operations=operations) for _ in range(num_layers)]) + + def forward(self, x): + return self.layers(x) + + +# --- SAM3.1 Multiplex components --- + +class DecoupledMemoryAttnLayer(nn.Module): + """Decoupled cross-attention layer for SAM3.1: fuses image and memory projections.""" + + def __init__(self, d_model=256, num_heads=1, dim_ff=2048, device=None, dtype=None, operations=None): + super().__init__() + self.num_heads = num_heads + # Self-attention projections (flat, not nested) + self.self_attn_q_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.self_attn_k_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.self_attn_v_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.self_attn_out_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + # Cross-attention projections + self.cross_attn_q_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.cross_attn_k_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.cross_attn_v_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.cross_attn_out_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + # Image cross-attention (q/k only, fused with cross_attn) + self.image_cross_attn_q_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.image_cross_attn_k_proj = operations.Linear(d_model, d_model, device=device, dtype=dtype) + # FFN + self.linear1 = operations.Linear(d_model, dim_ff, device=device, dtype=dtype) + self.linear2 = operations.Linear(dim_ff, d_model, device=device, dtype=dtype) + self.norm1 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm2 = operations.LayerNorm(d_model, device=device, dtype=dtype) + self.norm3 = operations.LayerNorm(d_model, device=device, dtype=dtype) + + def forward(self, image, x, memory_image, memory, memory_image_pos=None, + rope=None, num_k_exclude_rope=0): + # Self-attention with RoPE + normed = self.norm1(x) + q = self.self_attn_q_proj(normed) + k = self.self_attn_k_proj(normed) + v = self.self_attn_v_proj(normed) + if rope is not None: + q, k = apply_rope_memory(q, k, rope, self.num_heads, 0) + x = x + self.self_attn_out_proj(optimized_attention(q, k, v, self.num_heads, low_precision_attention=False)) + + # Decoupled cross-attention: fuse image and memory projections + normed = self.norm2(x) + q = self.image_cross_attn_q_proj(image) + self.cross_attn_q_proj(normed) + k = self.image_cross_attn_k_proj(memory_image) + self.cross_attn_k_proj(memory) + if memory_image_pos is not None: + k = k + memory_image_pos + v = self.cross_attn_v_proj(memory) + if rope is not None: + q, k = apply_rope_memory(q, k, rope, self.num_heads, num_k_exclude_rope) + x = x + self.cross_attn_out_proj(optimized_attention(q, k, v, self.num_heads, low_precision_attention=False)) + + # FFN + x = x + self.linear2(F.gelu(self.linear1(self.norm3(x)))) + return image, x + + +class DecoupledMemoryEncoder(nn.Module): + """Memory attention encoder for SAM3.1 with decoupled cross-attention.""" + + def __init__(self, d_model=256, num_heads=1, dim_ff=2048, num_layers=4, image_size=1008, patch_size=14, + device=None, dtype=None, operations=None): + super().__init__() + self.layers = nn.ModuleList([ + DecoupledMemoryAttnLayer(d_model, num_heads, dim_ff, device=device, dtype=dtype, operations=operations) + for _ in range(num_layers) + ]) + self.norm = operations.LayerNorm(d_model, device=device, dtype=dtype) + hw = image_size // patch_size + self.register_buffer("_rope", rope_2d(hw, hw, d_model // num_heads), persistent=False) + + def forward(self, x, memory, memory_pos=None, src_pos=None, num_k_exclude_rope=0, + memory_image=None, memory_image_pos=None): + image = x # constant residual for decoupled cross-attention + output = x + if src_pos is not None: + output = output + 0.1 * src_pos + + B, _, C = x.shape + rope = self._rope.to(device=x.device) + + # memory_image: raw backbone features from past frames for decoupled cross-attention + if memory_image is None: + # Fallback: use spatial portion of memory (without obj pointers) + num_spatial = memory.shape[1] - num_k_exclude_rope + memory_image = memory[:, :num_spatial] + memory_image_pos = memory_pos[:, :num_spatial] if memory_pos is not None else None + # Pad memory_image to match memory length (zeros for obj pointer tokens) + if memory_image.shape[1] < memory.shape[1]: + pad_len = memory.shape[1] - memory_image.shape[1] + pad = torch.zeros(B, pad_len, C, device=memory.device, dtype=memory.dtype) + memory_image = torch.cat([memory_image, pad], dim=1) + if memory_image_pos is not None: + ptr_pos = memory_pos[:, -pad_len:] if memory_pos is not None else torch.zeros_like(pad) + memory_image_pos = torch.cat([memory_image_pos, ptr_pos], dim=1) + + for layer in self.layers: + image, output = layer(image, output, memory_image, memory, + memory_image_pos=memory_image_pos, rope=rope, + num_k_exclude_rope=num_k_exclude_rope) + + return self.norm(output) + + +class DecoupledMemoryTransformer(nn.Module): + def __init__(self, d_model=256, num_heads=1, dim_ff=2048, num_layers=4, device=None, dtype=None, operations=None): + super().__init__() + self.encoder = DecoupledMemoryEncoder(d_model, num_heads, dim_ff, num_layers, + device=device, dtype=dtype, operations=operations) + + +class MemoryBackbone(nn.Module): + """Memory encoder: downsamples mask, fuses with pixel features, optionally compresses.""" + + def __init__(self, d_model=256, out_dim=None, in_chans=1, channels=None, device=None, dtype=None, operations=None): + super().__init__() + self.mask_downsampler = MaskDownSampler(d_model, in_chans=in_chans, channels=channels, device=device, dtype=dtype, operations=operations) + self.pix_feat_proj = operations.Conv2d(d_model, d_model, kernel_size=1, device=device, dtype=dtype) + self.fuser = Fuser(d_model, num_layers=2, device=device, dtype=dtype, operations=operations) + self.has_out_proj = out_dim is not None and out_dim != d_model + if self.has_out_proj: + self.out_proj = operations.Conv2d(d_model, out_dim, kernel_size=1, device=device, dtype=dtype) + feat_dim = out_dim + else: + feat_dim = d_model + self.position_encoding = PositionEmbeddingSine(num_pos_feats=feat_dim, normalize=True) + + def forward(self, image_features, mask_for_mem, skip_mask_sigmoid=False): + if not skip_mask_sigmoid: + mask_for_mem = mask_for_mem.sigmoid() + mask_features = self.mask_downsampler(cast_to_input(mask_for_mem, image_features)) + if mask_features.shape[-2:] != image_features.shape[-2:]: + mask_features = F.interpolate(mask_features, size=image_features.shape[-2:], mode="bilinear", align_corners=False) + features = self.pix_feat_proj(image_features) + mask_features + features = self.fuser(features) + if self.has_out_proj: + features = self.out_proj(features) + pos = cast_to_input(self.position_encoding(features), features) + return {"vision_features": features, "vision_pos_enc": [pos]} + + +class MultiplexMaskDecoder(nn.Module): + """SAM mask decoder for SAM3.1 multiplex: predicts masks for num_multiplex objects simultaneously. + + Uses multimask_outputs_only=True: num_mask_output_per_object = num_multimask_outputs (no +1). + Hypernetwork MLPs are shared across multiplex objects. + Token order: [obj_score_token(M), iou_token(M), mask_tokens(M*T)]. + """ + + def __init__(self, d_model=256, num_multiplex=16, num_multimask_outputs=3, device=None, dtype=None, operations=None): + super().__init__() + self.num_multiplex = num_multiplex + self.num_mask_output_per_object = num_multimask_outputs # 3 (multimask_outputs_only) + total_mask_tokens = num_multiplex * self.num_mask_output_per_object # 48 + + self.transformer = SAMTwoWayTransformer(depth=2, embedding_dim=d_model, num_heads=8, mlp_dim=2048, device=device, dtype=dtype, operations=operations) + + self.obj_score_token = operations.Embedding(num_multiplex, d_model, device=device, dtype=dtype) + self.iou_token = operations.Embedding(num_multiplex, d_model, device=device, dtype=dtype) + self.mask_tokens = operations.Embedding(total_mask_tokens, d_model, device=device, dtype=dtype) + + LN2d = LayerNorm2d_op(operations) + self.output_upscaling = nn.Sequential( + operations.ConvTranspose2d(d_model, d_model // 4, kernel_size=2, stride=2, device=device, dtype=dtype), + LN2d(d_model // 4, device=device, dtype=dtype), nn.GELU(), + operations.ConvTranspose2d(d_model // 4, d_model // 8, kernel_size=2, stride=2, device=device, dtype=dtype), nn.GELU(), + ) + self.conv_s0 = operations.Conv2d(d_model, d_model // 8, kernel_size=1, device=device, dtype=dtype) + self.conv_s1 = operations.Conv2d(d_model, d_model // 4, kernel_size=1, device=device, dtype=dtype) + + # Shared across all multiplex objects (one per mask output) + self.output_hypernetworks_mlps = nn.ModuleList([ + MLP(d_model, d_model, d_model // 8, 3, device=device, dtype=dtype, operations=operations) + for _ in range(self.num_mask_output_per_object) + ]) + self.iou_prediction_head = MLP(d_model, d_model, self.num_mask_output_per_object, 3, device=device, dtype=dtype, operations=operations) + self.pred_obj_score_head = MLP(d_model, d_model, 1, 3, device=device, dtype=dtype, operations=operations) + + def forward(self, image_embeddings, image_pe, sparse_prompt_embeddings, dense_prompt_embeddings, + high_res_features=None, multimask_output=False, return_all=False, extra_per_object_embeddings=None): + B = sparse_prompt_embeddings.shape[0] + M = self.num_multiplex + T = self.num_mask_output_per_object + + # Token order: [obj_score(M), iou(M), mask(M*T)] + ref = sparse_prompt_embeddings + mask_tokens = cast_to_input(self.mask_tokens.weight, ref) + if extra_per_object_embeddings is not None: + mask_tokens = mask_tokens.view(1, M, T, -1).expand(B, -1, -1, -1) + extra_per_object_embeddings.unsqueeze(2) + mask_tokens = mask_tokens.flatten(1, 2) # [B, M*T, C] + other_tokens = torch.cat([cast_to_input(self.obj_score_token.weight, ref), + cast_to_input(self.iou_token.weight, ref)], dim=0).unsqueeze(0).expand(B, -1, -1) + tokens = torch.cat([other_tokens, mask_tokens, sparse_prompt_embeddings], dim=1) + else: + tokens = torch.cat([cast_to_input(self.obj_score_token.weight, ref), + cast_to_input(self.iou_token.weight, ref), mask_tokens], dim=0) + tokens = torch.cat([tokens.unsqueeze(0).expand(B, -1, -1), sparse_prompt_embeddings], dim=1) + + src = image_embeddings + if src.shape[0] != B: + src = src.expand(B, -1, -1, -1) + src = src + dense_prompt_embeddings + pos_src = image_pe.expand(B, -1, -1, -1) + + b, c, h, w = src.shape + hs, src_out = self.transformer(src.flatten(2).permute(0, 2, 1), pos_src.flatten(2).permute(0, 2, 1), tokens) + + # Parse output tokens + obj_score_token_out = hs[:, :M] + iou_token_out = hs[:, M:2 * M] + mask_tokens_out = hs[:, 2 * M:2 * M + M * T] + + src_out = src_out.permute(0, 2, 1).view(b, c, h, w) + upscaled = _upscale_masks(self.output_upscaling, self.conv_s0, self.conv_s1, src_out, high_res_features) + + # Reshape mask tokens to [B, M, T, C] and apply shared hypernetwork MLPs per mask output index + mask_tokens_2d = mask_tokens_out.view(B, M, T, -1) + hyper_in = torch.stack([ + self.output_hypernetworks_mlps[i](mask_tokens_2d[:, :, i, :]) # [B, M, C//8] + for i in range(T) + ], dim=2) # [B, M, T, C//8] + + # Generate masks: [B, M*T, H*W] -> [B, M, T, H, W] + masks = torch.bmm(hyper_in.flatten(1, 2), upscaled.flatten(2)).view(b, M, T, upscaled.shape[2], upscaled.shape[3]) + + # IoU and object scores + iou_pred = self.iou_prediction_head(iou_token_out).view(b, M, T) + object_score_logits = self.pred_obj_score_head(obj_score_token_out) # [B, M, 1] + + # multimask_outputs_only: always output all T masks (no singlemask token) + sam_tokens_out = mask_tokens_2d[:, :, 0:1] # [B, M, 1, C] + + if return_all: + return masks, iou_pred, sam_tokens_out, object_score_logits + return masks, iou_pred + + +class SAM3Tracker(nn.Module): + def __init__(self, d_model=256, mem_dim=64, num_maskmem=7, device=None, dtype=None, operations=None, **kwargs): + super().__init__() + + # Memory attention transformer + self.transformer = MemoryTransformer(d_model, num_heads=1, kv_dim=mem_dim, dim_ff=2048, num_layers=4, + device=device, dtype=dtype, operations=operations) + # SAM components + self.sam_mask_decoder = SAMMaskDecoder(d_model, device=device, dtype=dtype, operations=operations) + self.sam_prompt_encoder = SAMPromptEncoder(d_model, device=device, dtype=dtype, operations=operations) + + # Memory backbone + self.maskmem_backbone = MemoryBackbone(d_model, out_dim=mem_dim, device=device, dtype=dtype, operations=operations) + + # Standalone parameters + self.maskmem_tpos_enc = nn.Parameter(torch.zeros(num_maskmem, 1, 1, mem_dim, device=device, dtype=dtype)) + self.no_mem_embed = nn.Parameter(torch.zeros(1, 1, d_model, device=device, dtype=dtype)) + self.register_buffer("no_mem_pos_enc", torch.zeros(1, 1, d_model, device=device, dtype=dtype)) # checkpoint key, unused in forward + self.no_obj_embed_spatial = nn.Parameter(torch.zeros(1, mem_dim, device=device, dtype=dtype)) + self.no_obj_ptr = nn.Parameter(torch.zeros(1, d_model, device=device, dtype=dtype)) + + # Object pointer projection + self.obj_ptr_proj = MLP(d_model, d_model, d_model, 3, device=device, dtype=dtype, operations=operations) + self.obj_ptr_tpos_proj = operations.Linear(d_model, mem_dim, device=device, dtype=dtype) + + # Mask downsample: Conv2d stride 4 to reduce GT mask to SAM logit scale + self.mask_downsample = operations.Conv2d(1, 1, kernel_size=4, stride=4, device=device, dtype=dtype) + + # Config + self.d_model = d_model + self.mem_dim = mem_dim + self.num_maskmem = num_maskmem + self.image_size = 1008 + self.backbone_stride = 14 + self.max_obj_ptrs_in_encoder = 16 + self.sigmoid_scale_for_mem_enc = 20.0 + self.sigmoid_bias_for_mem_enc = -10.0 + + def _no_obj_blend(self, obj_ptr, is_obj): + alpha = is_obj.to(obj_ptr.dtype) + return torch.lerp(cast_to_input(self.no_obj_ptr, obj_ptr), obj_ptr, alpha) + + def _forward_sam_heads(self, backbone_features, point_inputs=None, mask_inputs=None, box_inputs=None, + high_res_features=None, multimask_output=False): + return forward_sam_heads(backbone_features, self.sam_prompt_encoder, self.sam_mask_decoder, + self.obj_ptr_proj, self._no_obj_blend, self.image_size, + point_inputs, mask_inputs, box_inputs, high_res_features, multimask_output) + + def _use_mask_as_output(self, backbone_features, high_res_features, mask_inputs): + return use_mask_as_output(backbone_features, high_res_features, mask_inputs, + self.mask_downsample, self.sam_prompt_encoder, self.sam_mask_decoder, + self.obj_ptr_proj, self._no_obj_blend, self.image_size, self.backbone_stride) + + def _prepare_memory_conditioned_features(self, frame_idx, is_init_cond_frame, current_vision_feats, current_vision_pos_embeds, feat_sizes, output_dict, num_frames): + """Fuse current frame features with memory from previous frames.""" + B = current_vision_feats[-1].shape[0] + C = self.d_model + H, W = feat_sizes[-1] + device = current_vision_feats[-1].device + + if self.num_maskmem == 0: + return current_vision_feats[-1].permute(0, 2, 1).view(B, C, H, W) + + if is_init_cond_frame: + # First conditioning frame: no memory yet, add no_mem_embed + pix_feat = current_vision_feats[-1] + cast_to_input(self.no_mem_embed, current_vision_feats[-1]) + return to_spatial(pix_feat, H, W) + + to_cat_memory, to_cat_memory_pos, _, _, cond_outputs = collect_memory_tokens( + output_dict, frame_idx, self.num_maskmem, self.maskmem_tpos_enc, device) + + max_obj_ptrs = min(num_frames, self.max_obj_ptrs_in_encoder) + pos_and_ptrs = [] + for t, out in cond_outputs.items(): + if t <= frame_idx: + pos_and_ptrs.append(((frame_idx - t), out["obj_ptr"].to(device))) + for t_diff in range(1, max_obj_ptrs): + t = frame_idx - t_diff + if t < 0: + break + out = output_dict["non_cond_frame_outputs"].get(t, None) + if out is not None: + pos_and_ptrs.append((t_diff, out["obj_ptr"].to(device))) + + num_obj_ptr_tokens = 0 + if len(pos_and_ptrs) > 0: + pos_list, ptrs_list = zip(*pos_and_ptrs) + obj_ptrs = torch.stack(ptrs_list, dim=1) # [B, N, C=256] + + # Temporal position encoding for pointers + obj_pos = compute_tpos_enc( + list(pos_list), device, self.d_model, self.obj_ptr_tpos_proj, + max_abs_pos=max_obj_ptrs, dtype=current_vision_feats[-1].dtype + ) # [N, mem_dim=64] + obj_pos = obj_pos.unsqueeze(0).expand(B, -1, -1) # [B, N, 64] + + # Split each 256-dim pointer into 4 x 64-dim tokens + if self.mem_dim < C: + N = obj_ptrs.shape[1] + obj_ptrs = obj_ptrs.view(B, N, C // self.mem_dim, self.mem_dim) # [B, N, 4, 64] + obj_ptrs = obj_ptrs.reshape(B, N * (C // self.mem_dim), self.mem_dim) # [B, N*4, 64] + obj_pos = obj_pos.unsqueeze(2).expand(-1, -1, C // self.mem_dim, -1) + obj_pos = obj_pos.reshape(B, N * (C // self.mem_dim), self.mem_dim) # [B, N*4, 64] + + to_cat_memory.append(obj_ptrs) + to_cat_memory_pos.append(obj_pos) + num_obj_ptr_tokens = obj_ptrs.shape[1] + + if len(to_cat_memory) == 0: + # No memory available yet, add no_mem_embed + pix_feat = current_vision_feats[-1] + cast_to_input(self.no_mem_embed, current_vision_feats[-1]) + return to_spatial(pix_feat, H, W) + + # Concatenate all memory and position encodings [B, total_mem, mem_dim=64] + memory = torch.cat(to_cat_memory, dim=1) + memory_pos = torch.cat(to_cat_memory_pos, dim=1) + + # Run memory attention encoder + pix_feat = current_vision_feats[-1] # [B, HW, C] + src_pos = current_vision_pos_embeds[-1] # [B, HW, C] + + pix_feat_with_mem = self.transformer.encoder( + x=pix_feat, + memory=memory, + src_pos=src_pos, + memory_pos=memory_pos, + num_k_exclude_rope=num_obj_ptr_tokens, + ) + return to_spatial(pix_feat_with_mem, H, W) + + def _encode_new_memory(self, pix_feat, pred_masks_high_res, object_score_logits, is_mask_from_pts=False): + """Encode predicted mask into memory features.""" + if is_mask_from_pts: + mask_for_mem = (pred_masks_high_res > 0).to(pix_feat.dtype) + else: + mask_for_mem = torch.sigmoid(pred_masks_high_res) + + mask_for_mem.mul_(self.sigmoid_scale_for_mem_enc).add_(self.sigmoid_bias_for_mem_enc) + + maskmem_out = self.maskmem_backbone(pix_feat, mask_for_mem, skip_mask_sigmoid=True) + maskmem_features = maskmem_out["vision_features"] + maskmem_pos_enc = maskmem_out["vision_pos_enc"] + + # Add no_obj_embed for occluded objects + alpha = (object_score_logits > 0).to(maskmem_features.dtype)[..., None, None] + no_obj = cast_to_input(self.no_obj_embed_spatial, maskmem_features)[..., None, None].expand_as(maskmem_features) + return maskmem_features + (1 - alpha) * no_obj, maskmem_pos_enc + + def track_step(self, frame_idx, is_init_cond_frame, current_vision_feats, current_vision_pos_embeds, feat_sizes, mask_inputs, output_dict, + num_frames, point_inputs=None): + """Track one frame: fuse with memory, predict mask, encode memory.""" + current_out = {} + + # High-res features for SAM head [stride-8, stride-4] + if len(current_vision_feats) > 1: + high_res_features = [ + x.view(x.shape[0], feat_sizes[i][0], feat_sizes[i][1], -1).permute(0, 3, 1, 2) + for i, x in enumerate(current_vision_feats[:-1]) + ] + else: + high_res_features = None + + # Top-level feature for memory + H, W = feat_sizes[-1] + + if mask_inputs is not None: + # Conditioning frame: use mask directly + pix_feat = to_spatial(current_vision_feats[-1], H, W) + sam_outputs = self._use_mask_as_output(pix_feat, high_res_features, mask_inputs) + else: + # Track frame: fuse with memory, then SAM decoder + pix_feat_with_mem = self._prepare_memory_conditioned_features( + frame_idx=frame_idx, + is_init_cond_frame=is_init_cond_frame, + current_vision_feats=current_vision_feats, + current_vision_pos_embeds=current_vision_pos_embeds, + feat_sizes=feat_sizes, + output_dict=output_dict, + num_frames=num_frames, + ) + # Use multimask for point prompts on init frames (picks best of 3 candidates) + num_pts = 0 if point_inputs is None else point_inputs["point_labels"].size(1) + multimask_output = is_init_cond_frame and 0 < num_pts <= 1 + sam_outputs = self._forward_sam_heads( + backbone_features=pix_feat_with_mem, + point_inputs=point_inputs, + high_res_features=high_res_features, + multimask_output=multimask_output, + ) + + (low_res_masks, high_res_masks, obj_ptr, object_score_logits) = sam_outputs + + # Clean low-res masks: remove sprinkles and fill holes + low_res_masks = fill_holes_in_mask_scores(low_res_masks, max_area=200) + high_res_masks = F.interpolate(low_res_masks, size=(self.image_size, self.image_size), mode="bilinear", align_corners=False) + + current_out["pred_masks"] = low_res_masks + current_out["pred_masks_high_res"] = high_res_masks + current_out["obj_ptr"] = obj_ptr + current_out["object_score_logits"] = object_score_logits + + # Encode memory + if self.num_maskmem > 0: + pix_feat = to_spatial(current_vision_feats[-1], H, W) + maskmem_features, maskmem_pos_enc = self._encode_new_memory( + pix_feat=pix_feat, + pred_masks_high_res=high_res_masks, + object_score_logits=object_score_logits, + is_mask_from_pts=(point_inputs is not None), + ) + current_out["maskmem_features"] = maskmem_features + current_out["maskmem_pos_enc"] = maskmem_pos_enc + else: + current_out["maskmem_features"] = None + current_out["maskmem_pos_enc"] = None + + return current_out + + def _compute_backbone_frame(self, backbone_fn, frame, frame_idx=None): + vision_feats, vision_pos, feat_sizes, _, _ = _compute_backbone(backbone_fn, frame, frame_idx) + # SAM3: drop last FPN level + return vision_feats[:-1], vision_pos[:-1], feat_sizes[:-1] + + def _track_single_object(self, backbone_fn, images, initial_mask, pbar=None): + """Track one object, computing backbone per frame to save VRAM.""" + N = images.shape[0] + device, dt = images.device, images.dtype + output_dict = {"cond_frame_outputs": {}, "non_cond_frame_outputs": {}} + all_masks = [] + + for frame_idx in tqdm(range(N), desc="tracking"): + vision_feats, vision_pos, feat_sizes = self._compute_backbone_frame( + backbone_fn, images[frame_idx:frame_idx + 1], frame_idx=frame_idx) + mask_input = None + if frame_idx == 0: + mask_input = F.interpolate(initial_mask.to(device=device, dtype=dt), + size=(self.image_size, self.image_size), mode="bilinear", align_corners=False) + mask_input = (mask_input > 0.5).to(dt) + + current_out = self.track_step( + frame_idx=frame_idx, is_init_cond_frame=(frame_idx == 0), + current_vision_feats=vision_feats, current_vision_pos_embeds=vision_pos, + feat_sizes=feat_sizes, mask_inputs=mask_input, output_dict=output_dict, num_frames=N) + + if frame_idx == 0: + output_dict["cond_frame_outputs"][frame_idx] = current_out + else: + output_dict["non_cond_frame_outputs"][frame_idx] = current_out + lookback = max(self.num_maskmem, self.max_obj_ptrs_in_encoder) + for old_idx in list(output_dict["non_cond_frame_outputs"]): + if old_idx < frame_idx - lookback: + del output_dict["non_cond_frame_outputs"][old_idx] + # Move masks to CPU immediately to free VRAM + all_masks.append(current_out["pred_masks_high_res"].to(comfy.model_management.intermediate_device())) + if pbar is not None: + pbar.update(1) + + return torch.cat(all_masks, dim=0) # [N, 1, H, W] + + def track_video(self, backbone_fn, images, initial_masks, pbar=None, **kwargs): + """Track one or more objects across video frames. + + Args: + backbone_fn: callable that returns (sam2_features, sam2_positions, trunk_out) for a frame + images: [N, 3, 1008, 1008] video frames + initial_masks: [N_obj, 1, H, W] binary masks for first frame (one per object) + pbar: optional progress bar + + Returns: + [N, N_obj, image_size, image_size] predicted mask logits per frame per object + """ + N_obj = initial_masks.shape[0] + per_object = [] + for obj_idx in range(N_obj): + obj_masks = self._track_single_object( + backbone_fn, images, initial_masks[obj_idx:obj_idx + 1], pbar=pbar) + per_object.append(obj_masks) + + return torch.cat(per_object, dim=1) # [N, N_obj, H, W] + + +class SAM31Tracker(nn.Module): + """SAM3.1 multiplex tracker: decoupled memory attention, dual decoder, 16-object multiplex.""" + + def __init__(self, d_model=256, mem_dim=256, num_maskmem=7, num_multiplex=16, device=None, dtype=None, operations=None, **kwargs): + super().__init__() + self.d_model = d_model + self.mem_dim = mem_dim + self.num_maskmem = num_maskmem + self.num_multiplex = num_multiplex + self.image_size = 1008 + self.backbone_stride = 14 + self.max_obj_ptrs_in_encoder = 16 + self.sigmoid_scale_for_mem_enc = 2.0 + self.sigmoid_bias_for_mem_enc = -1.0 + + # Memory attention (decoupled cross-attention, 8 heads matching reference) + self.transformer = DecoupledMemoryTransformer(d_model, num_heads=8, dim_ff=2048, num_layers=4, + device=device, dtype=dtype, operations=operations) + + # Propagation decoder (multiplex: 16 objects, multimask_outputs_only) + self.sam_mask_decoder = MultiplexMaskDecoder(d_model, num_multiplex, num_multimask_outputs=3, + device=device, dtype=dtype, operations=operations) + # Interactive decoder (single object, same as SAM3) + self.interactive_sam_mask_decoder = SAMMaskDecoder(d_model, num_multimask_outputs=3, + device=device, dtype=dtype, operations=operations) + self.interactive_sam_prompt_encoder = SAMPromptEncoder(d_model, device=device, dtype=dtype, operations=operations) + + # Memory backbone (mem_dim=256, no out_proj compression) + self.maskmem_backbone = MemoryBackbone(d_model, in_chans=num_multiplex * 2, channels=[16, 64, 256, 1024], + device=device, dtype=dtype, operations=operations) + + # Standalone parameters + self.maskmem_tpos_enc = nn.Parameter(torch.zeros(num_maskmem, 1, 1, mem_dim, device=device, dtype=dtype)) + self.no_obj_embed_spatial = nn.Parameter(torch.zeros(num_multiplex, mem_dim, device=device, dtype=dtype)) + self.interactivity_no_mem_embed = nn.Parameter(torch.zeros(1, 1, d_model, device=device, dtype=dtype)) + + # Object pointer projection + self.obj_ptr_proj = MLP(d_model, d_model, d_model, 3, device=device, dtype=dtype, operations=operations) + self.obj_ptr_tpos_proj = operations.Linear(d_model, mem_dim, device=device, dtype=dtype) + self.no_obj_ptr_linear = operations.Linear(d_model, d_model, device=device, dtype=dtype) + self.interactive_obj_ptr_proj = MLP(d_model, d_model, d_model, 3, device=device, dtype=dtype, operations=operations) + + # Interactive mask downsample + self.interactive_mask_downsample = operations.Conv2d(1, 1, kernel_size=4, stride=4, device=device, dtype=dtype) + + # Multiplex validity embeddings + self.output_valid_embed = nn.Parameter(torch.zeros(num_multiplex, d_model, device=device, dtype=dtype)) + self.output_invalid_embed = nn.Parameter(torch.zeros(num_multiplex, d_model, device=device, dtype=dtype)) + + # Position encoding for image (used by multiplex decoder) + self.image_pe_layer = PositionEmbeddingRandom(d_model // 2) + + def _no_obj_blend(self, obj_ptr, is_obj): + alpha = is_obj.to(obj_ptr.dtype) + return torch.lerp(self.no_obj_ptr_linear(obj_ptr), obj_ptr, alpha) + + def _forward_sam_heads(self, backbone_features, point_inputs=None, mask_inputs=None, box_inputs=None, + high_res_features=None, multimask_output=False): + return forward_sam_heads(backbone_features, self.interactive_sam_prompt_encoder, self.interactive_sam_mask_decoder, + self.interactive_obj_ptr_proj, self._no_obj_blend, self.image_size, + point_inputs, mask_inputs, box_inputs, high_res_features, multimask_output) + + def _use_mask_as_output(self, backbone_features, high_res_features, mask_inputs): + return use_mask_as_output(backbone_features, high_res_features, mask_inputs, + self.interactive_mask_downsample, self.interactive_sam_prompt_encoder, + self.interactive_sam_mask_decoder, self.interactive_obj_ptr_proj, + self._no_obj_blend, self.image_size, self.backbone_stride) + + def _prepare_memory_conditioned_features(self, frame_idx, is_init_cond_frame, current_vision_feats, + current_vision_pos_embeds, feat_sizes, output_dict, num_frames, + multiplex_state=None): + B = current_vision_feats[-1].shape[0] + C = self.d_model + H, W = feat_sizes[-1] + device = current_vision_feats[-1].device + num_buc = multiplex_state.num_buckets if multiplex_state is not None else None + + if self.num_maskmem == 0: + return current_vision_feats[-1].permute(0, 2, 1).view(B, C, H, W) + + if is_init_cond_frame: + pix_feat = current_vision_feats[-1] + cast_to_input(self.interactivity_no_mem_embed, current_vision_feats[-1]) + return to_spatial(pix_feat, H, W) + + to_cat_memory, to_cat_memory_pos, to_cat_image_feat, to_cat_image_pos, cond_outputs = collect_memory_tokens( + output_dict, frame_idx, self.num_maskmem, self.maskmem_tpos_enc, device, + collect_image_feats=True, tpos_v2=True, num_buckets=num_buc) + + max_obj_ptrs = min(num_frames, self.max_obj_ptrs_in_encoder) + pos_and_ptrs = [] + for t, out in cond_outputs.items(): + if t <= frame_idx and "obj_ptr" in out: + ptr = out["obj_ptr"].to(device) + if num_buc is not None: + ptr = _pad_to_buckets(ptr, num_buc) + pos_and_ptrs.append(((frame_idx - t), ptr)) + for t_diff in range(1, max_obj_ptrs): + t = frame_idx - t_diff + if t < 0: + break + out = output_dict["non_cond_frame_outputs"].get(t, None) + if out is not None and "obj_ptr" in out: + ptr = out["obj_ptr"].to(device) + if num_buc is not None: + ptr = _pad_to_buckets(ptr, num_buc) + pos_and_ptrs.append((t_diff, ptr)) + + num_obj_ptr_tokens = 0 + if len(pos_and_ptrs) > 0: + pos_list, ptrs_list = zip(*pos_and_ptrs) + obj_ptrs = torch.stack(ptrs_list, dim=1) # [num_buckets, N, M, C] + B_ptr = obj_ptrs.shape[0] + N_ptrs = obj_ptrs.shape[1] + M = obj_ptrs.shape[2] + obj_ptrs = obj_ptrs.reshape(B_ptr, N_ptrs * M, -1) + obj_pos = compute_tpos_enc(list(pos_list), device, self.d_model, self.obj_ptr_tpos_proj, + max_abs_pos=max_obj_ptrs, dtype=current_vision_feats[-1].dtype) + obj_pos = obj_pos.unsqueeze(0).expand(B_ptr, -1, -1) + obj_pos = obj_pos.unsqueeze(2).expand(-1, -1, M, -1).reshape(B_ptr, N_ptrs * M, -1) + to_cat_memory.append(obj_ptrs) + to_cat_memory_pos.append(obj_pos) + num_obj_ptr_tokens = obj_ptrs.shape[1] + + if len(to_cat_memory) == 0: + pix_feat = current_vision_feats[-1] + cast_to_input(self.interactivity_no_mem_embed, current_vision_feats[-1]) + return to_spatial(pix_feat, H, W) + + memory = torch.cat(to_cat_memory, dim=1) + memory_pos = torch.cat(to_cat_memory_pos, dim=1) + + # Expand vision features to num_buckets if memory has more buckets than B + mem_B = memory.shape[0] + x = current_vision_feats[-1] + x_pos = current_vision_pos_embeds[-1] + if x.shape[0] < mem_B: + x = x.expand(mem_B, -1, -1) + x_pos = x_pos.expand(mem_B, -1, -1) + + if len(to_cat_image_feat) > 0: + # Decoupled cross-attention: separate image features from memory + memory_image = cast_to_input(torch.cat(to_cat_image_feat, dim=1), x) + memory_image_pos = cast_to_input(torch.cat(to_cat_image_pos, dim=1), x) + if memory_image.shape[0] < mem_B: + memory_image = memory_image.expand(mem_B, -1, -1) + memory_image_pos = memory_image_pos.expand(mem_B, -1, -1) + pix_feat_with_mem = self.transformer.encoder( + x=x, + memory=cast_to_input(memory, x), + memory_pos=cast_to_input(memory_pos, x), + src_pos=cast_to_input(x_pos, x), + num_k_exclude_rope=num_obj_ptr_tokens, + memory_image=memory_image, + memory_image_pos=memory_image_pos, + ) + else: + pix_feat_with_mem = self.transformer.encoder( + x=x, + memory=memory, + memory_pos=memory_pos, + src_pos=x_pos, + num_k_exclude_rope=num_obj_ptr_tokens, + ) + return to_spatial(pix_feat_with_mem, H, W) + + def _encode_new_memory(self, pix_feat, pred_masks_high_res, object_score_logits, is_mask_from_pts=False, + multiplex_state=None, is_conditioning=False, cond_obj_mask=None): + if is_mask_from_pts: + mask_for_mem = (pred_masks_high_res > 0).to(pix_feat.dtype) + else: + mask_for_mem = torch.sigmoid(pred_masks_high_res) + mask_for_mem.mul_(self.sigmoid_scale_for_mem_enc).add_(self.sigmoid_bias_for_mem_enc) + + # Mux masks: [N_obj, 1, H, W] -> [num_buckets, M, H, W] + mux_masks = multiplex_state.mux(mask_for_mem[:, 0]) + + # Conditioning channel: 1.0 = clean mask (trust it), 0.0 = propagation (noisy) + N_obj = mask_for_mem.shape[0] + cond_values = torch.full((N_obj,), 0.0, device=mask_for_mem.device, dtype=mask_for_mem.dtype) + if is_conditioning: + cond_values[:] = 1.0 + elif cond_obj_mask is not None: + cond_values[cond_obj_mask] = 1.0 + cond_spatial = cond_values.view(-1, 1, 1, 1).expand_as(mask_for_mem[:, 0:1, :, :]).squeeze(1) + mux_cond = multiplex_state.mux(cond_spatial) # [num_buckets, M, H, W] + mux_input = torch.cat([mux_masks, mux_cond], dim=1) # [num_buckets, 2*M, H, W] + + maskmem_out = self.maskmem_backbone(pix_feat, mux_input, skip_mask_sigmoid=True) + maskmem_features = maskmem_out["vision_features"] + maskmem_pos_enc = maskmem_out["vision_pos_enc"] + + # Add no_obj_embed_spatial for occluded objects + is_obj = (object_score_logits > 0).float() # [N_obj, 1] + mux_is_obj = multiplex_state.mux(is_obj) # [num_buckets, M, 1] + no_obj_embed = cast_to_input(self.no_obj_embed_spatial, maskmem_features) # [M, C] + no_obj_spatial = no_obj_embed.unsqueeze(0)[..., None, None] # [1, M, C, 1, 1] + # Expand and sum across multiplex slots weighted by (1 - is_obj) + alpha = mux_is_obj[..., None, None] # [num_buckets, M, 1, 1, 1] + per_slot_no_obj = ((1 - alpha) * no_obj_spatial).sum(dim=1) # [num_buckets, C, 1, 1] + maskmem_features = maskmem_features + per_slot_no_obj.expand_as(maskmem_features) + + return maskmem_features, maskmem_pos_enc + + def _forward_propagation(self, backbone_features, high_res_features=None, multiplex_state=None): + """Propagation path using the multiplex SAM decoder (no prompts).""" + B = backbone_features.shape[0] + device = backbone_features.device + + # Suppression embeddings from valid object mask + valid_mask = cast_to_input(multiplex_state.get_valid_object_mask().unsqueeze(-1).float(), backbone_features) + output_valid = cast_to_input(self.output_valid_embed, backbone_features).unsqueeze(0) + output_invalid = cast_to_input(self.output_invalid_embed, backbone_features).unsqueeze(0) + extra_embed = valid_mask * output_valid + (1 - valid_mask) * output_invalid + + image_pe = self.image_pe_layer((backbone_features.shape[-2], backbone_features.shape[-1]), device=backbone_features.device) + image_pe = cast_to_input(image_pe, backbone_features) + + masks, iou_pred, sam_tokens_out, object_score_logits = self.sam_mask_decoder( + image_embeddings=backbone_features, image_pe=image_pe, + sparse_prompt_embeddings=torch.empty(B, 0, self.d_model, device=device, dtype=backbone_features.dtype), + dense_prompt_embeddings=torch.zeros(B, self.d_model, *backbone_features.shape[-2:], device=device, dtype=backbone_features.dtype), + high_res_features=high_res_features, multimask_output=True, return_all=True, + extra_per_object_embeddings=extra_embed.expand(B, -1, -1), + ) + # masks: [B=num_buckets, M, T, H, W] + # Demux to per-object: [N_obj, T, H, W] + masks_obj = multiplex_state.demux(masks) + iou_obj = multiplex_state.demux(iou_pred) + score_obj = multiplex_state.demux(object_score_logits) + tokens_obj = multiplex_state.demux(sam_tokens_out) + + # Select best mask by IoU for each object + best_idx = torch.argmax(iou_obj, dim=-1) # [N_obj] + N_obj = masks_obj.shape[0] + obj_range = torch.arange(N_obj, device=device) + low_res_masks = masks_obj[obj_range, best_idx].unsqueeze(1) # [N_obj, 1, H, W] + # Suppress masks for objects with low confidence + is_obj = score_obj > 0 + low_res_masks = torch.where(is_obj[:, :, None, None], low_res_masks, + torch.tensor(NO_OBJ_SCORE, device=device, dtype=low_res_masks.dtype)) + high_res_masks = F.interpolate(low_res_masks.float(), size=(self.image_size, self.image_size), mode="bilinear", align_corners=False) + + # Object pointer: compute per-object, mux for storage as [num_buckets, M, C] + sam_token = tokens_obj[:, 0] # [N_obj, C] + obj_ptr = self.obj_ptr_proj(sam_token) + is_obj = (score_obj > 0).float() + no_obj = self.no_obj_ptr_linear(obj_ptr) + obj_ptr = is_obj * obj_ptr + (1 - is_obj) * no_obj + obj_ptr_muxed = multiplex_state.mux(obj_ptr) # [num_buckets, M, C] + + return low_res_masks, high_res_masks, obj_ptr_muxed, score_obj + + def track_step(self, frame_idx, is_init_cond_frame, current_vision_feats, current_vision_pos_embeds, + feat_sizes, mask_inputs, output_dict, num_frames, point_inputs=None, + interactive_high_res=None, interactive_backbone=None, propagation_high_res=None, + multiplex_state=None, run_mem_encoder=True): + current_out = {} + H, W = feat_sizes[-1] + + if mask_inputs is not None: + # Conditioning frame: use interactive features if available, else propagation + if interactive_backbone is not None: + pix_feat = interactive_backbone + # Add no_mem_embed for interactive path + pix_flat = pix_feat.flatten(2) + bf = pix_flat.permute(0, 2, 1) + cast_to_input(self.interactivity_no_mem_embed, pix_flat) + pix_feat = to_spatial(bf, H, W) + hi_res = interactive_high_res + else: + # Fallback: interactive backbone not available (e.g. called outside track_video). + # Propagation features work but may produce lower-quality conditioning. + pix_feat = to_spatial(current_vision_feats[-1], H, W) + hi_res = propagation_high_res + sam_outputs = self._use_mask_as_output(pix_feat, hi_res, mask_inputs) + elif point_inputs is not None: + # Interactive path: use interactive SAM decoder + pix_feat_with_mem = self._prepare_memory_conditioned_features( + frame_idx=frame_idx, is_init_cond_frame=is_init_cond_frame, + current_vision_feats=current_vision_feats, current_vision_pos_embeds=current_vision_pos_embeds, + feat_sizes=feat_sizes, output_dict=output_dict, num_frames=num_frames, + multiplex_state=multiplex_state, + ) + hi_res = interactive_high_res if interactive_high_res is not None else propagation_high_res + num_pts = point_inputs["point_labels"].size(1) + multimask_output = is_init_cond_frame and 0 < num_pts <= 1 + sam_outputs = self._forward_sam_heads( + backbone_features=pix_feat_with_mem, point_inputs=point_inputs, + high_res_features=hi_res, multimask_output=multimask_output, + ) + else: + # Propagation path: use multiplex SAM decoder with propagation features + pix_feat_with_mem = self._prepare_memory_conditioned_features( + frame_idx=frame_idx, is_init_cond_frame=is_init_cond_frame, + current_vision_feats=current_vision_feats, current_vision_pos_embeds=current_vision_pos_embeds, + feat_sizes=feat_sizes, output_dict=output_dict, num_frames=num_frames, + multiplex_state=multiplex_state, + ) + sam_outputs = self._forward_propagation(pix_feat_with_mem, propagation_high_res, + multiplex_state=multiplex_state) + + (low_res_masks, high_res_masks, obj_ptr, object_score_logits) = sam_outputs + + # Mux obj_ptr if it came from interactive path (shape [B, C]) vs propagation ([num_buckets, M, C]) + if multiplex_state is not None and obj_ptr.dim() == 2: + obj_ptr = multiplex_state.mux(obj_ptr) # [N_obj, C] -> [num_buckets, M, C] + + # Encode memory (can be deferred with run_mem_encoder=False) + if run_mem_encoder and self.num_maskmem > 0: + pix_feat = to_spatial(current_vision_feats[-1], H, W) + maskmem_features, maskmem_pos_enc = self._encode_new_memory( + pix_feat=pix_feat, pred_masks_high_res=high_res_masks, + object_score_logits=object_score_logits, + is_mask_from_pts=(point_inputs is not None), + multiplex_state=multiplex_state, + is_conditioning=(mask_inputs is not None), + ) + current_out["maskmem_features"] = maskmem_features + current_out["maskmem_pos_enc"] = maskmem_pos_enc + else: + current_out["maskmem_features"] = None + current_out["maskmem_pos_enc"] = None + + # Store propagation image features for decoupled memory attention + current_out["image_features"] = current_vision_feats[-1] # [B, HW, C] + current_out["image_pos_enc"] = current_vision_pos_embeds[-1] # [B, HW, C] + + current_out["pred_masks"] = low_res_masks + current_out["pred_masks_high_res"] = high_res_masks + current_out["obj_ptr"] = obj_ptr + current_out["object_score_logits"] = object_score_logits + + return current_out + + def _compute_backbone_frame(self, backbone_fn, frame, frame_idx=None): + vision_feats, vision_pos, feat_sizes, features, trunk_out = _compute_backbone(backbone_fn, frame, frame_idx) + return vision_feats, vision_pos, feat_sizes, list(features[:-1]), trunk_out + + @staticmethod + def _suppress_recently_occluded(low_res_masks, last_occluded, frame_idx, threshold=0.3): + """Suppress overlapping masks for objects that were most recently occluded. + Prevents corrupted masks from occluded objects from contaminating other objects.""" + N_obj = low_res_masks.shape[0] + if N_obj <= 1: + return low_res_masks + binary = low_res_masks[:, 0] > 0 # [N_obj, H, W] + iou = _compute_mask_overlap(low_res_masks[:, 0], low_res_masks[:, 0]) + overlapping = torch.triu(iou >= threshold, diagonal=1) # [N, N] upper triangle + last_occ_i = last_occluded.unsqueeze(1) # [N, 1] + last_occ_j = last_occluded.unsqueeze(0) # [1, N] + # Suppress the more recently occluded object in each overlapping pair + suppress_i = overlapping & (last_occ_i > last_occ_j) & (last_occ_j > -1) + suppress_j = overlapping & (last_occ_j > last_occ_i) & (last_occ_i > -1) + to_suppress = suppress_i.any(dim=1) | suppress_j.any(dim=0) + # Update last_occluded for occluded/suppressed objects + is_empty = ~binary.any(dim=(-1, -2)) + newly_occluded = is_empty | to_suppress + last_occluded[newly_occluded] = frame_idx + # Suppress masks + low_res_masks[to_suppress] = -10.0 + return low_res_masks + + def _deferred_memory_encode(self, current_out, N_obj, vision_feats, feat_sizes, mux_state, device, + cond_obj_mask=None): + """Deferred memory encoding for propagation frames. cond_obj_mask: per-object bool for conditioning.""" + low_res_masks = current_out["pred_masks"] # [N_obj, 1, H_low, W_low] + + if N_obj > 1: + lr = low_res_masks.squeeze(1) # [N_obj, H, W] + max_obj = torch.argmax(lr, dim=0, keepdim=True) + batch_inds = torch.arange(N_obj, device=device)[:, None, None] + pixel_nol = torch.where(max_obj == batch_inds, lr, torch.clamp(lr, max=-10.0)) + area_before = (lr > 0).sum(dim=(-1, -2)).float().clamp(min=1) + area_after = (pixel_nol > 0).sum(dim=(-1, -2)).float() + shrink_ok = (area_after / area_before) >= 0.3 + low_res_masks = torch.where( + shrink_ok[:, None, None, None].expand_as(low_res_masks), + low_res_masks, torch.clamp(low_res_masks, max=-10.0)) + + interpol_size = self.maskmem_backbone.mask_downsampler.interpol_size + mem_masks = F.interpolate(low_res_masks, size=interpol_size, + mode="bilinear", align_corners=False) + + obj_scores = torch.where( + (mem_masks > 0).any(dim=(-1, -2)), 10.0, -10.0) + + pix_feat = to_spatial(vision_feats[-1], feat_sizes[-1][0], feat_sizes[-1][1]) + maskmem_features, maskmem_pos_enc = self._encode_new_memory( + pix_feat=pix_feat, pred_masks_high_res=mem_masks, + object_score_logits=obj_scores, + multiplex_state=mux_state, cond_obj_mask=cond_obj_mask) + current_out["maskmem_features"] = maskmem_features + current_out["maskmem_pos_enc"] = maskmem_pos_enc + + def _add_detected_objects(self, new_masks, mux_state, vision_feats, feat_sizes, current_out): + """Grow MultiplexState with new detections, merge masks, re-encode memory. Modifies current_out.""" + n_old = mux_state.total_valid_entries + mux_state.add_objects(new_masks.shape[0]) + N_obj = mux_state.total_valid_entries + # Stored memory with old bucket counts is padded at read time by _pad_to_buckets + for k in ("pred_masks", "pred_masks_high_res"): + det = F.interpolate(new_masks.unsqueeze(1), size=current_out[k].shape[-2:], + mode="bilinear", align_corners=False) + current_out[k] = torch.cat([current_out[k], det], dim=0) + if self.num_maskmem > 0: + # Mark new objects as conditioning (clean detection masks) so model trusts them + cond_mask = torch.zeros(N_obj, dtype=torch.bool, device=new_masks.device) + cond_mask[n_old:] = True + self._deferred_memory_encode(current_out, N_obj, vision_feats, feat_sizes, + mux_state, new_masks.device, cond_obj_mask=cond_mask) + + def _condition_with_masks(self, masks, frame_idx, vision_feats, vision_pos, feat_sizes, + high_res_prop, output_dict, N, mux_state, backbone_obj, frame, + trunk_out, threshold=0.5): + """Condition tracker with masks on a frame.""" + mask_input = F.interpolate(masks if masks.dim() == 4 else masks.unsqueeze(1), + size=(self.image_size, self.image_size), mode="bilinear", align_corners=False) + mask_input = (mask_input > threshold).to(masks.dtype) + hi_res = lo_feat = None + if backbone_obj is not None and backbone_obj.multiplex: + _, _, itf, _ = backbone_obj(frame, tracker_mode="interactive", cached_trunk=trunk_out, tracker_only=True) + hi_res, lo_feat = itf[:-1], itf[-1] + current_out = self.track_step( + frame_idx=frame_idx, is_init_cond_frame=True, current_vision_feats=vision_feats, + current_vision_pos_embeds=vision_pos, feat_sizes=feat_sizes, mask_inputs=mask_input, + output_dict=output_dict, num_frames=N, interactive_high_res=hi_res, + interactive_backbone=lo_feat, propagation_high_res=high_res_prop, + multiplex_state=mux_state, run_mem_encoder=True) + output_dict["cond_frame_outputs"][frame_idx] = current_out + return current_out + + def _match_and_add_detections(self, det_masks, det_scores, current_out, mux_state, + vision_feats, feat_sizes, device, max_objects=0, + keep_alive=None): + """Match detections against tracked masks, add new objects, recondition degraded tracks. + Updates keep_alive counters: +1 for matched tracks, -1 for unmatched.""" + N_obj = mux_state.total_valid_entries + if det_masks.shape[0] == 0: + if keep_alive is not None: + for i in range(N_obj): + keep_alive[i] = max(-4, keep_alive.get(i, 0) - 1) + return [] + + # Match at low-res (like reference) + trk_masks = current_out["pred_masks"][:, 0] # [N_obj, H_low, W_low] + det_resized = F.interpolate(det_masks.unsqueeze(1), size=trk_masks.shape[-2:], + mode="bilinear", align_corners=False)[:, 0] + overlap = _compute_mask_overlap(det_resized, trk_masks) + + # Update keep_alive and find matched tracks + matched = set() + if overlap.shape[1] > 0: + matched = set((overlap >= 0.5).any(dim=0).nonzero(as_tuple=True)[0].tolist()) + if keep_alive is not None: + for i in range(N_obj): + if i in matched: + keep_alive[i] = min(8, keep_alive.get(i, 0) + 1) + else: + keep_alive[i] = max(-4, keep_alive.get(i, 0) - 1) + + # Recondition: high-confidence detections (>=0.8) with high overlap refresh tracked masks + reconditioned = False + if det_scores is not None and overlap.shape[1] > 0: + HIGH_CONF = 0.8 + for det_idx in range(overlap.shape[0]): + if det_scores[det_idx] < HIGH_CONF: + continue + best_trk = overlap[det_idx].argmax().item() + if overlap[det_idx, best_trk] >= 0.5: + # Replace tracked mask with fresh detection mask + current_out["pred_masks"][best_trk] = det_resized[det_idx].unsqueeze(0) + det_hr = F.interpolate(det_masks[det_idx:det_idx+1].unsqueeze(1), + size=current_out["pred_masks_high_res"].shape[-2:], + mode="bilinear", align_corners=False) + current_out["pred_masks_high_res"][best_trk] = det_hr[0] + reconditioned = True + + # Re-encode memory if any tracks were reconditioned + if reconditioned and self.num_maskmem > 0: + self._deferred_memory_encode(current_out, N_obj, vision_feats, feat_sizes, mux_state, device) + + # Add new detections (not matching any track) + if max_objects > 0 and N_obj >= max_objects: + return [] + max_overlap = overlap.max(dim=1)[0] if overlap.shape[1] > 0 else torch.zeros(overlap.shape[0], device=device) + new_dets = max_overlap < 0.5 + if new_dets.any(): + if max_objects > 0: + slots = max_objects - N_obj + new_dets = new_dets & (torch.cumsum(new_dets.int(), 0) <= slots) + self._add_detected_objects(det_masks[new_dets], mux_state, + vision_feats, feat_sizes, current_out) + if keep_alive is not None: + for i in range(N_obj, mux_state.total_valid_entries): + keep_alive[i] = 1 + return det_scores[new_dets].tolist() if det_scores is not None else [0.0] * new_dets.sum().item() + return [] + + def track_video_with_detection(self, backbone_fn, images, initial_masks, detect_fn=None, + new_det_thresh=0.5, max_objects=0, detect_interval=1, + backbone_obj=None, pbar=None): + """Track with optional per-frame detection. Returns [N, max_N_obj, H, W] mask logits.""" + N, device, dt = images.shape[0], images.device, images.dtype + output_dict = {"cond_frame_outputs": {}, "non_cond_frame_outputs": {}} + all_masks = [] + idev = comfy.model_management.intermediate_device() + mux_state = None + if initial_masks is not None: + mux_state = MultiplexState(initial_masks.shape[0], self.num_multiplex, device, dt) + obj_scores = [] # per-object detection score (1.0 for initial masks) + keep_alive = {} if detect_fn is not None else None + last_occluded = torch.empty(0, device=device, dtype=torch.long) # per-object last occluded frame + + # Prefetch next frame's backbone on a separate CUDA stream + prefetch = False + backbone_stream = None + if comfy.model_management.is_device_cuda(device): + try: + backbone_stream = torch.cuda.Stream(device=device) + prefetch = True + except RuntimeError: + pass + cur_bb = self._compute_backbone_frame(backbone_fn, images[0:1], frame_idx=0) + + for frame_idx in tqdm(range(N), desc="tracking"): + vision_feats, vision_pos, feat_sizes, high_res_prop, trunk_out = cur_bb + + # Start next frame's backbone on separate stream (overlaps with current frame's work) + if prefetch and frame_idx + 1 < N: + backbone_stream.wait_stream(torch.cuda.current_stream(device)) + with torch.cuda.stream(backbone_stream): + next_bb = self._compute_backbone_frame( + backbone_fn, images[frame_idx + 1:frame_idx + 2], frame_idx=frame_idx + 1) + + # Per-frame detection with NMS (skip if no detect_fn, or interval/max not met) + det_masks = torch.empty(0, device=device) + det_scores = None + run_det = (detect_fn is not None + and frame_idx % max(detect_interval, 1) == 0 + and not (max_objects > 0 and mux_state is not None + and mux_state.total_valid_entries >= max_objects)) + if run_det: + det_out = detect_fn(trunk_out) + scores = det_out["scores"][0].sigmoid() + keep = scores > new_det_thresh + det_masks, det_scores = det_out["masks"][0][keep], scores[keep] + if det_masks.shape[0] > 1: + det_masks, det_scores = _nms_masks(det_masks, det_scores) + + if frame_idx == 0 and initial_masks is not None: + current_out = self._condition_with_masks( + initial_masks.to(device=device, dtype=dt), frame_idx, vision_feats, vision_pos, + feat_sizes, high_res_prop, output_dict, N, mux_state, backbone_obj, + images[frame_idx:frame_idx + 1], trunk_out) + last_occluded = torch.full((mux_state.total_valid_entries,), -1, device=device, dtype=torch.long) + obj_scores = [1.0] * mux_state.total_valid_entries + if keep_alive is not None: + for i in range(mux_state.total_valid_entries): + keep_alive[i] = 8 + elif mux_state is None or mux_state.total_valid_entries == 0: + if det_masks.shape[0] > 0: + if max_objects > 0: + det_scores = det_scores[:max_objects] + det_masks = det_masks[:max_objects] + mux_state = MultiplexState(det_masks.shape[0], self.num_multiplex, device, dt) + current_out = self._condition_with_masks( + det_masks, frame_idx, vision_feats, vision_pos, feat_sizes, high_res_prop, + output_dict, N, mux_state, backbone_obj, + images[frame_idx:frame_idx + 1], trunk_out, threshold=0.0) + last_occluded = torch.full((mux_state.total_valid_entries,), -1, device=device, dtype=torch.long) + obj_scores = det_scores[:mux_state.total_valid_entries].tolist() + if keep_alive is not None: + for i in range(mux_state.total_valid_entries): + keep_alive[i] = 1 + else: + all_masks.append(None) + if pbar is not None: + pbar.update(1) + # Skip to backbone advance at end of loop + if frame_idx + 1 < N: + if prefetch: + torch.cuda.current_stream(device).wait_stream(backbone_stream) + cur_bb = next_bb + else: + cur_bb = self._compute_backbone_frame(backbone_fn, images[frame_idx + 1:frame_idx + 2], frame_idx=frame_idx + 1) + continue + else: + N_obj = mux_state.total_valid_entries + current_out = self.track_step( + frame_idx=frame_idx, is_init_cond_frame=False, current_vision_feats=vision_feats, + current_vision_pos_embeds=vision_pos, feat_sizes=feat_sizes, mask_inputs=None, + output_dict=output_dict, num_frames=N, propagation_high_res=high_res_prop, + multiplex_state=mux_state, run_mem_encoder=False) + current_out["pred_masks"] = fill_holes_in_mask_scores( + current_out["pred_masks"], max_area=16) + if last_occluded.shape[0] == N_obj and N_obj > 1: + self._suppress_recently_occluded( + current_out["pred_masks"], last_occluded, frame_idx) + if self.num_maskmem > 0: + self._deferred_memory_encode(current_out, N_obj, vision_feats, feat_sizes, mux_state, device) + output_dict["non_cond_frame_outputs"][frame_idx] = current_out + lookback = max(self.num_maskmem, self.max_obj_ptrs_in_encoder) + for old_idx in list(output_dict["non_cond_frame_outputs"]): + if old_idx < frame_idx - lookback: + del output_dict["non_cond_frame_outputs"][old_idx] + n_before = mux_state.total_valid_entries + new_obj_scores = self._match_and_add_detections(det_masks, det_scores, current_out, mux_state, + vision_feats, feat_sizes, device, max_objects, + keep_alive if run_det else None) + n_added = mux_state.total_valid_entries - n_before + if n_added > 0: + last_occluded = torch.cat([last_occluded, + torch.full((n_added,), -1, device=device, dtype=torch.long)]) + obj_scores.extend(new_obj_scores) + + masks_out = current_out["pred_masks_high_res"][:, 0] + if keep_alive is not None: + for i in range(masks_out.shape[0]): + if keep_alive.get(i, 0) <= 0: + masks_out[i] = NO_OBJ_SCORE + N_obj_now = mux_state.total_valid_entries if mux_state is not None else 0 + if N_obj_now > 0: + all_masks.append(pack_masks(masks_out).to(idev)) + else: + all_masks.append(None) + if pbar is not None: + pbar.update(1) + + # Next frame's backbone + if frame_idx + 1 < N: + if prefetch: + torch.cuda.current_stream(device).wait_stream(backbone_stream) + cur_bb = next_bb + else: + cur_bb = self._compute_backbone_frame(backbone_fn, images[frame_idx + 1:frame_idx + 2], frame_idx=frame_idx + 1) + + if not all_masks or all(m is None for m in all_masks): + return {"packed_masks": None, "n_frames": N, "scores": []} + + max_obj = max(m.shape[0] for m in all_masks if m is not None) + sample = next(m for m in all_masks if m is not None) + empty_packed = torch.zeros(max_obj, *sample.shape[1:], dtype=torch.uint8, device=sample.device) + for i, m in enumerate(all_masks): + if m is None: + all_masks[i] = empty_packed + elif m.shape[0] < max_obj: + pad = torch.zeros(max_obj - m.shape[0], *m.shape[1:], dtype=torch.uint8, device=m.device) + all_masks[i] = torch.cat([m, pad], dim=0) + return {"packed_masks": torch.stack(all_masks, dim=0), "n_frames": N, "scores": obj_scores} diff --git a/comfy/ldm/supir/__init__.py b/comfy/ldm/supir/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/comfy/ldm/supir/supir_modules.py b/comfy/ldm/supir/supir_modules.py new file mode 100644 index 000000000..7389b01d2 --- /dev/null +++ b/comfy/ldm/supir/supir_modules.py @@ -0,0 +1,226 @@ +import torch +import torch.nn as nn + +from comfy.ldm.modules.diffusionmodules.util import timestep_embedding +from comfy.ldm.modules.diffusionmodules.openaimodel import Downsample, TimestepEmbedSequential, ResBlock, SpatialTransformer +from comfy.ldm.modules.attention import optimized_attention + + +class ZeroSFT(nn.Module): + def __init__(self, label_nc, norm_nc, concat_channels=0, dtype=None, device=None, operations=None): + super().__init__() + + ks = 3 + pw = ks // 2 + + self.param_free_norm = operations.GroupNorm(32, norm_nc + concat_channels, dtype=dtype, device=device) + + nhidden = 128 + + self.mlp_shared = nn.Sequential( + operations.Conv2d(label_nc, nhidden, kernel_size=ks, padding=pw, dtype=dtype, device=device), + nn.SiLU() + ) + self.zero_mul = operations.Conv2d(nhidden, norm_nc + concat_channels, kernel_size=ks, padding=pw, dtype=dtype, device=device) + self.zero_add = operations.Conv2d(nhidden, norm_nc + concat_channels, kernel_size=ks, padding=pw, dtype=dtype, device=device) + + self.zero_conv = operations.Conv2d(label_nc, norm_nc, 1, 1, 0, dtype=dtype, device=device) + self.pre_concat = bool(concat_channels != 0) + + def forward(self, c, h, h_ori=None, control_scale=1): + if h_ori is not None and self.pre_concat: + h_raw = torch.cat([h_ori, h], dim=1) + else: + h_raw = h + + h = h + self.zero_conv(c) + if h_ori is not None and self.pre_concat: + h = torch.cat([h_ori, h], dim=1) + actv = self.mlp_shared(c) + gamma = self.zero_mul(actv) + beta = self.zero_add(actv) + h = self.param_free_norm(h) + h = torch.addcmul(h + beta, h, gamma) + if h_ori is not None and not self.pre_concat: + h = torch.cat([h_ori, h], dim=1) + return torch.lerp(h_raw, h, control_scale) + + +class _CrossAttnInner(nn.Module): + """Inner cross-attention module matching the state_dict layout of the original CrossAttention.""" + def __init__(self, query_dim, context_dim, heads, dim_head, dtype=None, device=None, operations=None): + super().__init__() + inner_dim = dim_head * heads + self.heads = heads + self.to_q = operations.Linear(query_dim, inner_dim, bias=False, dtype=dtype, device=device) + self.to_k = operations.Linear(context_dim, inner_dim, bias=False, dtype=dtype, device=device) + self.to_v = operations.Linear(context_dim, inner_dim, bias=False, dtype=dtype, device=device) + self.to_out = nn.Sequential( + operations.Linear(inner_dim, query_dim, dtype=dtype, device=device), + ) + + def forward(self, x, context): + q = self.to_q(x) + k = self.to_k(context) + v = self.to_v(context) + return self.to_out(optimized_attention(q, k, v, self.heads)) + + +class ZeroCrossAttn(nn.Module): + def __init__(self, context_dim, query_dim, dtype=None, device=None, operations=None): + super().__init__() + heads = query_dim // 64 + dim_head = 64 + self.attn = _CrossAttnInner(query_dim, context_dim, heads, dim_head, dtype=dtype, device=device, operations=operations) + self.norm1 = operations.GroupNorm(32, query_dim, dtype=dtype, device=device) + self.norm2 = operations.GroupNorm(32, context_dim, dtype=dtype, device=device) + + def forward(self, context, x, control_scale=1): + b, c, h, w = x.shape + x_in = x + + x = self.attn( + self.norm1(x).flatten(2).transpose(1, 2), + self.norm2(context).flatten(2).transpose(1, 2), + ).transpose(1, 2).unflatten(2, (h, w)) + + return x_in + x * control_scale + + +class GLVControl(nn.Module): + """SUPIR's Guided Latent Vector control encoder. Truncated UNet (input + middle blocks only).""" + def __init__( + self, + in_channels=4, + model_channels=320, + num_res_blocks=2, + attention_resolutions=(4, 2), + channel_mult=(1, 2, 4), + num_head_channels=64, + transformer_depth=(1, 2, 10), + context_dim=2048, + adm_in_channels=2816, + use_linear_in_transformer=True, + use_checkpoint=False, + dtype=None, + device=None, + operations=None, + **kwargs, + ): + super().__init__() + self.model_channels = model_channels + time_embed_dim = model_channels * 4 + + self.time_embed = nn.Sequential( + operations.Linear(model_channels, time_embed_dim, dtype=dtype, device=device), + nn.SiLU(), + operations.Linear(time_embed_dim, time_embed_dim, dtype=dtype, device=device), + ) + + self.label_emb = nn.Sequential( + nn.Sequential( + operations.Linear(adm_in_channels, time_embed_dim, dtype=dtype, device=device), + nn.SiLU(), + operations.Linear(time_embed_dim, time_embed_dim, dtype=dtype, device=device), + ) + ) + + self.input_blocks = nn.ModuleList([ + TimestepEmbedSequential( + operations.Conv2d(in_channels, model_channels, 3, padding=1, dtype=dtype, device=device) + ) + ]) + ch = model_channels + ds = 1 + for level, mult in enumerate(channel_mult): + for nr in range(num_res_blocks): + layers = [ + ResBlock(ch, time_embed_dim, 0, out_channels=mult * model_channels, + dtype=dtype, device=device, operations=operations) + ] + ch = mult * model_channels + if ds in attention_resolutions: + num_heads = ch // num_head_channels + layers.append( + SpatialTransformer(ch, num_heads, num_head_channels, + depth=transformer_depth[level], context_dim=context_dim, + use_linear=use_linear_in_transformer, + use_checkpoint=use_checkpoint, + dtype=dtype, device=device, operations=operations) + ) + self.input_blocks.append(TimestepEmbedSequential(*layers)) + if level != len(channel_mult) - 1: + self.input_blocks.append( + TimestepEmbedSequential( + Downsample(ch, True, out_channels=ch, dtype=dtype, device=device, operations=operations) + ) + ) + ds *= 2 + + num_heads = ch // num_head_channels + self.middle_block = TimestepEmbedSequential( + ResBlock(ch, time_embed_dim, 0, dtype=dtype, device=device, operations=operations), + SpatialTransformer(ch, num_heads, num_head_channels, + depth=transformer_depth[-1], context_dim=context_dim, + use_linear=use_linear_in_transformer, + use_checkpoint=use_checkpoint, + dtype=dtype, device=device, operations=operations), + ResBlock(ch, time_embed_dim, 0, dtype=dtype, device=device, operations=operations), + ) + + self.input_hint_block = TimestepEmbedSequential( + operations.Conv2d(in_channels, model_channels, 3, padding=1, dtype=dtype, device=device) + ) + + def forward(self, x, timesteps, xt, context=None, y=None, **kwargs): + t_emb = timestep_embedding(timesteps, self.model_channels, repeat_only=False).to(x.dtype) + emb = self.time_embed(t_emb) + self.label_emb(y) + + guided_hint = self.input_hint_block(x, emb, context) + + hs = [] + h = xt + for module in self.input_blocks: + if guided_hint is not None: + h = module(h, emb, context) + h += guided_hint + guided_hint = None + else: + h = module(h, emb, context) + hs.append(h) + h = self.middle_block(h, emb, context) + hs.append(h) + return hs + + +class SUPIR(nn.Module): + """ + SUPIR model containing GLVControl (control encoder) and project_modules (adapters). + State dict keys match the original SUPIR checkpoint layout: + control_model.* -> GLVControl + project_modules.* -> nn.ModuleList of ZeroSFT/ZeroCrossAttn + """ + def __init__(self, device=None, dtype=None, operations=None): + super().__init__() + + self.control_model = GLVControl(dtype=dtype, device=device, operations=operations) + + project_channel_scale = 2 + cond_output_channels = [320] * 4 + [640] * 3 + [1280] * 3 + project_channels = [int(c * project_channel_scale) for c in [160] * 4 + [320] * 3 + [640] * 3] + concat_channels = [320] * 2 + [640] * 3 + [1280] * 4 + [0] + cross_attn_insert_idx = [6, 3] + + self.project_modules = nn.ModuleList() + for i in range(len(cond_output_channels)): + self.project_modules.append(ZeroSFT( + project_channels[i], cond_output_channels[i], + concat_channels=concat_channels[i], + dtype=dtype, device=device, operations=operations, + )) + + for i in cross_attn_insert_idx: + self.project_modules.insert(i, ZeroCrossAttn( + cond_output_channels[i], concat_channels[i], + dtype=dtype, device=device, operations=operations, + )) diff --git a/comfy/ldm/supir/supir_patch.py b/comfy/ldm/supir/supir_patch.py new file mode 100644 index 000000000..b67ab4cd8 --- /dev/null +++ b/comfy/ldm/supir/supir_patch.py @@ -0,0 +1,103 @@ +import torch +from comfy.ldm.modules.diffusionmodules.openaimodel import Upsample + + +class SUPIRPatch: + """ + Holds GLVControl (control encoder) + project_modules (ZeroSFT/ZeroCrossAttn adapters). + Runs GLVControl lazily on first patch invocation per step, applies adapters through + middle_block_after_patch, output_block_merge_patch, and forward_timestep_embed_patch. + """ + SIGMA_MAX = 14.6146 + + def __init__(self, model_patch, project_modules, hint_latent, strength_start, strength_end): + self.model_patch = model_patch # CoreModelPatcher wrapping GLVControl + self.project_modules = project_modules # nn.ModuleList of ZeroSFT/ZeroCrossAttn + self.hint_latent = hint_latent # encoded LQ image latent + self.strength_start = strength_start + self.strength_end = strength_end + self.cached_features = None + self.adapter_idx = 0 + self.control_idx = 0 + self.current_control_idx = 0 + self.active = True + + def _ensure_features(self, kwargs): + """Run GLVControl on first call per step, cache results.""" + if self.cached_features is not None: + return + x = kwargs["x"] + b = x.shape[0] + hint = self.hint_latent.to(device=x.device, dtype=x.dtype) + if hint.shape[0] != b: + hint = hint.expand(b, -1, -1, -1) if hint.shape[0] == 1 else hint.repeat((b + hint.shape[0] - 1) // hint.shape[0], 1, 1, 1)[:b] + self.cached_features = self.model_patch.model.control_model( + hint, kwargs["timesteps"], x, + kwargs["context"], kwargs["y"] + ) + self.adapter_idx = len(self.project_modules) - 1 + self.control_idx = len(self.cached_features) - 1 + + def _get_control_scale(self, kwargs): + if self.strength_start == self.strength_end: + return self.strength_end + sigma = kwargs["transformer_options"].get("sigmas") + if sigma is None: + return self.strength_end + s = sigma[0].item() if sigma.dim() > 0 else sigma.item() + t = min(s / self.SIGMA_MAX, 1.0) + return t * (self.strength_start - self.strength_end) + self.strength_end + + def middle_after(self, kwargs): + """middle_block_after_patch: run GLVControl lazily, apply last adapter after middle block.""" + self.cached_features = None # reset from previous step + self.current_scale = self._get_control_scale(kwargs) + self.active = self.current_scale > 0 + if not self.active: + return {"h": kwargs["h"]} + self._ensure_features(kwargs) + h = kwargs["h"] + h = self.project_modules[self.adapter_idx]( + self.cached_features[self.control_idx], h, control_scale=self.current_scale + ) + self.adapter_idx -= 1 + self.control_idx -= 1 + return {"h": h} + + def output_block(self, h, hsp, transformer_options): + """output_block_patch: ZeroSFT adapter fusion replaces cat([h, hsp]). Returns (h, None) to skip cat.""" + if not self.active: + return h, hsp + self.current_control_idx = self.control_idx + h = self.project_modules[self.adapter_idx]( + self.cached_features[self.control_idx], hsp, h, control_scale=self.current_scale + ) + self.adapter_idx -= 1 + self.control_idx -= 1 + return h, None + + def pre_upsample(self, layer, x, emb, context, transformer_options, output_shape, *args, **kw): + """forward_timestep_embed_patch for Upsample: extra cross-attn adapter before upsample.""" + block_type, _ = transformer_options["block"] + if block_type == "output" and self.active and self.cached_features is not None: + x = self.project_modules[self.adapter_idx]( + self.cached_features[self.current_control_idx], x, control_scale=self.current_scale + ) + self.adapter_idx -= 1 + return layer(x, output_shape=output_shape) + + def to(self, device_or_dtype): + if isinstance(device_or_dtype, torch.device): + self.cached_features = None + if self.hint_latent is not None: + self.hint_latent = self.hint_latent.to(device_or_dtype) + return self + + def models(self): + return [self.model_patch] + + def register(self, model_patcher): + """Register all patches on a cloned model patcher.""" + model_patcher.set_model_patch(self.middle_after, "middle_block_after_patch") + model_patcher.set_model_output_block_patch(self.output_block) + model_patcher.set_model_patch((Upsample, self.pre_upsample), "forward_timestep_embed_patch") diff --git a/comfy/lora.py b/comfy/lora.py index 63ee85323..db8f16bcb 100644 --- a/comfy/lora.py +++ b/comfy/lora.py @@ -17,6 +17,7 @@ """ from __future__ import annotations +import comfy.memory_management import comfy.utils import comfy.model_management import comfy.model_base @@ -342,6 +343,12 @@ def model_lora_keys_unet(model, key_map={}): key_map["base_model.model.{}".format(key_lora)] = k # Official base model loras key_map["lycoris_{}".format(key_lora.replace(".", "_"))] = k # LyCORIS/LoKR format + if isinstance(model, comfy.model_base.ErnieImage): + for k in sdk: + if k.startswith("diffusion_model.") and k.endswith(".weight"): + key_lora = k[len("diffusion_model."):-len(".weight")] + key_map["transformer.{}".format(key_lora)] = k + return key_map @@ -467,3 +474,17 @@ def calculate_weight(patches, weight, key, intermediate_dtype=torch.float32, ori weight = old_weight return weight + +def prefetch_prepared_value(value, allocate_buffer, stream): + if isinstance(value, torch.Tensor): + dest = allocate_buffer(comfy.memory_management.vram_aligned_size(value)) + comfy.model_management.cast_to_gathered([value], dest, non_blocking=True, stream=stream) + return comfy.memory_management.interpret_gathered_like([value], dest)[0] + elif isinstance(value, weight_adapter.WeightAdapterBase): + return type(value)(value.loaded_keys, prefetch_prepared_value(value.weights, allocate_buffer, stream)) + elif isinstance(value, tuple): + return tuple(prefetch_prepared_value(item, allocate_buffer, stream) for item in value) + elif isinstance(value, list): + return [prefetch_prepared_value(item, allocate_buffer, stream) for item in value] + + return value diff --git a/comfy/model_base.py b/comfy/model_base.py index c2ae646aa..b61a2aa09 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -52,7 +52,10 @@ import comfy.ldm.qwen_image.model import comfy.ldm.kandinsky5.model import comfy.ldm.anima.model import comfy.ldm.ace.ace_step15 +import comfy.ldm.cogvideo.model import comfy.ldm.rt_detr.rtdetr_v4 +import comfy.ldm.ernie.model +import comfy.ldm.sam3.detector import comfy.model_management import comfy.patcher_extension @@ -79,6 +82,7 @@ class ModelType(Enum): IMG_TO_IMG = 9 FLOW_COSMOS = 10 IMG_TO_IMG_FLOW = 11 + V_PREDICTION_DDPM = 12 def model_sampling(model_config, model_type): @@ -113,6 +117,8 @@ def model_sampling(model_config, model_type): s = comfy.model_sampling.ModelSamplingCosmosRFlow elif model_type == ModelType.IMG_TO_IMG_FLOW: c = comfy.model_sampling.IMG_TO_IMG_FLOW + elif model_type == ModelType.V_PREDICTION_DDPM: + c = comfy.model_sampling.V_PREDICTION_DDPM class ModelSampling(s, c): pass @@ -208,6 +214,11 @@ class BaseModel(torch.nn.Module): if "latent_shapes" in extra_conds: xc = utils.unpack_latents(xc, extra_conds.pop("latent_shapes")) + transformer_options = transformer_options.copy() + transformer_options["prefetch_dynamic_vbars"] = ( + self.current_patcher is not None and self.current_patcher.is_dynamic() + ) + model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds) if len(model_output) > 1 and not torch.is_tensor(model_output): model_output, _ = utils.pack_latents(model_output) @@ -577,8 +588,8 @@ class Stable_Zero123(BaseModel): def __init__(self, model_config, model_type=ModelType.EPS, device=None, cc_projection_weight=None, cc_projection_bias=None): super().__init__(model_config, model_type, device=device) self.cc_projection = comfy.ops.manual_cast.Linear(cc_projection_weight.shape[1], cc_projection_weight.shape[0], dtype=self.get_dtype(), device=device) - self.cc_projection.weight.copy_(cc_projection_weight) - self.cc_projection.bias.copy_(cc_projection_bias) + self.cc_projection.weight = torch.nn.Parameter(cc_projection_weight.clone()) + self.cc_projection.bias = torch.nn.Parameter(cc_projection_bias.clone()) def extra_conds(self, **kwargs): out = {} @@ -1962,3 +1973,74 @@ class Kandinsky5Image(Kandinsky5): class RT_DETR_v4(BaseModel): def __init__(self, model_config, model_type=ModelType.FLOW, device=None): super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.rt_detr.rtdetr_v4.RTv4) + +class ErnieImage(BaseModel): + def __init__(self, model_config, model_type=ModelType.FLOW, device=None): + super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.ernie.model.ErnieImageModel) + + def extra_conds(self, **kwargs): + out = super().extra_conds(**kwargs) + cross_attn = kwargs.get("cross_attn", None) + if cross_attn is not None: + out['c_crossattn'] = comfy.conds.CONDRegular(cross_attn) + return out + +class SAM3(BaseModel): + def __init__(self, model_config, model_type=ModelType.FLOW, device=None): + super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.sam3.detector.SAM3Model) + +class CogVideoX(BaseModel): + def __init__(self, model_config, model_type=ModelType.V_PREDICTION_DDPM, image_to_video=False, device=None): + super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.cogvideo.model.CogVideoXTransformer3DModel) + self.image_to_video = image_to_video + + def concat_cond(self, **kwargs): + noise = kwargs.get("noise", None) + # Detect extra channels needed (e.g. 32 - 16 = 16 for ref latent) + extra_channels = self.diffusion_model.in_channels - noise.shape[1] + if extra_channels == 0: + return None + + image = kwargs.get("concat_latent_image", None) + device = kwargs["device"] + + if image is None: + shape = list(noise.shape) + shape[1] = extra_channels + return torch.zeros(shape, dtype=noise.dtype, layout=noise.layout, device=noise.device) + + latent_dim = self.latent_format.latent_channels + image = utils.common_upscale(image.to(device), noise.shape[-1], noise.shape[-2], "bilinear", "center") + + if noise.ndim == 5 and image.ndim == 5: + if image.shape[-3] < noise.shape[-3]: + image = torch.nn.functional.pad(image, (0, 0, 0, 0, 0, noise.shape[-3] - image.shape[-3]), "constant", 0) + elif image.shape[-3] > noise.shape[-3]: + image = image[:, :, :noise.shape[-3]] + + for i in range(0, image.shape[1], latent_dim): + image[:, i:i + latent_dim] = self.process_latent_in(image[:, i:i + latent_dim]) + image = utils.resize_to_batch_size(image, noise.shape[0]) + + if image.shape[1] > extra_channels: + image = image[:, :extra_channels] + elif image.shape[1] < extra_channels: + repeats = extra_channels // image.shape[1] + remainder = extra_channels % image.shape[1] + parts = [image] * repeats + if remainder > 0: + parts.append(image[:, :remainder]) + image = torch.cat(parts, dim=1) + + return image + + def extra_conds(self, **kwargs): + out = super().extra_conds(**kwargs) + # OFS embedding (CogVideoX 1.5 I2V), default 2.0 as used by SparkVSR + if self.diffusion_model.ofs_proj_dim is not None: + ofs = kwargs.get("ofs", None) + if ofs is None: + noise = kwargs.get("noise", None) + ofs = torch.full((noise.shape[0],), 2.0, device=noise.device, dtype=noise.dtype) + out['ofs'] = comfy.conds.CONDRegular(ofs) + return out diff --git a/comfy/model_detection.py b/comfy/model_detection.py index 1c8ae2325..d9b67dcdf 100644 --- a/comfy/model_detection.py +++ b/comfy/model_detection.py @@ -490,6 +490,54 @@ def detect_unet_config(state_dict, key_prefix, metadata=None): return dit_config + if '{}blocks.0.norm1.linear.weight'.format(key_prefix) in state_dict_keys: # CogVideoX + dit_config = {} + dit_config["image_model"] = "cogvideox" + + # Extract config from weight shapes + norm1_weight = state_dict['{}blocks.0.norm1.linear.weight'.format(key_prefix)] + time_embed_dim = norm1_weight.shape[1] + dim = norm1_weight.shape[0] // 6 + + dit_config["num_attention_heads"] = dim // 64 + dit_config["attention_head_dim"] = 64 + dit_config["time_embed_dim"] = time_embed_dim + dit_config["num_layers"] = count_blocks(state_dict_keys, '{}blocks.'.format(key_prefix) + '{}.') + + # Detect in_channels from patch_embed + patch_proj_key = '{}patch_embed.proj.weight'.format(key_prefix) + if patch_proj_key in state_dict_keys: + w = state_dict[patch_proj_key] + if w.ndim == 4: + # Conv2d: [out, in, kh, kw] — CogVideoX 1.0 + dit_config["in_channels"] = w.shape[1] + dit_config["patch_size"] = w.shape[2] + elif w.ndim == 2: + # Linear: [out, in_channels * patch_size * patch_size * patch_size_t] — CogVideoX 1.5 + dit_config["patch_size"] = 2 + dit_config["patch_size_t"] = 2 + dit_config["in_channels"] = w.shape[1] // (2 * 2 * 2) # 256 // 8 = 32 + + text_proj_key = '{}patch_embed.text_proj.weight'.format(key_prefix) + if text_proj_key in state_dict_keys: + dit_config["text_embed_dim"] = state_dict[text_proj_key].shape[1] + + # Detect OFS embedding + ofs_key = '{}ofs_embedding_linear_1.weight'.format(key_prefix) + if ofs_key in state_dict_keys: + dit_config["ofs_embed_dim"] = state_dict[ofs_key].shape[1] + + # Detect positional embedding type + pos_key = '{}patch_embed.pos_embedding'.format(key_prefix) + if pos_key in state_dict_keys: + dit_config["use_learned_positional_embeddings"] = True + dit_config["use_rotary_positional_embeddings"] = False + else: + dit_config["use_learned_positional_embeddings"] = False + dit_config["use_rotary_positional_embeddings"] = True + + return dit_config + if '{}head.modulation'.format(key_prefix) in state_dict_keys: # Wan 2.1 dit_config = {} dit_config["image_model"] = "wan2.1" @@ -696,6 +744,15 @@ def detect_unet_config(state_dict, key_prefix, metadata=None): if '{}encoder.lyric_encoder.layers.0.input_layernorm.weight'.format(key_prefix) in state_dict_keys: dit_config = {} dit_config["audio_model"] = "ace1.5" + head_dim = 128 + dit_config["hidden_size"] = state_dict['{}decoder.layers.0.self_attn_norm.weight'.format(key_prefix)].shape[0] + dit_config["intermediate_size"] = state_dict['{}decoder.layers.0.mlp.gate_proj.weight'.format(key_prefix)].shape[0] + dit_config["num_heads"] = state_dict['{}decoder.layers.0.self_attn.q_proj.weight'.format(key_prefix)].shape[0] // head_dim + + dit_config["encoder_hidden_size"] = state_dict['{}encoder.lyric_encoder.layers.0.input_layernorm.weight'.format(key_prefix)].shape[0] + dit_config["encoder_num_heads"] = state_dict['{}encoder.lyric_encoder.layers.0.self_attn.q_proj.weight'.format(key_prefix)].shape[0] // head_dim + dit_config["encoder_intermediate_size"] = state_dict['{}encoder.lyric_encoder.layers.0.mlp.gate_proj.weight'.format(key_prefix)].shape[0] + dit_config["num_dit_layers"] = count_blocks(state_dict_keys, '{}decoder.layers.'.format(key_prefix) + '{}.') return dit_config if '{}encoder.pan_blocks.1.cv4.conv.weight'.format(key_prefix) in state_dict_keys: # RT-DETR_v4 @@ -704,6 +761,19 @@ def detect_unet_config(state_dict, key_prefix, metadata=None): dit_config["enc_h"] = state_dict['{}encoder.pan_blocks.1.cv4.conv.weight'.format(key_prefix)].shape[0] return dit_config + if '{}layers.0.mlp.linear_fc2.weight'.format(key_prefix) in state_dict_keys: # Ernie Image + dit_config = {} + dit_config["image_model"] = "ernie" + return dit_config + + if 'detector.backbone.vision_backbone.trunk.blocks.0.attn.qkv.weight' in state_dict_keys: # SAM3 / SAM3.1 + if 'detector.transformer.decoder.query_embed.weight' in state_dict_keys: + dit_config = {} + dit_config["image_model"] = "SAM3" + if 'detector.backbone.vision_backbone.propagation_convs.0.conv_1x1.weight' in state_dict_keys: + dit_config["image_model"] = "SAM31" + return dit_config + if '{}input_blocks.0.0.weight'.format(key_prefix) not in state_dict_keys: return None @@ -859,6 +929,10 @@ def model_config_from_unet(state_dict, unet_key_prefix, use_base_if_no_match=Fal return model_config def unet_prefix_from_state_dict(state_dict): + # SAM3: detector.* and tracker.* at top level, no common prefix + if any(k.startswith("detector.") for k in state_dict) and any(k.startswith("tracker.") for k in state_dict): + return "" + candidates = ["model.diffusion_model.", #ldm/sgm models "model.model.", #audio models "net.", #cosmos diff --git a/comfy/model_management.py b/comfy/model_management.py index ce079cf2f..02ad66656 100644 --- a/comfy/model_management.py +++ b/comfy/model_management.py @@ -31,6 +31,7 @@ from contextlib import nullcontext import comfy.memory_management import comfy.utils import comfy.quant_ops +import comfy_aimdo.vram_buffer class VRAMState(Enum): DISABLED = 0 #No vram present: no need to move models to vram @@ -112,10 +113,6 @@ if args.directml is not None: # torch_directml.disable_tiled_resources(True) lowvram_available = False #TODO: need to find a way to get free memory in directml before this can be enabled by default. -try: - import intel_extension_for_pytorch as ipex # noqa: F401 -except: - pass try: _ = torch.xpu.device_count() @@ -583,9 +580,6 @@ class LoadedModel: real_model = self.model.model - if is_intel_xpu() and not args.disable_ipex_optimize and 'ipex' in globals() and real_model is not None: - with torch.no_grad(): - real_model = ipex.optimize(real_model.eval(), inplace=True, graph_mode=True, concat_linear=True) self.real_model = weakref.ref(real_model) self.model_finalizer = weakref.finalize(real_model, cleanup_models) @@ -663,6 +657,7 @@ def minimum_inference_memory(): def free_memory(memory_required, device, keep_loaded=[], for_dynamic=False, pins_required=0, ram_required=0): cleanup_models_gc() + comfy.memory_management.extra_ram_release(max(pins_required, ram_required)) unloaded_model = [] can_unload = [] unloaded_models = [] @@ -1181,6 +1176,10 @@ stream_counters = {} STREAM_CAST_BUFFERS = {} LARGEST_CASTED_WEIGHT = (None, 0) +STREAM_AIMDO_CAST_BUFFERS = {} +LARGEST_AIMDO_CASTED_WEIGHT = (None, 0) + +DEFAULT_AIMDO_CAST_BUFFER_RESERVATION_SIZE = 16 * 1024 ** 3 def get_cast_buffer(offload_stream, device, size, ref): global LARGEST_CASTED_WEIGHT @@ -1214,13 +1213,26 @@ def get_cast_buffer(offload_stream, device, size, ref): return cast_buffer +def get_aimdo_cast_buffer(offload_stream, device): + cast_buffer = STREAM_AIMDO_CAST_BUFFERS.get(offload_stream, None) + if cast_buffer is None: + cast_buffer = comfy_aimdo.vram_buffer.VRAMBuffer(DEFAULT_AIMDO_CAST_BUFFER_RESERVATION_SIZE, device.index) + STREAM_AIMDO_CAST_BUFFERS[offload_stream] = cast_buffer + + return cast_buffer def reset_cast_buffers(): global LARGEST_CASTED_WEIGHT + global LARGEST_AIMDO_CASTED_WEIGHT + LARGEST_CASTED_WEIGHT = (None, 0) - for offload_stream in STREAM_CAST_BUFFERS: - offload_stream.synchronize() + LARGEST_AIMDO_CASTED_WEIGHT = (None, 0) + for offload_stream in set(STREAM_CAST_BUFFERS) | set(STREAM_AIMDO_CAST_BUFFERS): + if offload_stream is not None: + offload_stream.synchronize() synchronize() + STREAM_CAST_BUFFERS.clear() + STREAM_AIMDO_CAST_BUFFERS.clear() soft_empty_cache() def get_offload_stream(device): @@ -1326,9 +1338,9 @@ MAX_PINNED_MEMORY = -1 if not args.disable_pinned_memory: if is_nvidia() or is_amd(): if WINDOWS: - MAX_PINNED_MEMORY = get_total_memory(torch.device("cpu")) * 0.45 # Windows limit is apparently 50% + MAX_PINNED_MEMORY = get_total_memory(torch.device("cpu")) * 0.40 # Windows limit is apparently 50% else: - MAX_PINNED_MEMORY = get_total_memory(torch.device("cpu")) * 0.95 + MAX_PINNED_MEMORY = get_total_memory(torch.device("cpu")) * 0.90 logging.info("Enabled pinned memory {}".format(MAX_PINNED_MEMORY // (1024 * 1024))) PINNING_ALLOWED_TYPES = set(["Tensor", "Parameter", "QuantizedTensor"]) @@ -1403,8 +1415,6 @@ def unpin_memory(tensor): if torch.cuda.cudart().cudaHostUnregister(ptr) == 0: TOTAL_PINNED_MEMORY -= PINNED_MEMORY.pop(ptr) - if len(PINNED_MEMORY) == 0: - TOTAL_PINNED_MEMORY = 0 return True else: logging.warning("Unpin error.") @@ -1582,10 +1592,7 @@ def should_use_fp16(device=None, model_params=0, prioritize_performance=True, ma return False if is_intel_xpu(): - if torch_version_numeric < (2, 3): - return True - else: - return torch.xpu.get_device_properties(device).has_fp16 + return torch.xpu.get_device_properties(device).has_fp16 if is_ascend_npu(): return True @@ -1651,10 +1658,7 @@ def should_use_bf16(device=None, model_params=0, prioritize_performance=True, ma return False if is_intel_xpu(): - if torch_version_numeric < (2, 3): - return True - else: - return torch.xpu.is_bf16_supported() + return torch.xpu.is_bf16_supported() if is_ascend_npu(): return True @@ -1734,6 +1738,21 @@ def supports_mxfp8_compute(device=None): return True +def supports_fp64(device=None): + if is_device_mps(device): + return False + + if is_intel_xpu(): + return False + + if is_directml_enabled(): + return False + + if is_ixuca(): + return False + + return True + def extended_fp16_support(): # TODO: check why some models work with fp16 on newer torch versions but not on older if torch_version_numeric < (2, 7): @@ -1770,6 +1789,7 @@ def soft_empty_cache(force=False): if cpu_state == CPUState.MPS: torch.mps.empty_cache() elif is_intel_xpu(): + torch.xpu.synchronize() torch.xpu.empty_cache() elif is_ascend_npu(): torch.npu.empty_cache() @@ -1788,7 +1808,7 @@ def debug_memory_summary(): return torch.cuda.memory.memory_summary() return "" -class InterruptProcessingException(Exception): +class InterruptProcessingException(BaseException): pass interrupt_processing_mutex = threading.RLock() diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 6deb71e12..7d2d6883f 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -31,6 +31,7 @@ import comfy.float import comfy.hooks import comfy.lora import comfy.model_management +import comfy.ops import comfy.patcher_extension import comfy.utils from comfy.comfy_types import UnetWrapperFunction @@ -120,9 +121,20 @@ class LowVramPatch: self.patches = patches self.convert_func = convert_func # TODO: remove self.set_func = set_func + self.prepared_patches = None + + def prepare(self, allocate_buffer, stream): + self.prepared_patches = [ + (patch[0], comfy.lora.prefetch_prepared_value(patch[1], allocate_buffer, stream), patch[2], patch[3], patch[4]) + for patch in self.patches[self.key] + ] + + def clear_prepared(self): + self.prepared_patches = None def __call__(self, weight): - return comfy.lora.calculate_weight(self.patches[self.key], weight, self.key, intermediate_dtype=weight.dtype) + patches = self.prepared_patches if self.prepared_patches is not None else self.patches[self.key] + return comfy.lora.calculate_weight(patches, weight, self.key, intermediate_dtype=weight.dtype) LOWVRAM_PATCH_ESTIMATE_MATH_FACTOR = 2 @@ -506,6 +518,10 @@ class ModelPatcher: def set_model_noise_refiner_patch(self, patch): self.set_model_patch(patch, "noise_refiner") + def set_model_middle_block_after_patch(self, patch): + self.set_model_patch(patch, "middle_block_after_patch") + + def set_model_rope_options(self, scale_x, shift_x, scale_y, shift_y, scale_t, shift_t, **kwargs): rope_options = self.model_options["transformer_options"].get("rope_options", {}) rope_options["scale_x"] = scale_x @@ -681,9 +697,9 @@ class ModelPatcher: sd.pop(k) return sd - def patch_weight_to_device(self, key, device_to=None, inplace_update=False, return_weight=False): + def patch_weight_to_device(self, key, device_to=None, inplace_update=False, return_weight=False, force_cast=False): weight, set_func, convert_func = get_key_weight(self.model, key) - if key not in self.patches: + if key not in self.patches and not force_cast: return weight inplace_update = self.weight_inplace_update or inplace_update @@ -691,7 +707,7 @@ class ModelPatcher: if key not in self.backup and not return_weight: self.backup[key] = collections.namedtuple('Dimension', ['weight', 'inplace_update'])(weight.to(device=self.offload_device, copy=inplace_update), inplace_update) - temp_dtype = comfy.model_management.lora_compute_dtype(device_to) + temp_dtype = comfy.model_management.lora_compute_dtype(device_to) if key in self.patches else None if device_to is not None: temp_weight = comfy.model_management.cast_to_device(weight, device_to, temp_dtype, copy=True) else: @@ -699,9 +715,10 @@ class ModelPatcher: if convert_func is not None: temp_weight = convert_func(temp_weight, inplace=True) - out_weight = comfy.lora.calculate_weight(self.patches[key], temp_weight, key) + out_weight = comfy.lora.calculate_weight(self.patches[key], temp_weight, key) if key in self.patches else temp_weight if set_func is None: - out_weight = comfy.float.stochastic_rounding(out_weight, weight.dtype, seed=comfy.utils.string_to_seed(key)) + if key in self.patches: + out_weight = comfy.float.stochastic_rounding(out_weight, weight.dtype, seed=comfy.utils.string_to_seed(key)) if return_weight: return out_weight elif inplace_update: @@ -851,7 +868,9 @@ class ModelPatcher: if m.comfy_patched_weights == True: continue - for param in params: + for param, param_value in params.items(): + if hasattr(m, "comfy_cast_weights") and getattr(param_value, "is_meta", False): + comfy.ops.disable_weight_init._zero_init_parameter(m, param) key = key_param_name_to_key(n, param) self.unpin_weight(key) self.patch_weight_to_device(key, device_to=device_to) @@ -1580,7 +1599,7 @@ class ModelPatcherDynamic(ModelPatcher): key = key_param_name_to_key(n, param_key) if key in self.backup: comfy.utils.set_attr_param(self.model, key, self.backup[key].weight) - self.patch_weight_to_device(key, device_to=device_to) + self.patch_weight_to_device(key, device_to=device_to, force_cast=True) weight, _, _ = get_key_weight(self.model, key) if weight is not None: self.model.model_loaded_weight_memory += weight.numel() * weight.element_size() @@ -1605,6 +1624,10 @@ class ModelPatcherDynamic(ModelPatcher): m._v = vbar.alloc(v_weight_size) allocated_size += v_weight_size + for param in params: + if param not in ("weight", "bias"): + force_load_param(self, param, device_to) + else: for param in params: key = key_param_name_to_key(n, param) diff --git a/comfy/model_prefetch.py b/comfy/model_prefetch.py new file mode 100644 index 000000000..0ad35deb5 --- /dev/null +++ b/comfy/model_prefetch.py @@ -0,0 +1,65 @@ +import comfy_aimdo.model_vbar +import comfy.model_management +import comfy.ops + +PREFETCH_QUEUES = [] + +def cleanup_prefetched_modules(comfy_modules): + for s in comfy_modules: + prefetch = getattr(s, "_prefetch", None) + if prefetch is None: + continue + for param_key in ("weight", "bias"): + lowvram_fn = getattr(s, param_key + "_lowvram_function", None) + if lowvram_fn is not None: + lowvram_fn.clear_prepared() + if prefetch["signature"] is not None: + comfy_aimdo.model_vbar.vbar_unpin(s._v) + delattr(s, "_prefetch") + +def cleanup_prefetch_queues(): + global PREFETCH_QUEUES + + for queue in PREFETCH_QUEUES: + for entry in queue: + if entry is None or not isinstance(entry, tuple): + continue + _, prefetch_state = entry + comfy_modules = prefetch_state[1] + if comfy_modules is not None: + cleanup_prefetched_modules(comfy_modules) + PREFETCH_QUEUES = [] + +def prefetch_queue_pop(queue, device, module): + if queue is None: + return + + consumed = queue.pop(0) + if consumed is not None: + offload_stream, prefetch_state = consumed + offload_stream.wait_stream(comfy.model_management.current_stream(device)) + _, comfy_modules = prefetch_state + if comfy_modules is not None: + cleanup_prefetched_modules(comfy_modules) + + prefetch = queue[0] + if prefetch is not None: + comfy_modules = [] + for s in prefetch.modules(): + if hasattr(s, "_v"): + comfy_modules.append(s) + + offload_stream = comfy.ops.cast_modules_with_vbar(comfy_modules, None, device, None, True) + comfy.model_management.sync_stream(device, offload_stream) + queue[0] = (offload_stream, (prefetch, comfy_modules)) + +def make_prefetch_queue(queue, device, transformer_options): + if (not transformer_options.get("prefetch_dynamic_vbars", False) + or comfy.model_management.NUM_STREAMS == 0 + or comfy.model_management.is_device_cpu(device) + or not comfy.model_management.device_supports_non_blocking(device)): + return None + + queue = [None] + queue + [None] + PREFETCH_QUEUES.append(queue) + return queue diff --git a/comfy/model_sampling.py b/comfy/model_sampling.py index 13860e6a2..cf2b5db5f 100644 --- a/comfy/model_sampling.py +++ b/comfy/model_sampling.py @@ -54,6 +54,30 @@ class V_PREDICTION(EPS): sigma = reshape_sigma(sigma, model_output.ndim) return model_input * self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) - model_output * sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 +class V_PREDICTION_DDPM: + """CogVideoX v-prediction: model receives raw x_t (unscaled), predicts velocity v. + x_0 = sqrt(alpha) * x_t - sqrt(1-alpha) * v + = x_t / sqrt(sigma^2 + 1) - v * sigma / sqrt(sigma^2 + 1) + """ + def calculate_input(self, sigma, noise): + return noise + + def calculate_denoised(self, sigma, model_output, model_input): + sigma = reshape_sigma(sigma, model_output.ndim) + return model_input / (sigma ** 2 + 1.0) ** 0.5 - model_output * sigma / (sigma ** 2 + 1.0) ** 0.5 + + def noise_scaling(self, sigma, noise, latent_image, max_denoise=False): + sigma = reshape_sigma(sigma, noise.ndim) + if max_denoise: + noise = noise * torch.sqrt(1.0 + sigma ** 2.0) + else: + noise = noise * sigma + noise += latent_image + return noise + + def inverse_noise_scaling(self, sigma, latent): + return latent + class EDM(V_PREDICTION): def calculate_denoised(self, sigma, model_output, model_input): sigma = reshape_sigma(sigma, model_output.ndim) diff --git a/comfy/ops.py b/comfy/ops.py index b5cd1d47e..4f0338346 100644 --- a/comfy/ops.py +++ b/comfy/ops.py @@ -79,37 +79,68 @@ def cast_to_input(weight, input, non_blocking=False, copy=True): return comfy.model_management.cast_to(weight, input.dtype, input.device, non_blocking=non_blocking, copy=copy) -def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compute_dtype, want_requant): +def materialize_meta_param(s, param_keys): + for param_key in param_keys: + param = getattr(s, param_key, None) + if param is not None and getattr(param, "is_meta", False): + setattr(s, param_key, torch.nn.Parameter(torch.zeros(param.shape, dtype=param.dtype), requires_grad=param.requires_grad)) - #vbar doesn't support CPU weights, but some custom nodes have weird paths - #that might switch the layer to the CPU and expect it to work. We have to take - #a clone conservatively as we are mmapped and some SFT files are packed misaligned - #If you are a custom node author reading this, please move your layer to the GPU - #or declare your ModelPatcher as CPU in the first place. - if comfy.model_management.is_device_cpu(device): - weight = s.weight.to(dtype=dtype, copy=True) - if isinstance(weight, QuantizedTensor): - weight = weight.dequantize() - bias = None - if s.bias is not None: - bias = s.bias.to(dtype=bias_dtype, copy=True) - return weight, bias, (None, None, None) +# FIXME: add n=1 cache hit fast path +def cast_modules_with_vbar(comfy_modules, dtype, device, bias_dtype, non_blocking): offload_stream = None - xfer_dest = None + cast_buffer = None + cast_buffer_offset = 0 + + def ensure_offload_stream(module, required_size, check_largest): + nonlocal offload_stream + nonlocal cast_buffer + + if offload_stream is None: + offload_stream = comfy.model_management.get_offload_stream(device) + if offload_stream is None or not check_largest or len(comfy_modules) != 1: + return + + current_size = 0 if cast_buffer is None else cast_buffer.size() + if current_size < required_size and module is comfy.model_management.LARGEST_AIMDO_CASTED_WEIGHT[0]: + offload_stream = comfy.model_management.get_offload_stream(device) + cast_buffer = None + if required_size > comfy.model_management.LARGEST_AIMDO_CASTED_WEIGHT[1]: + comfy.model_management.LARGEST_AIMDO_CASTED_WEIGHT = (module, required_size) + + def get_cast_buffer(buffer_size): + nonlocal offload_stream + nonlocal cast_buffer + nonlocal cast_buffer_offset + + if buffer_size == 0: + return None + + if offload_stream is None: + return torch.empty((buffer_size,), dtype=torch.uint8, device=device) + + cast_buffer = comfy.model_management.get_aimdo_cast_buffer(offload_stream, device) + buffer = comfy_aimdo.torch.aimdo_to_tensor(cast_buffer.get(buffer_size, cast_buffer_offset), device) + cast_buffer_offset += buffer_size + return buffer + + for s in comfy_modules: + signature = comfy_aimdo.model_vbar.vbar_fault(s._v) + resident = comfy_aimdo.model_vbar.vbar_signature_compare(signature, s._v_signature) + prefetch = { + "signature": signature, + "resident": resident, + } - signature = comfy_aimdo.model_vbar.vbar_fault(s._v) - resident = comfy_aimdo.model_vbar.vbar_signature_compare(signature, s._v_signature) - if signature is not None: if resident: - weight = s._v_weight - bias = s._v_bias - else: - xfer_dest = comfy_aimdo.torch.aimdo_to_tensor(s._v, device) + s._prefetch = prefetch + continue - if not resident: + materialize_meta_param(s, ["weight", "bias"]) + xfer_dest = comfy_aimdo.torch.aimdo_to_tensor(s._v, device) if signature is not None else None cast_geometry = comfy.memory_management.tensors_to_geometries([ s.weight, s.bias ]) cast_dest = None + needs_cast = False xfer_source = [ s.weight, s.bias ] @@ -121,22 +152,15 @@ def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compu if data is None: continue if data.dtype != geometry.dtype: + needs_cast = True cast_dest = xfer_dest - if cast_dest is None: - cast_dest = torch.empty((comfy.memory_management.vram_aligned_size(cast_geometry),), dtype=torch.uint8, device=device) xfer_dest = None break dest_size = comfy.memory_management.vram_aligned_size(xfer_source) - offload_stream = comfy.model_management.get_offload_stream(device) - if xfer_dest is None and offload_stream is not None: - xfer_dest = comfy.model_management.get_cast_buffer(offload_stream, device, dest_size, s) - if xfer_dest is None: - offload_stream = comfy.model_management.get_offload_stream(device) - xfer_dest = comfy.model_management.get_cast_buffer(offload_stream, device, dest_size, s) + ensure_offload_stream(s, dest_size if xfer_dest is None else 0, True) if xfer_dest is None: - xfer_dest = torch.empty((dest_size,), dtype=torch.uint8, device=device) - offload_stream = None + xfer_dest = get_cast_buffer(dest_size) if signature is None and pin is None: comfy.pinned_memory.pin_memory(s) @@ -149,27 +173,54 @@ def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compu xfer_source = [ pin ] #send it over comfy.model_management.cast_to_gathered(xfer_source, xfer_dest, non_blocking=non_blocking, stream=offload_stream) - comfy.model_management.sync_stream(device, offload_stream) - if cast_dest is not None: + for param_key in ("weight", "bias"): + lowvram_fn = getattr(s, param_key + "_lowvram_function", None) + if lowvram_fn is not None: + ensure_offload_stream(s, cast_buffer_offset, False) + lowvram_fn.prepare(lambda size: get_cast_buffer(size), offload_stream) + + prefetch["xfer_dest"] = xfer_dest + prefetch["cast_dest"] = cast_dest + prefetch["cast_geometry"] = cast_geometry + prefetch["needs_cast"] = needs_cast + s._prefetch = prefetch + + return offload_stream + + +def resolve_cast_module_with_vbar(s, dtype, device, bias_dtype, compute_dtype, want_requant): + + prefetch = getattr(s, "_prefetch", None) + + if prefetch["resident"]: + weight = s._v_weight + bias = s._v_bias + else: + xfer_dest = prefetch["xfer_dest"] + if prefetch["needs_cast"]: + cast_dest = prefetch["cast_dest"] if prefetch["cast_dest"] is not None else torch.empty((comfy.memory_management.vram_aligned_size(prefetch["cast_geometry"]),), dtype=torch.uint8, device=device) for pre_cast, post_cast in zip(comfy.memory_management.interpret_gathered_like([s.weight, s.bias ], xfer_dest), - comfy.memory_management.interpret_gathered_like(cast_geometry, cast_dest)): + comfy.memory_management.interpret_gathered_like(prefetch["cast_geometry"], cast_dest)): if post_cast is not None: post_cast.copy_(pre_cast) xfer_dest = cast_dest - params = comfy.memory_management.interpret_gathered_like(cast_geometry, xfer_dest) + params = comfy.memory_management.interpret_gathered_like(prefetch["cast_geometry"], xfer_dest) weight = params[0] bias = params[1] - if signature is not None: + if prefetch["signature"] is not None: s._v_weight = weight s._v_bias = bias - s._v_signature=signature + s._v_signature = prefetch["signature"] def post_cast(s, param_key, x, dtype, resident, update_weight): lowvram_fn = getattr(s, param_key + "_lowvram_function", None) fns = getattr(s, param_key + "_function", []) + if x is None: + return None + orig = x def to_dequant(tensor, dtype): @@ -197,14 +248,12 @@ def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compu x = f(x) return x - update_weight = signature is not None + update_weight = prefetch["signature"] is not None + weight = post_cast(s, "weight", weight, dtype, prefetch["resident"], update_weight) + if bias is not None: + bias = post_cast(s, "bias", bias, bias_dtype, prefetch["resident"], update_weight) - weight = post_cast(s, "weight", weight, dtype, resident, update_weight) - if s.bias is not None: - bias = post_cast(s, "bias", bias, bias_dtype, resident, update_weight) - - #FIXME: weird offload return protocol - return weight, bias, (offload_stream, device if signature is not None else None, None) + return weight, bias def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None, offloadable=False, compute_dtype=None, want_requant=False): @@ -222,10 +271,46 @@ def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None, of if device is None: device = input.device + def format_return(result, offloadable): + weight, bias, offload_stream = result + return (weight, bias, offload_stream) if offloadable else (weight, bias) + non_blocking = comfy.model_management.device_supports_non_blocking(device) if hasattr(s, "_v"): - return cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compute_dtype, want_requant) + + #vbar doesn't support CPU weights, but some custom nodes have weird paths + #that might switch the layer to the CPU and expect it to work. We have to take + #a clone conservatively as we are mmapped and some SFT files are packed misaligned + #If you are a custom node author reading this, please move your layer to the GPU + #or declare your ModelPatcher as CPU in the first place. + if comfy.model_management.is_device_cpu(device): + materialize_meta_param(s, ["weight", "bias"]) + weight = s.weight.to(dtype=dtype, copy=True) + if isinstance(weight, QuantizedTensor): + weight = weight.dequantize() + bias = s.bias.to(dtype=bias_dtype, copy=True) if s.bias is not None else None + return format_return((weight, bias, (None, None, None)), offloadable) + + prefetched = hasattr(s, "_prefetch") + offload_stream = None + offload_device = None + if not prefetched: + offload_stream = cast_modules_with_vbar([s], dtype, device, bias_dtype, non_blocking) + comfy.model_management.sync_stream(device, offload_stream) + + weight, bias = resolve_cast_module_with_vbar(s, dtype, device, bias_dtype, compute_dtype, want_requant) + + if not prefetched: + if getattr(s, "_prefetch")["signature"] is not None: + offload_device = device + for param_key in ("weight", "bias"): + lowvram_fn = getattr(s, param_key + "_lowvram_function", None) + if lowvram_fn is not None: + lowvram_fn.clear_prepared() + delattr(s, "_prefetch") + return format_return((weight, bias, (offload_stream, offload_device, None)), offloadable) + if offloadable and (device != s.weight.device or (s.bias is not None and device != s.bias.device)): @@ -272,11 +357,7 @@ def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None, of for f in s.weight_function: weight = f(weight) - if offloadable: - return weight, bias, (offload_stream, weight_a, bias_a) - else: - #Legacy function signature - return weight, bias + return format_return((weight, bias, (offload_stream, weight_a, bias_a)), offloadable) def uncast_bias_weight(s, weight, bias, offload_stream): @@ -306,6 +387,12 @@ class CastWeightBiasOp: bias_function = [] class disable_weight_init: + @staticmethod + def _zero_init_parameter(module, name): + param = getattr(module, name) + device = None if getattr(param, "is_meta", False) else param.device + setattr(module, name, torch.nn.Parameter(torch.zeros(param.shape, device=device, dtype=param.dtype), requires_grad=False)) + @staticmethod def _lazy_load_from_state_dict(module, state_dict, prefix, local_metadata, missing_keys, unexpected_keys, weight_shape, @@ -1151,7 +1238,7 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec if param is None: continue p = fn(param) - if p.is_inference(): + if (not torch.is_inference_mode_enabled()) and p.is_inference(): p = p.clone() self.register_parameter(key, torch.nn.Parameter(p, requires_grad=False)) for key, buf in self._buffers.items(): @@ -1159,6 +1246,93 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec self._buffers[key] = fn(buf) return self + class Embedding(manual_cast.Embedding): + def _load_from_state_dict(self, state_dict, prefix, local_metadata, + strict, missing_keys, unexpected_keys, error_msgs): + weight_key = f"{prefix}weight" + layer_conf = state_dict.pop(f"{prefix}comfy_quant", None) + if layer_conf is not None: + layer_conf = json.loads(layer_conf.numpy().tobytes()) + + # Only fp8 makes sense for embeddings (per-row dequant via index select). + # Block-scaled formats (NVFP4, MXFP8) can't do per-row lookup efficiently. + quant_format = layer_conf.get("format", None) if layer_conf is not None else None + if quant_format in ["float8_e4m3fn", "float8_e5m2"] and weight_key in state_dict: + self.quant_format = quant_format + qconfig = QUANT_ALGOS[quant_format] + layout_cls = get_layout_class(qconfig["comfy_tensor_layout"]) + weight = state_dict.pop(weight_key) + manually_loaded_keys = [weight_key] + + scale_key = f"{prefix}weight_scale" + scale = state_dict.pop(scale_key, None) + if scale is not None: + scale = scale.float() + manually_loaded_keys.append(scale_key) + + params = layout_cls.Params( + scale=scale if scale is not None else torch.ones((), dtype=torch.float32), + orig_dtype=MixedPrecisionOps._compute_dtype, + orig_shape=(self.num_embeddings, self.embedding_dim), + ) + self.weight = torch.nn.Parameter( + QuantizedTensor(weight.to(dtype=qconfig["storage_t"]), qconfig["comfy_tensor_layout"], params), + requires_grad=False) + + super()._load_from_state_dict(state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) + for k in manually_loaded_keys: + if k in missing_keys: + missing_keys.remove(k) + else: + if layer_conf is not None: + state_dict[f"{prefix}comfy_quant"] = torch.tensor(list(json.dumps(layer_conf).encode('utf-8')), dtype=torch.uint8) + super()._load_from_state_dict(state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) + + def state_dict(self, *args, destination=None, prefix="", **kwargs): + if destination is not None: + sd = destination + else: + sd = {} + + if not hasattr(self, 'weight') or self.weight is None: + return sd + + if isinstance(self.weight, QuantizedTensor): + sd_out = self.weight.state_dict("{}weight".format(prefix)) + for k in sd_out: + sd[k] = sd_out[k] + + quant_conf = {"format": self.quant_format} + sd["{}comfy_quant".format(prefix)] = torch.tensor(list(json.dumps(quant_conf).encode('utf-8')), dtype=torch.uint8) + else: + sd["{}weight".format(prefix)] = self.weight + return sd + + def forward_comfy_cast_weights(self, input, out_dtype=None): + weight = self.weight + + # Optimized path: lookup in fp8, dequantize only the selected rows. + if isinstance(weight, QuantizedTensor) and len(self.weight_function) == 0: + qdata, _, offload_stream = cast_bias_weight(self, device=input.device, dtype=weight.dtype, offloadable=True) + if isinstance(qdata, QuantizedTensor): + scale = qdata._params.scale + qdata = qdata._qdata + else: + scale = None + + x = torch.nn.functional.embedding( + input, qdata, self.padding_idx, self.max_norm, + self.norm_type, self.scale_grad_by_freq, self.sparse) + uncast_bias_weight(self, qdata, None, offload_stream) + target_dtype = out_dtype if out_dtype is not None else weight._params.orig_dtype + x = x.to(dtype=target_dtype) + if scale is not None and scale != 1.0: + x = x * scale.to(dtype=target_dtype) + return x + + # Fallback for non-quantized or weight_function (LoRA) case + return super().forward_comfy_cast_weights(input, out_dtype=out_dtype) + return MixedPrecisionOps def pick_operations(weight_dtype, compute_dtype, load_device=None, disable_fast_fp8=False, fp8_optimizations=False, model_config=None): diff --git a/comfy/pinned_memory.py b/comfy/pinned_memory.py index 6f142282d..6d3ba367a 100644 --- a/comfy/pinned_memory.py +++ b/comfy/pinned_memory.py @@ -2,7 +2,6 @@ import comfy.model_management import comfy.memory_management import comfy_aimdo.host_buffer import comfy_aimdo.torch -import psutil from comfy.cli_args import args @@ -12,11 +11,6 @@ def get_pin(module): def pin_memory(module): if module.pin_failed or args.disable_pinned_memory or get_pin(module) is not None: return - #FIXME: This is a RAM cache trigger event - ram_headroom = comfy.memory_management.RAM_CACHE_HEADROOM - #we split the difference and assume half the RAM cache headroom is for us - if ram_headroom > 0 and psutil.virtual_memory().available < (ram_headroom * 0.5): - comfy.memory_management.extra_ram_release(ram_headroom) size = comfy.memory_management.vram_aligned_size([ module.weight, module.bias ]) diff --git a/comfy/rmsnorm.py b/comfy/rmsnorm.py index ab7cf14fa..e54be98d6 100644 --- a/comfy/rmsnorm.py +++ b/comfy/rmsnorm.py @@ -3,6 +3,7 @@ import comfy.model_management RMSNorm = torch.nn.RMSNorm +# Note: torch's fused F.rms_norm is faster but produces slightly different output than manual implementations (rsqrt/reduction rounding). def rms_norm(x, weight=None, eps=1e-6): if weight is None: return torch.nn.functional.rms_norm(x, (x.shape[-1],), eps=eps) diff --git a/comfy/sd.py b/comfy/sd.py index 7425765a4..9fce0e7d0 100644 --- a/comfy/sd.py +++ b/comfy/sd.py @@ -12,11 +12,13 @@ from .ldm.cascade.stage_c_coder import StageC_coder from .ldm.audio.autoencoder import AudioOobleckVAE import comfy.ldm.genmo.vae.model import comfy.ldm.lightricks.vae.causal_video_autoencoder +import comfy.ldm.lightricks.vae.audio_vae import comfy.ldm.cosmos.vae import comfy.ldm.wan.vae import comfy.ldm.wan.vae2_2 import comfy.ldm.hunyuan3d.vae import comfy.ldm.ace.vae.music_dcae_pipeline +import comfy.ldm.cogvideo.vae import comfy.ldm.hunyuan_video.vae import comfy.ldm.mmaudio.vae.autoencoder import comfy.pixel_space_convert @@ -62,6 +64,8 @@ import comfy.text_encoders.anima import comfy.text_encoders.ace15 import comfy.text_encoders.longcat_image import comfy.text_encoders.qwen35 +import comfy.text_encoders.ernie +import comfy.text_encoders.gemma4 import comfy.model_patcher import comfy.lora @@ -476,7 +480,10 @@ class VAE: encoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Encoder", 'params': encoder_config}, decoder_config={'target': "comfy.ldm.modules.temporal_ae.VideoDecoder", 'params': decoder_config}) elif "taesd_decoder.1.weight" in sd: - self.latent_channels = sd["taesd_decoder.1.weight"].shape[1] + if isinstance(metadata, dict) and "tae_latent_channels" in metadata: + self.latent_channels = metadata["tae_latent_channels"] + else: + self.latent_channels = sd["taesd_decoder.1.weight"].shape[1] self.first_stage_model = comfy.taesd.taesd.TAESD(latent_channels=self.latent_channels) elif "vquantizer.codebook.weight" in sd: #VQGan: stage a of stable cascade self.first_stage_model = StageA() @@ -556,12 +563,19 @@ class VAE: old_memory_used_decode = self.memory_used_decode self.memory_used_decode = lambda shape, dtype: old_memory_used_decode(shape, dtype) * 4.0 + decoder_ch = sd['decoder.conv_in.weight'].shape[0] // ddconfig['ch_mult'][-1] + if decoder_ch != ddconfig['ch']: + decoder_ddconfig = ddconfig.copy() + decoder_ddconfig['ch'] = decoder_ch + else: + decoder_ddconfig = None + if 'post_quant_conv.weight' in sd: - self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1]) + self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1], **({"decoder_ddconfig": decoder_ddconfig} if decoder_ddconfig is not None else {})) else: self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"}, encoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Encoder", 'params': ddconfig}, - decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig}) + decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': decoder_ddconfig if decoder_ddconfig is not None else ddconfig}) elif "decoder.layers.1.layers.0.beta" in sd: config = {} param_key = None @@ -643,6 +657,17 @@ class VAE: self.memory_used_encode = lambda shape, dtype: (1400 * 9 * shape[-2] * shape[-1]) * model_management.dtype_size(dtype) self.memory_used_decode = lambda shape, dtype: (3600 * 4 * shape[-2] * shape[-1] * 16 * 16) * model_management.dtype_size(dtype) + elif "decoder.conv_in.conv.weight" in sd and "decoder.mid_block.resnets.0.norm1.norm_layer.weight" in sd: # CogVideoX VAE + self.upscale_ratio = (lambda a: max(0, a * 4 - 3), 8, 8) + self.upscale_index_formula = (4, 8, 8) + self.downscale_ratio = (lambda a: max(0, math.floor((a + 3) / 4)), 8, 8) + self.downscale_index_formula = (4, 8, 8) + self.latent_dim = 3 + self.latent_channels = sd["encoder.conv_out.conv.weight"].shape[0] // 2 + self.first_stage_model = comfy.ldm.cogvideo.vae.AutoencoderKLCogVideoX(latent_channels=self.latent_channels) + self.memory_used_decode = lambda shape, dtype: (2800 * max(2, ((shape[2] - 1) * 4) + 1) * shape[3] * shape[4] * (8 * 8)) * model_management.dtype_size(dtype) + self.memory_used_encode = lambda shape, dtype: (1400 * max(1, shape[2]) * shape[3] * shape[4]) * model_management.dtype_size(dtype) + self.working_dtypes = [torch.bfloat16, torch.float16, torch.float32] elif "decoder.conv_in.conv.weight" in sd: ddconfig = {'double_z': True, 'z_channels': 4, 'resolution': 256, 'in_channels': 3, 'out_ch': 3, 'ch': 128, 'ch_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0} ddconfig["conv3d"] = True @@ -797,6 +822,24 @@ class VAE: self.downscale_index_formula = (4, 8, 8) self.memory_used_encode = lambda shape, dtype: (700 * (max(1, (shape[-3] ** 0.66 * 0.11)) * shape[-2] * shape[-1]) * model_management.dtype_size(dtype)) self.memory_used_decode = lambda shape, dtype: (50 * (max(1, (shape[-3] ** 0.65 * 0.26)) * shape[-2] * shape[-1] * 32 * 32) * model_management.dtype_size(dtype)) + elif "vocoder.resblocks.0.convs1.0.weight" in sd or "vocoder.vocoder.resblocks.0.convs1.0.weight" in sd: # LTX Audio + sd = comfy.utils.state_dict_prefix_replace(sd, {"audio_vae.": "autoencoder."}) + self.first_stage_model = comfy.ldm.lightricks.vae.audio_vae.AudioVAE(metadata=metadata) + self.memory_used_encode = lambda shape, dtype: (shape[2] * 330) * model_management.dtype_size(dtype) + self.memory_used_decode = lambda shape, dtype: (shape[2] * shape[3] * 87000) * model_management.dtype_size(dtype) + self.latent_channels = self.first_stage_model.latent_channels + self.audio_sample_rate_output = self.first_stage_model.output_sample_rate + self.autoencoder = self.first_stage_model.autoencoder # TODO: remove hack for ltxv custom nodes + self.output_channels = 2 + self.pad_channel_value = "replicate" + self.upscale_ratio = 4096 + self.downscale_ratio = 4096 + self.latent_dim = 2 + self.process_output = lambda audio: audio + self.process_input = lambda audio: audio + self.working_dtypes = [torch.float32] + self.disable_offload = True + self.extra_1d_channel = 16 else: logging.warning("WARNING: No VAE weights detected, VAE not initalized.") self.first_stage_model = None @@ -1228,6 +1271,10 @@ class TEModel(Enum): QWEN35_4B = 25 QWEN35_9B = 26 QWEN35_27B = 27 + MINISTRAL_3_3B = 28 + GEMMA_4_E4B = 29 + GEMMA_4_E2B = 30 + GEMMA_4_31B = 31 def detect_te_model(sd): @@ -1253,6 +1300,12 @@ def detect_te_model(sd): return TEModel.BYT5_SMALL_GLYPH return TEModel.T5_BASE if 'model.layers.0.post_feedforward_layernorm.weight' in sd: + if 'model.layers.59.self_attn.q_norm.weight' in sd: + return TEModel.GEMMA_4_31B + if 'model.layers.41.self_attn.q_norm.weight' in sd and 'model.layers.47.self_attn.q_norm.weight' not in sd: + return TEModel.GEMMA_4_E4B + if 'model.layers.34.self_attn.q_norm.weight' in sd and 'model.layers.41.self_attn.q_norm.weight' not in sd: + return TEModel.GEMMA_4_E2B if 'model.layers.47.self_attn.q_norm.weight' in sd: return TEModel.GEMMA_3_12B if 'model.layers.0.self_attn.q_norm.weight' in sd: @@ -1294,6 +1347,8 @@ def detect_te_model(sd): return TEModel.MISTRAL3_24B else: return TEModel.MISTRAL3_24B_PRUNED_FLUX2 + if weight.shape[0] == 3072: + return TEModel.MINISTRAL_3_3B return TEModel.LLAMA3_8 return None @@ -1390,6 +1445,13 @@ def load_text_encoder_state_dicts(state_dicts=[], embedding_directory=None, clip else: clip_target.clip = comfy.text_encoders.sa_t5.SAT5Model clip_target.tokenizer = comfy.text_encoders.sa_t5.SAT5Tokenizer + elif te_model in (TEModel.GEMMA_4_E4B, TEModel.GEMMA_4_E2B, TEModel.GEMMA_4_31B): + variant = {TEModel.GEMMA_4_E4B: comfy.text_encoders.gemma4.Gemma4_E4B, + TEModel.GEMMA_4_E2B: comfy.text_encoders.gemma4.Gemma4_E2B, + TEModel.GEMMA_4_31B: comfy.text_encoders.gemma4.Gemma4_31B}[te_model] + clip_target.clip = comfy.text_encoders.gemma4.gemma4_te(**llama_detect(clip_data), model_class=variant) + clip_target.tokenizer = variant.tokenizer + tokenizer_data["tokenizer_json"] = clip_data[0].get("tokenizer_json", None) elif te_model == TEModel.GEMMA_2_2B: clip_target.clip = comfy.text_encoders.lumina2.te(**llama_detect(clip_data)) clip_target.tokenizer = comfy.text_encoders.lumina2.LuminaTokenizer @@ -1451,6 +1513,10 @@ def load_text_encoder_state_dicts(state_dicts=[], embedding_directory=None, clip elif te_model == TEModel.QWEN3_06B: clip_target.clip = comfy.text_encoders.anima.te(**llama_detect(clip_data)) clip_target.tokenizer = comfy.text_encoders.anima.AnimaTokenizer + elif te_model == TEModel.MINISTRAL_3_3B: + clip_target.clip = comfy.text_encoders.ernie.te(**llama_detect(clip_data)) + clip_target.tokenizer = comfy.text_encoders.ernie.ErnieTokenizer + tokenizer_data["tekken_model"] = clip_data[0].get("tekken_model", None) else: # clip_l if clip_type == CLIPType.SD3: @@ -1745,6 +1811,8 @@ def load_diffusion_model_state_dict(sd, model_options={}, metadata=None, disable temp_sd = comfy.utils.state_dict_prefix_replace(sd, {diffusion_model_prefix: ""}, filter_keys=True) if len(temp_sd) > 0: sd = temp_sd + if custom_operations is None: + sd, metadata = comfy.utils.convert_old_quants(sd, "", metadata=metadata) parameters = comfy.utils.calculate_parameters(sd) weight_dtype = comfy.utils.weight_dtype(sd) diff --git a/comfy/supported_models.py b/comfy/supported_models.py index 9a5612716..e6c17fb98 100644 --- a/comfy/supported_models.py +++ b/comfy/supported_models.py @@ -26,6 +26,8 @@ import comfy.text_encoders.z_image import comfy.text_encoders.anima import comfy.text_encoders.ace15 import comfy.text_encoders.longcat_image +import comfy.text_encoders.ernie +import comfy.text_encoders.cogvideo from . import supported_models_base from . import latent_formats @@ -1749,6 +1751,214 @@ class RT_DETR_v4(supported_models_base.BASE): def clip_target(self, state_dict={}): return None -models = [LotusD, Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD3, StableAudio, AuraFlow, PixArtAlpha, PixArtSigma, HunyuanDiT, HunyuanDiT1, FluxInpaint, Flux, LongCatImage, FluxSchnell, GenmoMochi, LTXV, LTXAV, HunyuanVideo15_SR_Distilled, HunyuanVideo15, HunyuanImage21Refiner, HunyuanImage21, HunyuanVideoSkyreelsI2V, HunyuanVideoI2V, HunyuanVideo, CosmosT2V, CosmosI2V, CosmosT2IPredict2, CosmosI2VPredict2, ZImagePixelSpace, ZImage, Lumina2, WAN22_T2V, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, WAN21_Camera, WAN22_Camera, WAN22_S2V, WAN21_HuMo, WAN22_Animate, WAN21_FlowRVS, WAN21_SCAIL, Hunyuan3Dv2mini, Hunyuan3Dv2, Hunyuan3Dv2_1, HiDream, Chroma, ChromaRadiance, ACEStep, ACEStep15, Omnigen2, QwenImage, Flux2, Kandinsky5Image, Kandinsky5, Anima, RT_DETR_v4] -models += [SVD_img2vid] +class ErnieImage(supported_models_base.BASE): + unet_config = { + "image_model": "ernie", + } + + sampling_settings = { + "multiplier": 1000.0, + "shift": 3.0, + } + + memory_usage_factor = 10.0 + + unet_extra_config = {} + latent_format = latent_formats.Flux2 + + supported_inference_dtypes = [torch.bfloat16, torch.float32] + + vae_key_prefix = ["vae."] + text_encoder_key_prefix = ["text_encoders."] + + def get_model(self, state_dict, prefix="", device=None): + out = model_base.ErnieImage(self, device=device) + return out + + def clip_target(self, state_dict={}): + pref = self.text_encoder_key_prefix[0] + hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}ministral3_3b.transformer.".format(pref)) + return supported_models_base.ClipTarget(comfy.text_encoders.ernie.ErnieTokenizer, comfy.text_encoders.ernie.te(**hunyuan_detect)) + + +class SAM3(supported_models_base.BASE): + unet_config = {"image_model": "SAM3"} + supported_inference_dtypes = [torch.float16, torch.bfloat16, torch.float32] + text_encoder_key_prefix = ["detector.backbone.language_backbone."] + unet_extra_prefix = "" + + def process_clip_state_dict(self, state_dict): + clip_keys = getattr(self, "_clip_stash", {}) + clip_keys = utils.state_dict_prefix_replace(clip_keys, {"detector.backbone.language_backbone.": "", "backbone.language_backbone.": ""}, filter_keys=True) + clip_keys = utils.clip_text_transformers_convert(clip_keys, "encoder.", "sam3_clip.transformer.") + return {k: v for k, v in clip_keys.items() if not k.startswith("resizer.")} + + def process_unet_state_dict(self, state_dict): + self._clip_stash = {k: state_dict.pop(k) for k in list(state_dict.keys()) if "language_backbone" in k and "resizer" not in k} + # SAM3.1: remap tracker.model.* -> tracker.* + for k in list(state_dict.keys()): + if k.startswith("tracker.model."): + state_dict["tracker." + k[len("tracker.model."):]] = state_dict.pop(k) + # SAM3.1: remove per-block freqs_cis buffers (computed dynamically) + for k in [k for k in list(state_dict.keys()) if ".attn.freqs_cis" in k]: + state_dict.pop(k) + # Split fused QKV projections + for k in [k for k in list(state_dict.keys()) if k.endswith((".in_proj_weight", ".in_proj_bias"))]: + t = state_dict.pop(k) + base, suffix = k.rsplit(".in_proj_", 1) + s = ".weight" if suffix == "weight" else ".bias" + d = t.shape[0] // 3 + state_dict[base + ".q_proj" + s] = t[:d] + state_dict[base + ".k_proj" + s] = t[d:2*d] + state_dict[base + ".v_proj" + s] = t[2*d:] + # Remap tracker SAM decoder transformer key names to match sam.py TwoWayTransformer + for k in list(state_dict.keys()): + if "sam_mask_decoder.transformer." not in k: + continue + new_k = k.replace(".mlp.lin1.", ".mlp.0.").replace(".mlp.lin2.", ".mlp.2.").replace(".norm_final_attn.", ".norm_final.") + if new_k != k: + state_dict[new_k] = state_dict.pop(k) + return state_dict + + def get_model(self, state_dict, prefix="", device=None): + return model_base.SAM3(self, device=device) + + def clip_target(self, state_dict={}): + import comfy.text_encoders.sam3_clip + return supported_models_base.ClipTarget(comfy.text_encoders.sam3_clip.SAM3TokenizerWrapper, comfy.text_encoders.sam3_clip.SAM3ClipModelWrapper) + + +class SAM31(SAM3): + unet_config = {"image_model": "SAM31"} + + +class CogVideoX_T2V(supported_models_base.BASE): + unet_config = { + "image_model": "cogvideox", + } + + sampling_settings = { + "linear_start": 0.00085, + "linear_end": 0.012, + "beta_schedule": "linear", + "zsnr": True, + } + + unet_extra_config = {} + latent_format = latent_formats.CogVideoX + + supported_inference_dtypes = [torch.bfloat16, torch.float16, torch.float32] + + vae_key_prefix = ["vae."] + text_encoder_key_prefix = ["text_encoders."] + + def get_model(self, state_dict, prefix="", device=None): + # CogVideoX 1.5 (patch_size_t=2) has different training base dimensions for RoPE + if self.unet_config.get("patch_size_t") is not None: + self.unet_config.setdefault("sample_height", 96) + self.unet_config.setdefault("sample_width", 170) + self.unet_config.setdefault("sample_frames", 81) + out = model_base.CogVideoX(self, device=device) + return out + + def clip_target(self, state_dict={}): + return supported_models_base.ClipTarget(comfy.text_encoders.cogvideo.CogVideoXT5Tokenizer, comfy.text_encoders.sd3_clip.T5XXLModel) + +class CogVideoX_I2V(CogVideoX_T2V): + unet_config = { + "image_model": "cogvideox", + "in_channels": 32, + } + + def get_model(self, state_dict, prefix="", device=None): + if self.unet_config.get("patch_size_t") is not None: + self.unet_config.setdefault("sample_height", 96) + self.unet_config.setdefault("sample_width", 170) + self.unet_config.setdefault("sample_frames", 81) + out = model_base.CogVideoX(self, image_to_video=True, device=device) + return out + + +models = [ + LotusD, + Stable_Zero123, + SD15_instructpix2pix, + SD15, + SD20, + SD21UnclipL, + SD21UnclipH, + SDXL_instructpix2pix, + SDXLRefiner, + SDXL, + SSD1B, + KOALA_700M, + KOALA_1B, + Segmind_Vega, + SD_X4Upscaler, + Stable_Cascade_C, + Stable_Cascade_B, + SV3D_u, + SV3D_p, + SD3, + StableAudio, + AuraFlow, + PixArtAlpha, + PixArtSigma, + HunyuanDiT, + HunyuanDiT1, + FluxInpaint, + Flux, + LongCatImage, + FluxSchnell, + GenmoMochi, + LTXV, + LTXAV, + HunyuanVideo15_SR_Distilled, + HunyuanVideo15, + HunyuanImage21Refiner, + HunyuanImage21, + HunyuanVideoSkyreelsI2V, + HunyuanVideoI2V, + HunyuanVideo, + CosmosT2V, + CosmosI2V, + CosmosT2IPredict2, + CosmosI2VPredict2, + ZImagePixelSpace, + ZImage, + Lumina2, + WAN22_T2V, + WAN21_T2V, + WAN21_I2V, + WAN21_FunControl2V, + WAN21_Vace, + WAN21_Camera, + WAN22_Camera, + WAN22_S2V, + WAN21_HuMo, + WAN22_Animate, + WAN21_FlowRVS, + WAN21_SCAIL, + Hunyuan3Dv2mini, + Hunyuan3Dv2, + Hunyuan3Dv2_1, + HiDream, + Chroma, + ChromaRadiance, + ACEStep, + ACEStep15, + Omnigen2, + QwenImage, + Flux2, + Kandinsky5Image, + Kandinsky5, + Anima, + RT_DETR_v4, + ErnieImage, + SAM3, + SAM31, + CogVideoX_I2V, + CogVideoX_T2V, + SVD_img2vid, +] diff --git a/comfy/taesd/taehv.py b/comfy/taesd/taehv.py index 6c06ce19d..696013200 100644 --- a/comfy/taesd/taehv.py +++ b/comfy/taesd/taehv.py @@ -7,6 +7,7 @@ from tqdm.auto import tqdm from collections import namedtuple, deque import comfy.ops +import comfy.model_management operations=comfy.ops.disable_weight_init DecoderResult = namedtuple("DecoderResult", ("frame", "memory")) @@ -47,11 +48,14 @@ class TGrow(nn.Module): x = self.conv(x) return x.reshape(-1, C, H, W) -def apply_model_with_memblocks(model, x, parallel, show_progress_bar): +def apply_model_with_memblocks(model, x, parallel, show_progress_bar, output_device=None, + patch_size=1, decode=False): B, T, C, H, W = x.shape if parallel: x = x.reshape(B*T, C, H, W) + if not decode and patch_size > 1: + x = F.pixel_unshuffle(x, patch_size) # parallel over input timesteps, iterate over blocks for b in tqdm(model, disable=not show_progress_bar): if isinstance(b, MemBlock): @@ -62,20 +66,27 @@ def apply_model_with_memblocks(model, x, parallel, show_progress_bar): x = b(x, mem) else: x = b(x) - BT, C, H, W = x.shape - T = BT // B - x = x.view(B, T, C, H, W) + if decode and patch_size > 1: + x = F.pixel_shuffle(x, patch_size) + x = x.view(B, x.shape[0] // B, *x.shape[1:]) + x = x.to(output_device) else: out = [] - work_queue = deque([TWorkItem(xt, 0) for t, xt in enumerate(x.reshape(B, T * C, H, W).chunk(T, dim=1))]) + # Chunk along the time dim directly (chunks are [B,1,C,H,W] views, squeeze to [B,C,H,W] views). + # Avoids forcing a contiguous copy when x is non-contiguous (e.g. after movedim in encode/decode). + work_queue = deque([TWorkItem(xt.squeeze(1), 0) for xt in x.chunk(T, dim=1)]) progress_bar = tqdm(range(T), disable=not show_progress_bar) mem = [None] * len(model) while work_queue: xt, i = work_queue.popleft() if i == 0: progress_bar.update(1) + if not decode and patch_size > 1: + xt = F.pixel_unshuffle(xt, patch_size) if i == len(model): - out.append(xt) + if decode and patch_size > 1: + xt = F.pixel_shuffle(xt, patch_size) + out.append(xt.to(output_device)) del xt else: b = model[i] @@ -165,24 +176,20 @@ class TAEHV(nn.Module): def encode(self, x, **kwargs): x = x.movedim(2, 1) # [B, C, T, H, W] -> [B, T, C, H, W] - if self.patch_size > 1: - B, T, C, H, W = x.shape - x = x.reshape(B * T, C, H, W) - x = F.pixel_unshuffle(x, self.patch_size) - x = x.reshape(B, T, C * self.patch_size ** 2, H // self.patch_size, W // self.patch_size) if x.shape[1] % self.t_downscale != 0: # pad at end to multiple of t_downscale n_pad = self.t_downscale - x.shape[1] % self.t_downscale padding = x[:, -1:].repeat_interleave(n_pad, dim=1) x = torch.cat([x, padding], 1) - x = apply_model_with_memblocks(self.encoder, x, self.parallel, self.show_progress_bar).movedim(2, 1) + x = apply_model_with_memblocks(self.encoder, x, self.parallel, self.show_progress_bar, + patch_size=self.patch_size).movedim(2, 1) return self.process_out(x) def decode(self, x, **kwargs): x = x.unsqueeze(0) if x.ndim == 4 else x # [T, C, H, W] -> [1, T, C, H, W] x = x.movedim(1, 2) if x.shape[1] != self.latent_channels else x # [B, T, C, H, W] or [B, C, T, H, W] x = self.process_in(x).movedim(2, 1) # [B, C, T, H, W] -> [B, T, C, H, W] - x = apply_model_with_memblocks(self.decoder, x, self.parallel, self.show_progress_bar) - if self.patch_size > 1: - x = F.pixel_shuffle(x, self.patch_size) + x = apply_model_with_memblocks(self.decoder, x, self.parallel, self.show_progress_bar, + output_device=comfy.model_management.intermediate_device(), + patch_size=self.patch_size, decode=True) return x[:, self.frames_to_trim:].movedim(2, 1) diff --git a/comfy/taesd/taesd.py b/comfy/taesd/taesd.py index ce36f1a84..05d370209 100644 --- a/comfy/taesd/taesd.py +++ b/comfy/taesd/taesd.py @@ -17,32 +17,79 @@ class Clamp(nn.Module): return torch.tanh(x / 3) * 3 class Block(nn.Module): - def __init__(self, n_in, n_out): + def __init__(self, n_in: int, n_out: int, use_midblock_gn: bool = False): super().__init__() self.conv = nn.Sequential(conv(n_in, n_out), nn.ReLU(), conv(n_out, n_out), nn.ReLU(), conv(n_out, n_out)) self.skip = comfy.ops.disable_weight_init.Conv2d(n_in, n_out, 1, bias=False) if n_in != n_out else nn.Identity() self.fuse = nn.ReLU() - def forward(self, x): + if not use_midblock_gn: + self.pool = None + return + n_gn = n_in * 4 + self.pool = nn.Sequential( + comfy.ops.disable_weight_init.Conv2d(n_in, n_gn, 1, bias=False), + comfy.ops.disable_weight_init.GroupNorm(4, n_gn), + nn.ReLU(inplace=True), + comfy.ops.disable_weight_init.Conv2d(n_gn, n_in, 1, bias=False), + ) + + def forward(self, x: torch.Tensor) -> torch.Tensor: + if self.pool is not None: + x = x + self.pool(x) return self.fuse(self.conv(x) + self.skip(x)) -def Encoder(latent_channels=4): - return nn.Sequential( - conv(3, 64), Block(64, 64), - conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), - conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), - conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), - conv(64, latent_channels), - ) +class Encoder(nn.Sequential): + def __init__(self, latent_channels: int = 4, use_gn: bool = False): + super().__init__( + conv(3, 64), Block(64, 64), + conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), + conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), + conv(64, 64, stride=2, bias=False), Block(64, 64, use_gn), Block(64, 64, use_gn), Block(64, 64, use_gn), + conv(64, latent_channels), + ) +class Decoder(nn.Sequential): + def __init__(self, latent_channels: int = 4, use_gn: bool = False): + super().__init__( + Clamp(), conv(latent_channels, 64), nn.ReLU(), + Block(64, 64, use_gn), Block(64, 64, use_gn), Block(64, 64, use_gn), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), + Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), + Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), + Block(64, 64), conv(64, 3), + ) + +class DecoderFlux2(Decoder): + def __init__(self, latent_channels: int = 128, use_gn: bool = True): + if latent_channels != 128 or not use_gn: + raise ValueError("Unexpected parameters for Flux2 TAE module") + super().__init__(latent_channels=32, use_gn=True) + + def forward(self, x: torch.Tensor) -> torch.Tensor: + B, C, H, W = x.shape + x = ( + x + .reshape(B, 32, 2, 2, H, W) + .permute(0, 1, 4, 2, 5, 3) + .reshape(B, 32, H * 2, W * 2) + ) + return super().forward(x) + +class EncoderFlux2(Encoder): + def __init__(self, latent_channels: int = 128, use_gn: bool = True): + if latent_channels != 128 or not use_gn: + raise ValueError("Unexpected parameters for Flux2 TAE module") + super().__init__(latent_channels=32, use_gn=True) + + def forward(self, x: torch.Tensor) -> torch.Tensor: + result = super().forward(x) + B, C, H, W = result.shape + return ( + result + .reshape(B, C, H // 2, 2, W // 2, 2) + .permute(0, 1, 3, 5, 2, 4) + .reshape(B, 128, H // 2, W // 2) + ) -def Decoder(latent_channels=4): - return nn.Sequential( - Clamp(), conv(latent_channels, 64), nn.ReLU(), - Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), - Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), - Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), - Block(64, 64), conv(64, 3), - ) class TAESD(nn.Module): latent_magnitude = 3 @@ -51,8 +98,15 @@ class TAESD(nn.Module): def __init__(self, encoder_path=None, decoder_path=None, latent_channels=4): """Initialize pretrained TAESD on the given device from the given checkpoints.""" super().__init__() - self.taesd_encoder = Encoder(latent_channels=latent_channels) - self.taesd_decoder = Decoder(latent_channels=latent_channels) + if latent_channels == 128: + encoder_class = EncoderFlux2 + decoder_class = DecoderFlux2 + else: + encoder_class = Encoder + decoder_class = Decoder + self.taesd_encoder = encoder_class(latent_channels=latent_channels) + self.taesd_decoder = decoder_class(latent_channels=latent_channels) + self.vae_scale = torch.nn.Parameter(torch.tensor(1.0)) self.vae_shift = torch.nn.Parameter(torch.tensor(0.0)) if encoder_path is not None: @@ -61,19 +115,19 @@ class TAESD(nn.Module): self.taesd_decoder.load_state_dict(comfy.utils.load_torch_file(decoder_path, safe_load=True)) @staticmethod - def scale_latents(x): + def scale_latents(x: torch.Tensor) -> torch.Tensor: """raw latents -> [0, 1]""" return x.div(2 * TAESD.latent_magnitude).add(TAESD.latent_shift).clamp(0, 1) @staticmethod - def unscale_latents(x): + def unscale_latents(x: torch.Tensor) -> torch.Tensor: """[0, 1] -> raw latents""" return x.sub(TAESD.latent_shift).mul(2 * TAESD.latent_magnitude) - def decode(self, x): + def decode(self, x: torch.Tensor) -> torch.Tensor: x_sample = self.taesd_decoder((x - self.vae_shift) * self.vae_scale) x_sample = x_sample.sub(0.5).mul(2) return x_sample - def encode(self, x): + def encode(self, x: torch.Tensor) -> torch.Tensor: return (self.taesd_encoder(x * 0.5 + 0.5) / self.vae_scale) + self.vae_shift diff --git a/comfy/text_encoders/cogvideo.py b/comfy/text_encoders/cogvideo.py new file mode 100644 index 000000000..f1e8e3f5d --- /dev/null +++ b/comfy/text_encoders/cogvideo.py @@ -0,0 +1,6 @@ +import comfy.text_encoders.sd3_clip + + +class CogVideoXT5Tokenizer(comfy.text_encoders.sd3_clip.T5XXLTokenizer): + def __init__(self, embedding_directory=None, tokenizer_data={}): + super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, min_length=226) diff --git a/comfy/text_encoders/ernie.py b/comfy/text_encoders/ernie.py new file mode 100644 index 000000000..46d24d222 --- /dev/null +++ b/comfy/text_encoders/ernie.py @@ -0,0 +1,38 @@ +from .flux import Mistral3Tokenizer +from comfy import sd1_clip +import comfy.text_encoders.llama + +class Ministral3_3BTokenizer(Mistral3Tokenizer): + def __init__(self, embedding_directory=None, embedding_size=5120, embedding_key='ministral3_3b', tokenizer_data={}): + return super().__init__(embedding_directory=embedding_directory, embedding_size=embedding_size, embedding_key=embedding_key, tokenizer_data=tokenizer_data) + +class ErnieTokenizer(sd1_clip.SD1Tokenizer): + def __init__(self, embedding_directory=None, tokenizer_data={}): + super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, name="ministral3_3b", tokenizer=Mistral3Tokenizer) + + def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, **kwargs): + tokens = super().tokenize_with_weights(text, return_word_ids=return_word_ids, disable_weights=True, **kwargs) + return tokens + + +class Ministral3_3BModel(sd1_clip.SDClipModel): + def __init__(self, device="cpu", layer="hidden", layer_idx=-2, dtype=None, attention_mask=True, model_options={}): + textmodel_json_config = {} + super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"start": 1, "pad": 0}, layer_norm_hidden_state=False, model_class=comfy.text_encoders.llama.Ministral3_3B, enable_attention_masks=attention_mask, return_attention_masks=attention_mask, model_options=model_options) + + +class ErnieTEModel(sd1_clip.SD1ClipModel): + def __init__(self, device="cpu", dtype=None, model_options={}, name="ministral3_3b", clip_model=Ministral3_3BModel): + super().__init__(device=device, dtype=dtype, name=name, clip_model=clip_model, model_options=model_options) + + +def te(dtype_llama=None, llama_quantization_metadata=None): + class ErnieTEModel_(ErnieTEModel): + def __init__(self, device="cpu", dtype=None, model_options={}): + if dtype_llama is not None: + dtype = dtype_llama + if llama_quantization_metadata is not None: + model_options = model_options.copy() + model_options["quantization_metadata"] = llama_quantization_metadata + super().__init__(device=device, dtype=dtype, model_options=model_options) + return ErnieTEModel_ diff --git a/comfy/text_encoders/flux.py b/comfy/text_encoders/flux.py index 1ae398789..d5eb91dcb 100644 --- a/comfy/text_encoders/flux.py +++ b/comfy/text_encoders/flux.py @@ -116,9 +116,9 @@ class MistralTokenizerClass: return LlamaTokenizerFast(**kwargs) class Mistral3Tokenizer(sd1_clip.SDTokenizer): - def __init__(self, embedding_directory=None, tokenizer_data={}): + def __init__(self, embedding_directory=None, embedding_size=5120, embedding_key='mistral3_24b', tokenizer_data={}): self.tekken_data = tokenizer_data.get("tekken_model", None) - super().__init__("", pad_with_end=False, embedding_directory=embedding_directory, embedding_size=5120, embedding_key='mistral3_24b', tokenizer_class=MistralTokenizerClass, has_end_token=False, pad_to_max_length=False, pad_token=11, start_token=1, max_length=99999999, min_length=1, pad_left=True, tokenizer_args=load_mistral_tokenizer(self.tekken_data), tokenizer_data=tokenizer_data) + super().__init__("", pad_with_end=False, embedding_directory=embedding_directory, embedding_size=embedding_size, embedding_key=embedding_key, tokenizer_class=MistralTokenizerClass, has_end_token=False, pad_to_max_length=False, pad_token=11, start_token=1, max_length=99999999, min_length=1, pad_left=True, disable_weights=True, tokenizer_args=load_mistral_tokenizer(self.tekken_data), tokenizer_data=tokenizer_data) def state_dict(self): return {"tekken_model": self.tekken_data} diff --git a/comfy/text_encoders/gemma4.py b/comfy/text_encoders/gemma4.py new file mode 100644 index 000000000..f050061ed --- /dev/null +++ b/comfy/text_encoders/gemma4.py @@ -0,0 +1,1298 @@ +import torch +import torch.nn as nn +import numpy as np +from dataclasses import dataclass +import math + +from comfy import sd1_clip +import comfy.model_management +from comfy.ldm.modules.attention import optimized_attention_for_device +from comfy.rmsnorm import rms_norm +from comfy.text_encoders.llama import RMSNorm, MLP, BaseLlama, BaseGenerate, _make_scaled_embedding + + +# Intentional minor divergences from transformers -reference implementation: +# - Embedding sqrt(hidden_size) scale applied as a Python scalar (full precision) instead of dtype-matched buffer tensor. +# - RMSNorm uses torch fused F.rms_norm, very slight numerical differences, but considerably faster +# - Input image and audio resizing/resampling slightly different numerically + + +GEMMA4_VISION_CONFIG = {"hidden_size": 768, "image_size": 896, "intermediate_size": 3072, "num_attention_heads": 12, "num_hidden_layers": 16, "patch_size": 16, "head_dim": 64, "rms_norm_eps": 1e-6, "position_embedding_size": 10240, "pooling_kernel_size": 3} +GEMMA4_VISION_31B_CONFIG = {"hidden_size": 1152, "image_size": 896, "intermediate_size": 4304, "num_attention_heads": 16, "num_hidden_layers": 27, "patch_size": 16, "head_dim": 72, "rms_norm_eps": 1e-6, "position_embedding_size": 10240, "pooling_kernel_size": 3} +GEMMA4_AUDIO_CONFIG = {"hidden_size": 1024, "num_hidden_layers": 12, "num_attention_heads": 8, "intermediate_size": 4096, "conv_kernel_size": 5, "attention_chunk_size": 12, "attention_context_left": 13, "attention_context_right": 0, "attention_logit_cap": 50.0, "output_proj_dims": 1536, "rms_norm_eps": 1e-6, "residual_weight": 0.5} + +@dataclass +class Gemma4Config: + vocab_size: int = 262144 + hidden_size: int = 2560 + intermediate_size: int = 10240 + num_hidden_layers: int = 42 + num_attention_heads: int = 8 + num_key_value_heads: int = 2 + max_position_embeddings: int = 131072 + rms_norm_eps: float = 1e-6 + rope_theta = [1000000.0, 10000.0] + transformer_type: str = "gemma4" + head_dim = 256 + global_head_dim = 512 + rms_norm_add = False + mlp_activation = "gelu_pytorch_tanh" + qkv_bias = False + rope_dims = None + q_norm = "gemma3" + k_norm = "gemma3" + sliding_attention = [512, 512, 512, 512, 512, False] + rope_scale = None + partial_rotary_factor: float = 0.25 + final_norm: bool = True + lm_head: bool = False + final_logit_softcapping: float = 30.0 + hidden_size_per_layer_input: int = 256 + num_kv_shared_layers: int = 18 + use_double_wide_mlp: bool = False + stop_tokens = [1, 50, 106] + vision_config = GEMMA4_VISION_CONFIG + audio_config = GEMMA4_AUDIO_CONFIG + mm_tokens_per_image = 280 + +@dataclass +class Gemma4_E2B_Config(Gemma4Config): + hidden_size: int = 1536 + intermediate_size: int = 6144 + num_hidden_layers: int = 35 + num_key_value_heads: int = 1 + sliding_attention = [512, 512, 512, 512, False] + num_kv_shared_layers: int = 20 + use_double_wide_mlp: bool = True + +@dataclass +class Gemma4_31B_Config(Gemma4Config): + hidden_size: int = 5376 + intermediate_size: int = 21504 + num_hidden_layers: int = 60 + num_attention_heads: int = 32 + num_key_value_heads: int = 16 + sliding_attention = [1024, 1024, 1024, 1024, 1024, False] + hidden_size_per_layer_input: int = 0 + num_kv_shared_layers: int = 0 + audio_config = None + vision_config = GEMMA4_VISION_31B_CONFIG + + +# unfused RoPE as addcmul_ RoPE diverges from reference code +def _apply_rotary_pos_emb(x, freqs_cis): + cos, sin = freqs_cis[0], freqs_cis[1] + half = x.shape[-1] // 2 + out = x * cos + out[..., :half] -= x[..., half:] * sin[..., :half] + out[..., half:] += x[..., :half] * sin[..., half:] + return out + +class Gemma4Attention(nn.Module): + def __init__(self, config, head_dim, device=None, dtype=None, ops=None): + super().__init__() + self.num_heads = config.num_attention_heads + self.num_kv_heads = config.num_key_value_heads + self.hidden_size = config.hidden_size + self.head_dim = head_dim + self.inner_size = self.num_heads * head_dim + + self.q_proj = ops.Linear(config.hidden_size, self.inner_size, bias=config.qkv_bias, device=device, dtype=dtype) + self.k_proj = ops.Linear(config.hidden_size, self.num_kv_heads * head_dim, bias=config.qkv_bias, device=device, dtype=dtype) + self.v_proj = ops.Linear(config.hidden_size, self.num_kv_heads * head_dim, bias=config.qkv_bias, device=device, dtype=dtype) + self.o_proj = ops.Linear(self.inner_size, config.hidden_size, bias=False, device=device, dtype=dtype) + + self.q_norm = None + self.k_norm = None + if config.q_norm == "gemma3": + self.q_norm = RMSNorm(head_dim, eps=config.rms_norm_eps, device=device, dtype=dtype) + if config.k_norm == "gemma3": + self.k_norm = RMSNorm(head_dim, eps=config.rms_norm_eps, device=device, dtype=dtype) + + def forward( + self, + hidden_states: torch.Tensor, + attention_mask=None, + freqs_cis=None, + past_key_value=None, + sliding_window=None, + shared_kv=None, + ): + batch_size, seq_length, _ = hidden_states.shape + + xq = self.q_proj(hidden_states) + xq = xq.view(batch_size, seq_length, self.num_heads, self.head_dim).transpose(1, 2) + if self.q_norm is not None: + xq = self.q_norm(xq) + + if shared_kv is not None: + xk, xv = shared_kv + # Apply RoPE to Q only (K already has RoPE from source layer) + xq = _apply_rotary_pos_emb(xq, freqs_cis) + present_key_value = None + shareable_kv = None + else: + xk = self.k_proj(hidden_states).view(batch_size, seq_length, self.num_kv_heads, self.head_dim) + xv = self.v_proj(hidden_states).view(batch_size, seq_length, self.num_kv_heads, self.head_dim) + if self.k_norm is not None: + xk = self.k_norm(xk) + xv = rms_norm(xv) + xk = xk.transpose(1, 2) + xv = xv.transpose(1, 2) + xq = _apply_rotary_pos_emb(xq, freqs_cis) + xk = _apply_rotary_pos_emb(xk, freqs_cis) + + present_key_value = None + if past_key_value is not None: + cumulative_len = 0 + if len(past_key_value) > 0: + past_key, past_value, cumulative_len = past_key_value + xk = torch.cat((past_key, xk), dim=2) + xv = torch.cat((past_value, xv), dim=2) + new_cumulative = cumulative_len + seq_length + if sliding_window is not None and xk.shape[2] > sliding_window - 1: + cache_k = xk[:, :, -(sliding_window - 1):] + cache_v = xv[:, :, -(sliding_window - 1):] + else: + cache_k = xk + cache_v = xv + present_key_value = (cache_k, cache_v, new_cumulative) + + # KV for sharing: full xk/xv that SDPA sees (not evicted cache) + shareable_kv = (xk, xv) + + # GQA: pass unexpanded KV with enable_gqa when no sliding mask, + # expand heads when sliding mask is present + # has to be done within SDPA itself to match the reference code, pre-scaling expansion causes numerical differences + expand_kv = (self.num_heads != self.num_kv_heads and + sliding_window is not None and + xk.shape[2] >= sliding_window) + if expand_kv: + xk = xk.repeat_interleave(self.num_heads // self.num_kv_heads, dim=1) + xv = xv.repeat_interleave(self.num_heads // self.num_kv_heads, dim=1) + gqa_kwargs = {} if expand_kv else ({"enable_gqa": True} if self.num_heads != self.num_kv_heads else {}) + output = optimized_attention_for_device(xq.device, mask=attention_mask is not None, small_input=True)(xq, xk, xv, self.num_heads, mask=attention_mask, skip_reshape=True, scale=1.0, **gqa_kwargs) + + return self.o_proj(output), present_key_value, shareable_kv + + +class TransformerBlockGemma4(nn.Module): + def __init__(self, config, index, device=None, dtype=None, ops=None): + super().__init__() + if config.sliding_attention is not None: + self.sliding_attention = config.sliding_attention[index % len(config.sliding_attention)] + else: + self.sliding_attention = False + + head_dim = config.head_dim if self.sliding_attention else config.global_head_dim + + self.self_attn = Gemma4Attention(config, head_dim=head_dim, device=device, dtype=dtype, ops=ops) + + num_kv_shared = config.num_kv_shared_layers + first_kv_shared = config.num_hidden_layers - num_kv_shared + mlp_size = config.intermediate_size * 2 if config.use_double_wide_mlp and index >= first_kv_shared else None + self.mlp = MLP(config, device=device, dtype=dtype, ops=ops, intermediate_size=mlp_size) + + self.input_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps, device=device, dtype=dtype) + self.post_attention_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps, device=device, dtype=dtype) + self.pre_feedforward_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps, device=device, dtype=dtype) + self.post_feedforward_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps, device=device, dtype=dtype) + + self.hidden_size_per_layer_input = config.hidden_size_per_layer_input + if self.hidden_size_per_layer_input: + self.per_layer_input_gate = ops.Linear(config.hidden_size, self.hidden_size_per_layer_input, bias=False, device=device, dtype=dtype) + self.per_layer_projection = ops.Linear(self.hidden_size_per_layer_input, config.hidden_size, bias=False, device=device, dtype=dtype) + self.post_per_layer_input_norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps, device=device, dtype=dtype) + self.register_buffer("layer_scalar", torch.ones(1, device=device, dtype=dtype)) + else: + self.layer_scalar = None + + def forward(self, x, attention_mask=None, freqs_cis=None, past_key_value=None, per_layer_input=None, shared_kv=None): + sliding_window = None + if self.sliding_attention: + sliding_window = self.sliding_attention + # For prefill > sliding window, add sliding window restriction to the causal mask. + if x.shape[1] > self.sliding_attention: + sw_mask = torch.zeros(x.shape[1], x.shape[1], dtype=x.dtype, device=x.device) + sw_mask.masked_fill_(torch.ones_like(sw_mask, dtype=torch.bool).tril_(-self.sliding_attention), torch.finfo(x.dtype).min) + attention_mask = attention_mask + sw_mask if attention_mask is not None else sw_mask + freqs_cis = freqs_cis[1] + else: + freqs_cis = freqs_cis[0] + + residual = x + x = self.input_layernorm(x) + x, present_key_value, shareable_kv = self.self_attn( + hidden_states=x, attention_mask=attention_mask, freqs_cis=freqs_cis, + past_key_value=past_key_value, sliding_window=sliding_window, shared_kv=shared_kv, + ) + x = self.post_attention_layernorm(x) + x = residual + x + + residual = x + x = self.pre_feedforward_layernorm(x) + x = self.mlp(x) + x = self.post_feedforward_layernorm(x) + x = residual + x + + if self.hidden_size_per_layer_input and per_layer_input is not None: + residual = x + x = self.per_layer_input_gate(x) + x = torch.nn.functional.gelu(x, approximate="tanh") + x = x * per_layer_input + x = self.per_layer_projection(x) + x = self.post_per_layer_input_norm(x) + x = residual + x + + if self.layer_scalar is not None: + x = x * self.layer_scalar + + return x, present_key_value, shareable_kv + + +class Gemma4Transformer(nn.Module): + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + self.config = config + + self.embed_tokens = _make_scaled_embedding(ops, config.vocab_size, config.hidden_size, config.hidden_size ** 0.5, device, dtype) + + self.layers = nn.ModuleList([ + TransformerBlockGemma4(config, index=i, device=device, dtype=dtype, ops=ops) + for i in range(config.num_hidden_layers) + ]) + + self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps, device=device, dtype=dtype) if config.final_norm else None + + # Precompute RoPE inv_freq on CPU to match reference code's exact value + rope_angles_global = int(config.partial_rotary_factor * config.global_head_dim // 2) + nope_global = config.global_head_dim // 2 - rope_angles_global + global_inv = 1.0 / (config.rope_theta[0] ** (torch.arange(0, 2 * rope_angles_global, 2).float() / config.global_head_dim)) + if nope_global > 0: + global_inv = torch.cat([global_inv, torch.zeros(nope_global)]) + self.register_buffer("_global_inv_freq", global_inv, persistent=False) + + sliding_inv = 1.0 / (config.rope_theta[1] ** (torch.arange(0, config.head_dim, 2).float() / config.head_dim)) + self.register_buffer("_sliding_inv_freq", sliding_inv, persistent=False) + + # Per-layer input mechanism + self.hidden_size_per_layer_input = config.hidden_size_per_layer_input + if self.hidden_size_per_layer_input: + self.embed_tokens_per_layer = _make_scaled_embedding(ops, config.vocab_size, config.num_hidden_layers * self.hidden_size_per_layer_input, self.hidden_size_per_layer_input ** 0.5, device, dtype) + self.per_layer_model_projection = ops.Linear( + config.hidden_size, config.num_hidden_layers * self.hidden_size_per_layer_input, + bias=False, device=device, dtype=dtype) + self.per_layer_projection_norm = RMSNorm( + self.hidden_size_per_layer_input, eps=config.rms_norm_eps, + device=device, dtype=dtype) + + def get_past_len(self, past_key_values): + for kv in past_key_values: + if len(kv) >= 3: + return kv[2] + return 0 + + def _freqs_from_inv(self, inv_freq, position_ids, device, dtype): + """Compute cos/sin from stored inv_freq""" + inv_exp = inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(device) + pos_exp = position_ids[:, None, :].float() + freqs = (inv_exp @ pos_exp).transpose(1, 2) + emb = torch.cat((freqs, freqs), dim=-1) + return emb.cos().unsqueeze(1).to(dtype), emb.sin().unsqueeze(1).to(dtype) + + def compute_freqs_cis(self, position_ids, device, dtype=None): + global_freqs = self._freqs_from_inv(self._global_inv_freq, position_ids, device, dtype) + sliding_freqs = self._freqs_from_inv(self._sliding_inv_freq, position_ids, device, dtype) + return [global_freqs, sliding_freqs] + + def forward(self, x, attention_mask=None, embeds=None, num_tokens=None, intermediate_output=None, + final_layer_norm_intermediate=True, dtype=None, position_ids=None, embeds_info=None, + past_key_values=None, input_ids=None): + if embeds is not None: + x = embeds + else: + x = self.embed_tokens(x, out_dtype=dtype) + + seq_len = x.shape[1] + past_len = 0 + if past_key_values is not None and len(past_key_values) > 0: + past_len = self.get_past_len(past_key_values) + + if position_ids is None: + position_ids = torch.arange(past_len, past_len + seq_len, device=x.device).unsqueeze(0) + + freqs_cis = self.compute_freqs_cis(position_ids, x.device, dtype=x.dtype) + + mask = None + min_val = torch.finfo(x.dtype).min + if attention_mask is not None: + mask = 1.0 - attention_mask.to(x.dtype).reshape((attention_mask.shape[0], 1, -1, attention_mask.shape[-1])).expand(attention_mask.shape[0], 1, seq_len, attention_mask.shape[-1]) + mask = mask.masked_fill(mask.to(torch.bool), min_val) + + if seq_len > 1: + causal_mask = torch.zeros(past_len + seq_len, past_len + seq_len, dtype=x.dtype, device=x.device) + causal_mask.masked_fill_(torch.ones_like(causal_mask, dtype=torch.bool).triu_(1), min_val) + mask = mask + causal_mask if mask is not None else causal_mask + + # Per-layer inputs + per_layer_inputs = None + if self.hidden_size_per_layer_input: + num_layers = self.config.num_hidden_layers + hpl = self.hidden_size_per_layer_input + per_layer_proj = self.per_layer_model_projection(x) * (1.0 / (self.config.hidden_size ** 0.5)) + per_layer_proj = self.per_layer_projection_norm(per_layer_proj.reshape(*x.shape[:-1], num_layers, hpl)) + if input_ids is not None and input_ids.shape[1] == x.shape[1]: + per_layer_emb = self.embed_tokens_per_layer(input_ids).reshape(*input_ids.shape, num_layers, hpl) + per_layer_inputs = (per_layer_proj + per_layer_emb) * (0.5 ** 0.5) + else: + per_layer_inputs = per_layer_proj + + # KV sharing: later layers reuse KV from the last non-shared sliding/global layer + num_kv_shared = self.config.num_kv_shared_layers + first_kv_shared = self.config.num_hidden_layers - num_kv_shared if num_kv_shared > 0 else self.config.num_hidden_layers + shared_sliding_kv = None # KV from last non-shared sliding layer + shared_global_kv = None # KV from last non-shared global layer + + intermediate = None + next_key_values = [] + for i, layer in enumerate(self.layers): + past_kv = past_key_values[i] if past_key_values is not None and len(past_key_values) > 0 else None + + layer_kwargs = {} + if per_layer_inputs is not None: + layer_kwargs['per_layer_input'] = per_layer_inputs[:, :, i, :] + + is_sliding = hasattr(layer, 'sliding_attention') and layer.sliding_attention + if i >= first_kv_shared and num_kv_shared > 0: + shared = shared_sliding_kv if is_sliding else shared_global_kv + if shared is not None: + layer_kwargs['shared_kv'] = shared + + x, current_kv, shareable_kv = layer(x=x, attention_mask=mask, freqs_cis=freqs_cis, past_key_value=past_kv, **layer_kwargs) + + next_key_values.append(current_kv if current_kv is not None else ()) + + # Only track the last sliding/global before the sharing boundary + if i < first_kv_shared and shareable_kv is not None: + if is_sliding: + shared_sliding_kv = shareable_kv + else: + shared_global_kv = shareable_kv + + if i == intermediate_output: + intermediate = x.clone() + + if self.norm is not None: + x = self.norm(x) + + if len(next_key_values) > 0: + return x, intermediate, next_key_values + return x, intermediate + + +class Gemma4Base(BaseLlama, BaseGenerate, torch.nn.Module): + """Common base for all Gemma4 variants: text model + vision.""" + def _init_model(self, config, dtype, device, operations): + self.num_layers = config.num_hidden_layers + self.model = Gemma4Transformer(config, device=device, dtype=dtype, ops=operations) + self.dtype = dtype + self.multi_modal_projector = Gemma4MultiModalProjector(config, dtype=dtype, device=device, ops=operations) + self.vision_model = Gemma4VisionEncoder(config.vision_config, dtype=dtype, device=device, ops=operations) + + def logits(self, x): + logits = super().logits(x) + cap = self.model.config.final_logit_softcapping + if cap: + logits = cap * torch.tanh(logits / cap) + return logits + + def init_kv_cache(self, batch, max_cache_len, device, execution_dtype): + past_key_values = [] + for _ in range(self.model.config.num_hidden_layers): + past_key_values.append(()) + return past_key_values + + def preprocess_embed(self, embed, device): + if embed["type"] == "image": + image = embed.pop("data").movedim(-1, 1) # [B, H, W, C] -> [B, C, H, W] + max_soft_tokens = embed.get("max_soft_tokens", None) + vision_out = self.vision_model(image.to(device, dtype=torch.float32), max_soft_tokens=max_soft_tokens) + return self.multi_modal_projector(vision_out), None + return None, None + + +class Gemma4AudioMixin: + """Adds audio support to a Gemma4 model.""" + def _init_audio(self, config, dtype, device, operations): + self.audio_model = Gemma4AudioEncoder(config.audio_config, dtype=dtype, device=device, ops=operations) + self.audio_projector = Gemma4AudioProjector({"audio_output_proj_dims": config.audio_config["output_proj_dims"], "text_hidden_size": config.hidden_size, "rms_norm_eps": config.rms_norm_eps}, dtype=dtype, device=device, ops=operations) + + def preprocess_embed(self, embed, device): + result, extra = super().preprocess_embed(embed, device) + if result is not None: + return result, extra + if embed["type"] == "audio": + audio = embed.pop("data").to(device, dtype=torch.float32) + audio_mask = embed.pop("mask", None) + if audio_mask is not None: + audio_mask = audio_mask.to(device) + audio_out = self.audio_model(audio, audio_mask=audio_mask) + return self.audio_projector(audio_out), None + return None, None + + +# Vision Encoder + +def _compute_vision_2d_rope(head_dim, pixel_position_ids, theta=100.0, device=None): + """Compute 2D RoPE for vision: separate frequencies for x and y dimensions. + + Args: + head_dim: dimension per head (e.g. 64) + pixel_position_ids: [batch, num_patches, 2] with (x, y) coords + theta: RoPE base frequency + Returns: + (cos, sin) each of shape [batch, num_patches, head_dim] + """ + rotary_dim_per_axis = head_dim // 2 + freq_indices = torch.arange(0, rotary_dim_per_axis, 2, device=device).float() + inv_freq = 1.0 / (theta ** (freq_indices / rotary_dim_per_axis)) + + all_cos, all_sin = [], [] + for i in range(2): # x and y + dim_positions = pixel_position_ids[:, :, i].float() # [batch, num_patches] + freqs = torch.einsum('bi,j->bij', dim_positions, inv_freq.to(device)) # [batch, num_patches, rotary_dim/2] + emb = torch.cat([freqs, freqs], dim=-1) # [batch, num_patches, rotary_dim] + all_cos.append(emb.cos()) + all_sin.append(emb.sin()) + + cos = torch.cat(all_cos, dim=-1).to(pixel_position_ids.device) # [batch, num_patches, head_dim] + sin = torch.cat(all_sin, dim=-1).to(pixel_position_ids.device) + return cos, sin + + +def _apply_vision_2d_rope(x, freqs): + """Apply 2D RoPE (multidimensional) to vision query/key states. + + Splits x and cos/sin into ndim=2 parts, applies 1D RoPE to each independently. + + x: [batch, heads, seq, head_dim] + freqs: (cos, sin) each [batch, seq, head_dim] + """ + cos = freqs[0].unsqueeze(1) # [batch, 1, seq, head_dim] + sin = freqs[1].unsqueeze(1) + half = x.shape[-1] // 2 + a = _apply_rotary_pos_emb(x[..., :half], (cos[..., :half], sin[..., :half])) + b = _apply_rotary_pos_emb(x[..., half:], (cos[..., half:], sin[..., half:])) + return torch.cat([a, b], dim=-1) + + +class ClippedLinear(nn.Module): + """Linear layer with activation clipping (from quantization-aware training). + + Stores input_max/min and output_max/min as buffers loaded from checkpoint. + """ + def __init__(self, in_features, out_features, bias=False, device=None, dtype=None, ops=None): + super().__init__() + self.linear = ops.Linear(in_features, out_features, bias=bias, device=device, dtype=dtype) + self.register_buffer('input_max', torch.tensor(float('inf'), device=device, dtype=dtype)) + self.register_buffer('input_min', torch.tensor(float('-inf'), device=device, dtype=dtype)) + self.register_buffer('output_max', torch.tensor(float('inf'), device=device, dtype=dtype)) + self.register_buffer('output_min', torch.tensor(float('-inf'), device=device, dtype=dtype)) + + @property + def weight(self): + return self.linear.weight + + def forward(self, x): + x = x.clamp(min=self.input_min, max=self.input_max) + x = self.linear(x) + return x.clamp_(min=self.output_min, max=self.output_max) + + +class Gemma4VisionMLP(nn.Module): + """SwiGLU MLP matching gate_proj/up_proj/down_proj structure.""" + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + hidden_size = config["hidden_size"] + intermediate_size = config["intermediate_size"] + self.gate_proj = ClippedLinear(hidden_size, intermediate_size, device=device, dtype=dtype, ops=ops) + self.up_proj = ClippedLinear(hidden_size, intermediate_size, device=device, dtype=dtype, ops=ops) + self.down_proj = ClippedLinear(intermediate_size, hidden_size, device=device, dtype=dtype, ops=ops) + + def forward(self, x): + return self.down_proj(torch.nn.functional.gelu(self.gate_proj(x), approximate="tanh") * self.up_proj(x)) + + +class Gemma4VisionAttention(nn.Module): + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + self.hidden_size = config["hidden_size"] + self.num_heads = config["num_attention_heads"] + self.head_dim = config.get("head_dim", self.hidden_size // self.num_heads) + + self.q_proj = ClippedLinear(self.hidden_size, self.num_heads * self.head_dim, device=device, dtype=dtype, ops=ops) + self.k_proj = ClippedLinear(self.hidden_size, self.num_heads * self.head_dim, device=device, dtype=dtype, ops=ops) + self.v_proj = ClippedLinear(self.hidden_size, self.num_heads * self.head_dim, device=device, dtype=dtype, ops=ops) + self.o_proj = ClippedLinear(self.num_heads * self.head_dim, self.hidden_size, device=device, dtype=dtype, ops=ops) + + self.q_norm = RMSNorm(self.head_dim, eps=config["rms_norm_eps"], device=device, dtype=dtype) + self.k_norm = RMSNorm(self.head_dim, eps=config["rms_norm_eps"], device=device, dtype=dtype) + + def forward(self, x, freqs, attention_mask=None): + batch_size, seq_length, _ = x.shape + + xq = self.q_proj(x).view(batch_size, seq_length, self.num_heads, self.head_dim) + xk = self.k_proj(x).view(batch_size, seq_length, self.num_heads, self.head_dim) + xv = self.v_proj(x).view(batch_size, seq_length, self.num_heads, self.head_dim) + + xq = self.q_norm(xq).transpose(1, 2) + xk = self.k_norm(xk).transpose(1, 2) + xv = rms_norm(xv) + + xq = _apply_vision_2d_rope(xq, freqs) + xk = _apply_vision_2d_rope(xk, freqs) + + xv = xv.to(xq.dtype).transpose(1, 2) + + output = optimized_attention_for_device(xq.device, mask=attention_mask is not None, small_input=True)(xq, xk, xv, self.num_heads, mask=attention_mask, skip_reshape=True, scale=1.0) + return self.o_proj(output) + + +class Gemma4VisionLayer(nn.Module): + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + self.self_attn = Gemma4VisionAttention(config, device=device, dtype=dtype, ops=ops) + self.mlp = Gemma4VisionMLP(config, device=device, dtype=dtype, ops=ops) + norm_kwargs = dict(eps=config["rms_norm_eps"], device=device, dtype=dtype) + hidden = config["hidden_size"] + self.input_layernorm = RMSNorm(hidden, **norm_kwargs) + self.post_attention_layernorm = RMSNorm(hidden, **norm_kwargs) + self.pre_feedforward_layernorm = RMSNorm(hidden, **norm_kwargs) + self.post_feedforward_layernorm = RMSNorm(hidden, **norm_kwargs) + + def forward(self, x, freqs, attention_mask=None): + residual = x + x = self.input_layernorm(x) + x = self.self_attn(x, freqs, attention_mask=attention_mask) + x = self.post_attention_layernorm(x) + x = residual + x + + residual = x + x = self.pre_feedforward_layernorm(x) + x = self.mlp(x) + x = self.post_feedforward_layernorm(x) + x = residual + x + return x + + +class Gemma4PatchEmbedder(nn.Module): + """Patch embedding with learned 2D position embeddings via one-hot lookup.""" + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + hidden_size = config["hidden_size"] + patch_size = config["patch_size"] + self.patch_size = patch_size + self.position_embedding_size = config.get("position_embedding_size", 10240) + + self.input_proj = ops.Linear(3 * patch_size * patch_size, hidden_size, bias=False, device=device, dtype=dtype) + self.position_embedding_table = nn.Parameter( + torch.empty(2, self.position_embedding_size, hidden_size, device=device, dtype=dtype) + ) + + def forward(self, patches, pixel_position_ids): + """ + patches: [B, num_patches, 3*patch_size²] in [0,1] range (normalized to [-1,1] inside, matching HF) + pixel_position_ids: [B, num_patches, 2] with (x,y) positions, (-1,-1) for padding + """ + hidden_states = self.input_proj((2.0 * (patches - 0.5)).to(self.input_proj.weight.dtype)) + + clamped_positions = pixel_position_ids.clamp(min=0) + pos_table = comfy.model_management.cast_to_device(self.position_embedding_table, hidden_states.device, hidden_states.dtype) + position_embeddings = pos_table[0][clamped_positions[..., 0]] + pos_table[1][clamped_positions[..., 1]] + + # Zero out position embeddings for padding patches (matching HF) + padding_positions = (pixel_position_ids == -1).all(dim=-1) + position_embeddings = torch.where(padding_positions.unsqueeze(-1), 0.0, position_embeddings) + + return hidden_states + position_embeddings + + +class Gemma4VisionEncoderLayers(nn.Module): + """Wrapper to produce state dict keys as encoder.layers.X.*""" + def __init__(self, config, dtype=None, device=None, ops=None): + super().__init__() + self.layers = nn.ModuleList([ + Gemma4VisionLayer(config, device=device, dtype=dtype, ops=ops) + for _ in range(config["num_hidden_layers"]) + ]) + + +class Gemma4VisionEncoder(nn.Module): + def __init__(self, config, dtype=None, device=None, ops=None): + super().__init__() + self.config = config + self.hidden_size = config["hidden_size"] + self.head_dim = config.get("head_dim", config["hidden_size"] // config["num_attention_heads"]) + self.patch_size = config["patch_size"] + self.pooling_kernel_size = config.get("pooling_kernel_size", 3) + self.root_hidden_size = self.hidden_size ** 0.5 + + self.patch_embedder = Gemma4PatchEmbedder(config, device=device, dtype=dtype, ops=ops) + self.encoder = Gemma4VisionEncoderLayers(config, dtype=dtype, device=device, ops=ops) + + def forward(self, pixel_values, max_soft_tokens=None): + """ + pixel_values: [B, C, H, W] in [0,1] range + max_soft_tokens: if provided, pad to max_soft_tokens * k² total patches + """ + batch_size, _, height, width = pixel_values.shape + ps = self.patch_size + k = self.pooling_kernel_size + patches_h, patches_w = height // ps, width // ps + num_patches = patches_h * patches_w + output_length = max_soft_tokens if max_soft_tokens is not None else num_patches // (k * k) + n_padding = output_length * k * k - num_patches + + # Patchify and build position grid + patches = pixel_values.reshape(batch_size, -1, patches_h, ps, patches_w, ps) + patches = patches.permute(0, 2, 4, 3, 5, 1).reshape(batch_size, num_patches, -1) + grid_y, grid_x = torch.meshgrid(torch.arange(patches_h, device=pixel_values.device), torch.arange(patches_w, device=pixel_values.device), indexing='ij') + position_ids = torch.stack([grid_x.flatten(), grid_y.flatten()], dim=-1).unsqueeze(0).expand(batch_size, -1, -1) + + # Append zero-pixel padding with (-1,-1) positions + if n_padding > 0: + patches = torch.cat([patches, patches.new_zeros(batch_size, n_padding, patches.shape[-1])], dim=1) + position_ids = torch.cat([position_ids, position_ids.new_full((batch_size, n_padding, 2), -1)], dim=1) + + padding = (position_ids == -1).all(dim=-1) + + # Embed, encode, pool + x = self.patch_embedder(patches, position_ids) + freqs = _compute_vision_2d_rope(self.head_dim, position_ids, device=pixel_values.device) + freqs = tuple(t.to(x.dtype) for t in freqs) + if n_padding > 0: + mask = padding.unsqueeze(1).unsqueeze(2).expand(-1, 1, position_ids.shape[1], -1) + mask = torch.zeros_like(mask, dtype=x.dtype).masked_fill_(mask, torch.finfo(x.dtype).min) + else: + mask = None + + for layer in self.encoder.layers: + x = layer(x, freqs, attention_mask=mask) + + if n_padding > 0: + x = x.masked_fill(padding.unsqueeze(-1), 0.0) + + # Average pool by spatial position + clamped = position_ids.clamp(min=0) + max_x = clamped[:, :, 0].max(dim=-1, keepdim=True)[0] + 1 + ki = torch.div(clamped, k, rounding_mode="floor") + ki = ki[:, :, 0] + (max_x // k) * ki[:, :, 1] + weights = torch.nn.functional.one_hot(ki.long(), output_length).float() / (k * k) + x = (weights.transpose(1, 2) @ x.float()).to(x.dtype) + + # Strip empty output tokens + valid_out = ~((weights == 0).all(dim=1)) + if valid_out.any() and not valid_out.all(): + x = x[:, valid_out[0]] if batch_size > 1 else x[valid_out].unsqueeze(0) + + return x * self.root_hidden_size + + +class Gemma4RMSNormProjector(nn.Module): + """Shared projector: parameterless RMSNorm → linear. Used for both vision and audio.""" + def __init__(self, in_dim, out_dim, dtype=None, device=None, ops=None): + super().__init__() + self.embedding_projection = ops.Linear(in_dim, out_dim, bias=False, device=device, dtype=dtype) + + def forward(self, x): + return self.embedding_projection(rms_norm(x)) + + +class Gemma4MultiModalProjector(Gemma4RMSNormProjector): + def __init__(self, config, dtype=None, device=None, ops=None): + super().__init__(config.vision_config["hidden_size"], config.hidden_size, dtype=dtype, device=device, ops=ops) + + +# Audio Encoder + +class Gemma4AudioConvSubsampler(nn.Module): + """2D convolution subsampling for audio features""" + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + eps = config["rms_norm_eps"] + self.layer0 = nn.ModuleDict({ + 'conv': ops.Conv2d(1, 128, kernel_size=3, stride=2, padding=1, bias=False, device=device, dtype=dtype), + 'norm': ops.LayerNorm(128, eps=eps, elementwise_affine=True, bias=False, device=device, dtype=dtype), + }) + self.layer1 = nn.ModuleDict({ + 'conv': ops.Conv2d(128, 32, kernel_size=3, stride=2, padding=1, bias=False, device=device, dtype=dtype), + 'norm': ops.LayerNorm(32, eps=eps, elementwise_affine=True, bias=False, device=device, dtype=dtype), + }) + # proj_input_dim = (128 // 4) * 32 = 1024 + self.input_proj_linear = ops.Linear(1024, config["hidden_size"], bias=False, device=device, dtype=dtype) + + def _conv_layer(self, x, layer, mask): + if mask is not None: + x = x * mask[:, None, :, None].to(x.device) + x = layer['conv'](x.to(layer['conv'].weight.dtype)) + x = torch.relu(layer['norm'](x.permute(0, 2, 3, 1)).permute(0, 3, 1, 2).contiguous()) + if mask is not None: + mask = mask[:, ::2] + return x, mask + + def forward(self, x, mask=None): + x = x.unsqueeze(1) + x, mask = self._conv_layer(x, self.layer0, mask) + x, mask = self._conv_layer(x, self.layer1, mask) + batch_size, _, seq_len, _ = x.shape + x = x.permute(0, 2, 3, 1).contiguous().reshape(batch_size, seq_len, -1) + return self.input_proj_linear(x), mask + + +class Gemma4AudioFeedForward(nn.Module): + """Conformer feed-forward with residual scaling.""" + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + hidden_size = config["hidden_size"] + intermediate_size = config.get("intermediate_size", hidden_size * 4) + self.pre_layer_norm = RMSNorm(hidden_size, eps=config["rms_norm_eps"], device=device, dtype=dtype) + self.ffw_layer_1 = ClippedLinear(hidden_size, intermediate_size, device=device, dtype=dtype, ops=ops) + self.ffw_layer_2 = ClippedLinear(intermediate_size, hidden_size, device=device, dtype=dtype, ops=ops) + self.post_layer_norm = RMSNorm(hidden_size, eps=config["rms_norm_eps"], device=device, dtype=dtype) + self.post_layer_scale = config.get("residual_weight", 0.5) + + def forward(self, x): + residual = x + x = self.pre_layer_norm(x) + x = torch.nn.functional.silu(self.ffw_layer_1(x)) + x = self.ffw_layer_2(x) + x = self.post_layer_norm(x) + x = x * self.post_layer_scale + return x + residual + + +class Gemma4AudioRelPositionalEncoding(nn.Module): + """Sinusoidal relative positional encoding for audio attention.""" + def __init__(self, config, device=None, dtype=None): + super().__init__() + hidden_size = config["hidden_size"] + context_left = config.get("attention_context_left", 13) + context_right = config.get("attention_context_right", 0) + self.chunk_size = config.get("attention_chunk_size", 12) + self.context_size = self.chunk_size + context_left - 1 + context_right + + num_timescales = hidden_size // 2 + log_inc = math.log(10000.0) / max(num_timescales - 1, 1) + inv_timescales = torch.exp(torch.arange(num_timescales) * -log_inc).to(dtype=dtype).unsqueeze(0).unsqueeze(0) + self.register_buffer("inv_timescales", inv_timescales, persistent=False) + + def forward(self, hidden_states): + positions = torch.arange(self.chunk_size, -1, -1, device=hidden_states.device).unsqueeze(-1) + scaled = positions * self.inv_timescales.to(device=hidden_states.device) + return torch.cat([torch.sin(scaled), torch.cos(scaled)], dim=-1).to(dtype=hidden_states.dtype) + + +class Gemma4AudioAttention(nn.Module): + """Chunked block attention with relative position bias and softcap.""" + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + self.hidden_size = config["hidden_size"] + self.num_heads = config["num_attention_heads"] + self.head_dim = self.hidden_size // self.num_heads + self.chunk_size = config.get("attention_chunk_size", 12) + self.max_past_horizon = config.get("attention_context_left", 13) - 1 + self.max_future_horizon = config.get("attention_context_right", 0) + self.context_size = self.chunk_size + self.max_past_horizon + self.max_future_horizon + + self.q_scale = (self.head_dim ** -0.5) / math.log(2) + self.k_scale = math.log(1 + math.e) / math.log(2) + self.register_buffer("softcap", torch.tensor(config.get("attention_logit_cap", 50.0), dtype=dtype), persistent=False) + + self.q_proj = ClippedLinear(self.hidden_size, self.hidden_size, device=device, dtype=dtype, ops=ops) + self.k_proj = ClippedLinear(self.hidden_size, self.hidden_size, device=device, dtype=dtype, ops=ops) + self.v_proj = ClippedLinear(self.hidden_size, self.hidden_size, device=device, dtype=dtype, ops=ops) + self.post = ClippedLinear(self.hidden_size, self.hidden_size, device=device, dtype=dtype, ops=ops) + self.per_dim_scale = nn.Parameter(torch.empty(self.head_dim, device=device, dtype=dtype)) + self.relative_k_proj = ops.Linear(self.hidden_size, self.hidden_size, bias=False, device=device, dtype=dtype) + + def _convert_to_block(self, x): + B, S, H, D = x.shape + num_blocks = (S + self.chunk_size - 1) // self.chunk_size + pad = num_blocks * self.chunk_size - S + x = torch.nn.functional.pad(x, (0, 0, 0, 0, 0, pad)) + return x.reshape(B, num_blocks, self.chunk_size, H, D).contiguous() + + def _extract_block_context(self, x): + x = torch.nn.functional.pad(x, (0, 0, 0, 0, self.max_past_horizon, self.max_future_horizon + self.chunk_size - 1)) + x = x.unfold(1, self.context_size, self.chunk_size) + return torch.movedim(x, -1, 2).contiguous() + + def _rel_shift(self, x): + B, H, NB, BS, PL = x.shape + CS = self.context_size + x = torch.nn.functional.pad(x, (0, CS + 1 - PL)) + x = x.view(B, H, NB, BS * (CS + 1)) + x = x[..., :BS * CS] + return x.view(B, H, NB, BS, CS) + + def _build_blocked_mask(self, seq_len, num_blocks, device, audio_mask=None): + """Build 5D boolean blocked attention mask (True=attend, False=mask)""" + q = torch.arange(seq_len, device=device) + dist = q[:, None] - q[None, :] + mask = (dist >= 0) & (dist < self.max_past_horizon) + if self.max_future_horizon > 0: + mask = mask | ((dist < 0) & ((-dist) < self.max_future_horizon)) + if audio_mask is not None: + mask = mask & audio_mask[0, None, :].bool() + m = mask[None, None] + # Reshape to blocked 5D matching reference code + p = num_blocks * self.chunk_size - seq_len + m = torch.nn.functional.pad(m, (0, p, 0, p), value=False) + m = m.reshape(1, 1, num_blocks, self.chunk_size, -1) + m = torch.nn.functional.pad(m, (self.max_past_horizon, self.max_future_horizon), value=False) + idx = (torch.arange(num_blocks, device=device) * self.chunk_size)[:, None] + torch.arange(self.context_size, device=device)[None, :] + return m.gather(-1, idx[None, None, :, None, :].expand(1, 1, -1, self.chunk_size, -1)) + + def forward(self, x, position_embeddings=None, attn_mask=None): + B, S, _ = x.shape + + q = self.q_proj(x).float().view(B, S, self.num_heads, self.head_dim) + k = self.k_proj(x).float().view(B, S, self.num_heads, self.head_dim) + v = self.v_proj(x).float().view(B, S, self.num_heads, self.head_dim) + + q = q * self.q_scale * torch.nn.functional.softplus(self.per_dim_scale) + k = k * self.k_scale + + q_blocks = self._convert_to_block(q) + k_context = self._extract_block_context(k) + v_context = self._extract_block_context(v) + num_blocks = q_blocks.shape[1] + + rel_k = self.relative_k_proj(position_embeddings).view(-1, self.num_heads, self.head_dim).to(q.dtype) + + queries = q_blocks.permute(0, 3, 1, 2, 4) # [B, H, NB, CS, D] + matrix_ac = queries @ k_context.permute(0, 3, 1, 4, 2) + + queries_flat = queries.reshape(B, self.num_heads, -1, self.head_dim) + matrix_bd = queries_flat @ rel_k.permute(1, 2, 0) + matrix_bd = matrix_bd.reshape(B, self.num_heads, num_blocks, self.chunk_size, -1) + matrix_bd = self._rel_shift(matrix_bd) + + attn_weights = matrix_ac + matrix_bd + attn_weights = torch.tanh(attn_weights / self.softcap) * self.softcap + + # Mask out invalid positions in chunk context (matching reference's masked_fill approach) + if attn_mask is None: + attn_mask = self._build_blocked_mask(S, num_blocks, x.device) + attn_weights = attn_weights.masked_fill(attn_mask.logical_not(), -1e9) + + attn_weights = torch.nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(v.dtype) + out = attn_weights @ v_context.permute(0, 3, 1, 2, 4) + out = out.permute(0, 2, 3, 1, 4).reshape(B, num_blocks * self.chunk_size, -1) + out = out[:, :S].contiguous() + return self.post(out.to(self.post.linear.weight.dtype)) + + +class Gemma4AudioLConv1d(nn.Module): + """Lightweight convolution with standard GLU.""" + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + hidden_size = config["hidden_size"] + conv_kernel_size = config.get("conv_kernel_size", 5) + self.pre_layer_norm = RMSNorm(hidden_size, eps=config["rms_norm_eps"], device=device, dtype=dtype) + self.linear_start = ClippedLinear(hidden_size, hidden_size * 2, device=device, dtype=dtype, ops=ops) + # Causal conv: left-pad only + self.depthwise_conv1d = ops.Conv1d(hidden_size, hidden_size, kernel_size=conv_kernel_size, padding=0, groups=hidden_size, bias=False, device=device, dtype=dtype) + self.conv_left_pad = conv_kernel_size - 1 # causal: pad left by kernel-1 + self.conv_norm = RMSNorm(hidden_size, eps=config["rms_norm_eps"], device=device, dtype=dtype) + self.linear_end = ClippedLinear(hidden_size, hidden_size, device=device, dtype=dtype, ops=ops) + + def forward(self, x): + residual = x + x = self.pre_layer_norm(x) + x = self.linear_start(x) + x = torch.nn.functional.glu(x, dim=-1) + x = x.transpose(1, 2) + x = torch.nn.functional.pad(x, (self.conv_left_pad, 0)) + x = self.depthwise_conv1d(x).transpose(1, 2) + x = self.conv_norm(x) + x = torch.nn.functional.silu(x) + x = self.linear_end(x) + return x + residual + + +class Gemma4AudioLayer(nn.Module): + """Conformer block: FFN1 -> Attention -> LConv -> FFN2.""" + def __init__(self, config, device=None, dtype=None, ops=None): + super().__init__() + self.feed_forward1 = Gemma4AudioFeedForward(config, device=device, dtype=dtype, ops=ops) + self.self_attn = Gemma4AudioAttention(config, device=device, dtype=dtype, ops=ops) + norm_kwargs = dict(eps=config["rms_norm_eps"], device=device, dtype=dtype) + hidden_size = config["hidden_size"] + self.norm_pre_attn = RMSNorm(hidden_size, **norm_kwargs) + self.norm_post_attn = RMSNorm(hidden_size, **norm_kwargs) + self.lconv1d = Gemma4AudioLConv1d(config, device=device, dtype=dtype, ops=ops) + self.feed_forward2 = Gemma4AudioFeedForward(config, device=device, dtype=dtype, ops=ops) + self.norm_out = RMSNorm(hidden_size, **norm_kwargs) + + def forward(self, x, position_embeddings=None, attn_mask=None): + x = self.feed_forward1(x) + + residual = x + x = self.norm_pre_attn(x) + x = self.self_attn(x, position_embeddings=position_embeddings, attn_mask=attn_mask) + x = self.norm_post_attn(x) + x = x + residual + + x = self.lconv1d(x) + x = self.feed_forward2(x) + + x = self.norm_out(x) + return x + + +class Gemma4AudioEncoder(nn.Module): + def __init__(self, config, dtype=None, device=None, ops=None): + super().__init__() + self.hidden_size = config["hidden_size"] + self.output_proj_dims = config.get("output_proj_dims", 1536) + + self.subsample_conv_projection = Gemma4AudioConvSubsampler(config, device=device, dtype=dtype, ops=ops) + self.rel_pos_enc = Gemma4AudioRelPositionalEncoding(config, device=device, dtype=dtype) + + self.layers = nn.ModuleList([ + Gemma4AudioLayer(config, device=device, dtype=dtype, ops=ops) + for _ in range(config["num_hidden_layers"]) + ]) + + self.output_proj = ops.Linear(self.hidden_size, self.output_proj_dims, bias=True, device=device, dtype=dtype) + + def forward(self, audio_features, audio_mask=None): + x, audio_mask = self.subsample_conv_projection(audio_features, audio_mask) + position_embeddings = self.rel_pos_enc(x) + + # Build blocked attention mask once for all layers + attn_mask = self.layers[0].self_attn._build_blocked_mask( + x.shape[1], (x.shape[1] + self.layers[0].self_attn.chunk_size - 1) // self.layers[0].self_attn.chunk_size, + x.device, audio_mask=audio_mask) + + for layer in self.layers: + x = layer(x, position_embeddings=position_embeddings, attn_mask=attn_mask) + + x = self.output_proj(x) + return x + + +class Gemma4AudioProjector(Gemma4RMSNormProjector): + def __init__(self, config, dtype=None, device=None, ops=None): + super().__init__(config.get("audio_output_proj_dims", 1536), config.get("text_hidden_size", 2560), dtype=dtype, device=device, ops=ops) + + +# Tokenizer and Wrappers + +class Gemma4_Tokenizer(): + tokenizer_json_data = None + + def state_dict(self): + if self.tokenizer_json_data is not None: + return {"tokenizer_json": self.tokenizer_json_data} + return {} + + def _extract_mel_spectrogram(self, waveform, sample_rate): + """Extract 128-bin log mel spectrogram. + Uses numpy for FFT/matmul/log to produce bit-identical results with reference code. + """ + # Mix to mono first, then resample to 16kHz + if waveform.dim() > 1 and waveform.shape[0] > 1: + waveform = waveform.mean(dim=0, keepdim=True) + if waveform.dim() == 1: + waveform = waveform.unsqueeze(0) + audio = waveform.squeeze(0).float().numpy() + if sample_rate != 16000: + # Use scipy's resample_poly with a high-quality FIR filter to get as close as possible to librosa's resampling (while still not full match) + from scipy.signal import resample_poly, firwin + from math import gcd + g = gcd(sample_rate, 16000) + up, down = 16000 // g, sample_rate // g + L = max(up, down) + h = firwin(160 * L + 1, 0.96 / L, window=('kaiser', 6.5)) + audio = resample_poly(audio, up, down, window=h).astype(np.float32) + n = len(audio) + + # Pad to multiple of 128, build sample-level mask + if n % 128 != 0: + audio = np.pad(audio, (0, 128 - n % 128)) + mask_raw = np.ones(len(audio), dtype=np.float32) + mask_raw[n:] = 0.0 + + # Semicausal padding: 160 zeros prepended + audio = np.pad(audio, (160, 0)) + mask_raw = np.pad(mask_raw, (160, 0)) + + # Extract 321-sample frames via stride tricks, drop last → 320 + nf = (len(audio) - 321) // 160 + 1 + strides = (audio.strides[0] * 160, audio.strides[0]) + frames = np.lib.stride_tricks.as_strided(audio, (nf, 321), strides)[..., :-1].copy() + + # Periodic Hann window, FFT magnitude, mel filterbank, log + window = (0.5 - 0.5 * np.cos(2 * np.pi * np.arange(320) / 320)).astype(np.float32) + magnitude = np.abs(np.fft.rfft(frames * window, n=512, axis=-1)) + mel_fb = self._build_mel_filterbank() + log_mel = np.log(np.matmul(magnitude, mel_fb) + np.float64(0.001)).astype(np.float32) + + # Frame mask: valid when last sample in window is real audio + mask = mask_raw[np.arange(nf) * 160 + 320].astype(bool) + log_mel = log_mel * mask[:, None] + return torch.from_numpy(log_mel), torch.from_numpy(mask) # [T, 128], [T] + + @staticmethod + def _build_mel_filterbank(): + """Build 128-bin HTK mel filterbank [257, 128] for 512-pt FFT at 16kHz.""" + mel_freqs = np.linspace(0.0, 2595.0 * np.log10(1.0 + 8000.0 / 700.0), 130) + filter_freqs = 700.0 * (10.0 ** (mel_freqs / 2595.0) - 1.0) + fft_freqs = np.linspace(0, 16000 // 2, 257) + filter_diff = np.diff(filter_freqs) + slopes = np.expand_dims(filter_freqs, 0) - np.expand_dims(fft_freqs, 1) + down_slopes = -slopes[:, :-2] / filter_diff[:-1] + up_slopes = slopes[:, 2:] / filter_diff[1:] + return np.maximum(np.zeros(1), np.minimum(down_slopes, up_slopes)) + + def tokenize_with_weights(self, text, return_word_ids=False, image=None, audio=None, video=None, llama_template=None, skip_template=True, thinking=False, **kwargs): + + # Process audio + audio_features = [] + if audio is not None: + waveform = audio["waveform"].squeeze(0) if hasattr(audio, "__getitem__") else audio + sample_rate = audio.get("sample_rate", 16000) if hasattr(audio, "get") else 16000 + mel, mel_mask = self._extract_mel_spectrogram(waveform, sample_rate) + audio_features = [(mel.unsqueeze(0), mel_mask.unsqueeze(0))] # ([1, T, 128], [1, T]) + + # Process image/video frames + is_video = video is not None + source = video if is_video else image + images = [] + if source is not None: + samples = source.movedim(-1, 1) # [B, C, H, W] + num_frames = samples.shape[0] + + # Subsample video to 1fps + if is_video: + fps = kwargs.get("fps", 24) + step = max(1, round(fps)) + indices = list(range(0, num_frames, step)) + if len(indices) == 0: + indices = [0] + samples = samples[indices] + num_frames = len(indices) + + h, w = samples.shape[2], samples.shape[3] + patch_size = 16 + pooling_k = 3 + max_soft_tokens = 70 if is_video else 280 # video uses smaller token budget per frame + max_patches = max_soft_tokens * pooling_k * pooling_k + target_px = max_patches * patch_size * patch_size + factor = (target_px / (h * w)) ** 0.5 + side_mult = pooling_k * patch_size + target_h = max(int(factor * h // side_mult) * side_mult, side_mult) + target_w = max(int(factor * w // side_mult) * side_mult, side_mult) + + import torchvision.transforms.functional as TVF + for i in range(num_frames): + # rescaling to match reference code + s = (samples[i].clamp(0, 1) * 255).to(torch.uint8) # [C, H, W] uint8 + if target_h != h or target_w != w: + s = TVF.resize(s, [target_h, target_w], interpolation=TVF.InterpolationMode.BICUBIC, antialias=True) + s = s.float() * (1.0 / 255.0) + images.append({"pixels": s.unsqueeze(0).movedim(1, -1)[:, :, :, :3], "max_soft_tokens": max_soft_tokens}) + + if text.startswith('<|turn>'): + skip_template = True + + if skip_template: + llama_text = text + else: + if llama_template is not None: + llama_text = llama_template.format(text) + else: + # Build template from modalities present + system = "<|turn>system\n<|think|>\n" if thinking else "" + media = "" + if len(images) > 0: + if is_video: + media += "\n\n" + for i in range(len(images)): + ts = f"{int(i // 60):02d}:{int(i % 60):02d}" + sep = "" if i == 0 else " " + media += f"{sep}{ts} <|image><|video|>" + media += "\n\n" + else: + media += "\n\n" + for i in range(len(images)): + if i > 0: + media += "\n\n\n\n" + media += "<|image><|image|>" + media += "\n\n" + if len(audio_features) > 0: + # Compute audio token count (always at 16kHz) + num_samples = int(waveform.shape[-1] * 16000 / sample_rate) if sample_rate != 16000 else waveform.shape[-1] + _fl = 320 # int(round(16000 * 20.0 / 1000.0)) + _hl = 160 # int(round(16000 * 10.0 / 1000.0)) + _nmel = (num_samples + _fl // 2 - (_fl + 1)) // _hl + 1 + _t = _nmel + for _ in range(2): + _t = (_t + 2 - 3) // 2 + 1 + n_audio_tokens = min(_t, 750) + media += "<|audio>" + "<|audio|>" * n_audio_tokens + "" + llama_text = f"{system}<|turn>user\n{media}{text}\n<|turn>model\n" + + text_tokens = super().tokenize_with_weights(llama_text, return_word_ids) + + def _replace_placeholders(token_list, token_id, embeds): + """Replace first placeholder with embed dict, remove remaining consecutive ones.""" + embed_idx = 0 + i = 0 + while i < len(token_list): + if token_list[i][0] == token_id and embed_idx < len(embeds): + token_list[i] = (embeds[embed_idx],) + token_list[i][1:] + embed_idx += 1 + i += 1 + while i < len(token_list) and token_list[i][0] == token_id: + token_list.pop(i) + else: + i += 1 + + if len(images) > 0: + img_token_id = 258884 if is_video else 258880 + img_embeds = [{"type": "image", "data": img["pixels"], "max_soft_tokens": img["max_soft_tokens"]} for img in images] + for r in text_tokens: + _replace_placeholders(r, img_token_id, img_embeds) + + if len(audio_features) > 0: + aud_embeds = [{"type": "audio", "data": mel, "mask": mask} for mel, mask in audio_features] + for r in text_tokens: + _replace_placeholders(r, 258881, aud_embeds) + + return text_tokens + + +class _Gemma4Tokenizer: + """Tokenizer using the tokenizers (Gemma4 doesn't come with sentencepiece model)""" + def __init__(self, tokenizer_json_bytes=None, **kwargs): + from tokenizers import Tokenizer + if isinstance(tokenizer_json_bytes, torch.Tensor): + tokenizer_json_bytes = bytes(tokenizer_json_bytes.tolist()) + self.tokenizer = Tokenizer.from_str(tokenizer_json_bytes.decode("utf-8")) + + @classmethod + def from_pretrained(cls, tokenizer_data, **kwargs): + return cls(tokenizer_json_bytes=tokenizer_data, **kwargs) + + def __call__(self, text): + return {"input_ids": self.tokenizer.encode(text, add_special_tokens=False).ids} + + def get_vocab(self): + return self.tokenizer.get_vocab() + + def convert_tokens_to_ids(self, tokens): + return [self.tokenizer.token_to_id(t) for t in tokens] + + def decode(self, ids, **kwargs): + return self.tokenizer.decode(ids, skip_special_tokens=kwargs.get("skip_special_tokens", False)) + + +# Tokenizer +class Gemma4SDTokenizer(Gemma4_Tokenizer, sd1_clip.SDTokenizer): + embedding_size = 2560 + def __init__(self, embedding_directory=None, tokenizer_data={}): + tokenizer_json = tokenizer_data.get("tokenizer_json", None) + self.tokenizer_json_data = tokenizer_json + super().__init__(tokenizer_json, pad_with_end=False, embedding_size=self.embedding_size, embedding_key='gemma4', tokenizer_class=_Gemma4Tokenizer, has_start_token=True, has_end_token=False, pad_to_max_length=False, max_length=99999999, min_length=1, pad_left=True, disable_weights=True, start_token=2, tokenizer_data=tokenizer_data) + + def decode(self, token_ids, **kwargs): + text = super().decode(token_ids, skip_special_tokens=False) + # Translate thinking channel markers to standard / tags + text = text.replace("<|channel>thought\n", "\n") + text = text.replace("", "") + # Strip remaining special tokens + text = text.replace("", "").replace("", "").strip() + return text + + +class Gemma4Tokenizer(sd1_clip.SD1Tokenizer): + tokenizer_class = Gemma4SDTokenizer + def __init__(self, embedding_directory=None, tokenizer_data={}): + super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, name="gemma4", tokenizer=self.tokenizer_class) + + +# Model wrappers +class Gemma4Model(sd1_clip.SDClipModel): + model_class = None + def __init__(self, device="cpu", layer="all", layer_idx=None, dtype=None, attention_mask=True, model_options={}): + self.dtypes = set() + self.dtypes.add(dtype) + super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config={}, dtype=dtype, special_tokens={"start": 2, "pad": 0}, layer_norm_hidden_state=False, model_class=self.model_class, enable_attention_masks=attention_mask, return_attention_masks=attention_mask, model_options=model_options) + + def process_tokens(self, tokens, device): + embeds, _, _, _ = super().process_tokens(tokens, device) + return embeds + + def generate(self, tokens, do_sample, max_length, temperature, top_k, top_p, min_p, repetition_penalty, seed, presence_penalty=0.0): + if isinstance(tokens, dict): + tokens = next(iter(tokens.values())) + tokens_only = [[t[0] for t in b] for b in tokens] + embeds, _, _, embeds_info = sd1_clip.SDClipModel.process_tokens(self, tokens_only, self.execution_device) + seq_len = embeds.shape[1] + ids = [0] * seq_len + expanded_idx = 0 + embed_map = {info["index"]: info["size"] for info in embeds_info} + for t in tokens_only[0]: + if expanded_idx in embed_map: + expanded_idx += embed_map[expanded_idx] + elif isinstance(t, int): + if expanded_idx < seq_len: + ids[expanded_idx] = t + expanded_idx += 1 + else: + expanded_idx += 1 + initial_token_ids = [ids] + input_ids = torch.tensor(initial_token_ids, device=self.execution_device) + return self.transformer.generate(embeds, do_sample, max_length, temperature, top_k, top_p, min_p, repetition_penalty, seed, initial_tokens=initial_token_ids[0], presence_penalty=presence_penalty, initial_input_ids=input_ids) + + +def gemma4_te(dtype_llama=None, llama_quantization_metadata=None, model_class=None): + clip_model = type('Gemma4Model_', (Gemma4Model,), {'model_class': model_class}) + class Gemma4TEModel_(sd1_clip.SD1ClipModel): + def __init__(self, device="cpu", dtype=None, model_options={}): + if llama_quantization_metadata is not None: + model_options = model_options.copy() + model_options["quantization_metadata"] = llama_quantization_metadata + if dtype_llama is not None: + dtype = dtype_llama + super().__init__(device=device, dtype=dtype, name="gemma4", clip_model=clip_model, model_options=model_options) + return Gemma4TEModel_ + + +# Variants + +def _make_variant(config_cls): + audio = config_cls.audio_config is not None + bases = (Gemma4AudioMixin, Gemma4Base) if audio else (Gemma4Base,) + class Variant(*bases): + def __init__(self, config_dict, dtype, device, operations): + super().__init__() + self._init_model(config_cls(**config_dict), dtype, device, operations) + if audio: + self._init_audio(self.model.config, dtype, device, operations) + embedding_size = config_cls.hidden_size + if embedding_size != Gemma4SDTokenizer.embedding_size: + tok_cls = type('T', (Gemma4SDTokenizer,), {'embedding_size': embedding_size}) + class Tokenizer(Gemma4Tokenizer): + tokenizer_class = tok_cls + Variant.tokenizer = Tokenizer + else: + Variant.tokenizer = Gemma4Tokenizer + return Variant + +Gemma4_E4B = _make_variant(Gemma4Config) +Gemma4_E2B = _make_variant(Gemma4_E2B_Config) +Gemma4_31B = _make_variant(Gemma4_31B_Config) diff --git a/comfy/text_encoders/llama.py b/comfy/text_encoders/llama.py index 06f2fbf74..a34c41144 100644 --- a/comfy/text_encoders/llama.py +++ b/comfy/text_encoders/llama.py @@ -60,6 +60,30 @@ class Mistral3Small24BConfig: final_norm: bool = True lm_head: bool = False +@dataclass +class Ministral3_3BConfig: + vocab_size: int = 131072 + hidden_size: int = 3072 + intermediate_size: int = 9216 + num_hidden_layers: int = 26 + num_attention_heads: int = 32 + num_key_value_heads: int = 8 + max_position_embeddings: int = 262144 + rms_norm_eps: float = 1e-5 + rope_theta: float = 1000000.0 + transformer_type: str = "llama" + head_dim = 128 + rms_norm_add = False + mlp_activation = "silu" + qkv_bias = False + rope_dims = None + q_norm = None + k_norm = None + rope_scale = None + final_norm: bool = True + lm_head: bool = False + stop_tokens = [2] + @dataclass class Qwen25_3BConfig: vocab_size: int = 151936 @@ -497,7 +521,7 @@ class Attention(nn.Module): else: present_key_value = (xk, xv, index + num_tokens) - if sliding_window is not None and xk.shape[2] > sliding_window: + if sliding_window is not None and xk.shape[2] > sliding_window and seq_length == 1: xk = xk[:, :, -sliding_window:] xv = xv[:, :, -sliding_window:] attention_mask = attention_mask[..., -sliding_window:] if attention_mask is not None else None @@ -509,12 +533,12 @@ class Attention(nn.Module): return self.o_proj(output), present_key_value class MLP(nn.Module): - def __init__(self, config: Llama2Config, device=None, dtype=None, ops: Any = None): + def __init__(self, config: Llama2Config, device=None, dtype=None, ops: Any = None, intermediate_size=None): super().__init__() - ops = ops or nn - self.gate_proj = ops.Linear(config.hidden_size, config.intermediate_size, bias=False, device=device, dtype=dtype) - self.up_proj = ops.Linear(config.hidden_size, config.intermediate_size, bias=False, device=device, dtype=dtype) - self.down_proj = ops.Linear(config.intermediate_size, config.hidden_size, bias=False, device=device, dtype=dtype) + intermediate_size = intermediate_size or config.intermediate_size + self.gate_proj = ops.Linear(config.hidden_size, intermediate_size, bias=False, device=device, dtype=dtype) + self.up_proj = ops.Linear(config.hidden_size, intermediate_size, bias=False, device=device, dtype=dtype) + self.down_proj = ops.Linear(intermediate_size, config.hidden_size, bias=False, device=device, dtype=dtype) if config.mlp_activation == "silu": self.activation = torch.nn.functional.silu elif config.mlp_activation == "gelu_pytorch_tanh": @@ -623,24 +647,25 @@ class TransformerBlockGemma2(nn.Module): return x, present_key_value +def _make_scaled_embedding(ops, vocab_size, hidden_size, scale, device, dtype): + class ScaledEmbedding(ops.Embedding): + def forward(self, input_ids, out_dtype=None): + return super().forward(input_ids, out_dtype=out_dtype) * scale + return ScaledEmbedding(vocab_size, hidden_size, device=device, dtype=dtype) + + class Llama2_(nn.Module): def __init__(self, config, device=None, dtype=None, ops=None): super().__init__() self.config = config self.vocab_size = config.vocab_size - self.embed_tokens = ops.Embedding( - config.vocab_size, - config.hidden_size, - device=device, - dtype=dtype - ) if self.config.transformer_type == "gemma2" or self.config.transformer_type == "gemma3": transformer = TransformerBlockGemma2 - self.normalize_in = True + self.embed_tokens = _make_scaled_embedding(ops, config.vocab_size, config.hidden_size, config.hidden_size ** 0.5, device, dtype) else: transformer = TransformerBlock - self.normalize_in = False + self.embed_tokens = ops.Embedding(config.vocab_size, config.hidden_size, device=device, dtype=dtype) self.layers = nn.ModuleList([ transformer(config, index=i, device=device, dtype=dtype, ops=ops) @@ -666,15 +691,12 @@ class Llama2_(nn.Module): self.config.rope_dims, device=device) - def forward(self, x, attention_mask=None, embeds=None, num_tokens=None, intermediate_output=None, final_layer_norm_intermediate=True, dtype=None, position_ids=None, embeds_info=[], past_key_values=None): + def forward(self, x, attention_mask=None, embeds=None, num_tokens=None, intermediate_output=None, final_layer_norm_intermediate=True, dtype=None, position_ids=None, embeds_info=[], past_key_values=None, input_ids=None): if embeds is not None: x = embeds else: x = self.embed_tokens(x, out_dtype=dtype) - if self.normalize_in: - x *= self.config.hidden_size ** 0.5 - seq_len = x.shape[1] past_len = 0 if past_key_values is not None and len(past_key_values) > 0: @@ -826,7 +848,7 @@ class BaseGenerate: torch.empty([batch, model_config.num_key_value_heads, max_cache_len, model_config.head_dim], device=device, dtype=execution_dtype), 0)) return past_key_values - def generate(self, embeds=None, do_sample=True, max_length=256, temperature=1.0, top_k=50, top_p=0.9, min_p=0.0, repetition_penalty=1.0, seed=42, stop_tokens=None, initial_tokens=[], execution_dtype=None, min_tokens=0, presence_penalty=0.0): + def generate(self, embeds=None, do_sample=True, max_length=256, temperature=1.0, top_k=50, top_p=0.9, min_p=0.0, repetition_penalty=1.0, seed=42, stop_tokens=None, initial_tokens=[], execution_dtype=None, min_tokens=0, presence_penalty=0.0, initial_input_ids=None): device = embeds.device if stop_tokens is None: @@ -851,14 +873,16 @@ class BaseGenerate: pbar = comfy.utils.ProgressBar(max_length) # Generation loop + current_input_ids = initial_input_ids for step in tqdm(range(max_length), desc="Generating tokens"): - x, _, past_key_values = self.model.forward(None, embeds=embeds, attention_mask=None, past_key_values=past_key_values) + x, _, past_key_values = self.model.forward(None, embeds=embeds, attention_mask=None, past_key_values=past_key_values, input_ids=current_input_ids) logits = self.logits(x)[:, -1] next_token = self.sample_token(logits, temperature, top_k, top_p, min_p, repetition_penalty, initial_tokens + generated_token_ids, generator, do_sample=do_sample, presence_penalty=presence_penalty) token_id = next_token[0].item() generated_token_ids.append(token_id) embeds = self.model.embed_tokens(next_token).to(execution_dtype) + current_input_ids = next_token if initial_input_ids is not None else None pbar.update(1) if token_id in stop_tokens: @@ -946,6 +970,15 @@ class Mistral3Small24B(BaseLlama, torch.nn.Module): self.model = Llama2_(config, device=device, dtype=dtype, ops=operations) self.dtype = dtype +class Ministral3_3B(BaseLlama, BaseQwen3, BaseGenerate, torch.nn.Module): + def __init__(self, config_dict, dtype, device, operations): + super().__init__() + config = Ministral3_3BConfig(**config_dict) + self.num_layers = config.num_hidden_layers + + self.model = Llama2_(config, device=device, dtype=dtype, ops=operations) + self.dtype = dtype + class Qwen25_3B(BaseLlama, torch.nn.Module): def __init__(self, config_dict, dtype, device, operations): super().__init__() diff --git a/comfy/text_encoders/lt.py b/comfy/text_encoders/lt.py index 5aee1f4c0..bc5cbae28 100644 --- a/comfy/text_encoders/lt.py +++ b/comfy/text_encoders/lt.py @@ -93,8 +93,7 @@ class Gemma3_12BModel(sd1_clip.SDClipModel): def generate(self, tokens, do_sample, max_length, temperature, top_k, top_p, min_p, repetition_penalty, seed, presence_penalty): tokens_only = [[t[0] for t in b] for b in tokens] - embeds, _, _, embeds_info = self.process_tokens(tokens_only, self.execution_device) - comfy.utils.normalize_image_embeddings(embeds, embeds_info, self.transformer.model.config.hidden_size ** 0.5) + embeds, _, _, _ = self.process_tokens(tokens_only, self.execution_device) return self.transformer.generate(embeds, do_sample, max_length, temperature, top_k, top_p, min_p, repetition_penalty, seed, stop_tokens=[106], presence_penalty=presence_penalty) # 106 is class DualLinearProjection(torch.nn.Module): diff --git a/comfy/text_encoders/lumina2.py b/comfy/text_encoders/lumina2.py index 01ebdfabe..b1f1dbb9f 100644 --- a/comfy/text_encoders/lumina2.py +++ b/comfy/text_encoders/lumina2.py @@ -50,8 +50,7 @@ class Gemma3_4B_Vision_Model(sd1_clip.SDClipModel): super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config={}, dtype=dtype, special_tokens={"start": 2, "pad": 0}, layer_norm_hidden_state=False, model_class=comfy.text_encoders.llama.Gemma3_4B_Vision, enable_attention_masks=attention_mask, return_attention_masks=attention_mask, model_options=model_options) def process_tokens(self, tokens, device): - embeds, _, _, embeds_info = super().process_tokens(tokens, device) - comfy.utils.normalize_image_embeddings(embeds, embeds_info, self.transformer.model.config.hidden_size ** 0.5) + embeds, _, _, _ = super().process_tokens(tokens, device) return embeds class LuminaModel(sd1_clip.SD1ClipModel): diff --git a/comfy/text_encoders/qwen35.py b/comfy/text_encoders/qwen35.py index ce9b07464..d8ed9cd32 100644 --- a/comfy/text_encoders/qwen35.py +++ b/comfy/text_encoders/qwen35.py @@ -408,8 +408,6 @@ class Qwen35Transformer(Llama2_): nn.Module.__init__(self) self.config = config self.vocab_size = config.vocab_size - self.normalize_in = False - self.embed_tokens = ops.Embedding(config.vocab_size, config.hidden_size, device=device, dtype=dtype) self.layers = nn.ModuleList([ Qwen35TransformerBlock(config, index=i, device=device, dtype=dtype, ops=ops) diff --git a/comfy/text_encoders/sam3_clip.py b/comfy/text_encoders/sam3_clip.py new file mode 100644 index 000000000..11cb7d9db --- /dev/null +++ b/comfy/text_encoders/sam3_clip.py @@ -0,0 +1,97 @@ +import re +from comfy import sd1_clip + +SAM3_CLIP_CONFIG = { + "architectures": ["CLIPTextModel"], + "hidden_act": "quick_gelu", + "hidden_size": 1024, + "intermediate_size": 4096, + "num_attention_heads": 16, + "num_hidden_layers": 24, + "max_position_embeddings": 32, + "projection_dim": 512, + "vocab_size": 49408, + "layer_norm_eps": 1e-5, + "eos_token_id": 49407, +} + + +class SAM3ClipModel(sd1_clip.SDClipModel): + def __init__(self, device="cpu", dtype=None, model_options={}): + super().__init__(device=device, dtype=dtype, max_length=32, layer="last", textmodel_json_config=SAM3_CLIP_CONFIG, special_tokens={"start": 49406, "end": 49407, "pad": 0}, return_projected_pooled=False, return_attention_masks=True, enable_attention_masks=True, model_options=model_options) + + +class SAM3Tokenizer(sd1_clip.SDTokenizer): + def __init__(self, embedding_directory=None, tokenizer_data={}): + super().__init__(max_length=32, pad_with_end=False, pad_token=0, embedding_directory=embedding_directory, embedding_size=1024, embedding_key="sam3_clip", tokenizer_data=tokenizer_data) + self.disable_weights = True + + +def _parse_prompts(text): + """Split comma-separated prompts with optional :N max detections per category""" + text = text.replace("(", "").replace(")", "") + parts = [p.strip() for p in text.split(",") if p.strip()] + result = [] + for part in parts: + m = re.match(r'^(.+?)\s*:\s*([\d.]+)\s*$', part) + if m: + text_part = m.group(1).strip() + val = m.group(2) + max_det = max(1, round(float(val))) + result.append((text_part, max_det)) + else: + result.append((part, 1)) + return result + + +class SAM3TokenizerWrapper(sd1_clip.SD1Tokenizer): + def __init__(self, embedding_directory=None, tokenizer_data={}): + super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, clip_name="l", tokenizer=SAM3Tokenizer, name="sam3_clip") + + def tokenize_with_weights(self, text: str, return_word_ids=False, **kwargs): + parsed = _parse_prompts(text) + if len(parsed) <= 1 and (not parsed or parsed[0][1] == 1): + return super().tokenize_with_weights(text, return_word_ids, **kwargs) + # Tokenize each prompt part separately, store per-part batches and metadata + inner = getattr(self, self.clip) + per_prompt = [] + for prompt_text, max_det in parsed: + batches = inner.tokenize_with_weights(prompt_text, return_word_ids, **kwargs) + per_prompt.append((batches, max_det)) + # Main output uses first prompt's tokens (for compatibility) + out = {self.clip_name: per_prompt[0][0], "sam3_per_prompt": per_prompt} + return out + + +class SAM3ClipModelWrapper(sd1_clip.SD1ClipModel): + def __init__(self, device="cpu", dtype=None, model_options={}, **kwargs): + super().__init__(device=device, dtype=dtype, model_options=model_options, clip_name="l", clip_model=SAM3ClipModel, name="sam3_clip") + + def encode_token_weights(self, token_weight_pairs): + per_prompt = token_weight_pairs.pop("sam3_per_prompt", None) + if per_prompt is None: + return super().encode_token_weights(token_weight_pairs) + + # Encode each prompt separately, pack into extra dict + inner = getattr(self, self.clip) + multi_cond = [] + first_pooled = None + for batches, max_det in per_prompt: + out = inner.encode_token_weights(batches) + cond, pooled = out[0], out[1] + extra = out[2] if len(out) > 2 else {} + if first_pooled is None: + first_pooled = pooled + multi_cond.append({ + "cond": cond, + "attention_mask": extra.get("attention_mask"), + "max_detections": max_det, + }) + + # Return first prompt as main (for non-SAM3 consumers), all prompts in metadata + main = multi_cond[0] + main_extra = {} + if main["attention_mask"] is not None: + main_extra["attention_mask"] = main["attention_mask"] + main_extra["sam3_multi_cond"] = multi_cond + return (main["cond"], first_pooled, main_extra) diff --git a/comfy/utils.py b/comfy/utils.py index 78c491b98..7b7faad3a 100644 --- a/comfy/utils.py +++ b/comfy/utils.py @@ -1446,10 +1446,3 @@ def deepcopy_list_dict(obj, memo=None): memo[obj_id] = res return res -def normalize_image_embeddings(embeds, embeds_info, scale_factor): - """Normalize image embeddings to match text embedding scale""" - for info in embeds_info: - if info.get("type") == "image": - start_idx = info["index"] - end_idx = start_idx + info["size"] - embeds[:, start_idx:end_idx, :] /= scale_factor diff --git a/comfy_api/input/__init__.py b/comfy_api/input/__init__.py index 16d4acfd1..dc33533cc 100644 --- a/comfy_api/input/__init__.py +++ b/comfy_api/input/__init__.py @@ -9,6 +9,7 @@ from comfy_api.latest._input import ( CurveInput, MonotoneCubicCurve, LinearCurve, + RangeInput, ) __all__ = [ @@ -21,4 +22,5 @@ __all__ = [ "CurveInput", "MonotoneCubicCurve", "LinearCurve", + "RangeInput", ] diff --git a/comfy_api/latest/_input/__init__.py b/comfy_api/latest/_input/__init__.py index 05cd3d40a..f0229717e 100644 --- a/comfy_api/latest/_input/__init__.py +++ b/comfy_api/latest/_input/__init__.py @@ -1,5 +1,6 @@ from .basic_types import ImageInput, AudioInput, MaskInput, LatentInput from .curve_types import CurvePoint, CurveInput, MonotoneCubicCurve, LinearCurve +from .range_types import RangeInput from .video_types import VideoInput __all__ = [ @@ -12,4 +13,5 @@ __all__ = [ "CurveInput", "MonotoneCubicCurve", "LinearCurve", + "RangeInput", ] diff --git a/comfy_api/latest/_input/range_types.py b/comfy_api/latest/_input/range_types.py new file mode 100644 index 000000000..f4c5cb290 --- /dev/null +++ b/comfy_api/latest/_input/range_types.py @@ -0,0 +1,70 @@ +from __future__ import annotations + +import logging +import math +import numpy as np + +logger = logging.getLogger(__name__) + + +class RangeInput: + """Represents a levels/range adjustment: input range [min, max] with + optional midpoint (gamma control). + + Generates a 1D LUT identical to GIMP's levels mapping: + 1. Normalize input to [0, 1] using [min, max] + 2. Apply gamma correction: pow(value, 1/gamma) + 3. Clamp to [0, 1] + + The midpoint field is a position in [0, 1] representing where the + midtone falls within [min, max]. It maps to gamma via: + gamma = -log2(midpoint) + So midpoint=0.5 → gamma=1.0 (linear). + """ + + def __init__(self, min_val: float, max_val: float, midpoint: float | None = None): + self.min_val = min_val + self.max_val = max_val + self.midpoint = midpoint + + @staticmethod + def from_raw(data) -> RangeInput: + if isinstance(data, RangeInput): + return data + if isinstance(data, dict): + return RangeInput( + min_val=float(data.get("min", 0.0)), + max_val=float(data.get("max", 1.0)), + midpoint=float(data["midpoint"]) if data.get("midpoint") is not None else None, + ) + raise TypeError(f"Cannot convert {type(data)} to RangeInput") + + def to_lut(self, size: int = 256) -> np.ndarray: + """Generate a float64 lookup table mapping [0, 1] input through this + levels adjustment. + + The LUT maps normalized input values (0..1) to output values (0..1), + matching the GIMP levels formula. + """ + xs = np.linspace(0.0, 1.0, size, dtype=np.float64) + + in_range = self.max_val - self.min_val + if abs(in_range) < 1e-10: + return np.where(xs >= self.min_val, 1.0, 0.0).astype(np.float64) + + # Normalize: map [min, max] → [0, 1] + result = (xs - self.min_val) / in_range + result = np.clip(result, 0.0, 1.0) + + # Gamma correction from midpoint + if self.midpoint is not None and self.midpoint > 0 and self.midpoint != 0.5: + gamma = max(-math.log2(self.midpoint), 0.001) + inv_gamma = 1.0 / gamma + mask = result > 0 + result[mask] = np.power(result[mask], inv_gamma) + + return result + + def __repr__(self) -> str: + mid = f", midpoint={self.midpoint}" if self.midpoint is not None else "" + return f"RangeInput(min={self.min_val}, max={self.max_val}{mid})" diff --git a/comfy_api/latest/_input_impl/video_types.py b/comfy_api/latest/_input_impl/video_types.py index 1b4993aa7..942278d88 100644 --- a/comfy_api/latest/_input_impl/video_types.py +++ b/comfy_api/latest/_input_impl/video_types.py @@ -12,6 +12,7 @@ import numpy as np import math import torch from .._util import VideoContainer, VideoCodec, VideoComponents +import logging def container_to_output_format(container_format: str | None) -> str | None: @@ -238,64 +239,125 @@ class VideoFromFile(VideoInput): start_time = max(self._get_raw_duration() + self.__start_time, 0) else: start_time = self.__start_time + # Get video frames frames = [] + audio_frames = [] + alphas = None start_pts = int(start_time / video_stream.time_base) end_pts = int((start_time + self.__duration) / video_stream.time_base) - container.seek(start_pts, stream=video_stream) - for frame in container.decode(video_stream): - if frame.pts < start_pts: - continue - if self.__duration and frame.pts >= end_pts: - break - img = frame.to_ndarray(format='rgb24') # shape: (H, W, 3) - img = torch.from_numpy(img) / 255.0 # shape: (H, W, 3) - frames.append(img) - images = torch.stack(frames) if len(frames) > 0 else torch.zeros(0, 3, 0, 0) + if start_pts != 0: + container.seek(start_pts, stream=video_stream) + + image_format = 'gbrpf32le' + process_image_format = lambda a: a + audio = None + + streams = [video_stream] + has_first_audio_frame = False + checked_alpha = False + + # Default to False so we decode until EOF if duration is 0 + video_done = False + audio_done = True + + if len(container.streams.audio): + audio_stream = container.streams.audio[-1] + streams += [audio_stream] + resampler = av.audio.resampler.AudioResampler(format='fltp') + audio_done = False + + for packet in container.demux(*streams): + if video_done and audio_done: + break + + if packet.stream.type == "video": + if video_done: + continue + try: + for frame in packet.decode(): + if frame.pts < start_pts: + continue + if self.__duration and frame.pts >= end_pts: + video_done = True + break + + if not checked_alpha: + alpha_channel = False + for comp in frame.format.components: + if comp.is_alpha or frame.format.name == "pal8": + alphas = [] + alpha_channel = True + break + if frame.format.name in ("yuvj420p", "yuvj422p", "yuvj444p", "rgb24", "rgba", "pal8"): + process_image_format = lambda a: a.float() / 255.0 + if alpha_channel: + image_format = 'rgba' + else: + image_format = 'rgb24' + else: + process_image_format = lambda a: a + if alpha_channel: + image_format = 'gbrapf32le' + else: + image_format = 'gbrpf32le' + + checked_alpha = True + + img = frame.to_ndarray(format=image_format) # shape: (H, W, 4) + if frame.rotation != 0: + k = int(round(frame.rotation // 90)) + img = np.rot90(img, k=k, axes=(0, 1)).copy() + if alphas is None: + frames.append(torch.from_numpy(img)) + else: + frames.append(torch.from_numpy(img[..., :-1])) + alphas.append(torch.from_numpy(img[..., -1:])) + except av.error.InvalidDataError: + logging.info("pyav decode error") + + elif packet.stream.type == "audio": + if audio_done: + continue + + aframes = itertools.chain.from_iterable( + map(resampler.resample, packet.decode()) + ) + for frame in aframes: + if self.__duration and frame.time > start_time + self.__duration: + audio_done = True + break + + if not has_first_audio_frame: + offset_seconds = start_time - frame.pts * audio_stream.time_base + to_skip = max(0, int(offset_seconds * audio_stream.sample_rate)) + if to_skip < frame.samples: + has_first_audio_frame = True + audio_frames.append(frame.to_ndarray()[..., to_skip:]) + else: + audio_frames.append(frame.to_ndarray()) + + images = process_image_format(torch.stack(frames)) if len(frames) > 0 else torch.zeros(0, 0, 0, 3) + if alphas is not None: + alphas = process_image_format(torch.stack(alphas)) if len(alphas) > 0 else torch.zeros(0, 0, 0, 1) # Get frame rate frame_rate = Fraction(video_stream.average_rate) if video_stream.average_rate else Fraction(1) - # Get audio if available - audio = None - container.seek(start_pts, stream=video_stream) - # Use last stream for consistency - if len(container.streams.audio): - audio_stream = container.streams.audio[-1] - audio_frames = [] - resample = av.audio.resampler.AudioResampler(format='fltp').resample - frames = itertools.chain.from_iterable( - map(resample, container.decode(audio_stream)) - ) + if len(audio_frames) > 0: + audio_data = np.concatenate(audio_frames, axis=1) # shape: (channels, total_samples) + if self.__duration: + audio_data = audio_data[..., :int(self.__duration * audio_stream.sample_rate)] - has_first_frame = False - for frame in frames: - offset_seconds = start_time - frame.pts * audio_stream.time_base - to_skip = max(0, int(offset_seconds * audio_stream.sample_rate)) - if to_skip < frame.samples: - has_first_frame = True - break - if has_first_frame: - audio_frames.append(frame.to_ndarray()[..., to_skip:]) - - for frame in frames: - if self.__duration and frame.time > start_time + self.__duration: - break - audio_frames.append(frame.to_ndarray()) # shape: (channels, samples) - if len(audio_frames) > 0: - audio_data = np.concatenate(audio_frames, axis=1) # shape: (channels, total_samples) - if self.__duration: - audio_data = audio_data[..., :int(self.__duration * audio_stream.sample_rate)] - - audio_tensor = torch.from_numpy(audio_data).unsqueeze(0) # shape: (1, channels, total_samples) - audio = AudioInput({ - "waveform": audio_tensor, - "sample_rate": int(audio_stream.sample_rate) if audio_stream.sample_rate else 1, - }) + audio_tensor = torch.from_numpy(audio_data).unsqueeze(0) # shape: (1, channels, total_samples) + audio = AudioInput({ + "waveform": audio_tensor, + "sample_rate": int(audio_stream.sample_rate) if audio_stream.sample_rate else 1, + }) metadata = container.metadata - return VideoComponents(images=images, audio=audio, frame_rate=frame_rate, metadata=metadata) + return VideoComponents(images=images, alpha=alphas, audio=audio, frame_rate=frame_rate, metadata=metadata) def get_components(self) -> VideoComponents: if isinstance(self.__file, io.BytesIO): diff --git a/comfy_api/latest/_io.py b/comfy_api/latest/_io.py index fdeffea2d..4942ed46c 100644 --- a/comfy_api/latest/_io.py +++ b/comfy_api/latest/_io.py @@ -1266,6 +1266,43 @@ class Histogram(ComfyTypeIO): Type = list[int] +@comfytype(io_type="RANGE") +class Range(ComfyTypeIO): + from comfy_api.input import RangeInput + if TYPE_CHECKING: + Type = RangeInput + + class Input(WidgetInput): + def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None, + socketless: bool=True, default: dict=None, + display: str=None, + gradient_stops: list=None, + show_midpoint: bool=None, + midpoint_scale: str=None, + value_min: float=None, + value_max: float=None, + advanced: bool=None): + super().__init__(id, display_name, optional, tooltip, None, default, socketless, None, None, None, None, advanced) + if default is None: + self.default = {"min": 0.0, "max": 1.0} + self.display = display + self.gradient_stops = gradient_stops + self.show_midpoint = show_midpoint + self.midpoint_scale = midpoint_scale + self.value_min = value_min + self.value_max = value_max + + def as_dict(self): + return super().as_dict() | prune_dict({ + "display": self.display, + "gradient_stops": self.gradient_stops, + "show_midpoint": self.show_midpoint, + "midpoint_scale": self.midpoint_scale, + "value_min": self.value_min, + "value_max": self.value_max, + }) + + DYNAMIC_INPUT_LOOKUP: dict[str, Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]] = {} def register_dynamic_input_func(io_type: str, func: Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]): DYNAMIC_INPUT_LOOKUP[io_type] = func @@ -2276,5 +2313,6 @@ __all__ = [ "BoundingBox", "Curve", "Histogram", + "Range", "NodeReplace", ] diff --git a/comfy_api/latest/_util/video_types.py b/comfy_api/latest/_util/video_types.py index fd3b5a510..c92477f08 100644 --- a/comfy_api/latest/_util/video_types.py +++ b/comfy_api/latest/_util/video_types.py @@ -3,7 +3,7 @@ from dataclasses import dataclass from enum import Enum from fractions import Fraction from typing import Optional -from .._input import ImageInput, AudioInput +from .._input import ImageInput, AudioInput, MaskInput class VideoCodec(str, Enum): AUTO = "auto" @@ -48,5 +48,4 @@ class VideoComponents: frame_rate: Fraction audio: Optional[AudioInput] = None metadata: Optional[dict] = None - - + alpha: Optional[MaskInput] = None diff --git a/comfy_api_nodes/apis/bytedance.py b/comfy_api_nodes/apis/bytedance.py index 18455396d..c05bd6893 100644 --- a/comfy_api_nodes/apis/bytedance.py +++ b/comfy_api_nodes/apis/bytedance.py @@ -52,6 +52,26 @@ class TaskImageContent(BaseModel): role: Literal["first_frame", "last_frame", "reference_image"] | None = Field(None) +class TaskVideoContentUrl(BaseModel): + url: str = Field(...) + + +class TaskVideoContent(BaseModel): + type: str = Field("video_url") + video_url: TaskVideoContentUrl = Field(...) + role: str = Field("reference_video") + + +class TaskAudioContentUrl(BaseModel): + url: str = Field(...) + + +class TaskAudioContent(BaseModel): + type: str = Field("audio_url") + audio_url: TaskAudioContentUrl = Field(...) + role: str = Field("reference_audio") + + class Text2VideoTaskCreationRequest(BaseModel): model: str = Field(...) content: list[TaskTextContent] = Field(..., min_length=1) @@ -64,6 +84,17 @@ class Image2VideoTaskCreationRequest(BaseModel): generate_audio: bool | None = Field(...) +class Seedance2TaskCreationRequest(BaseModel): + model: str = Field(...) + content: list[TaskTextContent | TaskImageContent | TaskVideoContent | TaskAudioContent] = Field(..., min_length=1) + generate_audio: bool | None = Field(None) + resolution: str | None = Field(None) + ratio: str | None = Field(None) + duration: int | None = Field(None, ge=4, le=15) + seed: int | None = Field(None, ge=0, le=2147483647) + watermark: bool | None = Field(None) + + class TaskCreationResponse(BaseModel): id: str = Field(...) @@ -77,12 +108,67 @@ class TaskStatusResult(BaseModel): video_url: str = Field(...) +class TaskStatusUsage(BaseModel): + completion_tokens: int = Field(0) + total_tokens: int = Field(0) + + class TaskStatusResponse(BaseModel): id: str = Field(...) model: str = Field(...) status: Literal["queued", "running", "cancelled", "succeeded", "failed"] = Field(...) error: TaskStatusError | None = Field(None) content: TaskStatusResult | None = Field(None) + usage: TaskStatusUsage | None = Field(None) + + +class GetAssetResponse(BaseModel): + id: str = Field(...) + name: str | None = Field(None) + url: str | None = Field(None) + asset_type: str = Field(...) + group_id: str = Field(...) + status: str = Field(...) + error: TaskStatusError | None = Field(None) + + +class SeedanceCreateVisualValidateSessionResponse(BaseModel): + session_id: str = Field(...) + h5_link: str = Field(...) + + +class SeedanceGetVisualValidateSessionResponse(BaseModel): + session_id: str = Field(...) + status: str = Field(...) + group_id: str | None = Field(None) + error_code: str | None = Field(None) + error_message: str | None = Field(None) + + +class SeedanceCreateAssetRequest(BaseModel): + group_id: str = Field(...) + url: str = Field(...) + asset_type: str = Field(...) + name: str | None = Field(None, max_length=64) + project_name: str | None = Field(None) + + +class SeedanceCreateAssetResponse(BaseModel): + asset_id: str = Field(...) + + +class SeedanceVirtualLibraryCreateAssetRequest(BaseModel): + url: str = Field(..., description="Publicly accessible URL of the image asset to upload.") + hash: str = Field(..., description="Dedup key. Re-submitting the same hash returns the existing asset id.") + + +# Dollars per 1K tokens, keyed by (model_id, has_video_input). +SEEDANCE2_PRICE_PER_1K_TOKENS = { + ("dreamina-seedance-2-0-260128", False): 0.007, + ("dreamina-seedance-2-0-260128", True): 0.0043, + ("dreamina-seedance-2-0-fast-260128", False): 0.0056, + ("dreamina-seedance-2-0-fast-260128", True): 0.0033, +} RECOMMENDED_PRESETS = [ @@ -112,6 +198,19 @@ RECOMMENDED_PRESETS_SEEDREAM_4 = [ ("Custom", None, None), ] +# Seedance 2.0 reference video pixel count limits per model and output resolution. +SEEDANCE2_REF_VIDEO_PIXEL_LIMITS = { + "dreamina-seedance-2-0-260128": { + "480p": {"min": 409_600, "max": 927_408}, + "720p": {"min": 409_600, "max": 927_408}, + "1080p": {"min": 409_600, "max": 2_073_600}, + }, + "dreamina-seedance-2-0-fast-260128": { + "480p": {"min": 409_600, "max": 927_408}, + "720p": {"min": 409_600, "max": 927_408}, + }, +} + # The time in this dictionary are given for 10 seconds duration. VIDEO_TASKS_EXECUTION_TIME = { "seedance-1-0-lite-t2v-250428": { diff --git a/comfy_api_nodes/apis/moonvalley.py b/comfy_api_nodes/apis/moonvalley.py deleted file mode 100644 index 7ec7a4ade..000000000 --- a/comfy_api_nodes/apis/moonvalley.py +++ /dev/null @@ -1,152 +0,0 @@ -from enum import Enum -from typing import Optional, Dict, Any - -from pydantic import BaseModel, Field, StrictBytes - - -class MoonvalleyPromptResponse(BaseModel): - error: Optional[Dict[str, Any]] = None - frame_conditioning: Optional[Dict[str, Any]] = None - id: Optional[str] = None - inference_params: Optional[Dict[str, Any]] = None - meta: Optional[Dict[str, Any]] = None - model_params: Optional[Dict[str, Any]] = None - output_url: Optional[str] = None - prompt_text: Optional[str] = None - status: Optional[str] = None - - -class MoonvalleyTextToVideoInferenceParams(BaseModel): - add_quality_guidance: Optional[bool] = Field( - True, description='Whether to add quality guidance' - ) - caching_coefficient: Optional[float] = Field( - 0.3, description='Caching coefficient for optimization' - ) - caching_cooldown: Optional[int] = Field( - 3, description='Number of caching cooldown steps' - ) - caching_warmup: Optional[int] = Field( - 3, description='Number of caching warmup steps' - ) - clip_value: Optional[float] = Field( - 3, description='CLIP value for generation control' - ) - conditioning_frame_index: Optional[int] = Field( - 0, description='Index of the conditioning frame' - ) - cooldown_steps: Optional[int] = Field( - 75, description='Number of cooldown steps (calculated based on num_frames)' - ) - fps: Optional[int] = Field( - 24, description='Frames per second of the generated video' - ) - guidance_scale: Optional[float] = Field( - 10, description='Guidance scale for generation control' - ) - height: Optional[int] = Field( - 1080, description='Height of the generated video in pixels' - ) - negative_prompt: Optional[str] = Field(None, description='Negative prompt text') - num_frames: Optional[int] = Field(64, description='Number of frames to generate') - seed: Optional[int] = Field( - None, description='Random seed for generation (default: random)' - ) - shift_value: Optional[float] = Field( - 3, description='Shift value for generation control' - ) - steps: Optional[int] = Field(80, description='Number of denoising steps') - use_guidance_schedule: Optional[bool] = Field( - True, description='Whether to use guidance scheduling' - ) - use_negative_prompts: Optional[bool] = Field( - False, description='Whether to use negative prompts' - ) - use_timestep_transform: Optional[bool] = Field( - True, description='Whether to use timestep transformation' - ) - warmup_steps: Optional[int] = Field( - 0, description='Number of warmup steps (calculated based on num_frames)' - ) - width: Optional[int] = Field( - 1920, description='Width of the generated video in pixels' - ) - - -class MoonvalleyTextToVideoRequest(BaseModel): - image_url: Optional[str] = None - inference_params: Optional[MoonvalleyTextToVideoInferenceParams] = None - prompt_text: Optional[str] = None - webhook_url: Optional[str] = None - - -class MoonvalleyUploadFileRequest(BaseModel): - file: Optional[StrictBytes] = None - - -class MoonvalleyUploadFileResponse(BaseModel): - access_url: Optional[str] = None - - -class MoonvalleyVideoToVideoInferenceParams(BaseModel): - add_quality_guidance: Optional[bool] = Field( - True, description='Whether to add quality guidance' - ) - caching_coefficient: Optional[float] = Field( - 0.3, description='Caching coefficient for optimization' - ) - caching_cooldown: Optional[int] = Field( - 3, description='Number of caching cooldown steps' - ) - caching_warmup: Optional[int] = Field( - 3, description='Number of caching warmup steps' - ) - clip_value: Optional[float] = Field( - 3, description='CLIP value for generation control' - ) - conditioning_frame_index: Optional[int] = Field( - 0, description='Index of the conditioning frame' - ) - cooldown_steps: Optional[int] = Field( - 36, description='Number of cooldown steps (calculated based on num_frames)' - ) - guidance_scale: Optional[float] = Field( - 15, description='Guidance scale for generation control' - ) - negative_prompt: Optional[str] = Field(None, description='Negative prompt text') - seed: Optional[int] = Field( - None, description='Random seed for generation (default: random)' - ) - shift_value: Optional[float] = Field( - 3, description='Shift value for generation control' - ) - steps: Optional[int] = Field(80, description='Number of denoising steps') - use_guidance_schedule: Optional[bool] = Field( - True, description='Whether to use guidance scheduling' - ) - use_negative_prompts: Optional[bool] = Field( - False, description='Whether to use negative prompts' - ) - use_timestep_transform: Optional[bool] = Field( - True, description='Whether to use timestep transformation' - ) - warmup_steps: Optional[int] = Field( - 24, description='Number of warmup steps (calculated based on num_frames)' - ) - - -class ControlType(str, Enum): - motion_control = 'motion_control' - pose_control = 'pose_control' - - -class MoonvalleyVideoToVideoRequest(BaseModel): - control_type: ControlType = Field( - ..., description='Supported types for video control' - ) - inference_params: Optional[MoonvalleyVideoToVideoInferenceParams] = None - prompt_text: str = Field(..., description='Describes the video to generate') - video_url: str = Field(..., description='Url to control video') - webhook_url: Optional[str] = Field( - None, description='Optional webhook URL for notifications' - ) diff --git a/comfy_api_nodes/apis/topaz.py b/comfy_api_nodes/apis/topaz.py index a9e6235a7..f91980e3d 100644 --- a/comfy_api_nodes/apis/topaz.py +++ b/comfy_api_nodes/apis/topaz.py @@ -1,4 +1,4 @@ -from typing import Optional, Union +from typing import Optional from pydantic import BaseModel, Field @@ -72,8 +72,11 @@ class VideoEnhancementFilter(BaseModel): grain: Optional[float] = Field(None, description="Grain after AI model processing") grainSize: Optional[float] = Field(None, description="Size of generated grain") recoverOriginalDetailValue: Optional[float] = Field(None, description="Source details into the output video") - creativity: Optional[str] = Field(None, description="Creativity level(high, low) for slc-1 only") + creativity: float | str | None = Field(None, description="slc-1/slp-2.5: enum (low/middle/high). ast-2: decimal 0.0-1.0.") isOptimizedMode: Optional[bool] = Field(None, description="Set to true for Starlight Creative (slc-1) only") + prompt: str | None = Field(None, description="Descriptive scene prompt (ast-2 only)") + sharp: float | None = Field(None, description="ast-2 pre-enhance sharpness") + realism: float | None = Field(None, description="ast-2 realism control") class OutputInformationVideo(BaseModel): @@ -90,7 +93,7 @@ class Overrides(BaseModel): class CreateVideoRequest(BaseModel): source: CreateVideoRequestSource = Field(...) - filters: list[Union[VideoFrameInterpolationFilter, VideoEnhancementFilter]] = Field(...) + filters: list[VideoFrameInterpolationFilter | VideoEnhancementFilter] = Field(...) output: OutputInformationVideo = Field(...) overrides: Overrides = Field(Overrides(isPaidDiffusion=True)) diff --git a/comfy_api_nodes/apis/wan.py b/comfy_api_nodes/apis/wan.py new file mode 100644 index 000000000..c64acae97 --- /dev/null +++ b/comfy_api_nodes/apis/wan.py @@ -0,0 +1,226 @@ +from pydantic import BaseModel, Field + + +class Text2ImageInputField(BaseModel): + prompt: str = Field(...) + negative_prompt: str | None = Field(None) + + +class Image2ImageInputField(BaseModel): + prompt: str = Field(...) + negative_prompt: str | None = Field(None) + images: list[str] = Field(..., min_length=1, max_length=2) + + +class Text2VideoInputField(BaseModel): + prompt: str = Field(...) + negative_prompt: str | None = Field(None) + audio_url: str | None = Field(None) + + +class Image2VideoInputField(BaseModel): + prompt: str = Field(...) + negative_prompt: str | None = Field(None) + img_url: str = Field(...) + audio_url: str | None = Field(None) + + +class Reference2VideoInputField(BaseModel): + prompt: str = Field(...) + negative_prompt: str | None = Field(None) + reference_video_urls: list[str] = Field(...) + + +class Txt2ImageParametersField(BaseModel): + size: str = Field(...) + n: int = Field(1, description="Number of images to generate.") # we support only value=1 + seed: int = Field(..., ge=0, le=2147483647) + prompt_extend: bool = Field(True) + watermark: bool = Field(False) + + +class Image2ImageParametersField(BaseModel): + size: str | None = Field(None) + n: int = Field(1, description="Number of images to generate.") # we support only value=1 + seed: int = Field(..., ge=0, le=2147483647) + watermark: bool = Field(False) + + +class Text2VideoParametersField(BaseModel): + size: str = Field(...) + seed: int = Field(..., ge=0, le=2147483647) + duration: int = Field(5, ge=5, le=15) + prompt_extend: bool = Field(True) + watermark: bool = Field(False) + audio: bool = Field(False, description="Whether to generate audio automatically.") + shot_type: str = Field("single") + + +class Image2VideoParametersField(BaseModel): + resolution: str = Field(...) + seed: int = Field(..., ge=0, le=2147483647) + duration: int = Field(5, ge=5, le=15) + prompt_extend: bool = Field(True) + watermark: bool = Field(False) + audio: bool = Field(False, description="Whether to generate audio automatically.") + shot_type: str = Field("single") + + +class Reference2VideoParametersField(BaseModel): + size: str = Field(...) + duration: int = Field(5, ge=5, le=15) + shot_type: str = Field("single") + seed: int = Field(..., ge=0, le=2147483647) + watermark: bool = Field(False) + + +class Text2ImageTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Text2ImageInputField = Field(...) + parameters: Txt2ImageParametersField = Field(...) + + +class Image2ImageTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Image2ImageInputField = Field(...) + parameters: Image2ImageParametersField = Field(...) + + +class Text2VideoTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Text2VideoInputField = Field(...) + parameters: Text2VideoParametersField = Field(...) + + +class Image2VideoTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Image2VideoInputField = Field(...) + parameters: Image2VideoParametersField = Field(...) + + +class Reference2VideoTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Reference2VideoInputField = Field(...) + parameters: Reference2VideoParametersField = Field(...) + + +class Wan27MediaItem(BaseModel): + type: str = Field(...) + url: str = Field(...) + + +class Wan27ReferenceVideoInputField(BaseModel): + prompt: str = Field(...) + negative_prompt: str | None = Field(None) + media: list[Wan27MediaItem] = Field(...) + + +class Wan27ReferenceVideoParametersField(BaseModel): + resolution: str = Field(...) + ratio: str | None = Field(None) + duration: int = Field(5, ge=2, le=15) + watermark: bool = Field(False) + seed: int = Field(..., ge=0, le=2147483647) + + +class Wan27ReferenceVideoTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Wan27ReferenceVideoInputField = Field(...) + parameters: Wan27ReferenceVideoParametersField = Field(...) + + +class Wan27ImageToVideoInputField(BaseModel): + prompt: str | None = Field(None) + negative_prompt: str | None = Field(None) + media: list[Wan27MediaItem] = Field(...) + + +class Wan27ImageToVideoParametersField(BaseModel): + resolution: str = Field(...) + duration: int = Field(5, ge=2, le=15) + prompt_extend: bool = Field(True) + watermark: bool = Field(False) + seed: int = Field(..., ge=0, le=2147483647) + + +class Wan27ImageToVideoTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Wan27ImageToVideoInputField = Field(...) + parameters: Wan27ImageToVideoParametersField = Field(...) + + +class Wan27VideoEditInputField(BaseModel): + prompt: str = Field(...) + media: list[Wan27MediaItem] = Field(...) + + +class Wan27VideoEditParametersField(BaseModel): + resolution: str = Field(...) + ratio: str | None = Field(None) + duration: int | None = Field(0) + audio_setting: str = Field("auto") + watermark: bool = Field(False) + seed: int = Field(..., ge=0, le=2147483647) + + +class Wan27VideoEditTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Wan27VideoEditInputField = Field(...) + parameters: Wan27VideoEditParametersField = Field(...) + + +class Wan27Text2VideoParametersField(BaseModel): + resolution: str = Field(...) + ratio: str | None = Field(None) + duration: int = Field(5, ge=2, le=15) + prompt_extend: bool = Field(True) + watermark: bool = Field(False) + seed: int = Field(..., ge=0, le=2147483647) + + +class Wan27Text2VideoTaskCreationRequest(BaseModel): + model: str = Field(...) + input: Text2VideoInputField = Field(...) + parameters: Wan27Text2VideoParametersField = Field(...) + + +class TaskCreationOutputField(BaseModel): + task_id: str = Field(...) + task_status: str = Field(...) + + +class TaskCreationResponse(BaseModel): + output: TaskCreationOutputField | None = Field(None) + request_id: str = Field(...) + code: str | None = Field(None, description="Error code for the failed request.") + message: str | None = Field(None, description="Details about the failed request.") + + +class TaskResult(BaseModel): + url: str | None = Field(None) + code: str | None = Field(None) + message: str | None = Field(None) + + +class ImageTaskStatusOutputField(TaskCreationOutputField): + task_id: str = Field(...) + task_status: str = Field(...) + results: list[TaskResult] | None = Field(None) + + +class VideoTaskStatusOutputField(TaskCreationOutputField): + task_id: str = Field(...) + task_status: str = Field(...) + video_url: str | None = Field(None) + code: str | None = Field(None) + message: str | None = Field(None) + + +class ImageTaskStatusResponse(BaseModel): + output: ImageTaskStatusOutputField | None = Field(None) + request_id: str = Field(...) + + +class VideoTaskStatusResponse(BaseModel): + output: VideoTaskStatusOutputField | None = Field(None) + request_id: str = Field(...) diff --git a/comfy_api_nodes/nodes_bytedance.py b/comfy_api_nodes/nodes_bytedance.py index de0c22e70..2f241a775 100644 --- a/comfy_api_nodes/nodes_bytedance.py +++ b/comfy_api_nodes/nodes_bytedance.py @@ -1,5 +1,7 @@ +import hashlib import logging import math +import re import torch from typing_extensions import override @@ -8,16 +10,29 @@ from comfy_api.latest import IO, ComfyExtension, Input from comfy_api_nodes.apis.bytedance import ( RECOMMENDED_PRESETS, RECOMMENDED_PRESETS_SEEDREAM_4, + SEEDANCE2_PRICE_PER_1K_TOKENS, + SEEDANCE2_REF_VIDEO_PIXEL_LIMITS, VIDEO_TASKS_EXECUTION_TIME, + GetAssetResponse, Image2VideoTaskCreationRequest, ImageTaskCreationResponse, + Seedance2TaskCreationRequest, + SeedanceCreateAssetRequest, + SeedanceCreateAssetResponse, + SeedanceCreateVisualValidateSessionResponse, + SeedanceGetVisualValidateSessionResponse, + SeedanceVirtualLibraryCreateAssetRequest, Seedream4Options, Seedream4TaskCreationRequest, + TaskAudioContent, + TaskAudioContentUrl, TaskCreationResponse, TaskImageContent, TaskImageContentUrl, TaskStatusResponse, TaskTextContent, + TaskVideoContent, + TaskVideoContentUrl, Text2ImageTaskCreationRequest, Text2VideoTaskCreationRequest, ) @@ -28,15 +43,25 @@ from comfy_api_nodes.util import ( get_number_of_images, image_tensor_pair_to_batch, poll_op, + resize_video_to_pixel_budget, sync_op, + upload_audio_to_comfyapi, + upload_image_to_comfyapi, upload_images_to_comfyapi, + upload_video_to_comfyapi, validate_image_aspect_ratio, validate_image_dimensions, validate_string, + validate_video_dimensions, + validate_video_duration, ) +from server import PromptServer BYTEPLUS_IMAGE_ENDPOINT = "/proxy/byteplus/api/v3/images/generations" +_VERIFICATION_POLL_TIMEOUT_SEC = 120 +_VERIFICATION_POLL_INTERVAL_SEC = 3 + SEEDREAM_MODELS = { "seedream 5.0 lite": "seedream-5-0-260128", "seedream-4-5-251128": "seedream-4-5-251128", @@ -46,12 +71,246 @@ SEEDREAM_MODELS = { # Long-running tasks endpoints(e.g., video) BYTEPLUS_TASK_ENDPOINT = "/proxy/byteplus/api/v3/contents/generations/tasks" BYTEPLUS_TASK_STATUS_ENDPOINT = "/proxy/byteplus/api/v3/contents/generations/tasks" # + /{task_id} +BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT = "/proxy/byteplus-seedance2/api/v3/contents/generations/tasks" # + /{task_id} + +SEEDANCE_MODELS = { + "Seedance 2.0": "dreamina-seedance-2-0-260128", + "Seedance 2.0 Fast": "dreamina-seedance-2-0-fast-260128", +} DEPRECATED_MODELS = {"seedance-1-0-lite-t2v-250428", "seedance-1-0-lite-i2v-250428"} + logger = logging.getLogger(__name__) +def _validate_ref_video_pixels(video: Input.Video, model_id: str, resolution: str, index: int) -> None: + """Validate reference video pixel count against Seedance 2.0 model limits for the selected resolution.""" + model_limits = SEEDANCE2_REF_VIDEO_PIXEL_LIMITS.get(model_id) + if not model_limits: + return + limits = model_limits.get(resolution) + if not limits: + return + try: + w, h = video.get_dimensions() + except Exception: + return + pixels = w * h + min_px = limits.get("min") + max_px = limits.get("max") + if min_px and pixels < min_px: + raise ValueError( + f"Reference video {index} is too small: {w}x{h} = {pixels:,}px. " f"Minimum is {min_px:,}px for this model." + ) + if max_px and pixels > max_px: + raise ValueError( + f"Reference video {index} is too large: {w}x{h} = {pixels:,}px. " + f"Maximum is {max_px:,}px for this model. Try downscaling the video." + ) + + +async def _resolve_reference_assets( + cls: type[IO.ComfyNode], + asset_ids: list[str], +) -> tuple[dict[str, str], dict[str, str], dict[str, str]]: + """Look up each asset, validate Active status, group by asset_type. + + Returns (image_assets, video_assets, audio_assets), each mapping asset_id -> "asset://". + """ + image_assets: dict[str, str] = {} + video_assets: dict[str, str] = {} + audio_assets: dict[str, str] = {} + for i, raw_id in enumerate(asset_ids, 1): + asset_id = (raw_id or "").strip() + if not asset_id: + continue + result = await sync_op( + cls, + ApiEndpoint(path=f"/proxy/seedance/assets/{asset_id}"), + response_model=GetAssetResponse, + ) + if result.status != "Active": + extra = f" {result.error.code}: {result.error.message}" if result.error else "" + raise ValueError(f"Reference asset {i} (Id={asset_id}) is not Active (Status={result.status}).{extra}") + asset_uri = f"asset://{asset_id}" + if result.asset_type == "Image": + image_assets[asset_id] = asset_uri + elif result.asset_type == "Video": + video_assets[asset_id] = asset_uri + elif result.asset_type == "Audio": + audio_assets[asset_id] = asset_uri + return image_assets, video_assets, audio_assets + + +_ASSET_REF_RE = re.compile(r"\basset ?(\d{1,2})\b", re.IGNORECASE) + + +def _build_asset_labels( + reference_assets: dict[str, str], + image_asset_uris: dict[str, str], + video_asset_uris: dict[str, str], + audio_asset_uris: dict[str, str], + n_reference_images: int, + n_reference_videos: int, + n_reference_audios: int, +) -> dict[int, str]: + """Map asset slot number (from 'asset_N' keys) to its positional label. + + Asset entries are appended to `content` after the reference_images/videos/audios, + so their 1-indexed labels continue from the count of existing same-type refs: + one reference_images entry + one Image-type asset -> asset labelled "Image 2". + """ + image_n = n_reference_images + video_n = n_reference_videos + audio_n = n_reference_audios + labels: dict[int, str] = {} + for slot_key, raw_id in reference_assets.items(): + asset_id = (raw_id or "").strip() + if not asset_id: + continue + try: + slot_num = int(slot_key.rsplit("_", 1)[-1]) + except ValueError: + continue + if asset_id in image_asset_uris: + image_n += 1 + labels[slot_num] = f"Image {image_n}" + elif asset_id in video_asset_uris: + video_n += 1 + labels[slot_num] = f"Video {video_n}" + elif asset_id in audio_asset_uris: + audio_n += 1 + labels[slot_num] = f"Audio {audio_n}" + return labels + + +def _rewrite_asset_refs(prompt: str, labels: dict[int, str]) -> str: + """Case-insensitively replace 'assetNN' (1-2 digit) tokens with their labels.""" + if not labels: + return prompt + + def _sub(m: "re.Match[str]") -> str: + return labels.get(int(m.group(1)), m.group(0)) + + return _ASSET_REF_RE.sub(_sub, prompt) + + +async def _obtain_group_id_via_h5_auth(cls: type[IO.ComfyNode]) -> str: + session = await sync_op( + cls, + ApiEndpoint(path="/proxy/seedance/visual-validate/sessions", method="POST"), + response_model=SeedanceCreateVisualValidateSessionResponse, + ) + logger.warning("Seedance authentication required. Open link: %s", session.h5_link) + + h5_text = f"Open this link in your browser and complete face verification:\n\n{session.h5_link}" + + result = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/seedance/visual-validate/sessions/{session.session_id}"), + response_model=SeedanceGetVisualValidateSessionResponse, + status_extractor=lambda r: r.status, + completed_statuses=["completed"], + failed_statuses=["failed"], + poll_interval=_VERIFICATION_POLL_INTERVAL_SEC, + max_poll_attempts=(_VERIFICATION_POLL_TIMEOUT_SEC // _VERIFICATION_POLL_INTERVAL_SEC) - 1, + estimated_duration=_VERIFICATION_POLL_TIMEOUT_SEC - 1, + extra_text=h5_text, + ) + + if not result.group_id: + raise RuntimeError(f"Seedance session {session.session_id} completed without a group_id") + + logger.warning("Seedance authentication complete. New GroupId: %s", result.group_id) + PromptServer.instance.send_progress_text( + f"Authentication complete. New GroupId: {result.group_id}", cls.hidden.unique_id + ) + return result.group_id + + +async def _resolve_group_id(cls: type[IO.ComfyNode], group_id: str) -> str: + if group_id and group_id.strip(): + return group_id.strip() + return await _obtain_group_id_via_h5_auth(cls) + + +async def _create_seedance_asset( + cls: type[IO.ComfyNode], + *, + group_id: str, + url: str, + name: str, + asset_type: str, +) -> str: + req = SeedanceCreateAssetRequest( + group_id=group_id, + url=url, + asset_type=asset_type, + name=name or None, + ) + result = await sync_op( + cls, + ApiEndpoint(path="/proxy/seedance/assets", method="POST"), + response_model=SeedanceCreateAssetResponse, + data=req, + ) + return result.asset_id + + +async def _wait_for_asset_active(cls: type[IO.ComfyNode], asset_id: str, group_id: str) -> GetAssetResponse: + """Poll the newly created asset until its status becomes Active.""" + return await poll_op( + cls, + ApiEndpoint(path=f"/proxy/seedance/assets/{asset_id}"), + response_model=GetAssetResponse, + status_extractor=lambda r: r.status, + completed_statuses=["Active"], + failed_statuses=["Failed"], + poll_interval=5, + max_poll_attempts=1200, + extra_text=f"Waiting for asset pre-processing...\n\nasset_id: {asset_id}\n\ngroup_id: {group_id}", + ) + + +async def _seedance_virtual_library_upload_image_asset( + cls: type[IO.ComfyNode], + image: torch.Tensor, + *, + wait_label: str = "Uploading image", +) -> str: + """Upload an image into the caller's per-customer Seedance virtual library.""" + public_url = await upload_image_to_comfyapi(cls, image, wait_label=wait_label) + normalized = image.detach().cpu().contiguous().to(torch.float32) + digest = hashlib.sha256() + digest.update(str(tuple(normalized.shape)).encode("utf-8")) + digest.update(b"\0") + digest.update(normalized.numpy().tobytes()) + image_hash = digest.hexdigest() + create_resp = await sync_op( + cls, + ApiEndpoint(path="/proxy/seedance/virtual-library/assets", method="POST"), + response_model=SeedanceCreateAssetResponse, + data=SeedanceVirtualLibraryCreateAssetRequest(url=public_url, hash=image_hash), + ) + await _wait_for_asset_active(cls, create_resp.asset_id, group_id="virtual-library") + return f"asset://{create_resp.asset_id}" + + +def _seedance2_price_extractor(model_id: str, has_video_input: bool): + """Returns a price_extractor closure for Seedance 2.0 poll_op.""" + rate = SEEDANCE2_PRICE_PER_1K_TOKENS.get((model_id, has_video_input)) + if rate is None: + return None + + def extractor(response: TaskStatusResponse) -> float | None: + if response.usage is None: + return None + return response.usage.total_tokens * 1.43 * rate / 1_000.0 + + return extractor + + def get_image_url_from_response(response: ImageTaskCreationResponse) -> str: if response.error: error_msg = f"ByteDance request failed. Code: {response.error['code']}, message: {response.error['message']}" @@ -335,8 +594,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode): mp_provided = out_num_pixels / 1_000_000.0 if ("seedream-4-5" in model or "seedream-5-0" in model) and out_num_pixels < 3686400: raise ValueError( - f"Minimum image resolution for the selected model is 3.68MP, " - f"but {mp_provided:.2f}MP provided." + f"Minimum image resolution for the selected model is 3.68MP, " f"but {mp_provided:.2f}MP provided." ) if "seedream-4-0" in model and out_num_pixels < 921600: raise ValueError( @@ -952,33 +1210,6 @@ class ByteDanceImageReferenceNode(IO.ComfyNode): ) -async def process_video_task( - cls: type[IO.ComfyNode], - payload: Text2VideoTaskCreationRequest | Image2VideoTaskCreationRequest, - estimated_duration: int | None, -) -> IO.NodeOutput: - if payload.model in DEPRECATED_MODELS: - logger.warning( - "Model '%s' is deprecated and will be deactivated on May 13, 2026. " - "Please switch to a newer model. Recommended: seedance-1-0-pro-fast-251015.", - payload.model, - ) - initial_response = await sync_op( - cls, - ApiEndpoint(path=BYTEPLUS_TASK_ENDPOINT, method="POST"), - data=payload, - response_model=TaskCreationResponse, - ) - response = await poll_op( - cls, - ApiEndpoint(path=f"{BYTEPLUS_TASK_STATUS_ENDPOINT}/{initial_response.id}"), - status_extractor=lambda r: r.status, - estimated_duration=estimated_duration, - response_model=TaskStatusResponse, - ) - return IO.NodeOutput(await download_url_to_video_output(response.content.video_url)) - - def raise_if_text_params(prompt: str, text_params: list[str]) -> None: for i in text_params: if f"--{i} " in prompt: @@ -1040,6 +1271,821 @@ PRICE_BADGE_VIDEO = IO.PriceBadge( ) +def _seedance2_text_inputs(resolutions: list[str]): + return [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Text prompt for video generation.", + ), + IO.Combo.Input( + "resolution", + options=resolutions, + tooltip="Resolution of the output video.", + ), + IO.Combo.Input( + "ratio", + options=["16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive"], + tooltip="Aspect ratio of the output video.", + ), + IO.Int.Input( + "duration", + default=7, + min=4, + max=15, + step=1, + tooltip="Duration of the output video in seconds (4-15).", + display_mode=IO.NumberDisplay.slider, + ), + IO.Boolean.Input( + "generate_audio", + default=True, + tooltip="Enable audio generation for the output video.", + ), + ] + + +class ByteDance2TextToVideoNode(IO.ComfyNode): + + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="ByteDance2TextToVideoNode", + display_name="ByteDance Seedance 2.0 Text to Video", + category="api node/video/ByteDance", + description="Generate video using Seedance 2.0 models based on a text prompt.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option("Seedance 2.0", _seedance2_text_inputs(["480p", "720p", "1080p"])), + IO.DynamicCombo.Option("Seedance 2.0 Fast", _seedance2_text_inputs(["480p", "720p"])), + ], + tooltip="Seedance 2.0 for maximum quality; Seedance 2.0 Fast for speed optimization.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed controls whether the node should re-run; " + "results are non-deterministic regardless of seed.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add a watermark to the video.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $rate480 := 10044; + $rate720 := 21600; + $rate1080 := 48800; + $m := widgets.model; + $pricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001; + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $rate := $res = "1080p" ? $rate1080 : + $res = "720p" ? $rate720 : + $rate480; + $cost := $dur * $rate * $pricePer1K / 1000; + {"type": "usd", "usd": $cost, "format": {"approximate": true}} + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + seed: int, + watermark: bool, + ) -> IO.NodeOutput: + validate_string(model["prompt"], strip_whitespace=True, min_length=1) + model_id = SEEDANCE_MODELS[model["model"]] + initial_response = await sync_op( + cls, + ApiEndpoint(path=BYTEPLUS_TASK_ENDPOINT, method="POST"), + data=Seedance2TaskCreationRequest( + model=model_id, + content=[TaskTextContent(text=model["prompt"])], + generate_audio=model["generate_audio"], + resolution=model["resolution"], + ratio=model["ratio"], + duration=model["duration"], + seed=seed, + watermark=watermark, + ), + response_model=TaskCreationResponse, + ) + response = await poll_op( + cls, + ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"), + response_model=TaskStatusResponse, + status_extractor=lambda r: r.status, + price_extractor=_seedance2_price_extractor(model_id, has_video_input=False), + poll_interval=9, + ) + return IO.NodeOutput(await download_url_to_video_output(response.content.video_url)) + + +class ByteDance2FirstLastFrameNode(IO.ComfyNode): + + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="ByteDance2FirstLastFrameNode", + display_name="ByteDance Seedance 2.0 First-Last-Frame to Video", + category="api node/video/ByteDance", + description="Generate video using Seedance 2.0 from a first frame image and optional last frame image.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option("Seedance 2.0", _seedance2_text_inputs(["480p", "720p", "1080p"])), + IO.DynamicCombo.Option("Seedance 2.0 Fast", _seedance2_text_inputs(["480p", "720p"])), + ], + tooltip="Seedance 2.0 for maximum quality; Seedance 2.0 Fast for speed optimization.", + ), + IO.Image.Input( + "first_frame", + tooltip="First frame image for the video.", + optional=True, + ), + IO.Image.Input( + "last_frame", + tooltip="Last frame image for the video.", + optional=True, + ), + IO.String.Input( + "first_frame_asset_id", + default="", + tooltip="Seedance asset_id to use as the first frame. " + "Mutually exclusive with the first_frame image input.", + optional=True, + ), + IO.String.Input( + "last_frame_asset_id", + default="", + tooltip="Seedance asset_id to use as the last frame. " + "Mutually exclusive with the last_frame image input.", + optional=True, + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed controls whether the node should re-run; " + "results are non-deterministic regardless of seed.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add a watermark to the video.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $rate480 := 10044; + $rate720 := 21600; + $rate1080 := 48800; + $m := widgets.model; + $pricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001; + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $rate := $res = "1080p" ? $rate1080 : + $res = "720p" ? $rate720 : + $rate480; + $cost := $dur * $rate * $pricePer1K / 1000; + {"type": "usd", "usd": $cost, "format": {"approximate": true}} + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + seed: int, + watermark: bool, + first_frame: Input.Image | None = None, + last_frame: Input.Image | None = None, + first_frame_asset_id: str = "", + last_frame_asset_id: str = "", + ) -> IO.NodeOutput: + validate_string(model["prompt"], strip_whitespace=True, min_length=1) + model_id = SEEDANCE_MODELS[model["model"]] + + first_frame_asset_id = first_frame_asset_id.strip() + last_frame_asset_id = last_frame_asset_id.strip() + + if first_frame is not None and first_frame_asset_id: + raise ValueError("Provide only one of first_frame or first_frame_asset_id, not both.") + if first_frame is None and not first_frame_asset_id: + raise ValueError("Either first_frame or first_frame_asset_id is required.") + if last_frame is not None and last_frame_asset_id: + raise ValueError("Provide only one of last_frame or last_frame_asset_id, not both.") + + asset_ids_to_resolve = [a for a in (first_frame_asset_id, last_frame_asset_id) if a] + image_assets: dict[str, str] = {} + if asset_ids_to_resolve: + image_assets, _, _ = await _resolve_reference_assets(cls, asset_ids_to_resolve) + for aid in asset_ids_to_resolve: + if aid not in image_assets: + raise ValueError(f"Asset {aid} is not an Image asset.") + + if first_frame_asset_id: + first_frame_url = image_assets[first_frame_asset_id] + else: + first_frame_url = await _seedance_virtual_library_upload_image_asset( + cls, first_frame, wait_label="Uploading first frame." + ) + + content: list[TaskTextContent | TaskImageContent] = [ + TaskTextContent(text=model["prompt"]), + TaskImageContent( + image_url=TaskImageContentUrl(url=first_frame_url), + role="first_frame", + ), + ] + if last_frame_asset_id: + content.append( + TaskImageContent( + image_url=TaskImageContentUrl(url=image_assets[last_frame_asset_id]), + role="last_frame", + ), + ) + elif last_frame is not None: + content.append( + TaskImageContent( + image_url=TaskImageContentUrl( + url=await _seedance_virtual_library_upload_image_asset( + cls, last_frame, wait_label="Uploading last frame." + ) + ), + role="last_frame", + ), + ) + + initial_response = await sync_op( + cls, + ApiEndpoint(path=BYTEPLUS_TASK_ENDPOINT, method="POST"), + data=Seedance2TaskCreationRequest( + model=model_id, + content=content, + generate_audio=model["generate_audio"], + resolution=model["resolution"], + ratio=model["ratio"], + duration=model["duration"], + seed=seed, + watermark=watermark, + ), + response_model=TaskCreationResponse, + ) + response = await poll_op( + cls, + ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"), + response_model=TaskStatusResponse, + status_extractor=lambda r: r.status, + price_extractor=_seedance2_price_extractor(model_id, has_video_input=False), + poll_interval=9, + ) + return IO.NodeOutput(await download_url_to_video_output(response.content.video_url)) + + +def _seedance2_reference_inputs(resolutions: list[str]): + return [ + *_seedance2_text_inputs(resolutions), + IO.Autogrow.Input( + "reference_images", + template=IO.Autogrow.TemplateNames( + IO.Image.Input("reference_image"), + names=[ + "image_1", + "image_2", + "image_3", + "image_4", + "image_5", + "image_6", + "image_7", + "image_8", + "image_9", + ], + min=0, + ), + ), + IO.Autogrow.Input( + "reference_videos", + template=IO.Autogrow.TemplateNames( + IO.Video.Input("reference_video"), + names=["video_1", "video_2", "video_3"], + min=0, + ), + ), + IO.Autogrow.Input( + "reference_audios", + template=IO.Autogrow.TemplateNames( + IO.Audio.Input("reference_audio"), + names=["audio_1", "audio_2", "audio_3"], + min=0, + ), + ), + IO.Boolean.Input( + "auto_downscale", + default=False, + advanced=True, + optional=True, + tooltip="Automatically downscale reference videos that exceed the model's pixel budget " + "for the selected resolution. Aspect ratio is preserved; videos already within limits are untouched.", + ), + IO.Autogrow.Input( + "reference_assets", + template=IO.Autogrow.TemplateNames( + IO.String.Input("reference_asset"), + names=[ + "asset_1", + "asset_2", + "asset_3", + "asset_4", + "asset_5", + "asset_6", + "asset_7", + "asset_8", + "asset_9", + ], + min=0, + ), + ), + ] + + +class ByteDance2ReferenceNode(IO.ComfyNode): + + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="ByteDance2ReferenceNode", + display_name="ByteDance Seedance 2.0 Reference to Video", + category="api node/video/ByteDance", + description="Generate, edit, or extend video using Seedance 2.0 with reference images, " + "videos, and audio. Supports multimodal reference, video editing, and video extension.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option("Seedance 2.0", _seedance2_reference_inputs(["480p", "720p", "1080p"])), + IO.DynamicCombo.Option("Seedance 2.0 Fast", _seedance2_reference_inputs(["480p", "720p"])), + ], + tooltip="Seedance 2.0 for maximum quality; Seedance 2.0 Fast for speed optimization.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed controls whether the node should re-run; " + "results are non-deterministic regardless of seed.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add a watermark to the video.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends( + widgets=["model", "model.resolution", "model.duration"], + input_groups=["model.reference_videos"], + ), + expr=""" + ( + $rate480 := 10044; + $rate720 := 21600; + $rate1080 := 48800; + $m := widgets.model; + $hasVideo := $lookup(inputGroups, "model.reference_videos") > 0; + $noVideoPricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001; + $videoPricePer1K := $contains($m, "fast") ? 0.004719 : 0.006149; + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $rate := $res = "1080p" ? $rate1080 : + $res = "720p" ? $rate720 : + $rate480; + $noVideoCost := $dur * $rate * $noVideoPricePer1K / 1000; + $minVideoFactor := $ceil($dur * 5 / 3); + $minVideoCost := $minVideoFactor * $rate * $videoPricePer1K / 1000; + $maxVideoCost := (15 + $dur) * $rate * $videoPricePer1K / 1000; + $hasVideo + ? { + "type": "range_usd", + "min_usd": $minVideoCost, + "max_usd": $maxVideoCost, + "format": {"approximate": true} + } + : { + "type": "usd", + "usd": $noVideoCost, + "format": {"approximate": true} + } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + seed: int, + watermark: bool, + ) -> IO.NodeOutput: + validate_string(model["prompt"], strip_whitespace=True, min_length=1) + + reference_images = model.get("reference_images", {}) + reference_videos = model.get("reference_videos", {}) + reference_audios = model.get("reference_audios", {}) + reference_assets = model.get("reference_assets", {}) + + reference_image_assets, reference_video_assets, reference_audio_assets = await _resolve_reference_assets( + cls, list(reference_assets.values()) + ) + + if not reference_images and not reference_videos and not reference_image_assets and not reference_video_assets: + raise ValueError("At least one reference image or video or asset is required.") + + total_images = len(reference_images) + len(reference_image_assets) + if total_images > 9: + raise ValueError( + f"Too many reference images: {total_images} " + f"(images={len(reference_images)}, image assets={len(reference_image_assets)}). Maximum is 9." + ) + total_videos = len(reference_videos) + len(reference_video_assets) + if total_videos > 3: + raise ValueError( + f"Too many reference videos: {total_videos} " + f"(videos={len(reference_videos)}, video assets={len(reference_video_assets)}). Maximum is 3." + ) + total_audios = len(reference_audios) + len(reference_audio_assets) + if total_audios > 3: + raise ValueError( + f"Too many reference audios: {total_audios} " + f"(audios={len(reference_audios)}, audio assets={len(reference_audio_assets)}). Maximum is 3." + ) + + model_id = SEEDANCE_MODELS[model["model"]] + has_video_input = total_videos > 0 + + if model.get("auto_downscale") and reference_videos: + max_px = SEEDANCE2_REF_VIDEO_PIXEL_LIMITS.get(model_id, {}).get(model["resolution"], {}).get("max") + if max_px: + for key in reference_videos: + reference_videos[key] = resize_video_to_pixel_budget(reference_videos[key], max_px) + + total_video_duration = 0.0 + for i, key in enumerate(reference_videos, 1): + video = reference_videos[key] + _validate_ref_video_pixels(video, model_id, model["resolution"], i) + try: + dur = video.get_duration() + if dur < 1.8: + raise ValueError(f"Reference video {i} is too short: {dur:.1f}s. Minimum duration is 1.8 seconds.") + total_video_duration += dur + except ValueError: + raise + except Exception: + pass + if total_video_duration > 15.1: + raise ValueError(f"Total reference video duration is {total_video_duration:.1f}s. Maximum is 15.1 seconds.") + + total_audio_duration = 0.0 + for i, key in enumerate(reference_audios, 1): + audio = reference_audios[key] + dur = int(audio["waveform"].shape[-1]) / int(audio["sample_rate"]) + if dur < 1.8: + raise ValueError(f"Reference audio {i} is too short: {dur:.1f}s. Minimum duration is 1.8 seconds.") + total_audio_duration += dur + if total_audio_duration > 15.1: + raise ValueError(f"Total reference audio duration is {total_audio_duration:.1f}s. Maximum is 15.1 seconds.") + + asset_labels = _build_asset_labels( + reference_assets, + reference_image_assets, + reference_video_assets, + reference_audio_assets, + len(reference_images), + len(reference_videos), + len(reference_audios), + ) + prompt_text = _rewrite_asset_refs(model["prompt"], asset_labels) + + content: list[TaskTextContent | TaskImageContent | TaskVideoContent | TaskAudioContent] = [ + TaskTextContent(text=prompt_text), + ] + for i, key in enumerate(reference_images, 1): + content.append( + TaskImageContent( + image_url=TaskImageContentUrl( + url=await _seedance_virtual_library_upload_image_asset( + cls, + reference_images[key], + wait_label=f"Uploading image {i}", + ), + ), + role="reference_image", + ), + ) + for i, key in enumerate(reference_videos, 1): + content.append( + TaskVideoContent( + video_url=TaskVideoContentUrl( + url=await upload_video_to_comfyapi( + cls, + reference_videos[key], + wait_label=f"Uploading video {i}", + ), + ), + ), + ) + for key in reference_audios: + content.append( + TaskAudioContent( + audio_url=TaskAudioContentUrl( + url=await upload_audio_to_comfyapi( + cls, + reference_audios[key], + container_format="mp3", + codec_name="libmp3lame", + mime_type="audio/mpeg", + ), + ), + ), + ) + for url in reference_image_assets.values(): + content.append( + TaskImageContent( + image_url=TaskImageContentUrl(url=url), + role="reference_image", + ), + ) + for url in reference_video_assets.values(): + content.append( + TaskVideoContent(video_url=TaskVideoContentUrl(url=url)), + ) + for url in reference_audio_assets.values(): + content.append( + TaskAudioContent(audio_url=TaskAudioContentUrl(url=url)), + ) + initial_response = await sync_op( + cls, + ApiEndpoint(path=BYTEPLUS_TASK_ENDPOINT, method="POST"), + data=Seedance2TaskCreationRequest( + model=model_id, + content=content, + generate_audio=model["generate_audio"], + resolution=model["resolution"], + ratio=model["ratio"], + duration=model["duration"], + seed=seed, + watermark=watermark, + ), + response_model=TaskCreationResponse, + ) + response = await poll_op( + cls, + ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"), + response_model=TaskStatusResponse, + status_extractor=lambda r: r.status, + price_extractor=_seedance2_price_extractor(model_id, has_video_input=has_video_input), + poll_interval=9, + ) + return IO.NodeOutput(await download_url_to_video_output(response.content.video_url)) + + +async def process_video_task( + cls: type[IO.ComfyNode], + payload: Text2VideoTaskCreationRequest | Image2VideoTaskCreationRequest, + estimated_duration: int | None, +) -> IO.NodeOutput: + if payload.model in DEPRECATED_MODELS: + logger.warning( + "Model '%s' is deprecated and will be deactivated on May 13, 2026. " + "Please switch to a newer model. Recommended: seedance-1-0-pro-fast-251015.", + payload.model, + ) + initial_response = await sync_op( + cls, + ApiEndpoint(path=BYTEPLUS_TASK_ENDPOINT, method="POST"), + data=payload, + response_model=TaskCreationResponse, + ) + response = await poll_op( + cls, + ApiEndpoint(path=f"{BYTEPLUS_TASK_STATUS_ENDPOINT}/{initial_response.id}"), + status_extractor=lambda r: r.status, + estimated_duration=estimated_duration, + response_model=TaskStatusResponse, + ) + return IO.NodeOutput(await download_url_to_video_output(response.content.video_url)) + + +class ByteDanceCreateImageAsset(IO.ComfyNode): + + @classmethod + def define_schema(cls) -> IO.Schema: + return IO.Schema( + node_id="ByteDanceCreateImageAsset", + display_name="ByteDance Create Image Asset", + category="api node/image/ByteDance", + description=( + "Create a Seedance 2.0 personal image asset. Uploads the input image and " + "registers it in the given asset group. If group_id is empty, runs a real-person " + "H5 authentication flow to create a new group before adding the asset." + ), + inputs=[ + IO.Image.Input("image", tooltip="Image to register as a personal asset."), + IO.String.Input( + "group_id", + default="", + tooltip="Reuse an existing Seedance asset group ID to skip repeated human verification for the " + "same person. Leave empty to run real-person authentication in the browser and create a new group.", + ), + # IO.String.Input( + # "name", + # default="", + # tooltip="Asset name (up to 64 characters).", + # ), + ], + outputs=[ + IO.String.Output(display_name="asset_id"), + IO.String.Output(display_name="group_id"), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + # is_api_node=True, + ) + + @classmethod + async def execute( + cls, + image: Input.Image, + group_id: str = "", + # name: str = "", + ) -> IO.NodeOutput: + # if len(name) > 64: + # raise ValueError("Name of asset can not be greater then 64 symbols") + validate_image_dimensions(image, min_width=300, max_width=6000, min_height=300, max_height=6000) + validate_image_aspect_ratio(image, min_ratio=(0.4, 1), max_ratio=(2.5, 1)) + resolved_group = await _resolve_group_id(cls, group_id) + asset_id = await _create_seedance_asset( + cls, + group_id=resolved_group, + url=await upload_image_to_comfyapi(cls, image), + name="", + asset_type="Image", + ) + await _wait_for_asset_active(cls, asset_id, resolved_group) + PromptServer.instance.send_progress_text( + f"Please save the asset_id and group_id for reuse.\n\nasset_id: {asset_id}\n\n" + f"group_id: {resolved_group}", + cls.hidden.unique_id, + ) + return IO.NodeOutput(asset_id, resolved_group) + + +class ByteDanceCreateVideoAsset(IO.ComfyNode): + + @classmethod + def define_schema(cls) -> IO.Schema: + return IO.Schema( + node_id="ByteDanceCreateVideoAsset", + display_name="ByteDance Create Video Asset", + category="api node/video/ByteDance", + description=( + "Create a Seedance 2.0 personal video asset. Uploads the input video and " + "registers it in the given asset group. If group_id is empty, runs a real-person " + "H5 authentication flow to create a new group before adding the asset." + ), + inputs=[ + IO.Video.Input("video", tooltip="Video to register as a personal asset."), + IO.String.Input( + "group_id", + default="", + tooltip="Reuse an existing Seedance asset group ID to skip repeated human verification for the " + "same person. Leave empty to run real-person authentication in the browser and create a new group.", + ), + # IO.String.Input( + # "name", + # default="", + # tooltip="Asset name (up to 64 characters).", + # ), + ], + outputs=[ + IO.String.Output(display_name="asset_id"), + IO.String.Output(display_name="group_id"), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + # is_api_node=True, + ) + + @classmethod + async def execute( + cls, + video: Input.Video, + group_id: str = "", + # name: str = "", + ) -> IO.NodeOutput: + # if len(name) > 64: + # raise ValueError("Name of asset can not be greater then 64 symbols") + validate_video_duration(video, min_duration=2, max_duration=15) + validate_video_dimensions(video, min_width=300, max_width=6000, min_height=300, max_height=6000) + + w, h = video.get_dimensions() + if h > 0: + ratio = w / h + if not (0.4 <= ratio <= 2.5): + raise ValueError(f"Asset video aspect ratio (W/H) must be in [0.4, 2.5], got {ratio:.3f} ({w}x{h}).") + pixels = w * h + if not (409_600 <= pixels <= 927_408): + raise ValueError( + f"Asset video total pixels (W×H) must be in [409600, 927408], " f"got {pixels:,} ({w}x{h})." + ) + + fps = float(video.get_frame_rate()) + if not (24 <= fps <= 60): + raise ValueError(f"Asset video FPS must be in [24, 60], got {fps:.2f}.") + + resolved_group = await _resolve_group_id(cls, group_id) + asset_id = await _create_seedance_asset( + cls, + group_id=resolved_group, + url=await upload_video_to_comfyapi(cls, video), + name="", + asset_type="Video", + ) + await _wait_for_asset_active(cls, asset_id, resolved_group) + PromptServer.instance.send_progress_text( + f"Please save the asset_id and group_id for reuse.\n\nasset_id: {asset_id}\n\n" + f"group_id: {resolved_group}", + cls.hidden.unique_id, + ) + return IO.NodeOutput(asset_id, resolved_group) + + class ByteDanceExtension(ComfyExtension): @override async def get_node_list(self) -> list[type[IO.ComfyNode]]: @@ -1050,6 +2096,11 @@ class ByteDanceExtension(ComfyExtension): ByteDanceImageToVideoNode, ByteDanceFirstLastFrameNode, ByteDanceImageReferenceNode, + ByteDance2TextToVideoNode, + ByteDance2FirstLastFrameNode, + ByteDance2ReferenceNode, + ByteDanceCreateImageAsset, + ByteDanceCreateVideoAsset, ] diff --git a/comfy_api_nodes/nodes_grok.py b/comfy_api_nodes/nodes_grok.py index dabc899d6..f42d84616 100644 --- a/comfy_api_nodes/nodes_grok.py +++ b/comfy_api_nodes/nodes_grok.py @@ -558,7 +558,7 @@ class GrokVideoReferenceNode(IO.ComfyNode): ( $res := $lookup(widgets, "model.resolution"); $dur := $lookup(widgets, "model.duration"); - $refs := inputGroups["model.reference_images"]; + $refs := $lookup(inputGroups, "model.reference_images"); $rate := $res = "720p" ? 0.07 : 0.05; $price := ($rate * $dur + 0.002 * $refs) * 1.43; {"type":"usd","usd": $price} diff --git a/comfy_api_nodes/nodes_hitpaw.py b/comfy_api_nodes/nodes_hitpaw.py index 488080a74..bca5170e4 100644 --- a/comfy_api_nodes/nodes_hitpaw.py +++ b/comfy_api_nodes/nodes_hitpaw.py @@ -178,7 +178,6 @@ class HitPawGeneralImageEnhance(IO.ComfyNode): status_extractor=lambda x: x.data.status, price_extractor=lambda x: request_price, poll_interval=10.0, - max_poll_attempts=480, ) return IO.NodeOutput(await download_url_to_image_tensor(final_response.data.res_url)) @@ -324,7 +323,6 @@ class HitPawVideoEnhance(IO.ComfyNode): status_extractor=lambda x: x.data.status, price_extractor=lambda x: request_price, poll_interval=10.0, - max_poll_attempts=320, ) return IO.NodeOutput(await download_url_to_video_output(final_response.data.res_url)) diff --git a/comfy_api_nodes/nodes_hunyuan3d.py b/comfy_api_nodes/nodes_hunyuan3d.py index 44c94a98e..5fc31bccd 100644 --- a/comfy_api_nodes/nodes_hunyuan3d.py +++ b/comfy_api_nodes/nodes_hunyuan3d.py @@ -221,14 +221,17 @@ class TencentTextToModelNode(IO.ComfyNode): response_model=To3DProTaskResultResponse, status_extractor=lambda r: r.Status, ) - obj_result = await download_and_extract_obj_zip(get_file_from_response(result.ResultFile3Ds, "obj").Url) + obj_file_response = get_file_from_response(result.ResultFile3Ds, "obj", raise_if_not_found=False) + obj_result = None + if obj_file_response: + obj_result = await download_and_extract_obj_zip(obj_file_response.Url) return IO.NodeOutput( f"{task_id}.glb", await download_url_to_file_3d( get_file_from_response(result.ResultFile3Ds, "glb").Url, "glb", task_id=task_id ), - obj_result.obj, - obj_result.texture, + obj_result.obj if obj_result else None, + obj_result.texture if obj_result else None, ) @@ -378,17 +381,30 @@ class TencentImageToModelNode(IO.ComfyNode): response_model=To3DProTaskResultResponse, status_extractor=lambda r: r.Status, ) - obj_result = await download_and_extract_obj_zip(get_file_from_response(result.ResultFile3Ds, "obj").Url) + obj_file_response = get_file_from_response(result.ResultFile3Ds, "obj", raise_if_not_found=False) + if obj_file_response: + obj_result = await download_and_extract_obj_zip(obj_file_response.Url) + return IO.NodeOutput( + f"{task_id}.glb", + await download_url_to_file_3d( + get_file_from_response(result.ResultFile3Ds, "glb").Url, "glb", task_id=task_id + ), + obj_result.obj, + obj_result.texture, + obj_result.metallic if obj_result.metallic is not None else torch.zeros(1, 1, 1, 3), + obj_result.normal if obj_result.normal is not None else torch.zeros(1, 1, 1, 3), + obj_result.roughness if obj_result.roughness is not None else torch.zeros(1, 1, 1, 3), + ) return IO.NodeOutput( f"{task_id}.glb", await download_url_to_file_3d( get_file_from_response(result.ResultFile3Ds, "glb").Url, "glb", task_id=task_id ), - obj_result.obj, - obj_result.texture, - obj_result.metallic if obj_result.metallic is not None else torch.zeros(1, 1, 1, 3), - obj_result.normal if obj_result.normal is not None else torch.zeros(1, 1, 1, 3), - obj_result.roughness if obj_result.roughness is not None else torch.zeros(1, 1, 1, 3), + None, + None, + None, + None, + None, ) diff --git a/comfy_api_nodes/nodes_kling.py b/comfy_api_nodes/nodes_kling.py index 9a37ccc53..efd58fac3 100644 --- a/comfy_api_nodes/nodes_kling.py +++ b/comfy_api_nodes/nodes_kling.py @@ -862,7 +862,7 @@ class OmniProTextToVideoNode(IO.ComfyNode): ), IO.Combo.Input("aspect_ratio", options=["16:9", "9:16", "1:1"]), IO.Int.Input("duration", default=5, min=3, max=15, display_mode=IO.NumberDisplay.slider), - IO.Combo.Input("resolution", options=["1080p", "720p"], optional=True), + IO.Combo.Input("resolution", options=["4k", "1080p", "720p"], default="1080p", optional=True), IO.DynamicCombo.Input( "storyboards", options=[ @@ -904,12 +904,13 @@ class OmniProTextToVideoNode(IO.ComfyNode): depends_on=IO.PriceBadgeDepends(widgets=["duration", "resolution", "model_name", "generate_audio"]), expr=""" ( - $mode := (widgets.resolution = "720p") ? "std" : "pro"; + $res := widgets.resolution; + $mode := $res = "4k" ? "4k" : ($res = "720p" ? "std" : "pro"); $isV3 := $contains(widgets.model_name, "v3"); $audio := $isV3 and widgets.generate_audio; $rates := $audio - ? {"std": 0.112, "pro": 0.14} - : {"std": 0.084, "pro": 0.112}; + ? {"std": 0.112, "pro": 0.14, "4k": 0.42} + : {"std": 0.084, "pro": 0.112, "4k": 0.42}; {"type":"usd","usd": $lookup($rates, $mode) * widgets.duration} ) """, @@ -934,6 +935,8 @@ class OmniProTextToVideoNode(IO.ComfyNode): raise ValueError("kling-video-o1 only supports durations of 5 or 10 seconds.") if generate_audio: raise ValueError("kling-video-o1 does not support audio generation.") + if resolution == "4k": + raise ValueError("kling-video-o1 does not support 4k resolution.") stories_enabled = storyboards is not None and storyboards["storyboards"] != "disabled" if stories_enabled and model_name == "kling-video-o1": raise ValueError("kling-video-o1 does not support storyboards.") @@ -963,6 +966,12 @@ class OmniProTextToVideoNode(IO.ComfyNode): f"must equal the global duration ({duration}s)." ) + if resolution == "4k": + mode = "4k" + elif resolution == "1080p": + mode = "pro" + else: + mode = "std" response = await sync_op( cls, ApiEndpoint(path="/proxy/kling/v1/videos/omni-video", method="POST"), @@ -972,7 +981,7 @@ class OmniProTextToVideoNode(IO.ComfyNode): prompt=prompt, aspect_ratio=aspect_ratio, duration=str(duration), - mode="pro" if resolution == "1080p" else "std", + mode=mode, multi_shot=multi_shot, multi_prompt=multi_prompt_list, shot_type="customize" if multi_shot else None, @@ -1014,7 +1023,7 @@ class OmniProFirstLastFrameNode(IO.ComfyNode): optional=True, tooltip="Up to 6 additional reference images.", ), - IO.Combo.Input("resolution", options=["1080p", "720p"], optional=True), + IO.Combo.Input("resolution", options=["4k", "1080p", "720p"], default="1080p", optional=True), IO.DynamicCombo.Input( "storyboards", options=[ @@ -1061,12 +1070,13 @@ class OmniProFirstLastFrameNode(IO.ComfyNode): depends_on=IO.PriceBadgeDepends(widgets=["duration", "resolution", "model_name", "generate_audio"]), expr=""" ( - $mode := (widgets.resolution = "720p") ? "std" : "pro"; + $res := widgets.resolution; + $mode := $res = "4k" ? "4k" : ($res = "720p" ? "std" : "pro"); $isV3 := $contains(widgets.model_name, "v3"); $audio := $isV3 and widgets.generate_audio; $rates := $audio - ? {"std": 0.112, "pro": 0.14} - : {"std": 0.084, "pro": 0.112}; + ? {"std": 0.112, "pro": 0.14, "4k": 0.42} + : {"std": 0.084, "pro": 0.112, "4k": 0.42}; {"type":"usd","usd": $lookup($rates, $mode) * widgets.duration} ) """, @@ -1093,6 +1103,8 @@ class OmniProFirstLastFrameNode(IO.ComfyNode): raise ValueError("kling-video-o1 does not support durations greater than 10 seconds.") if generate_audio: raise ValueError("kling-video-o1 does not support audio generation.") + if resolution == "4k": + raise ValueError("kling-video-o1 does not support 4k resolution.") stories_enabled = storyboards is not None and storyboards["storyboards"] != "disabled" if stories_enabled and model_name == "kling-video-o1": raise ValueError("kling-video-o1 does not support storyboards.") @@ -1161,6 +1173,12 @@ class OmniProFirstLastFrameNode(IO.ComfyNode): validate_image_aspect_ratio(i, (1, 2.5), (2.5, 1)) for i in await upload_images_to_comfyapi(cls, reference_images, wait_label="Uploading reference frame(s)"): image_list.append(OmniParamImage(image_url=i)) + if resolution == "4k": + mode = "4k" + elif resolution == "1080p": + mode = "pro" + else: + mode = "std" response = await sync_op( cls, ApiEndpoint(path="/proxy/kling/v1/videos/omni-video", method="POST"), @@ -1170,7 +1188,7 @@ class OmniProFirstLastFrameNode(IO.ComfyNode): prompt=prompt, duration=str(duration), image_list=image_list, - mode="pro" if resolution == "1080p" else "std", + mode=mode, sound="on" if generate_audio else "off", multi_shot=multi_shot, multi_prompt=multi_prompt_list, @@ -1204,7 +1222,7 @@ class OmniProImageToVideoNode(IO.ComfyNode): "reference_images", tooltip="Up to 7 reference images.", ), - IO.Combo.Input("resolution", options=["1080p", "720p"], optional=True), + IO.Combo.Input("resolution", options=["4k", "1080p", "720p"], default="1080p", optional=True), IO.DynamicCombo.Input( "storyboards", options=[ @@ -1251,12 +1269,13 @@ class OmniProImageToVideoNode(IO.ComfyNode): depends_on=IO.PriceBadgeDepends(widgets=["duration", "resolution", "model_name", "generate_audio"]), expr=""" ( - $mode := (widgets.resolution = "720p") ? "std" : "pro"; + $res := widgets.resolution; + $mode := $res = "4k" ? "4k" : ($res = "720p" ? "std" : "pro"); $isV3 := $contains(widgets.model_name, "v3"); $audio := $isV3 and widgets.generate_audio; $rates := $audio - ? {"std": 0.112, "pro": 0.14} - : {"std": 0.084, "pro": 0.112}; + ? {"std": 0.112, "pro": 0.14, "4k": 0.42} + : {"std": 0.084, "pro": 0.112, "4k": 0.42}; {"type":"usd","usd": $lookup($rates, $mode) * widgets.duration} ) """, @@ -1282,6 +1301,8 @@ class OmniProImageToVideoNode(IO.ComfyNode): raise ValueError("kling-video-o1 does not support durations greater than 10 seconds.") if generate_audio: raise ValueError("kling-video-o1 does not support audio generation.") + if resolution == "4k": + raise ValueError("kling-video-o1 does not support 4k resolution.") stories_enabled = storyboards is not None and storyboards["storyboards"] != "disabled" if stories_enabled and model_name == "kling-video-o1": raise ValueError("kling-video-o1 does not support storyboards.") @@ -1320,6 +1341,12 @@ class OmniProImageToVideoNode(IO.ComfyNode): image_list: list[OmniParamImage] = [] for i in await upload_images_to_comfyapi(cls, reference_images, wait_label="Uploading reference image"): image_list.append(OmniParamImage(image_url=i)) + if resolution == "4k": + mode = "4k" + elif resolution == "1080p": + mode = "pro" + else: + mode = "std" response = await sync_op( cls, ApiEndpoint(path="/proxy/kling/v1/videos/omni-video", method="POST"), @@ -1330,7 +1357,7 @@ class OmniProImageToVideoNode(IO.ComfyNode): aspect_ratio=aspect_ratio, duration=str(duration), image_list=image_list, - mode="pro" if resolution == "1080p" else "std", + mode=mode, sound="on" if generate_audio else "off", multi_shot=multi_shot, multi_prompt=multi_prompt_list, @@ -2860,7 +2887,7 @@ class KlingVideoNode(IO.ComfyNode): IO.DynamicCombo.Option( "kling-v3", [ - IO.Combo.Input("resolution", options=["1080p", "720p"]), + IO.Combo.Input("resolution", options=["4k", "1080p", "720p"], default="1080p"), IO.Combo.Input( "aspect_ratio", options=["16:9", "9:16", "1:1"], @@ -2913,7 +2940,11 @@ class KlingVideoNode(IO.ComfyNode): ), expr=""" ( - $rates := {"1080p": {"off": 0.112, "on": 0.168}, "720p": {"off": 0.084, "on": 0.126}}; + $rates := { + "4k": {"off": 0.42, "on": 0.42}, + "1080p": {"off": 0.112, "on": 0.168}, + "720p": {"off": 0.084, "on": 0.126} + }; $res := $lookup(widgets, "model.resolution"); $audio := widgets.generate_audio ? "on" : "off"; $rate := $lookup($lookup($rates, $res), $audio); @@ -2943,7 +2974,12 @@ class KlingVideoNode(IO.ComfyNode): start_frame: Input.Image | None = None, ) -> IO.NodeOutput: _ = seed - mode = "pro" if model["resolution"] == "1080p" else "std" + if model["resolution"] == "4k": + mode = "4k" + elif model["resolution"] == "1080p": + mode = "pro" + else: + mode = "std" custom_multi_shot = False if multi_shot["multi_shot"] == "disabled": shot_type = None @@ -3057,7 +3093,7 @@ class KlingFirstLastFrameNode(IO.ComfyNode): IO.DynamicCombo.Option( "kling-v3", [ - IO.Combo.Input("resolution", options=["1080p", "720p"]), + IO.Combo.Input("resolution", options=["4k", "1080p", "720p"], default="1080p"), ], ), ], @@ -3089,7 +3125,11 @@ class KlingFirstLastFrameNode(IO.ComfyNode): ), expr=""" ( - $rates := {"1080p": {"off": 0.112, "on": 0.168}, "720p": {"off": 0.084, "on": 0.126}}; + $rates := { + "4k": {"off": 0.42, "on": 0.42}, + "1080p": {"off": 0.112, "on": 0.168}, + "720p": {"off": 0.084, "on": 0.126} + }; $res := $lookup(widgets, "model.resolution"); $audio := widgets.generate_audio ? "on" : "off"; $rate := $lookup($lookup($rates, $res), $audio); @@ -3118,6 +3158,12 @@ class KlingFirstLastFrameNode(IO.ComfyNode): validate_image_aspect_ratio(end_frame, (1, 2.5), (2.5, 1)) image_url = await upload_image_to_comfyapi(cls, first_frame, wait_label="Uploading first frame") image_tail_url = await upload_image_to_comfyapi(cls, end_frame, wait_label="Uploading end frame") + if model["resolution"] == "4k": + mode = "4k" + elif model["resolution"] == "1080p": + mode = "pro" + else: + mode = "std" response = await sync_op( cls, ApiEndpoint(path="/proxy/kling/v1/videos/image2video", method="POST"), @@ -3127,7 +3173,7 @@ class KlingFirstLastFrameNode(IO.ComfyNode): image=image_url, image_tail=image_tail_url, prompt=prompt, - mode="pro" if model["resolution"] == "1080p" else "std", + mode=mode, duration=str(duration), sound="on" if generate_audio else "off", ), diff --git a/comfy_api_nodes/nodes_magnific.py b/comfy_api_nodes/nodes_magnific.py index 0f53208d4..38b881fea 100644 --- a/comfy_api_nodes/nodes_magnific.py +++ b/comfy_api_nodes/nodes_magnific.py @@ -230,7 +230,6 @@ class MagnificImageUpscalerCreativeNode(IO.ComfyNode): status_extractor=lambda x: x.status, price_extractor=lambda _: price_usd, poll_interval=10.0, - max_poll_attempts=480, ) return IO.NodeOutput(await download_url_to_image_tensor(final_response.generated[0])) @@ -391,7 +390,6 @@ class MagnificImageUpscalerPreciseV2Node(IO.ComfyNode): status_extractor=lambda x: x.status, price_extractor=lambda _: price_usd, poll_interval=10.0, - max_poll_attempts=480, ) return IO.NodeOutput(await download_url_to_image_tensor(final_response.generated[0])) @@ -541,7 +539,6 @@ class MagnificImageStyleTransferNode(IO.ComfyNode): response_model=TaskResponse, status_extractor=lambda x: x.status, poll_interval=10.0, - max_poll_attempts=480, ) return IO.NodeOutput(await download_url_to_image_tensor(final_response.generated[0])) @@ -782,7 +779,6 @@ class MagnificImageRelightNode(IO.ComfyNode): response_model=TaskResponse, status_extractor=lambda x: x.status, poll_interval=10.0, - max_poll_attempts=480, ) return IO.NodeOutput(await download_url_to_image_tensor(final_response.generated[0])) @@ -924,7 +920,6 @@ class MagnificImageSkinEnhancerNode(IO.ComfyNode): response_model=TaskResponse, status_extractor=lambda x: x.status, poll_interval=10.0, - max_poll_attempts=480, ) return IO.NodeOutput(await download_url_to_image_tensor(final_response.generated[0])) diff --git a/comfy_api_nodes/nodes_moonvalley.py b/comfy_api_nodes/nodes_moonvalley.py deleted file mode 100644 index 78a230529..000000000 --- a/comfy_api_nodes/nodes_moonvalley.py +++ /dev/null @@ -1,534 +0,0 @@ -import logging - -from typing_extensions import override - -from comfy_api.latest import IO, ComfyExtension, Input -from comfy_api_nodes.apis.moonvalley import ( - MoonvalleyPromptResponse, - MoonvalleyTextToVideoInferenceParams, - MoonvalleyTextToVideoRequest, - MoonvalleyVideoToVideoInferenceParams, - MoonvalleyVideoToVideoRequest, -) -from comfy_api_nodes.util import ( - ApiEndpoint, - download_url_to_video_output, - poll_op, - sync_op, - trim_video, - upload_images_to_comfyapi, - upload_video_to_comfyapi, - validate_container_format_is_mp4, - validate_image_dimensions, - validate_string, -) - -API_UPLOADS_ENDPOINT = "/proxy/moonvalley/uploads" -API_PROMPTS_ENDPOINT = "/proxy/moonvalley/prompts" -API_VIDEO2VIDEO_ENDPOINT = "/proxy/moonvalley/prompts/video-to-video" -API_TXT2VIDEO_ENDPOINT = "/proxy/moonvalley/prompts/text-to-video" -API_IMG2VIDEO_ENDPOINT = "/proxy/moonvalley/prompts/image-to-video" - -MIN_WIDTH = 300 -MIN_HEIGHT = 300 - -MAX_WIDTH = 10000 -MAX_HEIGHT = 10000 - -MIN_VID_WIDTH = 300 -MIN_VID_HEIGHT = 300 - -MAX_VID_WIDTH = 10000 -MAX_VID_HEIGHT = 10000 - -MAX_VIDEO_SIZE = 1024 * 1024 * 1024 # 1 GB max for in-memory video processing - -MOONVALLEY_MAREY_MAX_PROMPT_LENGTH = 5000 - - -def is_valid_task_creation_response(response: MoonvalleyPromptResponse) -> bool: - """Verifies that the initial response contains a task ID.""" - return bool(response.id) - - -def validate_task_creation_response(response) -> None: - if not is_valid_task_creation_response(response): - error_msg = f"Moonvalley Marey API: Initial request failed. Code: {response.code}, Message: {response.message}, Data: {response}" - logging.error(error_msg) - raise RuntimeError(error_msg) - - -def validate_video_to_video_input(video: Input.Video) -> Input.Video: - """ - Validates and processes video input for Moonvalley Video-to-Video generation. - - Args: - video: Input video to validate - - Returns: - Validated and potentially trimmed video - - Raises: - ValueError: If video doesn't meet requirements - MoonvalleyApiError: If video duration is too short - """ - width, height = _get_video_dimensions(video) - _validate_video_dimensions(width, height) - validate_container_format_is_mp4(video) - - return _validate_and_trim_duration(video) - - -def _get_video_dimensions(video: Input.Video) -> tuple[int, int]: - """Extracts video dimensions with error handling.""" - try: - return video.get_dimensions() - except Exception as e: - logging.error("Error getting dimensions of video: %s", e) - raise ValueError(f"Cannot get video dimensions: {e}") from e - - -def _validate_video_dimensions(width: int, height: int) -> None: - """Validates video dimensions meet Moonvalley V2V requirements.""" - supported_resolutions = { - (1920, 1080), - (1080, 1920), - (1152, 1152), - (1536, 1152), - (1152, 1536), - } - - if (width, height) not in supported_resolutions: - supported_list = ", ".join([f"{w}x{h}" for w, h in sorted(supported_resolutions)]) - raise ValueError(f"Resolution {width}x{height} not supported. Supported: {supported_list}") - - -def _validate_and_trim_duration(video: Input.Video) -> Input.Video: - """Validates video duration and trims to 5 seconds if needed.""" - duration = video.get_duration() - _validate_minimum_duration(duration) - return _trim_if_too_long(video, duration) - - -def _validate_minimum_duration(duration: float) -> None: - """Ensures video is at least 5 seconds long.""" - if duration < 5: - raise ValueError("Input video must be at least 5 seconds long.") - - -def _trim_if_too_long(video: Input.Video, duration: float) -> Input.Video: - """Trims video to 5 seconds if longer.""" - if duration > 5: - return trim_video(video, 5) - return video - - -def parse_width_height_from_res(resolution: str): - # Accepts a string like "16:9 (1920 x 1080)" and returns width, height as a dict - res_map = { - "16:9 (1920 x 1080)": {"width": 1920, "height": 1080}, - "9:16 (1080 x 1920)": {"width": 1080, "height": 1920}, - "1:1 (1152 x 1152)": {"width": 1152, "height": 1152}, - "4:3 (1536 x 1152)": {"width": 1536, "height": 1152}, - "3:4 (1152 x 1536)": {"width": 1152, "height": 1536}, - # "21:9 (2560 x 1080)": {"width": 2560, "height": 1080}, - } - return res_map.get(resolution, {"width": 1920, "height": 1080}) - - -def parse_control_parameter(value): - control_map = { - "Motion Transfer": "motion_control", - "Canny": "canny_control", - "Pose Transfer": "pose_control", - "Depth": "depth_control", - } - return control_map.get(value, control_map["Motion Transfer"]) - - -async def get_response(cls: type[IO.ComfyNode], task_id: str) -> MoonvalleyPromptResponse: - return await poll_op( - cls, - ApiEndpoint(path=f"{API_PROMPTS_ENDPOINT}/{task_id}"), - response_model=MoonvalleyPromptResponse, - status_extractor=lambda r: (r.status if r and r.status else None), - poll_interval=16.0, - max_poll_attempts=240, - ) - - -class MoonvalleyImg2VideoNode(IO.ComfyNode): - - @classmethod - def define_schema(cls) -> IO.Schema: - return IO.Schema( - node_id="MoonvalleyImg2VideoNode", - display_name="Moonvalley Marey Image to Video", - category="api node/video/Moonvalley Marey", - description="Moonvalley Marey Image to Video Node", - inputs=[ - IO.Image.Input( - "image", - tooltip="The reference image used to generate the video", - ), - IO.String.Input( - "prompt", - multiline=True, - ), - IO.String.Input( - "negative_prompt", - multiline=True, - default=" gopro, bright, contrast, static, overexposed, vignette, " - "artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, " - "flare, saturation, distorted, warped, wide angle, saturated, vibrant, glowing, " - "cross dissolve, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, " - "blown out, horrible, blurry, worst quality, bad, dissolve, melt, fade in, fade out, " - "wobbly, weird, low quality, plastic, stock footage, video camera, boring", - tooltip="Negative prompt text", - ), - IO.Combo.Input( - "resolution", - options=[ - "16:9 (1920 x 1080)", - "9:16 (1080 x 1920)", - "1:1 (1152 x 1152)", - "4:3 (1536 x 1152)", - "3:4 (1152 x 1536)", - # "21:9 (2560 x 1080)", - ], - default="16:9 (1920 x 1080)", - tooltip="Resolution of the output video", - ), - IO.Float.Input( - "prompt_adherence", - default=4.5, - min=1.0, - max=20.0, - step=1.0, - tooltip="Guidance scale for generation control", - ), - IO.Int.Input( - "seed", - default=9, - min=0, - max=4294967295, - step=1, - display_mode=IO.NumberDisplay.number, - tooltip="Random seed value", - control_after_generate=True, - ), - IO.Int.Input( - "steps", - default=80, - min=75, # steps should be greater or equal to cooldown_steps(75) + warmup_steps(0) - max=100, - step=1, - tooltip="Number of denoising steps", - ), - ], - outputs=[IO.Video.Output()], - hidden=[ - IO.Hidden.auth_token_comfy_org, - IO.Hidden.api_key_comfy_org, - IO.Hidden.unique_id, - ], - is_api_node=True, - price_badge=IO.PriceBadge( - depends_on=IO.PriceBadgeDepends(), - expr="""{"type":"usd","usd": 1.5}""", - ), - ) - - @classmethod - async def execute( - cls, - image: Input.Image, - prompt: str, - negative_prompt: str, - resolution: str, - prompt_adherence: float, - seed: int, - steps: int, - ) -> IO.NodeOutput: - validate_image_dimensions(image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH) - validate_string(prompt, min_length=1, max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH) - validate_string(negative_prompt, field_name="negative_prompt", max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH) - width_height = parse_width_height_from_res(resolution) - - inference_params = MoonvalleyTextToVideoInferenceParams( - negative_prompt=negative_prompt, - steps=steps, - seed=seed, - guidance_scale=prompt_adherence, - width=width_height["width"], - height=width_height["height"], - use_negative_prompts=True, - ) - - # Get MIME type from tensor - assuming PNG format for image tensors - mime_type = "image/png" - image_url = (await upload_images_to_comfyapi(cls, image, max_images=1, mime_type=mime_type))[0] - task_creation_response = await sync_op( - cls, - endpoint=ApiEndpoint(path=API_IMG2VIDEO_ENDPOINT, method="POST"), - response_model=MoonvalleyPromptResponse, - data=MoonvalleyTextToVideoRequest( - image_url=image_url, prompt_text=prompt, inference_params=inference_params - ), - ) - validate_task_creation_response(task_creation_response) - final_response = await get_response(cls, task_creation_response.id) - video = await download_url_to_video_output(final_response.output_url) - return IO.NodeOutput(video) - - -class MoonvalleyVideo2VideoNode(IO.ComfyNode): - - @classmethod - def define_schema(cls) -> IO.Schema: - return IO.Schema( - node_id="MoonvalleyVideo2VideoNode", - display_name="Moonvalley Marey Video to Video", - category="api node/video/Moonvalley Marey", - description="", - inputs=[ - IO.String.Input( - "prompt", - multiline=True, - tooltip="Describes the video to generate", - ), - IO.String.Input( - "negative_prompt", - multiline=True, - default=" gopro, bright, contrast, static, overexposed, vignette, " - "artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, " - "flare, saturation, distorted, warped, wide angle, saturated, vibrant, glowing, " - "cross dissolve, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, " - "blown out, horrible, blurry, worst quality, bad, dissolve, melt, fade in, fade out, " - "wobbly, weird, low quality, plastic, stock footage, video camera, boring", - tooltip="Negative prompt text", - ), - IO.Int.Input( - "seed", - default=9, - min=0, - max=4294967295, - step=1, - display_mode=IO.NumberDisplay.number, - tooltip="Random seed value", - control_after_generate=False, - ), - IO.Video.Input( - "video", - tooltip="The reference video used to generate the output video. Must be at least 5 seconds long. " - "Videos longer than 5s will be automatically trimmed. Only MP4 format supported.", - ), - IO.Combo.Input( - "control_type", - options=["Motion Transfer", "Pose Transfer"], - default="Motion Transfer", - optional=True, - ), - IO.Int.Input( - "motion_intensity", - default=100, - min=0, - max=100, - step=1, - tooltip="Only used if control_type is 'Motion Transfer'", - optional=True, - ), - IO.Int.Input( - "steps", - default=60, - min=60, # steps should be greater or equal to cooldown_steps(36) + warmup_steps(24) - max=100, - step=1, - display_mode=IO.NumberDisplay.number, - tooltip="Number of inference steps", - ), - ], - outputs=[IO.Video.Output()], - hidden=[ - IO.Hidden.auth_token_comfy_org, - IO.Hidden.api_key_comfy_org, - IO.Hidden.unique_id, - ], - is_api_node=True, - price_badge=IO.PriceBadge( - depends_on=IO.PriceBadgeDepends(), - expr="""{"type":"usd","usd": 2.25}""", - ), - ) - - @classmethod - async def execute( - cls, - prompt: str, - negative_prompt: str, - seed: int, - video: Input.Video | None = None, - control_type: str = "Motion Transfer", - motion_intensity: int | None = 100, - steps=60, - prompt_adherence=4.5, - ) -> IO.NodeOutput: - validated_video = validate_video_to_video_input(video) - video_url = await upload_video_to_comfyapi(cls, validated_video) - validate_string(prompt, min_length=1, max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH) - validate_string(negative_prompt, field_name="negative_prompt", max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH) - - # Only include motion_intensity for Motion Transfer - control_params = {} - if control_type == "Motion Transfer" and motion_intensity is not None: - control_params["motion_intensity"] = motion_intensity - - inference_params = MoonvalleyVideoToVideoInferenceParams( - negative_prompt=negative_prompt, - seed=seed, - control_params=control_params, - steps=steps, - guidance_scale=prompt_adherence, - ) - - task_creation_response = await sync_op( - cls, - endpoint=ApiEndpoint(path=API_VIDEO2VIDEO_ENDPOINT, method="POST"), - response_model=MoonvalleyPromptResponse, - data=MoonvalleyVideoToVideoRequest( - control_type=parse_control_parameter(control_type), - video_url=video_url, - prompt_text=prompt, - inference_params=inference_params, - ), - ) - validate_task_creation_response(task_creation_response) - final_response = await get_response(cls, task_creation_response.id) - return IO.NodeOutput(await download_url_to_video_output(final_response.output_url)) - - -class MoonvalleyTxt2VideoNode(IO.ComfyNode): - - @classmethod - def define_schema(cls) -> IO.Schema: - return IO.Schema( - node_id="MoonvalleyTxt2VideoNode", - display_name="Moonvalley Marey Text to Video", - category="api node/video/Moonvalley Marey", - description="", - inputs=[ - IO.String.Input( - "prompt", - multiline=True, - ), - IO.String.Input( - "negative_prompt", - multiline=True, - default=" gopro, bright, contrast, static, overexposed, vignette, " - "artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, " - "flare, saturation, distorted, warped, wide angle, saturated, vibrant, glowing, " - "cross dissolve, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, " - "blown out, horrible, blurry, worst quality, bad, dissolve, melt, fade in, fade out, " - "wobbly, weird, low quality, plastic, stock footage, video camera, boring", - tooltip="Negative prompt text", - ), - IO.Combo.Input( - "resolution", - options=[ - "16:9 (1920 x 1080)", - "9:16 (1080 x 1920)", - "1:1 (1152 x 1152)", - "4:3 (1536 x 1152)", - "3:4 (1152 x 1536)", - "21:9 (2560 x 1080)", - ], - default="16:9 (1920 x 1080)", - tooltip="Resolution of the output video", - ), - IO.Float.Input( - "prompt_adherence", - default=4.0, - min=1.0, - max=20.0, - step=1.0, - tooltip="Guidance scale for generation control", - ), - IO.Int.Input( - "seed", - default=9, - min=0, - max=4294967295, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="Random seed value", - ), - IO.Int.Input( - "steps", - default=80, - min=75, # steps should be greater or equal to cooldown_steps(75) + warmup_steps(0) - max=100, - step=1, - tooltip="Inference steps", - ), - ], - outputs=[IO.Video.Output()], - hidden=[ - IO.Hidden.auth_token_comfy_org, - IO.Hidden.api_key_comfy_org, - IO.Hidden.unique_id, - ], - is_api_node=True, - price_badge=IO.PriceBadge( - depends_on=IO.PriceBadgeDepends(), - expr="""{"type":"usd","usd": 1.5}""", - ), - ) - - @classmethod - async def execute( - cls, - prompt: str, - negative_prompt: str, - resolution: str, - prompt_adherence: float, - seed: int, - steps: int, - ) -> IO.NodeOutput: - validate_string(prompt, min_length=1, max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH) - validate_string(negative_prompt, field_name="negative_prompt", max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH) - width_height = parse_width_height_from_res(resolution) - - inference_params = MoonvalleyTextToVideoInferenceParams( - negative_prompt=negative_prompt, - steps=steps, - seed=seed, - guidance_scale=prompt_adherence, - num_frames=128, - width=width_height["width"], - height=width_height["height"], - ) - - task_creation_response = await sync_op( - cls, - endpoint=ApiEndpoint(path=API_TXT2VIDEO_ENDPOINT, method="POST"), - response_model=MoonvalleyPromptResponse, - data=MoonvalleyTextToVideoRequest(prompt_text=prompt, inference_params=inference_params), - ) - validate_task_creation_response(task_creation_response) - final_response = await get_response(cls, task_creation_response.id) - return IO.NodeOutput(await download_url_to_video_output(final_response.output_url)) - - -class MoonvalleyExtension(ComfyExtension): - @override - async def get_node_list(self) -> list[type[IO.ComfyNode]]: - return [ - MoonvalleyImg2VideoNode, - MoonvalleyTxt2VideoNode, - MoonvalleyVideo2VideoNode, - ] - - -async def comfy_entrypoint() -> MoonvalleyExtension: - return MoonvalleyExtension() diff --git a/comfy_api_nodes/nodes_openai.py b/comfy_api_nodes/nodes_openai.py index 4ee896fa8..21fe470ce 100644 --- a/comfy_api_nodes/nodes_openai.py +++ b/comfy_api_nodes/nodes_openai.py @@ -357,13 +357,17 @@ def calculate_tokens_price_image_1_5(response: OpenAIImageGenerationResponse) -> return ((response.usage.input_tokens * 8.0) + (response.usage.output_tokens * 32.0)) / 1_000_000.0 +def calculate_tokens_price_image_2_0(response: OpenAIImageGenerationResponse) -> float | None: + return ((response.usage.input_tokens * 8.0) + (response.usage.output_tokens * 30.0)) / 1_000_000.0 + + class OpenAIGPTImage1(IO.ComfyNode): @classmethod def define_schema(cls): return IO.Schema( node_id="OpenAIGPTImage1", - display_name="OpenAI GPT Image 1.5", + display_name="OpenAI GPT Image 2", category="api node/image/OpenAI", description="Generates images synchronously via OpenAI's GPT Image endpoint.", inputs=[ @@ -401,8 +405,19 @@ class OpenAIGPTImage1(IO.ComfyNode): IO.Combo.Input( "size", default="auto", - options=["auto", "1024x1024", "1024x1536", "1536x1024"], - tooltip="Image size", + options=[ + "auto", + "1024x1024", + "1024x1536", + "1536x1024", + "2048x2048", + "2048x1152", + "1152x2048", + "3840x2160", + "2160x3840", + "Custom", + ], + tooltip="Image size. Select 'Custom' to use the custom width and height (GPT Image 2 only).", optional=True, ), IO.Int.Input( @@ -427,8 +442,26 @@ class OpenAIGPTImage1(IO.ComfyNode): ), IO.Combo.Input( "model", - options=["gpt-image-1", "gpt-image-1.5"], - default="gpt-image-1.5", + options=["gpt-image-1", "gpt-image-1.5", "gpt-image-2"], + default="gpt-image-2", + optional=True, + ), + IO.Int.Input( + "custom_width", + default=1024, + min=1024, + max=3840, + step=16, + tooltip="Used only when `size` is 'Custom'. Must be a multiple of 16 (GPT Image 2 only).", + optional=True, + ), + IO.Int.Input( + "custom_height", + default=1024, + min=1024, + max=3840, + step=16, + tooltip="Used only when `size` is 'Custom'. Must be a multiple of 16 (GPT Image 2 only).", optional=True, ), ], @@ -442,23 +475,36 @@ class OpenAIGPTImage1(IO.ComfyNode): ], is_api_node=True, price_badge=IO.PriceBadge( - depends_on=IO.PriceBadgeDepends(widgets=["quality", "n"]), + depends_on=IO.PriceBadgeDepends(widgets=["quality", "n", "model"]), expr=""" ( $ranges := { - "low": [0.011, 0.02], - "medium": [0.046, 0.07], - "high": [0.167, 0.3] + "gpt-image-1": { + "low": [0.011, 0.02], + "medium": [0.042, 0.07], + "high": [0.167, 0.25] + }, + "gpt-image-1.5": { + "low": [0.009, 0.02], + "medium": [0.034, 0.062], + "high": [0.133, 0.22] + }, + "gpt-image-2": { + "low": [0.0048, 0.019], + "medium": [0.041, 0.168], + "high": [0.165, 0.67] + } }; - $range := $lookup($ranges, widgets.quality); - $n := widgets.n; + $range := $lookup($lookup($ranges, widgets.model), widgets.quality); + $nRaw := widgets.n; + $n := ($nRaw != null and $nRaw != 0) ? $nRaw : 1; ($n = 1) - ? {"type":"range_usd","min_usd": $range[0], "max_usd": $range[1]} + ? {"type":"range_usd","min_usd": $range[0], "max_usd": $range[1], "format": {"approximate": true}} : { "type":"range_usd", - "min_usd": $range[0], - "max_usd": $range[1], - "format": { "suffix": " x " & $string($n) & "/Run" } + "min_usd": $range[0] * $n, + "max_usd": $range[1] * $n, + "format": { "suffix": "/Run", "approximate": true } } ) """, @@ -476,6 +522,8 @@ class OpenAIGPTImage1(IO.ComfyNode): mask: Input.Image | None = None, n: int = 1, size: str = "1024x1024", + custom_width: int = 1024, + custom_height: int = 1024, model: str = "gpt-image-1", ) -> IO.NodeOutput: validate_string(prompt, strip_whitespace=False) @@ -483,10 +531,36 @@ class OpenAIGPTImage1(IO.ComfyNode): if mask is not None and image is None: raise ValueError("Cannot use a mask without an input image") + if size == "Custom": + if model != "gpt-image-2": + raise ValueError("Custom resolution is only supported by GPT Image 2 model") + if custom_width % 16 != 0 or custom_height % 16 != 0: + raise ValueError(f"Custom width and height must be multiples of 16, got {custom_width}x{custom_height}") + if max(custom_width, custom_height) > 3840: + raise ValueError(f"Custom resolution max edge must be <= 3840, got {custom_width}x{custom_height}") + ratio = max(custom_width, custom_height) / min(custom_width, custom_height) + if ratio > 3: + raise ValueError( + f"Custom resolution aspect ratio must not exceed 3:1, got {custom_width}x{custom_height}" + ) + total_pixels = custom_width * custom_height + if not 655_360 <= total_pixels <= 8_294_400: + raise ValueError( + f"Custom resolution total pixels must be between 655,360 and 8,294,400, got {total_pixels}" + ) + size = f"{custom_width}x{custom_height}" + elif model in ("gpt-image-1", "gpt-image-1.5"): + if size not in ("auto", "1024x1024", "1024x1536", "1536x1024"): + raise ValueError(f"Resolution {size} is only supported by GPT Image 2 model") + if model == "gpt-image-1": price_extractor = calculate_tokens_price_image_1 elif model == "gpt-image-1.5": price_extractor = calculate_tokens_price_image_1_5 + elif model == "gpt-image-2": + price_extractor = calculate_tokens_price_image_2_0 + if background == "transparent": + raise ValueError("Transparent background is not supported for GPT Image 2 model") else: raise ValueError(f"Unknown model: {model}") diff --git a/comfy_api_nodes/nodes_quiver.py b/comfy_api_nodes/nodes_quiver.py index 61533263f..28862e368 100644 --- a/comfy_api_nodes/nodes_quiver.py +++ b/comfy_api_nodes/nodes_quiver.py @@ -17,6 +17,44 @@ from comfy_api_nodes.util import ( ) from comfy_extras.nodes_images import SVG +_ARROW_MODELS = ["arrow-1.1", "arrow-1.1-max", "arrow-preview"] + + +def _arrow_sampling_inputs(): + """Shared sampling inputs for all Arrow model variants.""" + return [ + IO.Float.Input( + "temperature", + default=1.0, + min=0.0, + max=2.0, + step=0.1, + display_mode=IO.NumberDisplay.slider, + tooltip="Randomness control. Higher values increase randomness.", + advanced=True, + ), + IO.Float.Input( + "top_p", + default=1.0, + min=0.05, + max=1.0, + step=0.05, + display_mode=IO.NumberDisplay.slider, + tooltip="Nucleus sampling parameter.", + advanced=True, + ), + IO.Float.Input( + "presence_penalty", + default=0.0, + min=-2.0, + max=2.0, + step=0.1, + display_mode=IO.NumberDisplay.slider, + tooltip="Token presence penalty.", + advanced=True, + ), + ] + class QuiverTextToSVGNode(IO.ComfyNode): @classmethod @@ -39,6 +77,7 @@ class QuiverTextToSVGNode(IO.ComfyNode): default="", tooltip="Additional style or formatting guidance.", optional=True, + advanced=True, ), IO.Autogrow.Input( "reference_images", @@ -53,43 +92,7 @@ class QuiverTextToSVGNode(IO.ComfyNode): ), IO.DynamicCombo.Input( "model", - options=[ - IO.DynamicCombo.Option( - "arrow-preview", - [ - IO.Float.Input( - "temperature", - default=1.0, - min=0.0, - max=2.0, - step=0.1, - display_mode=IO.NumberDisplay.slider, - tooltip="Randomness control. Higher values increase randomness.", - advanced=True, - ), - IO.Float.Input( - "top_p", - default=1.0, - min=0.05, - max=1.0, - step=0.05, - display_mode=IO.NumberDisplay.slider, - tooltip="Nucleus sampling parameter.", - advanced=True, - ), - IO.Float.Input( - "presence_penalty", - default=0.0, - min=-2.0, - max=2.0, - step=0.1, - display_mode=IO.NumberDisplay.slider, - tooltip="Token presence penalty.", - advanced=True, - ), - ], - ), - ], + options=[IO.DynamicCombo.Option(m, _arrow_sampling_inputs()) for m in _ARROW_MODELS], tooltip="Model to use for SVG generation.", ), IO.Int.Input( @@ -112,7 +115,16 @@ class QuiverTextToSVGNode(IO.ComfyNode): ], is_api_node=True, price_badge=IO.PriceBadge( - expr="""{"type":"usd","usd":0.429}""", + depends_on=IO.PriceBadgeDepends(widgets=["model"]), + expr=""" + ( + $contains(widgets.model, "max") + ? {"type":"usd","usd":0.3575} + : $contains(widgets.model, "preview") + ? {"type":"usd","usd":0.429} + : {"type":"usd","usd":0.286} + ) + """, ), ) @@ -176,12 +188,13 @@ class QuiverImageToSVGNode(IO.ComfyNode): "auto_crop", default=False, tooltip="Automatically crop to the dominant subject.", + advanced=True, ), IO.DynamicCombo.Input( "model", options=[ IO.DynamicCombo.Option( - "arrow-preview", + m, [ IO.Int.Input( "target_size", @@ -189,39 +202,12 @@ class QuiverImageToSVGNode(IO.ComfyNode): min=128, max=4096, tooltip="Square resize target in pixels.", - ), - IO.Float.Input( - "temperature", - default=1.0, - min=0.0, - max=2.0, - step=0.1, - display_mode=IO.NumberDisplay.slider, - tooltip="Randomness control. Higher values increase randomness.", - advanced=True, - ), - IO.Float.Input( - "top_p", - default=1.0, - min=0.05, - max=1.0, - step=0.05, - display_mode=IO.NumberDisplay.slider, - tooltip="Nucleus sampling parameter.", - advanced=True, - ), - IO.Float.Input( - "presence_penalty", - default=0.0, - min=-2.0, - max=2.0, - step=0.1, - display_mode=IO.NumberDisplay.slider, - tooltip="Token presence penalty.", advanced=True, ), + *_arrow_sampling_inputs(), ], - ), + ) + for m in _ARROW_MODELS ], tooltip="Model to use for SVG vectorization.", ), @@ -245,7 +231,16 @@ class QuiverImageToSVGNode(IO.ComfyNode): ], is_api_node=True, price_badge=IO.PriceBadge( - expr="""{"type":"usd","usd":0.429}""", + depends_on=IO.PriceBadgeDepends(widgets=["model"]), + expr=""" + ( + $contains(widgets.model, "max") + ? {"type":"usd","usd":0.3575} + : $contains(widgets.model, "preview") + ? {"type":"usd","usd":0.429} + : {"type":"usd","usd":0.286} + ) + """, ), ) diff --git a/comfy_api_nodes/nodes_sonilo.py b/comfy_api_nodes/nodes_sonilo.py new file mode 100644 index 000000000..5518f5902 --- /dev/null +++ b/comfy_api_nodes/nodes_sonilo.py @@ -0,0 +1,287 @@ +import base64 +import json +import logging +import time +from urllib.parse import urljoin + +import aiohttp +from typing_extensions import override + +from comfy_api.latest import IO, ComfyExtension, Input +from comfy_api_nodes.util import ( + ApiEndpoint, + audio_bytes_to_audio_input, + upload_video_to_comfyapi, + validate_string, +) +from comfy_api_nodes.util._helpers import ( + default_base_url, + get_auth_header, + get_node_id, + is_processing_interrupted, +) +from comfy_api_nodes.util.common_exceptions import ProcessingInterrupted +from server import PromptServer + +logger = logging.getLogger(__name__) + + +class SoniloVideoToMusic(IO.ComfyNode): + """Generate music from video using Sonilo's AI model.""" + + @classmethod + def define_schema(cls) -> IO.Schema: + return IO.Schema( + node_id="SoniloVideoToMusic", + display_name="Sonilo Video to Music", + category="api node/audio/Sonilo", + description="Generate music from video content using Sonilo's AI model. " + "Analyzes the video and creates matching music.", + inputs=[ + IO.Video.Input( + "video", + tooltip="Input video to generate music from. Maximum duration: 6 minutes.", + ), + IO.String.Input( + "prompt", + default="", + multiline=True, + tooltip="Optional text prompt to guide music generation. " + "Leave empty for best quality - the model will fully analyze the video content.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=0xFFFFFFFFFFFFFFFF, + control_after_generate=True, + tooltip="Seed for reproducibility. Currently ignored by the Sonilo " + "service but kept for graph consistency.", + ), + ], + outputs=[IO.Audio.Output()], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + expr='{"type":"usd","usd":0.009,"format":{"suffix":"/second"}}', + ), + ) + + @classmethod + async def execute( + cls, + video: Input.Video, + prompt: str = "", + seed: int = 0, + ) -> IO.NodeOutput: + video_url = await upload_video_to_comfyapi(cls, video, max_duration=360) + form = aiohttp.FormData() + form.add_field("video_url", video_url) + if prompt.strip(): + form.add_field("prompt", prompt.strip()) + audio_bytes = await _stream_sonilo_music( + cls, + ApiEndpoint(path="/proxy/sonilo/v2m/generate", method="POST"), + form, + ) + return IO.NodeOutput(audio_bytes_to_audio_input(audio_bytes)) + + +class SoniloTextToMusic(IO.ComfyNode): + """Generate music from a text prompt using Sonilo's AI model.""" + + @classmethod + def define_schema(cls) -> IO.Schema: + return IO.Schema( + node_id="SoniloTextToMusic", + display_name="Sonilo Text to Music", + category="api node/audio/Sonilo", + description="Generate music from a text prompt using Sonilo's AI model. " + "Leave duration at 0 to let the model infer it from the prompt.", + inputs=[ + IO.String.Input( + "prompt", + default="", + multiline=True, + tooltip="Text prompt describing the music to generate.", + ), + IO.Int.Input( + "duration", + default=0, + min=0, + max=360, + tooltip="Target duration in seconds. Set to 0 to let the model " + "infer the duration from the prompt. Maximum: 6 minutes.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=0xFFFFFFFFFFFFFFFF, + control_after_generate=True, + tooltip="Seed for reproducibility. Currently ignored by the Sonilo " + "service but kept for graph consistency.", + ), + ], + outputs=[IO.Audio.Output()], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["duration"]), + expr=""" + ( + widgets.duration > 0 + ? {"type":"usd","usd": 0.005 * widgets.duration} + : {"type":"usd","usd": 0.005, "format":{"suffix":"/second"}} + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + prompt: str, + duration: int = 0, + seed: int = 0, + ) -> IO.NodeOutput: + validate_string(prompt, strip_whitespace=True, min_length=1) + form = aiohttp.FormData() + form.add_field("prompt", prompt) + if duration > 0: + form.add_field("duration", str(duration)) + audio_bytes = await _stream_sonilo_music( + cls, + ApiEndpoint(path="/proxy/sonilo/t2m/generate", method="POST"), + form, + ) + return IO.NodeOutput(audio_bytes_to_audio_input(audio_bytes)) + + +async def _stream_sonilo_music( + cls: type[IO.ComfyNode], + endpoint: ApiEndpoint, + form: aiohttp.FormData, +) -> bytes: + """POST ``form`` to Sonilo, read the NDJSON stream, and return the first stream's audio bytes.""" + url = urljoin(default_base_url().rstrip("/") + "/", endpoint.path.lstrip("/")) + + headers: dict[str, str] = {} + headers.update(get_auth_header(cls)) + headers.update(endpoint.headers) + + node_id = get_node_id(cls) + start_ts = time.monotonic() + last_chunk_status_ts = 0.0 + audio_streams: dict[int, list[bytes]] = {} + title: str | None = None + + timeout = aiohttp.ClientTimeout(total=1200.0, sock_read=300.0) + async with aiohttp.ClientSession(timeout=timeout) as session: + PromptServer.instance.send_progress_text("Status: Queued", node_id) + async with session.post(url, data=form, headers=headers) as resp: + if resp.status >= 400: + msg = await _extract_error_message(resp) + raise Exception(f"Sonilo API error ({resp.status}): {msg}") + + while True: + if is_processing_interrupted(): + raise ProcessingInterrupted("Task cancelled") + + raw_line = await resp.content.readline() + if not raw_line: + break + + line = raw_line.decode("utf-8").strip() + if not line: + continue + + try: + evt = json.loads(line) + except json.JSONDecodeError: + logger.warning("Sonilo: skipping malformed NDJSON line") + continue + + evt_type = evt.get("type") + if evt_type == "error": + code = evt.get("code", "UNKNOWN") + message = evt.get("message", "Unknown error") + raise Exception(f"Sonilo generation error ({code}): {message}") + if evt_type == "duration": + duration_sec = evt.get("duration_sec") + if duration_sec is not None: + PromptServer.instance.send_progress_text( + f"Status: Generating\nVideo duration: {duration_sec:.1f}s", + node_id, + ) + elif evt_type in ("titles", "title"): + # v2m sends a "titles" list, t2m sends a scalar "title" + if evt_type == "titles": + titles = evt.get("titles", []) + if titles: + title = titles[0] + else: + title = evt.get("title") or title + if title: + PromptServer.instance.send_progress_text( + f"Status: Generating\nTitle: {title}", + node_id, + ) + elif evt_type == "audio_chunk": + stream_idx = evt.get("stream_index", 0) + chunk_data = base64.b64decode(evt["data"]) + + if stream_idx not in audio_streams: + audio_streams[stream_idx] = [] + audio_streams[stream_idx].append(chunk_data) + + now = time.monotonic() + if now - last_chunk_status_ts >= 1.0: + total_chunks = sum(len(chunks) for chunks in audio_streams.values()) + elapsed = int(now - start_ts) + status_lines = ["Status: Receiving audio"] + if title: + status_lines.append(f"Title: {title}") + status_lines.append(f"Chunks received: {total_chunks}") + status_lines.append(f"Time elapsed: {elapsed}s") + PromptServer.instance.send_progress_text("\n".join(status_lines), node_id) + last_chunk_status_ts = now + elif evt_type == "complete": + break + + if not audio_streams: + raise Exception("Sonilo API returned no audio data.") + + PromptServer.instance.send_progress_text("Status: Completed", node_id) + selected_stream = 0 if 0 in audio_streams else min(audio_streams) + return b"".join(audio_streams[selected_stream]) + + +async def _extract_error_message(resp: aiohttp.ClientResponse) -> str: + """Extract a human-readable error message from an HTTP error response.""" + try: + error_body = await resp.json() + detail = error_body.get("detail", {}) + if isinstance(detail, dict): + return detail.get("message", str(detail)) + return str(detail) + except Exception: + return await resp.text() + + +class SoniloExtension(ComfyExtension): + @override + async def get_node_list(self) -> list[type[IO.ComfyNode]]: + return [SoniloVideoToMusic, SoniloTextToMusic] + + +async def comfy_entrypoint() -> SoniloExtension: + return SoniloExtension() diff --git a/comfy_api_nodes/nodes_sora.py b/comfy_api_nodes/nodes_sora.py index afc18bb25..4d9075dcf 100644 --- a/comfy_api_nodes/nodes_sora.py +++ b/comfy_api_nodes/nodes_sora.py @@ -33,9 +33,13 @@ class OpenAIVideoSora2(IO.ComfyNode): def define_schema(cls): return IO.Schema( node_id="OpenAIVideoSora2", - display_name="OpenAI Sora - Video", + display_name="OpenAI Sora - Video (Deprecated)", category="api node/video/Sora", - description="OpenAI video and audio generation.", + description=( + "OpenAI video and audio generation.\n\n" + "DEPRECATION NOTICE: OpenAI will stop serving the Sora v2 API in September 2026. " + "This node will be removed from ComfyUI at that time." + ), inputs=[ IO.Combo.Input( "model", diff --git a/comfy_api_nodes/nodes_stability.py b/comfy_api_nodes/nodes_stability.py index 9ef13c83b..906d8ff35 100644 --- a/comfy_api_nodes/nodes_stability.py +++ b/comfy_api_nodes/nodes_stability.py @@ -401,7 +401,7 @@ class StabilityUpscaleConservativeNode(IO.ComfyNode): ], is_api_node=True, price_badge=IO.PriceBadge( - expr="""{"type":"usd","usd":0.25}""", + expr="""{"type":"usd","usd":0.4}""", ), ) @@ -510,7 +510,7 @@ class StabilityUpscaleCreativeNode(IO.ComfyNode): ], is_api_node=True, price_badge=IO.PriceBadge( - expr="""{"type":"usd","usd":0.25}""", + expr="""{"type":"usd","usd":0.6}""", ), ) @@ -593,7 +593,7 @@ class StabilityUpscaleFastNode(IO.ComfyNode): ], is_api_node=True, price_badge=IO.PriceBadge( - expr="""{"type":"usd","usd":0.01}""", + expr="""{"type":"usd","usd":0.02}""", ), ) diff --git a/comfy_api_nodes/nodes_topaz.py b/comfy_api_nodes/nodes_topaz.py index b18b31af1..e79c16d3c 100644 --- a/comfy_api_nodes/nodes_topaz.py +++ b/comfy_api_nodes/nodes_topaz.py @@ -36,11 +36,15 @@ from comfy_api_nodes.util import ( ) UPSCALER_MODELS_MAP = { + "Astra 2": "ast-2", "Starlight (Astra) Fast": "slf-1", "Starlight (Astra) Creative": "slc-1", "Starlight Precise 2.5": "slp-2.5", } +AST2_MAX_FRAMES = 9000 +AST2_MAX_FRAMES_WITH_PROMPT = 450 + class TopazImageEnhance(IO.ComfyNode): @classmethod @@ -230,13 +234,20 @@ class TopazVideoEnhance(IO.ComfyNode): def define_schema(cls): return IO.Schema( node_id="TopazVideoEnhance", - display_name="Topaz Video Enhance", + display_name="Topaz Video Enhance (Legacy)", category="api node/video/Topaz", description="Breathe new life into video with powerful upscaling and recovery technology.", inputs=[ IO.Video.Input("video"), IO.Boolean.Input("upscaler_enabled", default=True), - IO.Combo.Input("upscaler_model", options=list(UPSCALER_MODELS_MAP.keys())), + IO.Combo.Input( + "upscaler_model", + options=[ + "Starlight (Astra) Fast", + "Starlight (Astra) Creative", + "Starlight Precise 2.5", + ], + ), IO.Combo.Input("upscaler_resolution", options=["FullHD (1080p)", "4K (2160p)"]), IO.Combo.Input( "upscaler_creativity", @@ -304,6 +315,7 @@ class TopazVideoEnhance(IO.ComfyNode): IO.Hidden.unique_id, ], is_api_node=True, + is_deprecated=True, ) @classmethod @@ -453,7 +465,350 @@ class TopazVideoEnhance(IO.ComfyNode): progress_extractor=lambda x: getattr(x, "progress", 0), price_extractor=lambda x: (x.estimates.cost[0] * 0.08 if x.estimates and x.estimates.cost[0] else None), poll_interval=10.0, - max_poll_attempts=320, + ) + return IO.NodeOutput(await download_url_to_video_output(final_response.download.url)) + + +class TopazVideoEnhanceV2(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="TopazVideoEnhanceV2", + display_name="Topaz Video Enhance", + category="api node/video/Topaz", + description="Breathe new life into video with powerful upscaling and recovery technology.", + inputs=[ + IO.Video.Input("video"), + IO.DynamicCombo.Input( + "upscaler_model", + options=[ + IO.DynamicCombo.Option( + "Astra 2", + [ + IO.Combo.Input("upscaler_resolution", options=["FullHD (1080p)", "4K (2160p)"]), + IO.Float.Input( + "creativity", + default=0.5, + min=0.0, + max=1.0, + step=0.1, + display_mode=IO.NumberDisplay.slider, + tooltip="Creative strength of the upscale.", + ), + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Optional descriptive (not instructive) scene prompt." + f"Capping input at {AST2_MAX_FRAMES_WITH_PROMPT} frames (~15s @ 30fps) when set.", + ), + IO.Float.Input( + "sharp", + default=0.5, + min=0.0, + max=1.0, + step=0.01, + display_mode=IO.NumberDisplay.slider, + tooltip="Pre-enhance sharpness: " + "0.0=Gaussian blur, 0.5=passthrough (default), 1.0=USM sharpening.", + advanced=True, + ), + IO.Float.Input( + "realism", + default=0.0, + min=0.0, + max=1.0, + step=0.01, + display_mode=IO.NumberDisplay.slider, + tooltip="Pulls output toward photographic realism." + "Leave at 0 for the model default.", + advanced=True, + ), + ], + ), + IO.DynamicCombo.Option( + "Starlight (Astra) Fast", + [IO.Combo.Input("upscaler_resolution", options=["FullHD (1080p)", "4K (2160p)"]),], + ), + IO.DynamicCombo.Option( + "Starlight (Astra) Creative", + [ + IO.Combo.Input("upscaler_resolution", options=["FullHD (1080p)", "4K (2160p)"]), + IO.Combo.Input( + "creativity", + options=["low", "middle", "high"], + default="low", + tooltip="Creative strength of the upscale.", + ), + ], + ), + IO.DynamicCombo.Option( + "Starlight Precise 2.5", + [IO.Combo.Input("upscaler_resolution", options=["FullHD (1080p)", "4K (2160p)"])], + ), + IO.DynamicCombo.Option("Disabled", []), + ], + ), + IO.DynamicCombo.Input( + "interpolation_model", + options=[ + IO.DynamicCombo.Option("Disabled", []), + IO.DynamicCombo.Option( + "apo-8", + [ + IO.Int.Input( + "interpolation_frame_rate", + default=60, + min=15, + max=240, + display_mode=IO.NumberDisplay.number, + tooltip="Output frame rate.", + ), + IO.Int.Input( + "interpolation_slowmo", + default=1, + min=1, + max=16, + display_mode=IO.NumberDisplay.number, + tooltip="Slow-motion factor applied to the input video. " + "For example, 2 makes the output twice as slow and doubles the duration.", + advanced=True, + ), + IO.Boolean.Input( + "interpolation_duplicate", + default=False, + tooltip="Analyze the input for duplicate frames and remove them.", + advanced=True, + ), + IO.Float.Input( + "interpolation_duplicate_threshold", + default=0.01, + min=0.001, + max=0.1, + step=0.001, + display_mode=IO.NumberDisplay.number, + tooltip="Detection sensitivity for duplicate frames.", + advanced=True, + ), + ], + ), + ], + ), + IO.Combo.Input( + "dynamic_compression_level", + options=["Low", "Mid", "High"], + default="Low", + tooltip="CQP level.", + optional=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=[ + "upscaler_model", + "upscaler_model.upscaler_resolution", + "interpolation_model", + ]), + expr=""" + ( + $model := $lookup(widgets, "upscaler_model"); + $res := $lookup(widgets, "upscaler_model.upscaler_resolution"); + $interp := $lookup(widgets, "interpolation_model"); + $is4k := $contains($res, "4k"); + $hasInterp := $interp != "disabled"; + $rates := { + "starlight (astra) fast": {"hd": 0.43, "uhd": 0.85}, + "starlight precise 2.5": {"hd": 0.70, "uhd": 1.54}, + "astra 2": {"hd": 1.72, "uhd": 2.85}, + "starlight (astra) creative": {"hd": 2.25, "uhd": 3.99} + }; + $surcharge := $is4k ? 0.28 : 0.14; + $entry := $lookup($rates, $model); + $base := $is4k ? $entry.uhd : $entry.hd; + $hi := $base + ($hasInterp ? $surcharge : 0); + $model = "disabled" + ? {"type":"text","text":"Interpolation only"} + : ($hasInterp + ? {"type":"text","text":"~" & $string($base) & "–" & $string($hi) & " credits/src frame"} + : {"type":"text","text":"~" & $string($base) & " credits/src frame"}) + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + video: Input.Video, + upscaler_model: dict, + interpolation_model: dict, + dynamic_compression_level: str = "Low", + ) -> IO.NodeOutput: + upscaler_choice = upscaler_model["upscaler_model"] + interpolation_choice = interpolation_model["interpolation_model"] + if upscaler_choice == "Disabled" and interpolation_choice == "Disabled": + raise ValueError("There is nothing to do: both upscaling and interpolation are disabled.") + validate_container_format_is_mp4(video) + src_width, src_height = video.get_dimensions() + src_frame_rate = int(video.get_frame_rate()) + duration_sec = video.get_duration() + src_video_stream = video.get_stream_source() + target_width = src_width + target_height = src_height + target_frame_rate = src_frame_rate + filters = [] + if upscaler_choice != "Disabled": + if "1080p" in upscaler_model["upscaler_resolution"]: + target_pixel_p = 1080 + max_long_side = 1920 + else: + target_pixel_p = 2160 + max_long_side = 3840 + ar = src_width / src_height + if src_width >= src_height: + # Landscape or Square; Attempt to set height to target (e.g., 2160), calculate width + target_height = target_pixel_p + target_width = int(target_height * ar) + # Check if width exceeds standard bounds (for ultra-wide e.g., 21:9 ARs) + if target_width > max_long_side: + target_width = max_long_side + target_height = int(target_width / ar) + else: + # Portrait; Attempt to set width to target (e.g., 2160), calculate height + target_width = target_pixel_p + target_height = int(target_width / ar) + # Check if height exceeds standard bounds + if target_height > max_long_side: + target_height = max_long_side + target_width = int(target_height * ar) + if target_width % 2 != 0: + target_width += 1 + if target_height % 2 != 0: + target_height += 1 + model_id = UPSCALER_MODELS_MAP[upscaler_choice] + if model_id == "slc-1": + filters.append( + VideoEnhancementFilter( + model=model_id, + creativity=upscaler_model["creativity"], + isOptimizedMode=True, + ) + ) + elif model_id == "ast-2": + n_frames = video.get_frame_count() + ast2_prompt = (upscaler_model["prompt"] or "").strip() + if ast2_prompt and n_frames > AST2_MAX_FRAMES_WITH_PROMPT: + raise ValueError( + f"Astra 2 with a prompt is limited to {AST2_MAX_FRAMES_WITH_PROMPT} input frames " + f"(~15s @ 30fps); video has {n_frames}. Clear the prompt or shorten the clip." + ) + if n_frames > AST2_MAX_FRAMES: + raise ValueError(f"Astra 2 is limited to {AST2_MAX_FRAMES} input frames; video has {n_frames}.") + realism = upscaler_model["realism"] + filters.append( + VideoEnhancementFilter( + model=model_id, + creativity=upscaler_model["creativity"], + prompt=(ast2_prompt or None), + sharp=upscaler_model["sharp"], + realism=(realism if realism > 0 else None), + ) + ) + else: + filters.append(VideoEnhancementFilter(model=model_id)) + if interpolation_choice != "Disabled": + target_frame_rate = interpolation_model["interpolation_frame_rate"] + filters.append( + VideoFrameInterpolationFilter( + model=interpolation_choice, + slowmo=interpolation_model["interpolation_slowmo"], + fps=interpolation_model["interpolation_frame_rate"], + duplicate=interpolation_model["interpolation_duplicate"], + duplicate_threshold=interpolation_model["interpolation_duplicate_threshold"], + ), + ) + initial_res = await sync_op( + cls, + ApiEndpoint(path="/proxy/topaz/video/", method="POST"), + response_model=CreateVideoResponse, + data=CreateVideoRequest( + source=CreateVideoRequestSource( + container="mp4", + size=get_fs_object_size(src_video_stream), + duration=int(duration_sec), + frameCount=video.get_frame_count(), + frameRate=src_frame_rate, + resolution=Resolution(width=src_width, height=src_height), + ), + filters=filters, + output=OutputInformationVideo( + resolution=Resolution(width=target_width, height=target_height), + frameRate=target_frame_rate, + audioCodec="AAC", + audioTransfer="Copy", + dynamicCompressionLevel=dynamic_compression_level, + ), + ), + wait_label="Creating task", + final_label_on_success="Task created", + ) + upload_res = await sync_op( + cls, + ApiEndpoint( + path=f"/proxy/topaz/video/{initial_res.requestId}/accept", + method="PATCH", + ), + response_model=VideoAcceptResponse, + wait_label="Preparing upload", + final_label_on_success="Upload started", + ) + if len(upload_res.urls) > 1: + raise NotImplementedError( + "Large files are not currently supported. Please open an issue in the ComfyUI repository." + ) + async with aiohttp.ClientSession(headers={"Content-Type": "video/mp4"}) as session: + if isinstance(src_video_stream, BytesIO): + src_video_stream.seek(0) + async with session.put(upload_res.urls[0], data=src_video_stream, raise_for_status=True) as res: + upload_etag = res.headers["Etag"] + else: + with builtins.open(src_video_stream, "rb") as video_file: + async with session.put(upload_res.urls[0], data=video_file, raise_for_status=True) as res: + upload_etag = res.headers["Etag"] + await sync_op( + cls, + ApiEndpoint( + path=f"/proxy/topaz/video/{initial_res.requestId}/complete-upload", + method="PATCH", + ), + response_model=VideoCompleteUploadResponse, + data=VideoCompleteUploadRequest( + uploadResults=[ + VideoCompleteUploadRequestPart( + partNum=1, + eTag=upload_etag, + ), + ], + ), + wait_label="Finalizing upload", + final_label_on_success="Upload completed", + ) + final_response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/topaz/video/{initial_res.requestId}/status"), + response_model=VideoStatusResponse, + status_extractor=lambda x: x.status, + progress_extractor=lambda x: getattr(x, "progress", 0), + price_extractor=lambda x: (x.estimates.cost[0] * 0.08 if x.estimates and x.estimates.cost[0] else None), + poll_interval=10.0, ) return IO.NodeOutput(await download_url_to_video_output(final_response.download.url)) @@ -464,6 +819,7 @@ class TopazExtension(ComfyExtension): return [ TopazImageEnhance, TopazVideoEnhance, + TopazVideoEnhanceV2, ] diff --git a/comfy_api_nodes/nodes_veo2.py b/comfy_api_nodes/nodes_veo2.py index 13fc1cc36..2ff75d9b2 100644 --- a/comfy_api_nodes/nodes_veo2.py +++ b/comfy_api_nodes/nodes_veo2.py @@ -24,8 +24,9 @@ from comfy_api_nodes.util import ( AVERAGE_DURATION_VIDEO_GEN = 32 MODELS_MAP = { "veo-2.0-generate-001": "veo-2.0-generate-001", - "veo-3.1-generate": "veo-3.1-generate-preview", - "veo-3.1-fast-generate": "veo-3.1-fast-generate-preview", + "veo-3.1-generate": "veo-3.1-generate-001", + "veo-3.1-fast-generate": "veo-3.1-fast-generate-001", + "veo-3.1-lite": "veo-3.1-lite-generate-001", "veo-3.0-generate-001": "veo-3.0-generate-001", "veo-3.0-fast-generate-001": "veo-3.0-fast-generate-001", } @@ -247,17 +248,8 @@ class VeoVideoGenerationNode(IO.ComfyNode): raise Exception("Video generation completed but no video was returned") -class Veo3VideoGenerationNode(VeoVideoGenerationNode): - """ - Generates videos from text prompts using Google's Veo 3 API. - - Supported models: - - veo-3.0-generate-001 - - veo-3.0-fast-generate-001 - - This node extends the base Veo node with Veo 3 specific features including - audio generation and fixed 8-second duration. - """ +class Veo3VideoGenerationNode(IO.ComfyNode): + """Generates videos from text prompts using Google's Veo 3 API.""" @classmethod def define_schema(cls): @@ -279,6 +271,13 @@ class Veo3VideoGenerationNode(VeoVideoGenerationNode): default="16:9", tooltip="Aspect ratio of the output video", ), + IO.Combo.Input( + "resolution", + options=["720p", "1080p", "4k"], + default="720p", + tooltip="Output video resolution. 4K is not available for veo-3.1-lite and veo-3.0 models.", + optional=True, + ), IO.String.Input( "negative_prompt", multiline=True, @@ -289,11 +288,11 @@ class Veo3VideoGenerationNode(VeoVideoGenerationNode): IO.Int.Input( "duration_seconds", default=8, - min=8, + min=4, max=8, - step=1, + step=2, display_mode=IO.NumberDisplay.number, - tooltip="Duration of the output video in seconds (Veo 3 only supports 8 seconds)", + tooltip="Duration of the output video in seconds", optional=True, ), IO.Boolean.Input( @@ -332,10 +331,10 @@ class Veo3VideoGenerationNode(VeoVideoGenerationNode): options=[ "veo-3.1-generate", "veo-3.1-fast-generate", + "veo-3.1-lite", "veo-3.0-generate-001", "veo-3.0-fast-generate-001", ], - default="veo-3.0-generate-001", tooltip="Veo 3 model to use for video generation", optional=True, ), @@ -356,21 +355,111 @@ class Veo3VideoGenerationNode(VeoVideoGenerationNode): ], is_api_node=True, price_badge=IO.PriceBadge( - depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio"]), + depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio", "resolution", "duration_seconds"]), expr=""" ( $m := widgets.model; + $r := widgets.resolution; $a := widgets.generate_audio; - ($contains($m,"veo-3.0-fast-generate-001") or $contains($m,"veo-3.1-fast-generate")) - ? {"type":"usd","usd": ($a ? 1.2 : 0.8)} - : ($contains($m,"veo-3.0-generate-001") or $contains($m,"veo-3.1-generate")) - ? {"type":"usd","usd": ($a ? 3.2 : 1.6)} - : {"type":"range_usd","min_usd":0.8,"max_usd":3.2} + $seconds := widgets.duration_seconds; + $pps := + $contains($m, "lite") + ? ($r = "1080p" ? ($a ? 0.08 : 0.05) : ($a ? 0.05 : 0.03)) + : $contains($m, "3.1-fast") + ? ($r = "4k" ? ($a ? 0.30 : 0.25) : $r = "1080p" ? ($a ? 0.12 : 0.10) : ($a ? 0.10 : 0.08)) + : $contains($m, "3.1-generate") + ? ($r = "4k" ? ($a ? 0.60 : 0.40) : ($a ? 0.40 : 0.20)) + : $contains($m, "3.0-fast") + ? ($a ? 0.15 : 0.10) + : ($a ? 0.40 : 0.20); + {"type":"usd","usd": $pps * $seconds} ) """, ), ) + @classmethod + async def execute( + cls, + prompt, + aspect_ratio="16:9", + resolution="720p", + negative_prompt="", + duration_seconds=8, + enhance_prompt=True, + person_generation="ALLOW", + seed=0, + image=None, + model="veo-3.0-generate-001", + generate_audio=False, + ): + if resolution == "4k" and ("lite" in model or "3.0" in model): + raise Exception("4K resolution is not supported by the veo-3.1-lite or veo-3.0 models.") + + model = MODELS_MAP[model] + + instances = [{"prompt": prompt}] + if image is not None: + image_base64 = tensor_to_base64_string(image) + if image_base64: + instances[0]["image"] = {"bytesBase64Encoded": image_base64, "mimeType": "image/png"} + + parameters = { + "aspectRatio": aspect_ratio, + "personGeneration": person_generation, + "durationSeconds": duration_seconds, + "enhancePrompt": True, + "generateAudio": generate_audio, + } + if negative_prompt: + parameters["negativePrompt"] = negative_prompt + if seed > 0: + parameters["seed"] = seed + if "veo-3.1" in model: + parameters["resolution"] = resolution + + initial_response = await sync_op( + cls, + ApiEndpoint(path=f"/proxy/veo/{model}/generate", method="POST"), + response_model=VeoGenVidResponse, + data=VeoGenVidRequest( + instances=instances, + parameters=parameters, + ), + ) + + poll_response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/veo/{model}/poll", method="POST"), + response_model=VeoGenVidPollResponse, + status_extractor=lambda r: "completed" if r.done else "pending", + data=VeoGenVidPollRequest(operationName=initial_response.name), + poll_interval=9.0, + estimated_duration=AVERAGE_DURATION_VIDEO_GEN, + ) + + if poll_response.error: + raise Exception(f"Veo API error: {poll_response.error.message} (code: {poll_response.error.code})") + + response = poll_response.response + filtered_count = response.raiMediaFilteredCount + if filtered_count: + reasons = response.raiMediaFilteredReasons or [] + reason_part = f": {reasons[0]}" if reasons else "" + raise Exception( + f"Content blocked by Google's Responsible AI filters{reason_part} " + f"({filtered_count} video{'s' if filtered_count != 1 else ''} filtered)." + ) + + if response.videos: + video = response.videos[0] + if video.bytesBase64Encoded: + return IO.NodeOutput(InputImpl.VideoFromFile(BytesIO(base64.b64decode(video.bytesBase64Encoded)))) + if video.gcsUri: + return IO.NodeOutput(await download_url_to_video_output(video.gcsUri)) + raise Exception("Video returned but no data or URL was provided") + raise Exception("Video generation completed but no video was returned") + class Veo3FirstLastFrameNode(IO.ComfyNode): @@ -394,7 +483,7 @@ class Veo3FirstLastFrameNode(IO.ComfyNode): default="", tooltip="Negative text prompt to guide what to avoid in the video", ), - IO.Combo.Input("resolution", options=["720p", "1080p"]), + IO.Combo.Input("resolution", options=["720p", "1080p", "4k"]), IO.Combo.Input( "aspect_ratio", options=["16:9", "9:16"], @@ -424,8 +513,7 @@ class Veo3FirstLastFrameNode(IO.ComfyNode): IO.Image.Input("last_frame", tooltip="End frame"), IO.Combo.Input( "model", - options=["veo-3.1-generate", "veo-3.1-fast-generate"], - default="veo-3.1-fast-generate", + options=["veo-3.1-generate", "veo-3.1-fast-generate", "veo-3.1-lite"], ), IO.Boolean.Input( "generate_audio", @@ -443,26 +531,20 @@ class Veo3FirstLastFrameNode(IO.ComfyNode): ], is_api_node=True, price_badge=IO.PriceBadge( - depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio", "duration"]), + depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio", "duration", "resolution"]), expr=""" ( - $prices := { - "veo-3.1-fast-generate": { "audio": 0.15, "no_audio": 0.10 }, - "veo-3.1-generate": { "audio": 0.40, "no_audio": 0.20 } - }; $m := widgets.model; - $ga := (widgets.generate_audio = "true"); + $r := widgets.resolution; + $ga := widgets.generate_audio; $seconds := widgets.duration; - $modelKey := - $contains($m, "veo-3.1-fast-generate") ? "veo-3.1-fast-generate" : - $contains($m, "veo-3.1-generate") ? "veo-3.1-generate" : - ""; - $audioKey := $ga ? "audio" : "no_audio"; - $modelPrices := $lookup($prices, $modelKey); - $pps := $lookup($modelPrices, $audioKey); - ($pps != null) - ? {"type":"usd","usd": $pps * $seconds} - : {"type":"range_usd","min_usd": 0.4, "max_usd": 3.2} + $pps := + $contains($m, "lite") + ? ($r = "1080p" ? ($ga ? 0.08 : 0.05) : ($ga ? 0.05 : 0.03)) + : $contains($m, "fast") + ? ($r = "4k" ? ($ga ? 0.30 : 0.25) : $r = "1080p" ? ($ga ? 0.12 : 0.10) : ($ga ? 0.10 : 0.08)) + : ($r = "4k" ? ($ga ? 0.60 : 0.40) : ($ga ? 0.40 : 0.20)); + {"type":"usd","usd": $pps * $seconds} ) """, ), @@ -482,6 +564,9 @@ class Veo3FirstLastFrameNode(IO.ComfyNode): model: str, generate_audio: bool, ): + if "lite" in model and resolution == "4k": + raise Exception("4K resolution is not supported by the veo-3.1-lite model.") + model = MODELS_MAP[model] initial_response = await sync_op( cls, @@ -519,7 +604,7 @@ class Veo3FirstLastFrameNode(IO.ComfyNode): data=VeoGenVidPollRequest( operationName=initial_response.name, ), - poll_interval=5.0, + poll_interval=9.0, estimated_duration=AVERAGE_DURATION_VIDEO_GEN, ) diff --git a/comfy_api_nodes/nodes_vidu.py b/comfy_api_nodes/nodes_vidu.py index f04407eb5..8d90cefeb 100644 --- a/comfy_api_nodes/nodes_vidu.py +++ b/comfy_api_nodes/nodes_vidu.py @@ -38,7 +38,7 @@ async def execute_task( cls: type[IO.ComfyNode], vidu_endpoint: str, payload: TaskCreationRequest | TaskExtendCreationRequest | TaskMultiFrameCreationRequest, - max_poll_attempts: int = 320, + max_poll_attempts: int = 480, ) -> list[TaskResult]: task_creation_response = await sync_op( cls, @@ -1097,7 +1097,6 @@ class ViduExtendVideoNode(IO.ComfyNode): video_url=await upload_video_to_comfyapi(cls, video, wait_label="Uploading video"), images=[image_url] if image_url else None, ), - max_poll_attempts=480, ) return IO.NodeOutput(await download_url_to_video_output(results[0].url)) diff --git a/comfy_api_nodes/nodes_wan.py b/comfy_api_nodes/nodes_wan.py index e2afe7f9c..68061bb5c 100644 --- a/comfy_api_nodes/nodes_wan.py +++ b/comfy_api_nodes/nodes_wan.py @@ -1,9 +1,40 @@ import re -from pydantic import BaseModel, Field from typing_extensions import override from comfy_api.latest import IO, ComfyExtension, Input +from comfy_api_nodes.apis.wan import ( + Image2ImageInputField, + Image2ImageParametersField, + Image2ImageTaskCreationRequest, + Image2VideoInputField, + Image2VideoParametersField, + Image2VideoTaskCreationRequest, + ImageTaskStatusResponse, + Reference2VideoInputField, + Reference2VideoParametersField, + Reference2VideoTaskCreationRequest, + TaskCreationResponse, + Text2ImageInputField, + Text2ImageTaskCreationRequest, + Text2VideoInputField, + Text2VideoParametersField, + Text2VideoTaskCreationRequest, + Txt2ImageParametersField, + VideoTaskStatusResponse, + Wan27ImageToVideoInputField, + Wan27ImageToVideoParametersField, + Wan27ImageToVideoTaskCreationRequest, + Wan27MediaItem, + Wan27ReferenceVideoInputField, + Wan27ReferenceVideoParametersField, + Wan27ReferenceVideoTaskCreationRequest, + Wan27Text2VideoParametersField, + Wan27Text2VideoTaskCreationRequest, + Wan27VideoEditInputField, + Wan27VideoEditParametersField, + Wan27VideoEditTaskCreationRequest, +) from comfy_api_nodes.util import ( ApiEndpoint, audio_to_base64_string, @@ -13,157 +44,14 @@ from comfy_api_nodes.util import ( poll_op, sync_op, tensor_to_base64_string, + upload_audio_to_comfyapi, + upload_image_to_comfyapi, upload_video_to_comfyapi, validate_audio_duration, + validate_string, validate_video_duration, ) - -class Text2ImageInputField(BaseModel): - prompt: str = Field(...) - negative_prompt: str | None = Field(None) - - -class Image2ImageInputField(BaseModel): - prompt: str = Field(...) - negative_prompt: str | None = Field(None) - images: list[str] = Field(..., min_length=1, max_length=2) - - -class Text2VideoInputField(BaseModel): - prompt: str = Field(...) - negative_prompt: str | None = Field(None) - audio_url: str | None = Field(None) - - -class Image2VideoInputField(BaseModel): - prompt: str = Field(...) - negative_prompt: str | None = Field(None) - img_url: str = Field(...) - audio_url: str | None = Field(None) - - -class Reference2VideoInputField(BaseModel): - prompt: str = Field(...) - negative_prompt: str | None = Field(None) - reference_video_urls: list[str] = Field(...) - - -class Txt2ImageParametersField(BaseModel): - size: str = Field(...) - n: int = Field(1, description="Number of images to generate.") # we support only value=1 - seed: int = Field(..., ge=0, le=2147483647) - prompt_extend: bool = Field(True) - watermark: bool = Field(False) - - -class Image2ImageParametersField(BaseModel): - size: str | None = Field(None) - n: int = Field(1, description="Number of images to generate.") # we support only value=1 - seed: int = Field(..., ge=0, le=2147483647) - watermark: bool = Field(False) - - -class Text2VideoParametersField(BaseModel): - size: str = Field(...) - seed: int = Field(..., ge=0, le=2147483647) - duration: int = Field(5, ge=5, le=15) - prompt_extend: bool = Field(True) - watermark: bool = Field(False) - audio: bool = Field(False, description="Whether to generate audio automatically.") - shot_type: str = Field("single") - - -class Image2VideoParametersField(BaseModel): - resolution: str = Field(...) - seed: int = Field(..., ge=0, le=2147483647) - duration: int = Field(5, ge=5, le=15) - prompt_extend: bool = Field(True) - watermark: bool = Field(False) - audio: bool = Field(False, description="Whether to generate audio automatically.") - shot_type: str = Field("single") - - -class Reference2VideoParametersField(BaseModel): - size: str = Field(...) - duration: int = Field(5, ge=5, le=15) - shot_type: str = Field("single") - seed: int = Field(..., ge=0, le=2147483647) - watermark: bool = Field(False) - - -class Text2ImageTaskCreationRequest(BaseModel): - model: str = Field(...) - input: Text2ImageInputField = Field(...) - parameters: Txt2ImageParametersField = Field(...) - - -class Image2ImageTaskCreationRequest(BaseModel): - model: str = Field(...) - input: Image2ImageInputField = Field(...) - parameters: Image2ImageParametersField = Field(...) - - -class Text2VideoTaskCreationRequest(BaseModel): - model: str = Field(...) - input: Text2VideoInputField = Field(...) - parameters: Text2VideoParametersField = Field(...) - - -class Image2VideoTaskCreationRequest(BaseModel): - model: str = Field(...) - input: Image2VideoInputField = Field(...) - parameters: Image2VideoParametersField = Field(...) - - -class Reference2VideoTaskCreationRequest(BaseModel): - model: str = Field(...) - input: Reference2VideoInputField = Field(...) - parameters: Reference2VideoParametersField = Field(...) - - -class TaskCreationOutputField(BaseModel): - task_id: str = Field(...) - task_status: str = Field(...) - - -class TaskCreationResponse(BaseModel): - output: TaskCreationOutputField | None = Field(None) - request_id: str = Field(...) - code: str | None = Field(None, description="Error code for the failed request.") - message: str | None = Field(None, description="Details about the failed request.") - - -class TaskResult(BaseModel): - url: str | None = Field(None) - code: str | None = Field(None) - message: str | None = Field(None) - - -class ImageTaskStatusOutputField(TaskCreationOutputField): - task_id: str = Field(...) - task_status: str = Field(...) - results: list[TaskResult] | None = Field(None) - - -class VideoTaskStatusOutputField(TaskCreationOutputField): - task_id: str = Field(...) - task_status: str = Field(...) - video_url: str | None = Field(None) - code: str | None = Field(None) - message: str | None = Field(None) - - -class ImageTaskStatusResponse(BaseModel): - output: ImageTaskStatusOutputField | None = Field(None) - request_id: str = Field(...) - - -class VideoTaskStatusResponse(BaseModel): - output: VideoTaskStatusOutputField | None = Field(None) - request_id: str = Field(...) - - RES_IN_PARENS = re.compile(r"\((\d+)\s*[x×]\s*(\d+)\)") @@ -179,7 +67,6 @@ class WanTextToImageApi(IO.ComfyNode): IO.Combo.Input( "model", options=["wan2.5-t2i-preview"], - default="wan2.5-t2i-preview", tooltip="Model to use.", ), IO.String.Input( @@ -931,7 +818,1380 @@ class WanReferenceVideoApi(IO.ComfyNode): response_model=VideoTaskStatusResponse, status_extractor=lambda x: x.output.task_status, poll_interval=6, - max_poll_attempts=280, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class Wan2TextToVideoApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="Wan2TextToVideoApi", + display_name="Wan 2.7 Text to Video", + category="api node/video/Wan", + description="Generates a video based on a text prompt using the Wan 2.7 model.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "wan2.7-t2v", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Prompt describing the elements and visual features. " + "Supports English and Chinese.", + ), + IO.String.Input( + "negative_prompt", + multiline=True, + default="", + tooltip="Negative prompt describing what to avoid.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Combo.Input( + "ratio", + options=["16:9", "9:16", "1:1", "4:3", "3:4"], + ), + IO.Int.Input( + "duration", + default=5, + min=2, + max=15, + step=1, + display_mode=IO.NumberDisplay.number, + ), + ], + ), + ], + ), + IO.Audio.Input( + "audio", + optional=True, + tooltip="Audio for driving video generation (e.g., lip sync, beat-matched motion). " + "Duration: 3s-30s. If not provided, the model automatically generates matching " + "background music or sound effects.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "prompt_extend", + default=True, + tooltip="Whether to enhance the prompt with AI assistance.", + advanced=True, + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.1, "1080p": 0.15 }; + $pps := $lookup($ppsTable, $res); + { "type": "usd", "usd": $pps * $dur } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + seed: int, + prompt_extend: bool, + watermark: bool, + audio: Input.Audio | None = None, + ): + validate_string(model["prompt"], strip_whitespace=False, min_length=1) + audio_url = None + if audio is not None: + validate_audio_duration(audio, 1.5, 60.0) + audio_url = await upload_audio_to_comfyapi( + cls, audio, container_format="mp3", codec_name="libmp3lame", mime_type="audio/mpeg" + ) + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27Text2VideoTaskCreationRequest( + model=model["model"], + input=Text2VideoInputField( + prompt=model["prompt"], + negative_prompt=model["negative_prompt"] or None, + audio_url=audio_url, + ), + parameters=Wan27Text2VideoParametersField( + resolution=model["resolution"], + ratio=model["ratio"], + duration=model["duration"], + seed=seed, + prompt_extend=prompt_extend, + watermark=watermark, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class Wan2ImageToVideoApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="Wan2ImageToVideoApi", + display_name="Wan 2.7 Image to Video", + category="api node/video/Wan", + description="Generate a video from a first-frame image, with optional last-frame image and audio.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "wan2.7-i2v", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Prompt describing the elements and visual features. " + "Supports English and Chinese.", + ), + IO.String.Input( + "negative_prompt", + multiline=True, + default="", + tooltip="Negative prompt describing what to avoid.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Int.Input( + "duration", + default=5, + min=2, + max=15, + step=1, + display_mode=IO.NumberDisplay.number, + ), + ], + ), + ], + ), + IO.Image.Input( + "first_frame", + tooltip="First frame image. The output aspect ratio is derived from this image.", + ), + IO.Image.Input( + "last_frame", + optional=True, + tooltip="Last frame image. The model generates a video transitioning from first to last frame.", + ), + IO.Audio.Input( + "audio", + optional=True, + tooltip="Audio for driving video generation (e.g., lip sync, beat-matched motion). " + "Duration: 2s-30s. If not provided, the model automatically generates matching " + "background music or sound effects.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "prompt_extend", + default=True, + tooltip="Whether to enhance the prompt with AI assistance.", + advanced=True, + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.1, "1080p": 0.15 }; + $pps := $lookup($ppsTable, $res); + { "type": "usd", "usd": $pps * $dur } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + first_frame: Input.Image, + seed: int, + prompt_extend: bool, + watermark: bool, + last_frame: Input.Image | None = None, + audio: Input.Audio | None = None, + ): + media = [ + Wan27MediaItem( + type="first_frame", + url=await upload_image_to_comfyapi(cls, image=first_frame), + ) + ] + if last_frame is not None: + media.append( + Wan27MediaItem( + type="last_frame", + url=await upload_image_to_comfyapi(cls, image=last_frame), + ) + ) + if audio is not None: + validate_audio_duration(audio, 2.0, 30.0) + audio_url = await upload_audio_to_comfyapi( + cls, audio, container_format="mp3", codec_name="libmp3lame", mime_type="audio/mpeg" + ) + media.append(Wan27MediaItem(type="driving_audio", url=audio_url)) + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27ImageToVideoTaskCreationRequest( + model=model["model"], + input=Wan27ImageToVideoInputField( + prompt=model["prompt"] or None, + negative_prompt=model["negative_prompt"] or None, + media=media, + ), + parameters=Wan27ImageToVideoParametersField( + resolution=model["resolution"], + duration=model["duration"], + seed=seed, + prompt_extend=prompt_extend, + watermark=watermark, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class Wan2VideoContinuationApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="Wan2VideoContinuationApi", + display_name="Wan 2.7 Video Continuation", + category="api node/video/Wan", + description="Continue a video from where it left off, with optional last-frame control.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "wan2.7-i2v", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Prompt describing the elements and visual features. Supports English and Chinese.", + ), + IO.String.Input( + "negative_prompt", + multiline=True, + default="", + tooltip="Negative prompt describing what to avoid.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Int.Input( + "duration", + default=5, + min=2, + max=15, + step=1, + display_mode=IO.NumberDisplay.number, + tooltip="Total output duration in seconds. The model generates continuation " + "to fill the remaining time after the input clip.", + ), + ], + ), + ], + ), + IO.Video.Input( + "first_clip", + tooltip="Input video to continue from. Duration: 2s-10s. " + "The output aspect ratio is derived from this video.", + ), + IO.Image.Input( + "last_frame", + optional=True, + tooltip="Last frame image. The continuation will transition towards this frame.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "prompt_extend", + default=True, + tooltip="Whether to enhance the prompt with AI assistance.", + advanced=True, + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.1, "1080p": 0.15 }; + $pps := $lookup($ppsTable, $res); + $outputPrice := $pps * $dur; + { + "type": "range_usd", + "min_usd": 2 * $pps + $outputPrice, + "max_usd": 5 * $pps + $outputPrice + } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + first_clip: Input.Video, + prompt: str = "", + negative_prompt: str = "", + last_frame: Input.Image | None = None, + seed: int = 0, + prompt_extend: bool = True, + watermark: bool = False, + ): + validate_video_duration(first_clip, min_duration=2, max_duration=10) + media = [ + Wan27MediaItem( + type="first_clip", + url=await upload_video_to_comfyapi(cls, first_clip), + ) + ] + if last_frame is not None: + media.append( + Wan27MediaItem( + type="last_frame", + url=await upload_image_to_comfyapi(cls, image=last_frame), + ) + ) + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27ImageToVideoTaskCreationRequest( + model=model["model"], + input=Wan27ImageToVideoInputField( + prompt=model["prompt"] or None, + negative_prompt=model["negative_prompt"] or None, + media=media, + ), + parameters=Wan27ImageToVideoParametersField( + resolution=model["resolution"], + duration=model["duration"], + seed=seed, + prompt_extend=prompt_extend, + watermark=watermark, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class Wan2VideoEditApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="Wan2VideoEditApi", + display_name="Wan 2.7 Video Edit", + category="api node/video/Wan", + description="Edit a video using text instructions, reference images, or style transfer.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "wan2.7-videoedit", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Editing instructions or style transfer requirements.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Combo.Input( + "ratio", + options=["16:9", "9:16", "1:1", "4:3", "3:4"], + tooltip="Aspect ratio. If not changed, approximates the input video ratio.", + ), + IO.Combo.Input( + "duration", + options=["auto", "2", "3", "4", "5", "6", "7", "8", "9", "10"], + default="auto", + tooltip="Output duration in seconds. 'auto' matches the input video duration. " + "A specific value truncates from the start of the video.", + ), + IO.Autogrow.Input( + "reference_images", + template=IO.Autogrow.TemplateNames( + IO.Image.Input("reference_image"), + names=[ + "image1", + "image2", + "image3", + "image4", + ], + min=0, + ), + ), + ], + ), + ], + ), + IO.Video.Input( + "video", + tooltip="The video to edit.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Combo.Input( + "audio_setting", + options=["auto", "origin"], + default="auto", + tooltip="'auto': model decides whether to regenerate audio based on the prompt. " + "'origin': preserve the original audio from the input video.", + advanced=True, + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.1, "1080p": 0.15 }; + $pps := $lookup($ppsTable, $res); + { "type": "usd", "usd": $pps, "format": { "suffix": "/second", "note": "(input + output)" } } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + video: Input.Video, + seed: int, + audio_setting: str, + watermark: bool, + ): + validate_string(model["prompt"], strip_whitespace=False, min_length=1) + validate_video_duration(video, min_duration=2, max_duration=10) + duration = 0 if model["duration"] == "auto" else int(model["duration"]) + media = [Wan27MediaItem(type="video", url=await upload_video_to_comfyapi(cls, video))] + reference_images = model.get("reference_images", {}) + for key in reference_images: + media.append( + Wan27MediaItem( + type="reference_image", url=await upload_image_to_comfyapi(cls, image=reference_images[key]) + ) + ) + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27VideoEditTaskCreationRequest( + model=model["model"], + input=Wan27VideoEditInputField(prompt=model["prompt"], media=media), + parameters=Wan27VideoEditParametersField( + resolution=model["resolution"], + ratio=model["ratio"], + duration=duration, + audio_setting=audio_setting, + watermark=watermark, + seed=seed, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class Wan2ReferenceVideoApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="Wan2ReferenceVideoApi", + display_name="Wan 2.7 Reference to Video", + category="api node/video/Wan", + description="Generate a video featuring a person or object from reference materials. " + "Supports single-character performances and multi-character interactions.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "wan2.7-r2v", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Prompt describing the video. Use identifiers such as 'character1' and " + "'character2' to refer to the reference characters.", + ), + IO.String.Input( + "negative_prompt", + multiline=True, + default="", + tooltip="Negative prompt describing what to avoid.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Combo.Input( + "ratio", + options=["16:9", "9:16", "1:1", "4:3", "3:4"], + ), + IO.Int.Input( + "duration", + default=5, + min=2, + max=10, + step=1, + display_mode=IO.NumberDisplay.number, + ), + IO.Autogrow.Input( + "reference_videos", + template=IO.Autogrow.TemplateNames( + IO.Video.Input("reference_video"), + names=["video1", "video2", "video3"], + min=0, + ), + ), + IO.Autogrow.Input( + "reference_images", + template=IO.Autogrow.TemplateNames( + IO.Image.Input("reference_image"), + names=["image1", "image2", "image3", "image4", "image5"], + min=0, + ), + ), + ], + ), + ], + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.1, "1080p": 0.15 }; + $pps := $lookup($ppsTable, $res); + $outputPrice := $pps * $dur; + { + "type": "range_usd", + "min_usd": $outputPrice, + "max_usd": 5 * $pps + $outputPrice + } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + seed: int, + watermark: bool, + ): + validate_string(model["prompt"], strip_whitespace=False, min_length=1) + media = [] + reference_videos = model.get("reference_videos", {}) + for key in reference_videos: + media.append( + Wan27MediaItem(type="reference_video", url=await upload_video_to_comfyapi(cls, reference_videos[key])) + ) + reference_images = model.get("reference_images", {}) + for key in reference_images: + media.append( + Wan27MediaItem( + type="reference_image", + url=await upload_image_to_comfyapi(cls, image=reference_images[key]), + ) + ) + if not media: + raise ValueError("At least one reference video or reference image must be provided.") + if len(media) > 5: + raise ValueError( + f"Too many references ({len(media)}). The maximum total of reference videos and images is 5." + ) + + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27ReferenceVideoTaskCreationRequest( + model=model["model"], + input=Wan27ReferenceVideoInputField( + prompt=model["prompt"], + negative_prompt=model["negative_prompt"] or None, + media=media, + ), + parameters=Wan27ReferenceVideoParametersField( + resolution=model["resolution"], + ratio=model["ratio"], + duration=model["duration"], + watermark=watermark, + seed=seed, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class HappyHorseTextToVideoApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="HappyHorseTextToVideoApi", + display_name="HappyHorse Text to Video", + category="api node/video/Wan", + description="Generates a video based on a text prompt using the HappyHorse model.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "happyhorse-1.0-t2v", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Prompt describing the elements and visual features. " + "Supports English and Chinese.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Combo.Input( + "ratio", + options=["16:9", "9:16", "1:1", "4:3", "3:4"], + ), + IO.Int.Input( + "duration", + default=5, + min=3, + max=15, + step=1, + display_mode=IO.NumberDisplay.number, + ), + ], + ), + ], + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.14, "1080p": 0.24 }; + $pps := $lookup($ppsTable, $res); + { "type": "usd", "usd": $pps * $dur } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + seed: int, + watermark: bool, + ): + validate_string(model["prompt"], strip_whitespace=False, min_length=1) + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27Text2VideoTaskCreationRequest( + model=model["model"], + input=Text2VideoInputField( + prompt=model["prompt"], + negative_prompt=None, + ), + parameters=Wan27Text2VideoParametersField( + resolution=model["resolution"], + ratio=model["ratio"], + duration=model["duration"], + seed=seed, + watermark=watermark, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class HappyHorseImageToVideoApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="HappyHorseImageToVideoApi", + display_name="HappyHorse Image to Video", + category="api node/video/Wan", + description="Generate a video from a first-frame image using the HappyHorse model.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "happyhorse-1.0-i2v", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Prompt describing the elements and visual features. " + "Supports English and Chinese.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Int.Input( + "duration", + default=5, + min=3, + max=15, + step=1, + display_mode=IO.NumberDisplay.number, + ), + ], + ), + ], + ), + IO.Image.Input( + "first_frame", + tooltip="First frame image. The output aspect ratio is derived from this image.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.14, "1080p": 0.24 }; + $pps := $lookup($ppsTable, $res); + { "type": "usd", "usd": $pps * $dur } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + first_frame: Input.Image, + seed: int, + watermark: bool, + ): + media = [ + Wan27MediaItem( + type="first_frame", + url=await upload_image_to_comfyapi(cls, image=first_frame), + ) + ] + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27ImageToVideoTaskCreationRequest( + model=model["model"], + input=Wan27ImageToVideoInputField( + prompt=model["prompt"] or None, + negative_prompt=None, + media=media, + ), + parameters=Wan27ImageToVideoParametersField( + resolution=model["resolution"], + duration=model["duration"], + seed=seed, + watermark=watermark, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class HappyHorseVideoEditApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="HappyHorseVideoEditApi", + display_name="HappyHorse Video Edit", + category="api node/video/Wan", + description="Edit a video using text instructions or reference images with the HappyHorse model. " + "Output duration is 3-15s and matches the input video; inputs longer than 15s are truncated.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "happyhorse-1.0-video-edit", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Editing instructions or style transfer requirements.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Combo.Input( + "ratio", + options=["16:9", "9:16", "1:1", "4:3", "3:4"], + tooltip="Aspect ratio. If not changed, approximates the input video ratio.", + ), + IO.Autogrow.Input( + "reference_images", + template=IO.Autogrow.TemplateNames( + IO.Image.Input("reference_image"), + names=[ + "image1", + "image2", + "image3", + "image4", + "image5", + ], + min=0, + ), + ), + ], + ), + ], + ), + IO.Video.Input( + "video", + tooltip="The video to edit.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $ppsTable := { "720p": 0.14, "1080p": 0.24 }; + $pps := $lookup($ppsTable, $res); + { "type": "usd", "usd": $pps, "format": { "suffix": "/second" } } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + video: Input.Video, + seed: int, + watermark: bool, + ): + validate_string(model["prompt"], strip_whitespace=False, min_length=1) + validate_video_duration(video, min_duration=3, max_duration=60) + media = [Wan27MediaItem(type="video", url=await upload_video_to_comfyapi(cls, video))] + reference_images = model.get("reference_images", {}) + for key in reference_images: + media.append( + Wan27MediaItem( + type="reference_image", url=await upload_image_to_comfyapi(cls, image=reference_images[key]) + ) + ) + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27VideoEditTaskCreationRequest( + model=model["model"], + input=Wan27VideoEditInputField(prompt=model["prompt"], media=media), + parameters=Wan27VideoEditParametersField( + resolution=model["resolution"], + ratio=model["ratio"], + duration=None, + watermark=watermark, + seed=seed, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, + ) + return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) + + +class HappyHorseReferenceVideoApi(IO.ComfyNode): + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="HappyHorseReferenceVideoApi", + display_name="HappyHorse Reference to Video", + category="api node/video/Wan", + description="Generate a video featuring a person or object from reference materials with the HappyHorse " + "model. Supports single-character performances and multi-character interactions.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option( + "happyhorse-1.0-r2v", + [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Prompt describing the video. Use identifiers such as 'character1' and " + "'character2' to refer to the reference characters.", + ), + IO.Combo.Input( + "resolution", + options=["720P", "1080P"], + ), + IO.Combo.Input( + "ratio", + options=["16:9", "9:16", "1:1", "4:3", "3:4"], + ), + IO.Int.Input( + "duration", + default=5, + min=3, + max=15, + step=1, + display_mode=IO.NumberDisplay.number, + ), + IO.Autogrow.Input( + "reference_images", + template=IO.Autogrow.TemplateNames( + IO.Image.Input("reference_image"), + names=[ + "image1", + "image2", + "image3", + "image4", + "image5", + "image6", + "image7", + "image8", + "image9", + ], + min=1, + ), + ), + ], + ), + ], + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + step=1, + display_mode=IO.NumberDisplay.number, + control_after_generate=True, + tooltip="Seed to use for generation.", + ), + IO.Boolean.Input( + "watermark", + default=False, + tooltip="Whether to add an AI-generated watermark to the result.", + advanced=True, + ), + ], + outputs=[ + IO.Video.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]), + expr=""" + ( + $res := $lookup(widgets, "model.resolution"); + $dur := $lookup(widgets, "model.duration"); + $ppsTable := { "720p": 0.14, "1080p": 0.24 }; + $pps := $lookup($ppsTable, $res); + { "type": "usd", "usd": $pps * $dur } + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + model: dict, + seed: int, + watermark: bool, + ): + validate_string(model["prompt"], strip_whitespace=False, min_length=1) + media = [] + reference_images = model.get("reference_images", {}) + for key in reference_images: + media.append( + Wan27MediaItem( + type="reference_image", + url=await upload_image_to_comfyapi(cls, image=reference_images[key]), + ) + ) + if not media: + raise ValueError("At least one reference reference image must be provided.") + + initial_response = await sync_op( + cls, + ApiEndpoint( + path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", + method="POST", + ), + response_model=TaskCreationResponse, + data=Wan27ReferenceVideoTaskCreationRequest( + model=model["model"], + input=Wan27ReferenceVideoInputField( + prompt=model["prompt"], + negative_prompt=None, + media=media, + ), + parameters=Wan27ReferenceVideoParametersField( + resolution=model["resolution"], + ratio=model["ratio"], + duration=model["duration"], + watermark=watermark, + seed=seed, + ), + ), + ) + if not initial_response.output: + raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}") + response = await poll_op( + cls, + ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"), + response_model=VideoTaskStatusResponse, + status_extractor=lambda x: x.output.task_status, + poll_interval=7, ) return IO.NodeOutput(await download_url_to_video_output(response.output.video_url)) @@ -945,6 +2205,15 @@ class WanApiExtension(ComfyExtension): WanTextToVideoApi, WanImageToVideoApi, WanReferenceVideoApi, + Wan2TextToVideoApi, + Wan2ImageToVideoApi, + Wan2VideoContinuationApi, + Wan2VideoEditApi, + Wan2ReferenceVideoApi, + HappyHorseTextToVideoApi, + HappyHorseImageToVideoApi, + HappyHorseVideoEditApi, + HappyHorseReferenceVideoApi, ] diff --git a/comfy_api_nodes/nodes_wavespeed.py b/comfy_api_nodes/nodes_wavespeed.py index c59fafd3b..65e45f60a 100644 --- a/comfy_api_nodes/nodes_wavespeed.py +++ b/comfy_api_nodes/nodes_wavespeed.py @@ -84,7 +84,6 @@ class WavespeedFlashVSRNode(IO.ComfyNode): response_model=TaskResultResponse, status_extractor=lambda x: "failed" if x.data is None else x.data.status, poll_interval=10.0, - max_poll_attempts=480, ) if final_response.code != 200: raise ValueError( @@ -156,7 +155,6 @@ class WavespeedImageUpscaleNode(IO.ComfyNode): response_model=TaskResultResponse, status_extractor=lambda x: "failed" if x.data is None else x.data.status, poll_interval=10.0, - max_poll_attempts=480, ) if final_response.code != 200: raise ValueError( diff --git a/comfy_api_nodes/util/__init__.py b/comfy_api_nodes/util/__init__.py index 0cb9a47c7..f3584aba9 100644 --- a/comfy_api_nodes/util/__init__.py +++ b/comfy_api_nodes/util/__init__.py @@ -19,6 +19,7 @@ from .conversions import ( image_tensor_pair_to_batch, pil_to_bytesio, resize_mask_to_image, + resize_video_to_pixel_budget, tensor_to_base64_string, tensor_to_bytesio, tensor_to_pil, @@ -90,6 +91,7 @@ __all__ = [ "image_tensor_pair_to_batch", "pil_to_bytesio", "resize_mask_to_image", + "resize_video_to_pixel_budget", "tensor_to_base64_string", "tensor_to_bytesio", "tensor_to_pil", diff --git a/comfy_api_nodes/util/client.py b/comfy_api_nodes/util/client.py index 9d730b81a..a0b8d35e1 100644 --- a/comfy_api_nodes/util/client.py +++ b/comfy_api_nodes/util/client.py @@ -148,7 +148,7 @@ async def poll_op( queued_statuses: list[str | int] | None = None, data: BaseModel | None = None, poll_interval: float = 5.0, - max_poll_attempts: int = 160, + max_poll_attempts: int = 480, timeout_per_poll: float = 120.0, max_retries_per_poll: int = 10, retry_delay_per_poll: float = 1.0, @@ -156,6 +156,7 @@ async def poll_op( estimated_duration: int | None = None, cancel_endpoint: ApiEndpoint | None = None, cancel_timeout: float = 10.0, + extra_text: str | None = None, ) -> M: raw = await poll_op_raw( cls, @@ -176,6 +177,7 @@ async def poll_op( estimated_duration=estimated_duration, cancel_endpoint=cancel_endpoint, cancel_timeout=cancel_timeout, + extra_text=extra_text, ) if not isinstance(raw, dict): raise Exception("Expected JSON response to validate into a Pydantic model, got non-JSON (binary or text).") @@ -252,7 +254,7 @@ async def poll_op_raw( queued_statuses: list[str | int] | None = None, data: dict[str, Any] | BaseModel | None = None, poll_interval: float = 5.0, - max_poll_attempts: int = 160, + max_poll_attempts: int = 480, timeout_per_poll: float = 120.0, max_retries_per_poll: int = 10, retry_delay_per_poll: float = 1.0, @@ -260,6 +262,7 @@ async def poll_op_raw( estimated_duration: int | None = None, cancel_endpoint: ApiEndpoint | None = None, cancel_timeout: float = 10.0, + extra_text: str | None = None, ) -> dict[str, Any]: """ Polls an endpoint until the task reaches a terminal state. Displays time while queued/processing, @@ -299,6 +302,7 @@ async def poll_op_raw( price=state.price, is_queued=state.is_queued, processing_elapsed_seconds=int(proc_elapsed), + extra_text=extra_text, ) await asyncio.sleep(1.0) except Exception as exc: @@ -389,6 +393,7 @@ async def poll_op_raw( price=state.price, is_queued=False, processing_elapsed_seconds=int(state.base_processing_elapsed), + extra_text=extra_text, ) return resp_json @@ -462,6 +467,7 @@ def _display_time_progress( price: float | None = None, is_queued: bool | None = None, processing_elapsed_seconds: int | None = None, + extra_text: str | None = None, ) -> None: if estimated_total is not None and estimated_total > 0 and is_queued is False: pe = processing_elapsed_seconds if processing_elapsed_seconds is not None else elapsed_seconds @@ -469,7 +475,8 @@ def _display_time_progress( time_line = f"Time elapsed: {int(elapsed_seconds)}s (~{remaining}s remaining)" else: time_line = f"Time elapsed: {int(elapsed_seconds)}s" - _display_text(node_cls, time_line, status=status, price=price) + text = f"{time_line}\n\n{extra_text}" if extra_text else time_line + _display_text(node_cls, text, status=status, price=price) async def _diagnose_connectivity() -> dict[str, bool]: diff --git a/comfy_api_nodes/util/conversions.py b/comfy_api_nodes/util/conversions.py index 82b6d22a5..be5d5719b 100644 --- a/comfy_api_nodes/util/conversions.py +++ b/comfy_api_nodes/util/conversions.py @@ -129,22 +129,38 @@ def pil_to_bytesio(img: Image.Image, mime_type: str = "image/png") -> BytesIO: return img_byte_arr +def _compute_downscale_dims(src_w: int, src_h: int, total_pixels: int) -> tuple[int, int] | None: + """Return downscaled (w, h) with even dims fitting ``total_pixels``, or None if already fits. + + Source aspect ratio is preserved; output may drift by a fraction of a percent because both dimensions + are rounded down to even values (many codecs require divisible-by-2). + """ + pixels = src_w * src_h + if pixels <= total_pixels: + return None + scale = math.sqrt(total_pixels / pixels) + new_w = max(2, int(src_w * scale)) + new_h = max(2, int(src_h * scale)) + new_w -= new_w % 2 + new_h -= new_h % 2 + return new_w, new_h + + def downscale_image_tensor(image: torch.Tensor, total_pixels: int = 1536 * 1024) -> torch.Tensor: - """Downscale input image tensor to roughly the specified total pixels.""" + """Downscale input image tensor to roughly the specified total pixels. + + Output dimensions are rounded down to even values so that the result is guaranteed to fit within ``total_pixels`` + and is compatible with codecs that require even dimensions (e.g. yuv420p). + """ samples = image.movedim(-1, 1) - total = int(total_pixels) - scale_by = math.sqrt(total / (samples.shape[3] * samples.shape[2])) - if scale_by >= 1: + dims = _compute_downscale_dims(samples.shape[3], samples.shape[2], int(total_pixels)) + if dims is None: return image - width = round(samples.shape[3] * scale_by) - height = round(samples.shape[2] * scale_by) - - s = common_upscale(samples, width, height, "lanczos", "disabled") - s = s.movedim(1, -1) - return s + new_w, new_h = dims + return common_upscale(samples, new_w, new_h, "lanczos", "disabled").movedim(1, -1) -def downscale_image_tensor_by_max_side(image: torch.Tensor, *, max_side: int) -> torch.Tensor: +def downscale_image_tensor_by_max_side(image: torch.Tensor, *, max_side: int) -> torch.Tensor: """Downscale input image tensor so the largest dimension is at most max_side pixels.""" samples = image.movedim(-1, 1) height, width = samples.shape[2], samples.shape[3] @@ -399,6 +415,72 @@ def trim_video(video: Input.Video, duration_sec: float) -> Input.Video: raise RuntimeError(f"Failed to trim video: {str(e)}") from e +def resize_video_to_pixel_budget(video: Input.Video, total_pixels: int) -> Input.Video: + """Downscale a video to fit within ``total_pixels`` (w * h), preserving aspect ratio. + + Returns the original video object untouched when it already fits. Preserves frame rate, duration, and audio. + Aspect ratio is preserved up to a fraction of a percent (even-dim rounding). + """ + src_w, src_h = video.get_dimensions() + scale_dims = _compute_downscale_dims(src_w, src_h, total_pixels) + if scale_dims is None: + return video + return _apply_video_scale(video, scale_dims) + + +def _apply_video_scale(video: Input.Video, scale_dims: tuple[int, int]) -> Input.Video: + """Re-encode ``video`` scaled to ``scale_dims`` with a single decode/encode pass.""" + out_w, out_h = scale_dims + output_buffer = BytesIO() + input_container = None + output_container = None + + try: + input_source = video.get_stream_source() + input_container = av.open(input_source, mode="r") + output_container = av.open(output_buffer, mode="w", format="mp4") + + video_stream = output_container.add_stream("h264", rate=video.get_frame_rate()) + video_stream.width = out_w + video_stream.height = out_h + video_stream.pix_fmt = "yuv420p" + + audio_stream = None + for stream in input_container.streams: + if isinstance(stream, av.AudioStream): + audio_stream = output_container.add_stream("aac", rate=stream.sample_rate) + audio_stream.sample_rate = stream.sample_rate + audio_stream.layout = stream.layout + break + + for frame in input_container.decode(video=0): + frame = frame.reformat(width=out_w, height=out_h, format="yuv420p") + for packet in video_stream.encode(frame): + output_container.mux(packet) + for packet in video_stream.encode(): + output_container.mux(packet) + + if audio_stream is not None: + input_container.seek(0) + for audio_frame in input_container.decode(audio=0): + for packet in audio_stream.encode(audio_frame): + output_container.mux(packet) + for packet in audio_stream.encode(): + output_container.mux(packet) + + output_container.close() + input_container.close() + output_buffer.seek(0) + return InputImpl.VideoFromFile(output_buffer) + + except Exception as e: + if input_container is not None: + input_container.close() + if output_container is not None: + output_container.close() + raise RuntimeError(f"Failed to resize video: {str(e)}") from e + + def _f32_pcm(wav: torch.Tensor) -> torch.Tensor: """Convert audio to float 32 bits PCM format. Copy-paste from nodes_audio.py file.""" if wav.dtype.is_floating_point: diff --git a/comfy_execution/caching.py b/comfy_execution/caching.py index f9c913bdb..ba1e8bc84 100644 --- a/comfy_execution/caching.py +++ b/comfy_execution/caching.py @@ -5,6 +5,7 @@ import psutil import time import torch from typing import Sequence, Mapping, Dict +from comfy.model_patcher import ModelPatcher from comfy_execution.graph import DynamicPrompt from abc import ABC, abstractmethod @@ -523,13 +524,15 @@ class RAMPressureCache(LRUCache): self.timestamps[self.cache_key_set.get_data_key(node_id)] = time.time() super().set_local(node_id, value) - def ram_release(self, target): + def ram_release(self, target, free_active=False): if psutil.virtual_memory().available >= target: return clean_list = [] for key, cache_entry in self.cache.items(): + if not free_active and self.used_generation[key] == self.generation: + continue oom_score = RAM_CACHE_OLD_WORKFLOW_OOM_MULTIPLIER ** (self.generation - self.used_generation[key]) ram_usage = RAM_CACHE_DEFAULT_RAM_USAGE @@ -542,6 +545,9 @@ class RAMPressureCache(LRUCache): scan_list_for_ram_usage(output) elif isinstance(output, torch.Tensor) and output.device.type == 'cpu': ram_usage += output.numel() * output.element_size() + elif isinstance(output, ModelPatcher) and self.used_generation[key] != self.generation: + #old ModelPatchers are the first to go + ram_usage = 1e30 scan_list_for_ram_usage(cache_entry.outputs) oom_score *= ram_usage diff --git a/comfy_extras/frame_interpolation_models/film_net.py b/comfy_extras/frame_interpolation_models/film_net.py new file mode 100644 index 000000000..cf4f6e1e1 --- /dev/null +++ b/comfy_extras/frame_interpolation_models/film_net.py @@ -0,0 +1,258 @@ +"""FILM: Frame Interpolation for Large Motion (ECCV 2022).""" + +import torch +import torch.nn as nn +import torch.nn.functional as F + +import comfy.ops + +ops = comfy.ops.disable_weight_init + + +class FilmConv2d(nn.Module): + """Conv2d with optional LeakyReLU and FILM-style padding.""" + + def __init__(self, in_channels, out_channels, size, activation=True, device=None, dtype=None, operations=ops): + super().__init__() + self.even_pad = not size % 2 + self.conv = operations.Conv2d(in_channels, out_channels, kernel_size=size, padding=size // 2 if size % 2 else 0, device=device, dtype=dtype) + self.activation = nn.LeakyReLU(0.2) if activation else None + + def forward(self, x): + if self.even_pad: + x = F.pad(x, (0, 1, 0, 1)) + x = self.conv(x) + if self.activation is not None: + x = self.activation(x) + return x + + +def _warp_core(image, flow, grid_x, grid_y): + dtype = image.dtype + H, W = flow.shape[2], flow.shape[3] + dx = flow[:, 0].float() / (W * 0.5) + dy = flow[:, 1].float() / (H * 0.5) + grid = torch.stack([grid_x[None, None, :] + dx, grid_y[None, :, None] + dy], dim=3) + return F.grid_sample(image.float(), grid, mode="bilinear", padding_mode="border", align_corners=False).to(dtype) + + +def build_image_pyramid(image, pyramid_levels): + pyramid = [image] + for _ in range(1, pyramid_levels): + image = F.avg_pool2d(image, 2, 2) + pyramid.append(image) + return pyramid + + +def flow_pyramid_synthesis(residual_pyramid): + flow = residual_pyramid[-1] + flow_pyramid = [flow] + for residual_flow in residual_pyramid[:-1][::-1]: + flow = F.interpolate(flow, size=residual_flow.shape[2:4], mode="bilinear", scale_factor=None).mul_(2).add_(residual_flow) + flow_pyramid.append(flow) + flow_pyramid.reverse() + return flow_pyramid + + +def multiply_pyramid(pyramid, scalar): + return [image * scalar[:, None, None, None] for image in pyramid] + + +def pyramid_warp(feature_pyramid, flow_pyramid, warp_fn): + return [warp_fn(features, flow) for features, flow in zip(feature_pyramid, flow_pyramid)] + + +def concatenate_pyramids(pyramid1, pyramid2): + return [torch.cat([f1, f2], dim=1) for f1, f2 in zip(pyramid1, pyramid2)] + + +class SubTreeExtractor(nn.Module): + def __init__(self, in_channels=3, channels=64, n_layers=4, device=None, dtype=None, operations=ops): + super().__init__() + convs = [] + for i in range(n_layers): + out_ch = channels << i + convs.append(nn.Sequential( + FilmConv2d(in_channels, out_ch, 3, device=device, dtype=dtype, operations=operations), + FilmConv2d(out_ch, out_ch, 3, device=device, dtype=dtype, operations=operations))) + in_channels = out_ch + self.convs = nn.ModuleList(convs) + + def forward(self, image, n): + head = image + pyramid = [] + for i, layer in enumerate(self.convs): + head = layer(head) + pyramid.append(head) + if i < n - 1: + head = F.avg_pool2d(head, 2, 2) + return pyramid + + +class FeatureExtractor(nn.Module): + def __init__(self, in_channels=3, channels=64, sub_levels=4, device=None, dtype=None, operations=ops): + super().__init__() + self.extract_sublevels = SubTreeExtractor(in_channels, channels, sub_levels, device=device, dtype=dtype, operations=operations) + self.sub_levels = sub_levels + + def forward(self, image_pyramid): + sub_pyramids = [self.extract_sublevels(image_pyramid[i], min(len(image_pyramid) - i, self.sub_levels)) + for i in range(len(image_pyramid))] + feature_pyramid = [] + for i in range(len(image_pyramid)): + features = sub_pyramids[i][0] + for j in range(1, self.sub_levels): + if j <= i: + features = torch.cat([features, sub_pyramids[i - j][j]], dim=1) + feature_pyramid.append(features) + # Free sub-pyramids no longer needed by future levels + if i >= self.sub_levels - 1: + sub_pyramids[i - self.sub_levels + 1] = None + return feature_pyramid + + +class FlowEstimator(nn.Module): + def __init__(self, in_channels, num_convs, num_filters, device=None, dtype=None, operations=ops): + super().__init__() + self._convs = nn.ModuleList() + for _ in range(num_convs): + self._convs.append(FilmConv2d(in_channels, num_filters, 3, device=device, dtype=dtype, operations=operations)) + in_channels = num_filters + self._convs.append(FilmConv2d(in_channels, num_filters // 2, 1, device=device, dtype=dtype, operations=operations)) + self._convs.append(FilmConv2d(num_filters // 2, 2, 1, activation=False, device=device, dtype=dtype, operations=operations)) + + def forward(self, features_a, features_b): + net = torch.cat([features_a, features_b], dim=1) + for conv in self._convs: + net = conv(net) + return net + + +class PyramidFlowEstimator(nn.Module): + def __init__(self, filters=64, flow_convs=(3, 3, 3, 3), flow_filters=(32, 64, 128, 256), device=None, dtype=None, operations=ops): + super().__init__() + in_channels = filters << 1 + predictors = [] + for i in range(len(flow_convs)): + predictors.append(FlowEstimator(in_channels, flow_convs[i], flow_filters[i], device=device, dtype=dtype, operations=operations)) + in_channels += filters << (i + 2) + self._predictor = predictors[-1] + self._predictors = nn.ModuleList(predictors[:-1][::-1]) + + def forward(self, feature_pyramid_a, feature_pyramid_b, warp_fn): + levels = len(feature_pyramid_a) + v = self._predictor(feature_pyramid_a[-1], feature_pyramid_b[-1]) + residuals = [v] + # Coarse-to-fine: shared predictor for deep levels, then specialized predictors for fine levels + steps = [(i, self._predictor) for i in range(levels - 2, len(self._predictors) - 1, -1)] + steps += [(len(self._predictors) - 1 - k, p) for k, p in enumerate(self._predictors)] + for i, predictor in steps: + v = F.interpolate(v, size=feature_pyramid_a[i].shape[2:4], mode="bilinear").mul_(2) + v_residual = predictor(feature_pyramid_a[i], warp_fn(feature_pyramid_b[i], v)) + residuals.append(v_residual) + v = v.add_(v_residual) + residuals.reverse() + return residuals + + +def _get_fusion_channels(level, filters): + # Per direction: multi-scale features + RGB image (3ch) + flow (2ch), doubled for both directions + return (sum(filters << i for i in range(level)) + 3 + 2) * 2 + + +class Fusion(nn.Module): + def __init__(self, n_layers=4, specialized_layers=3, filters=64, device=None, dtype=None, operations=ops): + super().__init__() + self.output_conv = operations.Conv2d(filters, 3, kernel_size=1, device=device, dtype=dtype) + self.convs = nn.ModuleList() + in_channels = _get_fusion_channels(n_layers, filters) + increase = 0 + for i in range(n_layers)[::-1]: + num_filters = (filters << i) if i < specialized_layers else (filters << specialized_layers) + self.convs.append(nn.ModuleList([ + FilmConv2d(in_channels, num_filters, 2, activation=False, device=device, dtype=dtype, operations=operations), + FilmConv2d(in_channels + (increase or num_filters), num_filters, 3, device=device, dtype=dtype, operations=operations), + FilmConv2d(num_filters, num_filters, 3, device=device, dtype=dtype, operations=operations)])) + in_channels = num_filters + increase = _get_fusion_channels(i, filters) - num_filters // 2 + + def forward(self, pyramid): + net = pyramid[-1] + for k, layers in enumerate(self.convs): + i = len(self.convs) - 1 - k + net = layers[0](F.interpolate(net, size=pyramid[i].shape[2:4], mode="nearest")) + net = layers[2](layers[1](torch.cat([pyramid[i], net], dim=1))) + return self.output_conv(net) + + +class FILMNet(nn.Module): + def __init__(self, pyramid_levels=7, fusion_pyramid_levels=5, specialized_levels=3, sub_levels=4, + filters=64, flow_convs=(3, 3, 3, 3), flow_filters=(32, 64, 128, 256), device=None, dtype=None, operations=ops): + super().__init__() + self.pyramid_levels = pyramid_levels + self.fusion_pyramid_levels = fusion_pyramid_levels + self.extract = FeatureExtractor(3, filters, sub_levels, device=device, dtype=dtype, operations=operations) + self.predict_flow = PyramidFlowEstimator(filters, flow_convs, flow_filters, device=device, dtype=dtype, operations=operations) + self.fuse = Fusion(sub_levels, specialized_levels, filters, device=device, dtype=dtype, operations=operations) + self._warp_grids = {} + + def get_dtype(self): + return self.extract.extract_sublevels.convs[0][0].conv.weight.dtype + + def _build_warp_grids(self, H, W, device): + """Pre-compute warp grids for all pyramid levels.""" + if (H, W) in self._warp_grids: + return + self._warp_grids = {} # clear old resolution grids to prevent memory leaks + for _ in range(self.pyramid_levels): + self._warp_grids[(H, W)] = ( + torch.linspace(-(1 - 1 / W), 1 - 1 / W, W, dtype=torch.float32, device=device), + torch.linspace(-(1 - 1 / H), 1 - 1 / H, H, dtype=torch.float32, device=device), + ) + H, W = H // 2, W // 2 + + def warp(self, image, flow): + grid_x, grid_y = self._warp_grids[(flow.shape[2], flow.shape[3])] + return _warp_core(image, flow, grid_x, grid_y) + + def extract_features(self, img): + """Extract image and feature pyramids for a single frame. Can be cached across pairs.""" + image_pyramid = build_image_pyramid(img, self.pyramid_levels) + feature_pyramid = self.extract(image_pyramid) + return image_pyramid, feature_pyramid + + def forward(self, img0, img1, timestep=0.5, cache=None): + # FILM uses a scalar timestep per batch element (spatially-varying timesteps not supported) + t = timestep.mean(dim=(1, 2, 3)).item() if isinstance(timestep, torch.Tensor) else timestep + return self.forward_multi_timestep(img0, img1, [t], cache=cache) + + def forward_multi_timestep(self, img0, img1, timesteps, cache=None): + """Compute flow once, synthesize at multiple timesteps. Expects batch=1 inputs.""" + self._build_warp_grids(img0.shape[2], img0.shape[3], img0.device) + + image_pyr0, feat_pyr0 = cache["img0"] if cache and "img0" in cache else self.extract_features(img0) + image_pyr1, feat_pyr1 = cache["img1"] if cache and "img1" in cache else self.extract_features(img1) + + fwd_flow = flow_pyramid_synthesis(self.predict_flow(feat_pyr0, feat_pyr1, self.warp))[:self.fusion_pyramid_levels] + bwd_flow = flow_pyramid_synthesis(self.predict_flow(feat_pyr1, feat_pyr0, self.warp))[:self.fusion_pyramid_levels] + + # Build warp targets and free full pyramids (only first fpl levels needed from here) + fpl = self.fusion_pyramid_levels + p2w = [concatenate_pyramids(image_pyr0[:fpl], feat_pyr0[:fpl]), + concatenate_pyramids(image_pyr1[:fpl], feat_pyr1[:fpl])] + del image_pyr0, image_pyr1, feat_pyr0, feat_pyr1 + + results = [] + dt_tensors = torch.tensor(timesteps, device=img0.device, dtype=img0.dtype) + for idx in range(len(timesteps)): + batch_dt = dt_tensors[idx:idx + 1] + bwd_scaled = multiply_pyramid(bwd_flow, batch_dt) + fwd_scaled = multiply_pyramid(fwd_flow, 1 - batch_dt) + fwd_warped = pyramid_warp(p2w[0], bwd_scaled, self.warp) + bwd_warped = pyramid_warp(p2w[1], fwd_scaled, self.warp) + aligned = [torch.cat([fw, bw, bf, ff], dim=1) + for fw, bw, bf, ff in zip(fwd_warped, bwd_warped, bwd_scaled, fwd_scaled)] + del fwd_warped, bwd_warped, bwd_scaled, fwd_scaled + results.append(self.fuse(aligned)) + del aligned + return torch.cat(results, dim=0) diff --git a/comfy_extras/frame_interpolation_models/ifnet.py b/comfy_extras/frame_interpolation_models/ifnet.py new file mode 100644 index 000000000..03cb34c50 --- /dev/null +++ b/comfy_extras/frame_interpolation_models/ifnet.py @@ -0,0 +1,128 @@ +import torch +import torch.nn as nn +import torch.nn.functional as F + +import comfy.ops + +ops = comfy.ops.disable_weight_init + + +def _warp(img, flow, warp_grids): + B, _, H, W = img.shape + base_grid, flow_div = warp_grids[(H, W)] + flow_norm = torch.cat([flow[:, 0:1] / flow_div[0], flow[:, 1:2] / flow_div[1]], 1).float() + grid = (base_grid.expand(B, -1, -1, -1) + flow_norm).permute(0, 2, 3, 1) + return F.grid_sample(img.float(), grid, mode="bilinear", padding_mode="border", align_corners=True).to(img.dtype) + + +class Head(nn.Module): + def __init__(self, out_ch=4, device=None, dtype=None, operations=ops): + super().__init__() + self.cnn0 = operations.Conv2d(3, 16, 3, 2, 1, device=device, dtype=dtype) + self.cnn1 = operations.Conv2d(16, 16, 3, 1, 1, device=device, dtype=dtype) + self.cnn2 = operations.Conv2d(16, 16, 3, 1, 1, device=device, dtype=dtype) + self.cnn3 = operations.ConvTranspose2d(16, out_ch, 4, 2, 1, device=device, dtype=dtype) + self.relu = nn.LeakyReLU(0.2, True) + + def forward(self, x): + x = self.relu(self.cnn0(x)) + x = self.relu(self.cnn1(x)) + x = self.relu(self.cnn2(x)) + return self.cnn3(x) + + +class ResConv(nn.Module): + def __init__(self, c, device=None, dtype=None, operations=ops): + super().__init__() + self.conv = operations.Conv2d(c, c, 3, 1, 1, device=device, dtype=dtype) + self.beta = nn.Parameter(torch.ones((1, c, 1, 1), device=device, dtype=dtype)) + self.relu = nn.LeakyReLU(0.2, True) + + def forward(self, x): + return self.relu(torch.addcmul(x, self.conv(x), self.beta)) + + +class IFBlock(nn.Module): + def __init__(self, in_planes, c=64, device=None, dtype=None, operations=ops): + super().__init__() + self.conv0 = nn.Sequential( + nn.Sequential(operations.Conv2d(in_planes, c // 2, 3, 2, 1, device=device, dtype=dtype), nn.LeakyReLU(0.2, True)), + nn.Sequential(operations.Conv2d(c // 2, c, 3, 2, 1, device=device, dtype=dtype), nn.LeakyReLU(0.2, True))) + self.convblock = nn.Sequential(*(ResConv(c, device=device, dtype=dtype, operations=operations) for _ in range(8))) + self.lastconv = nn.Sequential(operations.ConvTranspose2d(c, 4 * 13, 4, 2, 1, device=device, dtype=dtype), nn.PixelShuffle(2)) + + def forward(self, x, flow=None, scale=1): + x = F.interpolate(x, scale_factor=1.0 / scale, mode="bilinear") + if flow is not None: + flow = F.interpolate(flow, scale_factor=1.0 / scale, mode="bilinear").div_(scale) + x = torch.cat((x, flow), 1) + feat = self.convblock(self.conv0(x)) + tmp = F.interpolate(self.lastconv(feat), scale_factor=scale, mode="bilinear") + return tmp[:, :4] * scale, tmp[:, 4:5], tmp[:, 5:] + + +class IFNet(nn.Module): + def __init__(self, head_ch=4, channels=(192, 128, 96, 64, 32), device=None, dtype=None, operations=ops): + super().__init__() + self.encode = Head(out_ch=head_ch, device=device, dtype=dtype, operations=operations) + block_in = [7 + 2 * head_ch] + [8 + 4 + 8 + 2 * head_ch] * 4 + self.blocks = nn.ModuleList([IFBlock(block_in[i], channels[i], device=device, dtype=dtype, operations=operations) for i in range(5)]) + self.scale_list = [16, 8, 4, 2, 1] + self.pad_align = 64 + self._warp_grids = {} + + def get_dtype(self): + return self.encode.cnn0.weight.dtype + + def _build_warp_grids(self, H, W, device): + if (H, W) in self._warp_grids: + return + self._warp_grids = {} # clear old resolution grids to prevent memory leaks + grid_y, grid_x = torch.meshgrid( + torch.linspace(-1.0, 1.0, H, device=device, dtype=torch.float32), + torch.linspace(-1.0, 1.0, W, device=device, dtype=torch.float32), indexing="ij") + self._warp_grids[(H, W)] = ( + torch.stack((grid_x, grid_y), dim=0).unsqueeze(0), + torch.tensor([(W - 1.0) / 2.0, (H - 1.0) / 2.0], dtype=torch.float32, device=device)) + + def warp(self, img, flow): + return _warp(img, flow, self._warp_grids) + + def extract_features(self, img): + """Extract head features for a single frame. Can be cached across pairs.""" + return self.encode(img) + + def forward(self, img0, img1, timestep=0.5, cache=None): + if not isinstance(timestep, torch.Tensor): + timestep = torch.full((img0.shape[0], 1, img0.shape[2], img0.shape[3]), timestep, device=img0.device, dtype=img0.dtype) + + self._build_warp_grids(img0.shape[2], img0.shape[3], img0.device) + + B = img0.shape[0] + f0 = cache["img0"].expand(B, -1, -1, -1) if cache and "img0" in cache else self.encode(img0) + f1 = cache["img1"].expand(B, -1, -1, -1) if cache and "img1" in cache else self.encode(img1) + flow = mask = feat = None + warped_img0, warped_img1 = img0, img1 + for i, block in enumerate(self.blocks): + if flow is None: + flow, mask, feat = block(torch.cat((img0, img1, f0, f1, timestep), 1), None, scale=self.scale_list[i]) + else: + fd, mask, feat = block( + torch.cat((warped_img0, warped_img1, self.warp(f0, flow[:, :2]), self.warp(f1, flow[:, 2:4]), timestep, mask, feat), 1), + flow, scale=self.scale_list[i]) + flow = flow.add_(fd) + warped_img0 = self.warp(img0, flow[:, :2]) + warped_img1 = self.warp(img1, flow[:, 2:4]) + return torch.lerp(warped_img1, warped_img0, torch.sigmoid(mask)) + + +def detect_rife_config(state_dict): + head_ch = state_dict["encode.cnn3.weight"].shape[1] # ConvTranspose2d: (in_ch, out_ch, kH, kW) + channels = [] + for i in range(5): + key = f"blocks.{i}.conv0.1.0.weight" + if key in state_dict: + channels.append(state_dict[key].shape[0]) + if len(channels) != 5: + raise ValueError(f"Unsupported RIFE model: expected 5 blocks, found {len(channels)}") + return head_ch, channels diff --git a/comfy_extras/nodes_ace.py b/comfy_extras/nodes_ace.py index 9cf84ab4d..1602add84 100644 --- a/comfy_extras/nodes_ace.py +++ b/comfy_extras/nodes_ace.py @@ -3,136 +3,136 @@ from typing_extensions import override import comfy.model_management import node_helpers -from comfy_api.latest import ComfyExtension, io +from comfy_api.latest import ComfyExtension, IO -class TextEncodeAceStepAudio(io.ComfyNode): +class TextEncodeAceStepAudio(IO.ComfyNode): @classmethod def define_schema(cls): - return io.Schema( + return IO.Schema( node_id="TextEncodeAceStepAudio", category="conditioning", inputs=[ - io.Clip.Input("clip"), - io.String.Input("tags", multiline=True, dynamic_prompts=True), - io.String.Input("lyrics", multiline=True, dynamic_prompts=True), - io.Float.Input("lyrics_strength", default=1.0, min=0.0, max=10.0, step=0.01), + IO.Clip.Input("clip"), + IO.String.Input("tags", multiline=True, dynamic_prompts=True), + IO.String.Input("lyrics", multiline=True, dynamic_prompts=True), + IO.Float.Input("lyrics_strength", default=1.0, min=0.0, max=10.0, step=0.01), ], - outputs=[io.Conditioning.Output()], + outputs=[IO.Conditioning.Output()], ) @classmethod - def execute(cls, clip, tags, lyrics, lyrics_strength) -> io.NodeOutput: + def execute(cls, clip, tags, lyrics, lyrics_strength) -> IO.NodeOutput: tokens = clip.tokenize(tags, lyrics=lyrics) conditioning = clip.encode_from_tokens_scheduled(tokens) conditioning = node_helpers.conditioning_set_values(conditioning, {"lyrics_strength": lyrics_strength}) - return io.NodeOutput(conditioning) + return IO.NodeOutput(conditioning) -class TextEncodeAceStepAudio15(io.ComfyNode): +class TextEncodeAceStepAudio15(IO.ComfyNode): @classmethod def define_schema(cls): - return io.Schema( + return IO.Schema( node_id="TextEncodeAceStepAudio1.5", category="conditioning", inputs=[ - io.Clip.Input("clip"), - io.String.Input("tags", multiline=True, dynamic_prompts=True), - io.String.Input("lyrics", multiline=True, dynamic_prompts=True), - io.Int.Input("seed", default=0, min=0, max=0xffffffffffffffff, control_after_generate=True), - io.Int.Input("bpm", default=120, min=10, max=300), - io.Float.Input("duration", default=120.0, min=0.0, max=2000.0, step=0.1), - io.Combo.Input("timesignature", options=['2', '3', '4', '6']), - io.Combo.Input("language", options=["en", "ja", "zh", "es", "de", "fr", "pt", "ru", "it", "nl", "pl", "tr", "vi", "cs", "fa", "id", "ko", "uk", "hu", "ar", "sv", "ro", "el"]), - io.Combo.Input("keyscale", options=[f"{root} {quality}" for quality in ["major", "minor"] for root in ["C", "C#", "Db", "D", "D#", "Eb", "E", "F", "F#", "Gb", "G", "G#", "Ab", "A", "A#", "Bb", "B"]]), - io.Boolean.Input("generate_audio_codes", default=True, tooltip="Enable the LLM that generates audio codes. This can be slow but will increase the quality of the generated audio. Turn this off if you are giving the model an audio reference.", advanced=True), - io.Float.Input("cfg_scale", default=2.0, min=0.0, max=100.0, step=0.1, advanced=True), - io.Float.Input("temperature", default=0.85, min=0.0, max=2.0, step=0.01, advanced=True), - io.Float.Input("top_p", default=0.9, min=0.0, max=2000.0, step=0.01, advanced=True), - io.Int.Input("top_k", default=0, min=0, max=100, advanced=True), - io.Float.Input("min_p", default=0.000, min=0.0, max=1.0, step=0.001, advanced=True), + IO.Clip.Input("clip"), + IO.String.Input("tags", multiline=True, dynamic_prompts=True), + IO.String.Input("lyrics", multiline=True, dynamic_prompts=True), + IO.Int.Input("seed", default=0, min=0, max=0xffffffffffffffff, control_after_generate=True), + IO.Int.Input("bpm", default=120, min=10, max=300), + IO.Float.Input("duration", default=120.0, min=0.0, max=2000.0, step=0.1), + IO.Combo.Input("timesignature", options=['2', '3', '4', '6']), + IO.Combo.Input("language", options=["en", "ja", "zh", "es", "de", "fr", "pt", "ru", "it", "nl", "pl", "tr", "vi", "cs", "fa", "id", "ko", "uk", "hu", "ar", "sv", "ro", "el"]), + IO.Combo.Input("keyscale", options=[f"{root} {quality}" for quality in ["major", "minor"] for root in ["C", "C#", "Db", "D", "D#", "Eb", "E", "F", "F#", "Gb", "G", "G#", "Ab", "A", "A#", "Bb", "B"]]), + IO.Boolean.Input("generate_audio_codes", default=True, tooltip="Enable the LLM that generates audio codes. This can be slow but will increase the quality of the generated audio. Turn this off if you are giving the model an audio reference.", advanced=True), + IO.Float.Input("cfg_scale", default=2.0, min=0.0, max=100.0, step=0.1, advanced=True), + IO.Float.Input("temperature", default=0.85, min=0.0, max=2.0, step=0.01, advanced=True), + IO.Float.Input("top_p", default=0.9, min=0.0, max=2000.0, step=0.01, advanced=True), + IO.Int.Input("top_k", default=0, min=0, max=100, advanced=True), + IO.Float.Input("min_p", default=0.000, min=0.0, max=1.0, step=0.001, advanced=True), ], - outputs=[io.Conditioning.Output()], + outputs=[IO.Conditioning.Output()], ) @classmethod - def execute(cls, clip, tags, lyrics, seed, bpm, duration, timesignature, language, keyscale, generate_audio_codes, cfg_scale, temperature, top_p, top_k, min_p) -> io.NodeOutput: + def execute(cls, clip, tags, lyrics, seed, bpm, duration, timesignature, language, keyscale, generate_audio_codes, cfg_scale, temperature, top_p, top_k, min_p) -> IO.NodeOutput: tokens = clip.tokenize(tags, lyrics=lyrics, bpm=bpm, duration=duration, timesignature=int(timesignature), language=language, keyscale=keyscale, seed=seed, generate_audio_codes=generate_audio_codes, cfg_scale=cfg_scale, temperature=temperature, top_p=top_p, top_k=top_k, min_p=min_p) conditioning = clip.encode_from_tokens_scheduled(tokens) - return io.NodeOutput(conditioning) + return IO.NodeOutput(conditioning) -class EmptyAceStepLatentAudio(io.ComfyNode): +class EmptyAceStepLatentAudio(IO.ComfyNode): @classmethod def define_schema(cls): - return io.Schema( + return IO.Schema( node_id="EmptyAceStepLatentAudio", display_name="Empty Ace Step 1.0 Latent Audio", category="latent/audio", inputs=[ - io.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.1), - io.Int.Input( + IO.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.1), + IO.Int.Input( "batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch." ), ], - outputs=[io.Latent.Output()], + outputs=[IO.Latent.Output()], ) @classmethod - def execute(cls, seconds, batch_size) -> io.NodeOutput: + def execute(cls, seconds, batch_size) -> IO.NodeOutput: length = int(seconds * 44100 / 512 / 8) - latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device()) - return io.NodeOutput({"samples": latent, "type": "audio"}) + latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype()) + return IO.NodeOutput({"samples": latent, "type": "audio"}) -class EmptyAceStep15LatentAudio(io.ComfyNode): +class EmptyAceStep15LatentAudio(IO.ComfyNode): @classmethod def define_schema(cls): - return io.Schema( + return IO.Schema( node_id="EmptyAceStep1.5LatentAudio", display_name="Empty Ace Step 1.5 Latent Audio", category="latent/audio", inputs=[ - io.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.01), - io.Int.Input( + IO.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.01), + IO.Int.Input( "batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch." ), ], - outputs=[io.Latent.Output()], + outputs=[IO.Latent.Output()], ) @classmethod - def execute(cls, seconds, batch_size) -> io.NodeOutput: + def execute(cls, seconds, batch_size) -> IO.NodeOutput: length = round((seconds * 48000 / 1920)) - latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device()) - return io.NodeOutput({"samples": latent, "type": "audio"}) + latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype()) + return IO.NodeOutput({"samples": latent, "type": "audio"}) -class ReferenceAudio(io.ComfyNode): +class ReferenceAudio(IO.ComfyNode): @classmethod def define_schema(cls): - return io.Schema( + return IO.Schema( node_id="ReferenceTimbreAudio", display_name="Reference Audio", category="advanced/conditioning/audio", is_experimental=True, description="This node sets the reference audio for ace step 1.5", inputs=[ - io.Conditioning.Input("conditioning"), - io.Latent.Input("latent", optional=True), + IO.Conditioning.Input("conditioning"), + IO.Latent.Input("latent", optional=True), ], outputs=[ - io.Conditioning.Output(), + IO.Conditioning.Output(), ] ) @classmethod - def execute(cls, conditioning, latent=None) -> io.NodeOutput: + def execute(cls, conditioning, latent=None) -> IO.NodeOutput: if latent is not None: conditioning = node_helpers.conditioning_set_values(conditioning, {"reference_audio_timbre_latents": [latent["samples"]]}, append=True) - return io.NodeOutput(conditioning) + return IO.NodeOutput(conditioning) class AceExtension(ComfyExtension): @override - async def get_node_list(self) -> list[type[io.ComfyNode]]: + async def get_node_list(self) -> list[type[IO.ComfyNode]]: return [ TextEncodeAceStepAudio, EmptyAceStepLatentAudio, diff --git a/comfy_extras/nodes_audio.py b/comfy_extras/nodes_audio.py index a395392d8..5f514716f 100644 --- a/comfy_extras/nodes_audio.py +++ b/comfy_extras/nodes_audio.py @@ -104,7 +104,7 @@ def vae_decode_audio(vae, samples, tile=None, overlap=None): std = torch.std(audio, dim=[1, 2], keepdim=True) * 5.0 std[std < 1.0] = 1.0 audio /= std - vae_sample_rate = getattr(vae, "audio_sample_rate", 44100) + vae_sample_rate = getattr(vae, "audio_sample_rate_output", getattr(vae, "audio_sample_rate", 44100)) return {"waveform": audio, "sample_rate": vae_sample_rate if "sample_rate" not in samples else samples["sample_rate"]} diff --git a/comfy_extras/nodes_curve.py b/comfy_extras/nodes_curve.py index 9016a84f9..9803e8034 100644 --- a/comfy_extras/nodes_curve.py +++ b/comfy_extras/nodes_curve.py @@ -1,5 +1,7 @@ from __future__ import annotations +import numpy as np + from comfy_api.latest import ComfyExtension, io from comfy_api.input import CurveInput from typing_extensions import override @@ -32,10 +34,58 @@ class CurveEditor(io.ComfyNode): return io.NodeOutput(result, ui=ui) if ui else io.NodeOutput(result) +class ImageHistogram(io.ComfyNode): + @classmethod + def define_schema(cls): + return io.Schema( + node_id="ImageHistogram", + display_name="Image Histogram", + category="utils", + inputs=[ + io.Image.Input("image"), + ], + outputs=[ + io.Histogram.Output("rgb"), + io.Histogram.Output("luminance"), + io.Histogram.Output("red"), + io.Histogram.Output("green"), + io.Histogram.Output("blue"), + ], + ) + + @classmethod + def execute(cls, image) -> io.NodeOutput: + img = image[0].cpu().numpy() + img_uint8 = np.clip(img * 255, 0, 255).astype(np.uint8) + + def bincount(data): + return np.bincount(data.ravel(), minlength=256)[:256] + + hist_r = bincount(img_uint8[:, :, 0]) + hist_g = bincount(img_uint8[:, :, 1]) + hist_b = bincount(img_uint8[:, :, 2]) + + # Average of R, G, B histograms (same as Photoshop's RGB composite) + rgb = ((hist_r + hist_g + hist_b) // 3).tolist() + + # ITU-R BT.709-6, Item 3.2 (p.6) — Derivation of luminance signal + # https://www.itu.int/rec/R-REC-BT.709-6-201506-I/en + lum = 0.2126 * img[:, :, 0] + 0.7152 * img[:, :, 1] + 0.0722 * img[:, :, 2] + luminance = bincount(np.clip(lum * 255, 0, 255).astype(np.uint8)).tolist() + + return io.NodeOutput( + rgb, + luminance, + hist_r.tolist(), + hist_g.tolist(), + hist_b.tolist(), + ) + + class CurveExtension(ComfyExtension): @override async def get_node_list(self): - return [CurveEditor] + return [CurveEditor, ImageHistogram] async def comfy_entrypoint(): diff --git a/comfy_extras/nodes_frame_interpolation.py b/comfy_extras/nodes_frame_interpolation.py new file mode 100644 index 000000000..a3b00d36e --- /dev/null +++ b/comfy_extras/nodes_frame_interpolation.py @@ -0,0 +1,211 @@ +import torch +from tqdm import tqdm +from typing_extensions import override + +import comfy.model_patcher +import comfy.utils +import folder_paths +from comfy import model_management +from comfy_extras.frame_interpolation_models.ifnet import IFNet, detect_rife_config +from comfy_extras.frame_interpolation_models.film_net import FILMNet +from comfy_api.latest import ComfyExtension, io + +FrameInterpolationModel = io.Custom("INTERP_MODEL") + + +class FrameInterpolationModelLoader(io.ComfyNode): + @classmethod + def define_schema(cls): + return io.Schema( + node_id="FrameInterpolationModelLoader", + display_name="Load Frame Interpolation Model", + category="loaders", + inputs=[ + io.Combo.Input("model_name", options=folder_paths.get_filename_list("frame_interpolation"), + tooltip="Select a frame interpolation model to load. Models must be placed in the 'frame_interpolation' folder."), + ], + outputs=[ + FrameInterpolationModel.Output(), + ], + ) + + @classmethod + def execute(cls, model_name) -> io.NodeOutput: + model_path = folder_paths.get_full_path_or_raise("frame_interpolation", model_name) + sd = comfy.utils.load_torch_file(model_path, safe_load=True) + + model = cls._detect_and_load(sd) + dtype = torch.float16 if model_management.should_use_fp16(model_management.get_torch_device()) else torch.float32 + model.eval().to(dtype) + patcher = comfy.model_patcher.ModelPatcher( + model, + load_device=model_management.get_torch_device(), + offload_device=model_management.unet_offload_device(), + ) + return io.NodeOutput(patcher) + + @classmethod + def _detect_and_load(cls, sd): + # Try FILM + if "extract.extract_sublevels.convs.0.0.conv.weight" in sd: + model = FILMNet() + model.load_state_dict(sd) + return model + + # Try RIFE (needs key remapping for raw checkpoints) + sd = comfy.utils.state_dict_prefix_replace(sd, {"module.": "", "flownet.": ""}) + key_map = {} + for k in sd: + for i in range(5): + if k.startswith(f"block{i}."): + key_map[k] = f"blocks.{i}.{k[len(f'block{i}.'):]}" + if key_map: + sd = {key_map.get(k, k): v for k, v in sd.items()} + sd = {k: v for k, v in sd.items() if not k.startswith(("teacher.", "caltime."))} + + try: + head_ch, channels = detect_rife_config(sd) + except (KeyError, ValueError): + raise ValueError("Unrecognized frame interpolation model format") + model = IFNet(head_ch=head_ch, channels=channels) + model.load_state_dict(sd) + return model + + +class FrameInterpolate(io.ComfyNode): + @classmethod + def define_schema(cls): + return io.Schema( + node_id="FrameInterpolate", + display_name="Frame Interpolate", + category="image/video", + search_aliases=["rife", "film", "frame interpolation", "slow motion", "interpolate frames", "vfi"], + inputs=[ + FrameInterpolationModel.Input("interp_model"), + io.Image.Input("images"), + io.Int.Input("multiplier", default=2, min=2, max=16), + ], + outputs=[ + io.Image.Output(), + ], + ) + + @classmethod + def execute(cls, interp_model, images, multiplier) -> io.NodeOutput: + offload_device = model_management.intermediate_device() + + num_frames = images.shape[0] + if num_frames < 2 or multiplier < 2: + return io.NodeOutput(images) + + model_management.load_model_gpu(interp_model) + device = interp_model.load_device + dtype = interp_model.model_dtype() + inference_model = interp_model.model + + # Free VRAM for inference activations (model weights + ~20x a single frame's worth) + H, W = images.shape[1], images.shape[2] + activation_mem = H * W * 3 * images.element_size() * 20 + model_management.free_memory(activation_mem, device) + align = getattr(inference_model, "pad_align", 1) + + # Prepare a single padded frame on device for determining output dimensions + def prepare_frame(idx): + frame = images[idx:idx + 1].movedim(-1, 1).to(dtype=dtype, device=device) + if align > 1: + from comfy.ldm.common_dit import pad_to_patch_size + frame = pad_to_patch_size(frame, (align, align), padding_mode="reflect") + return frame + + # Count total interpolation passes for progress bar + total_pairs = num_frames - 1 + num_interp = multiplier - 1 + total_steps = total_pairs * num_interp + pbar = comfy.utils.ProgressBar(total_steps) + tqdm_bar = tqdm(total=total_steps, desc="Frame interpolation") + + batch = num_interp # reduced on OOM and persists across pairs (same resolution = same limit) + t_values = [t / multiplier for t in range(1, multiplier)] + + out_dtype = model_management.intermediate_dtype() + total_out_frames = total_pairs * multiplier + 1 + result = torch.empty((total_out_frames, 3, H, W), dtype=out_dtype, device=offload_device) + result[0] = images[0].movedim(-1, 0).to(out_dtype) + out_idx = 1 + + # Pre-compute timestep tensor on device (padded dimensions needed) + sample = prepare_frame(0) + pH, pW = sample.shape[2], sample.shape[3] + ts_full = torch.tensor(t_values, device=device, dtype=dtype).reshape(num_interp, 1, 1, 1) + ts_full = ts_full.expand(-1, 1, pH, pW) + del sample + + multi_fn = getattr(inference_model, "forward_multi_timestep", None) + feat_cache = {} + prev_frame = None + + try: + for i in range(total_pairs): + img0_single = prev_frame if prev_frame is not None else prepare_frame(i) + img1_single = prepare_frame(i + 1) + prev_frame = img1_single + + # Cache features: img1 of pair N becomes img0 of pair N+1 + feat_cache["img0"] = feat_cache.pop("next") if "next" in feat_cache else inference_model.extract_features(img0_single) + feat_cache["img1"] = inference_model.extract_features(img1_single) + feat_cache["next"] = feat_cache["img1"] + + used_multi = False + if multi_fn is not None: + # Models with timestep-independent flow can compute it once for all timesteps + try: + mids = multi_fn(img0_single, img1_single, t_values, cache=feat_cache) + result[out_idx:out_idx + num_interp] = mids[:, :, :H, :W].to(out_dtype) + out_idx += num_interp + pbar.update(num_interp) + tqdm_bar.update(num_interp) + used_multi = True + except model_management.OOM_EXCEPTION: + model_management.soft_empty_cache() + multi_fn = None # fall through to single-timestep path + + if not used_multi: + j = 0 + while j < num_interp: + b = min(batch, num_interp - j) + try: + img0 = img0_single.expand(b, -1, -1, -1) + img1 = img1_single.expand(b, -1, -1, -1) + mids = inference_model(img0, img1, timestep=ts_full[j:j + b], cache=feat_cache) + result[out_idx:out_idx + b] = mids[:, :, :H, :W].to(out_dtype) + out_idx += b + pbar.update(b) + tqdm_bar.update(b) + j += b + except model_management.OOM_EXCEPTION: + if batch <= 1: + raise + batch = max(1, batch // 2) + model_management.soft_empty_cache() + + result[out_idx] = images[i + 1].movedim(-1, 0).to(out_dtype) + out_idx += 1 + finally: + tqdm_bar.close() + + # BCHW -> BHWC + result = result.movedim(1, -1).clamp_(0.0, 1.0) + return io.NodeOutput(result) + + +class FrameInterpolationExtension(ComfyExtension): + @override + async def get_node_list(self) -> list[type[io.ComfyNode]]: + return [ + FrameInterpolationModelLoader, + FrameInterpolate, + ] + + +async def comfy_entrypoint() -> FrameInterpolationExtension: + return FrameInterpolationExtension() diff --git a/comfy_extras/nodes_hunyuan3d.py b/comfy_extras/nodes_hunyuan3d.py index df0c3e4b1..fa55ead59 100644 --- a/comfy_extras/nodes_hunyuan3d.py +++ b/comfy_extras/nodes_hunyuan3d.py @@ -637,7 +637,7 @@ class SaveGLB(IO.ComfyNode): ], tooltip="Mesh or 3D file to save", ), - IO.String.Input("filename_prefix", default="mesh/ComfyUI"), + IO.String.Input("filename_prefix", default="3d/ComfyUI"), ], hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo] ) diff --git a/comfy_extras/nodes_lt.py b/comfy_extras/nodes_lt.py index d7c2e8744..19d8a387f 100644 --- a/comfy_extras/nodes_lt.py +++ b/comfy_extras/nodes_lt.py @@ -1,6 +1,7 @@ import nodes import node_helpers import torch +import torchaudio import comfy.model_management import comfy.model_sampling import comfy.samplers @@ -711,7 +712,14 @@ class LTXVReferenceAudio(io.ComfyNode): @classmethod def execute(cls, model, positive, negative, reference_audio, audio_vae, identity_guidance_scale, start_percent, end_percent) -> io.NodeOutput: # Encode reference audio to latents and patchify - audio_latents = audio_vae.encode(reference_audio) + sample_rate = reference_audio["sample_rate"] + vae_sample_rate = getattr(audio_vae, "audio_sample_rate", 44100) + if vae_sample_rate != sample_rate: + waveform = torchaudio.functional.resample(reference_audio["waveform"], sample_rate, vae_sample_rate) + else: + waveform = reference_audio["waveform"] + + audio_latents = audio_vae.encode(waveform.movedim(1, -1)) b, c, t, f = audio_latents.shape ref_tokens = audio_latents.permute(0, 2, 1, 3).reshape(b, t, c * f) ref_audio = {"tokens": ref_tokens} diff --git a/comfy_extras/nodes_lt_audio.py b/comfy_extras/nodes_lt_audio.py index 3e4222264..3ec635c75 100644 --- a/comfy_extras/nodes_lt_audio.py +++ b/comfy_extras/nodes_lt_audio.py @@ -3,9 +3,8 @@ import comfy.utils import comfy.model_management import torch -from comfy.ldm.lightricks.vae.audio_vae import AudioVAE from comfy_api.latest import ComfyExtension, io - +from comfy_extras.nodes_audio import VAEEncodeAudio class LTXVAudioVAELoader(io.ComfyNode): @classmethod @@ -28,10 +27,14 @@ class LTXVAudioVAELoader(io.ComfyNode): def execute(cls, ckpt_name: str) -> io.NodeOutput: ckpt_path = folder_paths.get_full_path_or_raise("checkpoints", ckpt_name) sd, metadata = comfy.utils.load_torch_file(ckpt_path, return_metadata=True) - return io.NodeOutput(AudioVAE(sd, metadata)) + sd = comfy.utils.state_dict_prefix_replace(sd, {"audio_vae.": "autoencoder.", "vocoder.": "vocoder."}, filter_keys=True) + vae = comfy.sd.VAE(sd=sd, metadata=metadata) + vae.throw_exception_if_invalid() + + return io.NodeOutput(vae) -class LTXVAudioVAEEncode(io.ComfyNode): +class LTXVAudioVAEEncode(VAEEncodeAudio): @classmethod def define_schema(cls) -> io.Schema: return io.Schema( @@ -50,15 +53,8 @@ class LTXVAudioVAEEncode(io.ComfyNode): ) @classmethod - def execute(cls, audio, audio_vae: AudioVAE) -> io.NodeOutput: - audio_latents = audio_vae.encode(audio) - return io.NodeOutput( - { - "samples": audio_latents, - "sample_rate": int(audio_vae.sample_rate), - "type": "audio", - } - ) + def execute(cls, audio, audio_vae) -> io.NodeOutput: + return super().execute(audio_vae, audio) class LTXVAudioVAEDecode(io.ComfyNode): @@ -80,12 +76,12 @@ class LTXVAudioVAEDecode(io.ComfyNode): ) @classmethod - def execute(cls, samples, audio_vae: AudioVAE) -> io.NodeOutput: + def execute(cls, samples, audio_vae) -> io.NodeOutput: audio_latent = samples["samples"] if audio_latent.is_nested: audio_latent = audio_latent.unbind()[-1] - audio = audio_vae.decode(audio_latent).to(audio_latent.device) - output_audio_sample_rate = audio_vae.output_sample_rate + audio = audio_vae.decode(audio_latent).movedim(-1, 1).to(audio_latent.device) + output_audio_sample_rate = audio_vae.first_stage_model.output_sample_rate return io.NodeOutput( { "waveform": audio, @@ -143,17 +139,17 @@ class LTXVEmptyLatentAudio(io.ComfyNode): frames_number: int, frame_rate: int, batch_size: int, - audio_vae: AudioVAE, + audio_vae, ) -> io.NodeOutput: """Generate empty audio latents matching the reference pipeline structure.""" assert audio_vae is not None, "Audio VAE model is required" z_channels = audio_vae.latent_channels - audio_freq = audio_vae.latent_frequency_bins - sampling_rate = int(audio_vae.sample_rate) + audio_freq = audio_vae.first_stage_model.latent_frequency_bins + sampling_rate = int(audio_vae.first_stage_model.sample_rate) - num_audio_latents = audio_vae.num_of_latents_from_frames(frames_number, frame_rate) + num_audio_latents = audio_vae.first_stage_model.num_of_latents_from_frames(frames_number, frame_rate) audio_latents = torch.zeros( (batch_size, z_channels, num_audio_latents, audio_freq), diff --git a/comfy_extras/nodes_mask.py b/comfy_extras/nodes_mask.py index c44602597..8ca947718 100644 --- a/comfy_extras/nodes_mask.py +++ b/comfy_extras/nodes_mask.py @@ -2,6 +2,7 @@ import numpy as np import scipy.ndimage import torch import comfy.utils +import comfy.model_management import node_helpers from typing_extensions import override from comfy_api.latest import ComfyExtension, IO, UI @@ -188,7 +189,7 @@ class SolidMask(IO.ComfyNode): @classmethod def execute(cls, value, width, height) -> IO.NodeOutput: - out = torch.full((1, height, width), value, dtype=torch.float32, device="cpu") + out = torch.full((1, height, width), value, dtype=torch.float32, device=comfy.model_management.intermediate_device()) return IO.NodeOutput(out) solid = execute # TODO: remove @@ -262,6 +263,7 @@ class MaskComposite(IO.ComfyNode): def execute(cls, destination, source, x, y, operation) -> IO.NodeOutput: output = destination.reshape((-1, destination.shape[-2], destination.shape[-1])).clone() source = source.reshape((-1, source.shape[-2], source.shape[-1])) + source = source.to(output.device) left, top = (x, y,) right, bottom = (min(left + source.shape[-1], destination.shape[-1]), min(top + source.shape[-2], destination.shape[-2])) diff --git a/comfy_extras/nodes_model_patch.py b/comfy_extras/nodes_model_patch.py index 176e6bc2f..748559a6b 100644 --- a/comfy_extras/nodes_model_patch.py +++ b/comfy_extras/nodes_model_patch.py @@ -7,7 +7,10 @@ import comfy.model_management import comfy.ldm.common_dit import comfy.latent_formats import comfy.ldm.lumina.controlnet +import comfy.ldm.supir.supir_modules from comfy.ldm.wan.model_multitalk import WanMultiTalkAttentionBlock, MultiTalkAudioProjModel +from comfy_api.latest import io +from comfy.ldm.supir.supir_patch import SUPIRPatch class BlockWiseControlBlock(torch.nn.Module): @@ -266,6 +269,27 @@ class ModelPatchLoader: out_dim=sd["audio_proj.norm.weight"].shape[0], device=comfy.model_management.unet_offload_device(), operations=comfy.ops.manual_cast) + elif 'model.control_model.input_hint_block.0.weight' in sd or 'control_model.input_hint_block.0.weight' in sd: + prefix_replace = {} + if 'model.control_model.input_hint_block.0.weight' in sd: + prefix_replace["model.control_model."] = "control_model." + prefix_replace["model.diffusion_model.project_modules."] = "project_modules." + else: + prefix_replace["control_model."] = "control_model." + prefix_replace["project_modules."] = "project_modules." + + # Extract denoise_encoder weights before filter_keys discards them + de_prefix = "first_stage_model.denoise_encoder." + denoise_encoder_sd = {} + for k in list(sd.keys()): + if k.startswith(de_prefix): + denoise_encoder_sd[k[len(de_prefix):]] = sd.pop(k) + + sd = comfy.utils.state_dict_prefix_replace(sd, prefix_replace, filter_keys=True) + sd.pop("control_model.mask_LQ", None) + model = comfy.ldm.supir.supir_modules.SUPIR(device=comfy.model_management.unet_offload_device(), dtype=dtype, operations=comfy.ops.manual_cast) + if denoise_encoder_sd: + model.denoise_encoder_sd = denoise_encoder_sd model_patcher = comfy.model_patcher.CoreModelPatcher(model, load_device=comfy.model_management.get_torch_device(), offload_device=comfy.model_management.unet_offload_device()) model.load_state_dict(sd, assign=model_patcher.is_dynamic()) @@ -565,9 +589,89 @@ class MultiTalkModelPatch(torch.nn.Module): ) +class SUPIRApply(io.ComfyNode): + @classmethod + def define_schema(cls) -> io.Schema: + return io.Schema( + node_id="SUPIRApply", + category="model_patches/supir", + is_experimental=True, + inputs=[ + io.Model.Input("model"), + io.ModelPatch.Input("model_patch"), + io.Vae.Input("vae"), + io.Image.Input("image"), + io.Float.Input("strength_start", default=1.0, min=0.0, max=10.0, step=0.01, + tooltip="Control strength at the start of sampling (high sigma)."), + io.Float.Input("strength_end", default=1.0, min=0.0, max=10.0, step=0.01, + tooltip="Control strength at the end of sampling (low sigma). Linearly interpolated from start."), + io.Float.Input("restore_cfg", default=4.0, min=0.0, max=20.0, step=0.1, advanced=True, + tooltip="Pulls denoised output toward the input latent. Higher = stronger fidelity to input. 0 to disable."), + io.Float.Input("restore_cfg_s_tmin", default=0.05, min=0.0, max=1.0, step=0.01, advanced=True, + tooltip="Sigma threshold below which restore_cfg is disabled."), + ], + outputs=[io.Model.Output()], + ) + + @classmethod + def _encode_with_denoise_encoder(cls, vae, model_patch, image): + """Encode using denoise_encoder weights from SUPIR checkpoint if available.""" + denoise_sd = getattr(model_patch.model, 'denoise_encoder_sd', None) + if not denoise_sd: + return vae.encode(image) + + # Clone VAE patcher, apply denoise_encoder weights to clone, encode + orig_patcher = vae.patcher + vae.patcher = orig_patcher.clone() + patches = {f"encoder.{k}": (v,) for k, v in denoise_sd.items()} + vae.patcher.add_patches(patches, strength_patch=1.0, strength_model=0.0) + try: + return vae.encode(image) + finally: + vae.patcher = orig_patcher + + @classmethod + def execute(cls, *, model: io.Model.Type, model_patch: io.ModelPatch.Type, vae: io.Vae.Type, image: io.Image.Type, + strength_start: float, strength_end: float, restore_cfg: float, restore_cfg_s_tmin: float) -> io.NodeOutput: + model_patched = model.clone() + hint_latent = model.get_model_object("latent_format").process_in( + cls._encode_with_denoise_encoder(vae, model_patch, image[:, :, :, :3])) + patch = SUPIRPatch(model_patch, model_patch.model.project_modules, hint_latent, strength_start, strength_end) + patch.register(model_patched) + + if restore_cfg > 0.0: + # Round-trip to match original pipeline: decode hint, re-encode with regular VAE + latent_format = model.get_model_object("latent_format") + decoded = vae.decode(latent_format.process_out(hint_latent)) + x_center = latent_format.process_in(vae.encode(decoded[:, :, :, :3])) + sigma_max = 14.6146 + + def restore_cfg_function(args): + denoised = args["denoised"] + sigma = args["sigma"] + if sigma.dim() > 0: + s = sigma[0].item() + else: + s = sigma.item() + if s > restore_cfg_s_tmin: + ref = x_center.to(device=denoised.device, dtype=denoised.dtype) + b = denoised.shape[0] + if ref.shape[0] != b: + ref = ref.expand(b, -1, -1, -1) if ref.shape[0] == 1 else ref.repeat((b + ref.shape[0] - 1) // ref.shape[0], 1, 1, 1)[:b] + sigma_val = sigma.view(-1, 1, 1, 1) if sigma.dim() > 0 else sigma + d_center = denoised - ref + denoised = denoised - d_center * ((sigma_val / sigma_max) ** restore_cfg) + return denoised + + model_patched.set_model_sampler_post_cfg_function(restore_cfg_function) + + return io.NodeOutput(model_patched) + + NODE_CLASS_MAPPINGS = { "ModelPatchLoader": ModelPatchLoader, "QwenImageDiffsynthControlnet": QwenImageDiffsynthControlnet, "ZImageFunControlnet": ZImageFunControlnet, "USOStyleReference": USOStyleReference, + "SUPIRApply": SUPIRApply, } diff --git a/comfy_extras/nodes_post_processing.py b/comfy_extras/nodes_post_processing.py index 9037c3d20..c932b747a 100644 --- a/comfy_extras/nodes_post_processing.py +++ b/comfy_extras/nodes_post_processing.py @@ -6,6 +6,7 @@ from PIL import Image import math from enum import Enum from typing import TypedDict, Literal +import kornia import comfy.utils import comfy.model_management @@ -660,6 +661,228 @@ class BatchImagesMasksLatentsNode(io.ComfyNode): return io.NodeOutput(batched) +class ColorTransfer(io.ComfyNode): + @classmethod + def define_schema(cls): + return io.Schema( + node_id="ColorTransfer", + category="image/postprocessing", + description="Match the colors of one image to another using various algorithms.", + search_aliases=["color match", "color grading", "color correction", "match colors", "color transform", "mkl", "reinhard", "histogram"], + inputs=[ + io.Image.Input("image_target", tooltip="Image(s) to apply the color transform to."), + io.Image.Input("image_ref", optional=True, tooltip="Reference image(s) to match colors to. If not provided, processing is skipped"), + io.Combo.Input("method", options=['reinhard_lab', 'mkl_lab', 'histogram'],), + io.DynamicCombo.Input("source_stats", + tooltip="per_frame: each frame matched to image_ref individually. uniform: pool stats across all source frames as baseline, match to image_ref. target_frame: use one chosen frame as the baseline for the transform to image_ref, applied uniformly to all frames (preserves relative differences)", + options=[ + io.DynamicCombo.Option("per_frame", []), + io.DynamicCombo.Option("uniform", []), + io.DynamicCombo.Option("target_frame", [ + io.Int.Input("target_index", default=0, min=0, max=10000, + tooltip="Frame index used as the source baseline for computing the transform to image_ref"), + ]), + ]), + io.Float.Input("strength", default=1.0, min=0.0, max=10.0, step=0.01), + ], + outputs=[ + io.Image.Output(display_name="image"), + ], + ) + + @staticmethod + def _to_lab(images, i, device): + return kornia.color.rgb_to_lab( + images[i:i+1].to(device, dtype=torch.float32).permute(0, 3, 1, 2)) + + @staticmethod + def _pool_stats(images, device, is_reinhard, eps): + """Two-pass pooled mean + std/cov across all frames.""" + N, C = images.shape[0], images.shape[3] + HW = images.shape[1] * images.shape[2] + mean = torch.zeros(C, 1, device=device, dtype=torch.float32) + for i in range(N): + mean += ColorTransfer._to_lab(images, i, device).view(C, -1).mean(dim=-1, keepdim=True) + mean /= N + acc = torch.zeros(C, 1 if is_reinhard else C, device=device, dtype=torch.float32) + for i in range(N): + centered = ColorTransfer._to_lab(images, i, device).view(C, -1) - mean + if is_reinhard: + acc += (centered * centered).mean(dim=-1, keepdim=True) + else: + acc += centered @ centered.T / HW + if is_reinhard: + return mean, torch.sqrt(acc / N).clamp_min_(eps) + return mean, acc / N + + @staticmethod + def _frame_stats(lab_flat, hw, is_reinhard, eps): + """Per-frame mean + std/cov.""" + mean = lab_flat.mean(dim=-1, keepdim=True) + if is_reinhard: + return mean, lab_flat.std(dim=-1, keepdim=True, unbiased=False).clamp_min_(eps) + centered = lab_flat - mean + return mean, centered @ centered.T / hw + + @staticmethod + def _mkl_matrix(cov_s, cov_r, eps): + """Compute MKL 3x3 transform matrix from source and ref covariances.""" + eig_val_s, eig_vec_s = torch.linalg.eigh(cov_s) + sqrt_val_s = torch.sqrt(eig_val_s.clamp_min(0)).clamp_min_(eps) + + scaled_V = eig_vec_s * sqrt_val_s.unsqueeze(0) + mid = scaled_V.T @ cov_r @ scaled_V + eig_val_m, eig_vec_m = torch.linalg.eigh(mid) + sqrt_m = torch.sqrt(eig_val_m.clamp_min(0)) + + inv_sqrt_s = 1.0 / sqrt_val_s + inv_scaled_V = eig_vec_s * inv_sqrt_s.unsqueeze(0) + M_half = (eig_vec_m * sqrt_m.unsqueeze(0)) @ eig_vec_m.T + return inv_scaled_V @ M_half @ inv_scaled_V.T + + @staticmethod + def _histogram_lut(src, ref, bins=256): + """Build per-channel LUT from source and ref histograms. src/ref: (C, HW) in [0,1].""" + s_bins = (src * (bins - 1)).long().clamp(0, bins - 1) + r_bins = (ref * (bins - 1)).long().clamp(0, bins - 1) + s_hist = torch.zeros(src.shape[0], bins, device=src.device, dtype=src.dtype) + r_hist = torch.zeros(src.shape[0], bins, device=src.device, dtype=src.dtype) + ones_s = torch.ones_like(src) + ones_r = torch.ones_like(ref) + s_hist.scatter_add_(1, s_bins, ones_s) + r_hist.scatter_add_(1, r_bins, ones_r) + s_cdf = s_hist.cumsum(1) + s_cdf = s_cdf / s_cdf[:, -1:] + r_cdf = r_hist.cumsum(1) + r_cdf = r_cdf / r_cdf[:, -1:] + return torch.searchsorted(r_cdf, s_cdf).clamp_max_(bins - 1).float() / (bins - 1) + + @classmethod + def _pooled_cdf(cls, images, device, num_bins=256): + """Build pooled CDF across all frames, one frame at a time.""" + C = images.shape[3] + hist = torch.zeros(C, num_bins, device=device, dtype=torch.float32) + for i in range(images.shape[0]): + frame = images[i].to(device, dtype=torch.float32).permute(2, 0, 1).reshape(C, -1) + bins = (frame * (num_bins - 1)).long().clamp(0, num_bins - 1) + hist.scatter_add_(1, bins, torch.ones_like(frame)) + cdf = hist.cumsum(1) + return cdf / cdf[:, -1:] + + @classmethod + def _build_histogram_transform(cls, image_target, image_ref, device, stats_mode, target_index, B): + """Build per-frame or uniform LUT transform for histogram mode.""" + if stats_mode == 'per_frame': + return None # LUT computed per-frame in the apply loop + + r_cdf = cls._pooled_cdf(image_ref, device) + if stats_mode == 'target_frame': + ti = min(target_index, B - 1) + s_cdf = cls._pooled_cdf(image_target[ti:ti+1], device) + else: + s_cdf = cls._pooled_cdf(image_target, device) + return torch.searchsorted(r_cdf, s_cdf).clamp_max_(255).float() / 255.0 + + @classmethod + def _build_lab_transform(cls, image_target, image_ref, device, stats_mode, target_index, is_reinhard): + """Build transform parameters for Lab-based methods. Returns a transform function.""" + eps = 1e-6 + B, H, W, C = image_target.shape + B_ref = image_ref.shape[0] + single_ref = B_ref == 1 + HW = H * W + HW_ref = image_ref.shape[1] * image_ref.shape[2] + + # Precompute ref stats + if single_ref or stats_mode in ('uniform', 'target_frame'): + ref_mean, ref_sc = cls._pool_stats(image_ref, device, is_reinhard, eps) + + # Uniform/target_frame: precompute single affine transform + if stats_mode in ('uniform', 'target_frame'): + if stats_mode == 'target_frame': + ti = min(target_index, B - 1) + s_lab = cls._to_lab(image_target, ti, device).view(C, -1) + s_mean, s_sc = cls._frame_stats(s_lab, HW, is_reinhard, eps) + else: + s_mean, s_sc = cls._pool_stats(image_target, device, is_reinhard, eps) + + if is_reinhard: + scale = ref_sc / s_sc + offset = ref_mean - scale * s_mean + return lambda src_flat, **_: src_flat * scale + offset + T = cls._mkl_matrix(s_sc, ref_sc, eps) + offset = ref_mean - T @ s_mean + return lambda src_flat, **_: T @ src_flat + offset + + # per_frame + def per_frame_transform(src_flat, frame_idx): + s_mean, s_sc = cls._frame_stats(src_flat, HW, is_reinhard, eps) + + if single_ref: + r_mean, r_sc = ref_mean, ref_sc + else: + ri = min(frame_idx, B_ref - 1) + r_mean, r_sc = cls._frame_stats(cls._to_lab(image_ref, ri, device).view(C, -1), HW_ref, is_reinhard, eps) + + centered = src_flat - s_mean + if is_reinhard: + return centered * (r_sc / s_sc) + r_mean + T = cls._mkl_matrix(centered @ centered.T / HW, r_sc, eps) + return T @ centered + r_mean + + return per_frame_transform + + @classmethod + def execute(cls, image_target, image_ref, method, source_stats, strength=1.0) -> io.NodeOutput: + stats_mode = source_stats["source_stats"] + target_index = source_stats.get("target_index", 0) + + if strength == 0 or image_ref is None: + return io.NodeOutput(image_target) + + device = comfy.model_management.get_torch_device() + intermediate_device = comfy.model_management.intermediate_device() + intermediate_dtype = comfy.model_management.intermediate_dtype() + + B, H, W, C = image_target.shape + B_ref = image_ref.shape[0] + pbar = comfy.utils.ProgressBar(B) + out = torch.empty(B, H, W, C, device=intermediate_device, dtype=intermediate_dtype) + + if method == 'histogram': + uniform_lut = cls._build_histogram_transform( + image_target, image_ref, device, stats_mode, target_index, B) + + for i in range(B): + src = image_target[i].to(device, dtype=torch.float32).permute(2, 0, 1) + src_flat = src.reshape(C, -1) + if uniform_lut is not None: + lut = uniform_lut + else: + ri = min(i, B_ref - 1) + ref = image_ref[ri].to(device, dtype=torch.float32).permute(2, 0, 1).reshape(C, -1) + lut = cls._histogram_lut(src_flat, ref) + bin_idx = (src_flat * 255).long().clamp(0, 255) + matched = lut.gather(1, bin_idx).view(C, H, W) + result = matched if strength == 1.0 else torch.lerp(src, matched, strength) + out[i] = result.permute(1, 2, 0).clamp_(0, 1).to(device=intermediate_device, dtype=intermediate_dtype) + pbar.update(1) + else: + transform = cls._build_lab_transform(image_target, image_ref, device, stats_mode, target_index, is_reinhard=method == "reinhard_lab") + + for i in range(B): + src_frame = cls._to_lab(image_target, i, device) + corrected = transform(src_frame.view(C, -1), frame_idx=i) + if strength == 1.0: + result = kornia.color.lab_to_rgb(corrected.view(1, C, H, W)) + else: + result = kornia.color.lab_to_rgb(torch.lerp(src_frame, corrected.view(1, C, H, W), strength)) + out[i] = result.squeeze(0).permute(1, 2, 0).clamp_(0, 1).to(device=intermediate_device, dtype=intermediate_dtype) + pbar.update(1) + + return io.NodeOutput(out) + + class PostProcessingExtension(ComfyExtension): @override async def get_node_list(self) -> list[type[io.ComfyNode]]: @@ -673,6 +896,7 @@ class PostProcessingExtension(ComfyExtension): BatchImagesNode, BatchMasksNode, BatchLatentsNode, + ColorTransfer, # BatchImagesMasksLatentsNode, ] diff --git a/comfy_extras/nodes_preview_any.py b/comfy_extras/nodes_preview_any.py index b0a6f279d..17e25d514 100644 --- a/comfy_extras/nodes_preview_any.py +++ b/comfy_extras/nodes_preview_any.py @@ -1,5 +1,6 @@ import json from comfy.comfy_types.node_typing import IO +import torch # Preview Any - original implement from # https://github.com/rgthree/rgthree-comfy/blob/main/py/display_any.py @@ -11,7 +12,7 @@ class PreviewAny(): "required": {"source": (IO.ANY, {})}, } - RETURN_TYPES = () + RETURN_TYPES = (IO.STRING,) FUNCTION = "main" OUTPUT_NODE = True @@ -19,6 +20,7 @@ class PreviewAny(): SEARCH_ALIASES = ["show output", "inspect", "debug", "print value", "show text"] def main(self, source=None): + torch.set_printoptions(edgeitems=6) value = 'None' if isinstance(source, str): value = source @@ -33,7 +35,8 @@ class PreviewAny(): except Exception: value = 'source exists, but could not be serialized.' - return {"ui": {"text": (value,)}} + torch.set_printoptions() + return {"ui": {"text": (value,)}, "result": (value,)} NODE_CLASS_MAPPINGS = { "PreviewAny": PreviewAny, diff --git a/comfy_extras/nodes_rtdetr.py b/comfy_extras/nodes_rtdetr.py index 61307e268..7feaf3ab3 100644 --- a/comfy_extras/nodes_rtdetr.py +++ b/comfy_extras/nodes_rtdetr.py @@ -32,10 +32,12 @@ class RTDETR_detect(io.ComfyNode): def execute(cls, model, image, threshold, class_name, max_detections) -> io.NodeOutput: B, H, W, C = image.shape - image_in = comfy.utils.common_upscale(image.movedim(-1, 1), 640, 640, "bilinear", crop="disabled") - comfy.model_management.load_model_gpu(model) - results = model.model.diffusion_model(image_in, (W, H)) # list of B dicts + results = [] + for i in range(0, B, 32): + batch = image[i:i + 32] + image_in = comfy.utils.common_upscale(batch.movedim(-1, 1), 640, 640, "bilinear", crop="disabled") + results.extend(model.model.diffusion_model(image_in, (W, H))) all_bbox_dicts = [] diff --git a/comfy_extras/nodes_sam3.py b/comfy_extras/nodes_sam3.py new file mode 100644 index 000000000..5cf92ccb3 --- /dev/null +++ b/comfy_extras/nodes_sam3.py @@ -0,0 +1,529 @@ +""" +SAM3 (Segment Anything 3) nodes for detection, segmentation, and video tracking. +""" + +from typing_extensions import override + +import json +import os +import torch +import torch.nn.functional as F +import comfy.model_management +import comfy.utils +import folder_paths +from comfy_api.latest import ComfyExtension, io, ui +import av +from fractions import Fraction + + +def _extract_text_prompts(conditioning, device, dtype): + """Extract list of (text_embeddings, text_mask) from conditioning.""" + cond_meta = conditioning[0][1] + multi = cond_meta.get("sam3_multi_cond") + prompts = [] + if multi is not None: + for entry in multi: + emb = entry["cond"].to(device=device, dtype=dtype) + mask = entry["attention_mask"].to(device) if entry["attention_mask"] is not None else None + if mask is None: + mask = torch.ones(emb.shape[0], emb.shape[1], dtype=torch.int64, device=device) + prompts.append((emb, mask, entry.get("max_detections", 1))) + else: + emb = conditioning[0][0].to(device=device, dtype=dtype) + mask = cond_meta.get("attention_mask") + if mask is not None: + mask = mask.to(device) + else: + mask = torch.ones(emb.shape[0], emb.shape[1], dtype=torch.int64, device=device) + prompts.append((emb, mask, 1)) + return prompts + + +def _refine_mask(sam3_model, orig_image_hwc, coarse_mask, box_xyxy, H, W, device, dtype, iterations): + """Refine a coarse detector mask via SAM decoder, cropping to the detection box. + + Returns: [1, H, W] binary mask + """ + def _coarse_fallback(): + return (F.interpolate(coarse_mask.unsqueeze(0).unsqueeze(0), size=(H, W), + mode="bilinear", align_corners=False)[0] > 0).float() + + if iterations <= 0: + return _coarse_fallback() + + pad_frac = 0.1 + x1, y1, x2, y2 = box_xyxy.tolist() + bw, bh = x2 - x1, y2 - y1 + cx1 = max(0, int(x1 - bw * pad_frac)) + cy1 = max(0, int(y1 - bh * pad_frac)) + cx2 = min(W, int(x2 + bw * pad_frac)) + cy2 = min(H, int(y2 + bh * pad_frac)) + if cx2 <= cx1 or cy2 <= cy1: + return _coarse_fallback() + + crop = orig_image_hwc[cy1:cy2, cx1:cx2, :3] + crop_1008 = comfy.utils.common_upscale(crop.unsqueeze(0).movedim(-1, 1), 1008, 1008, "bilinear", crop="disabled") + crop_frame = crop_1008.to(device=device, dtype=dtype) + crop_h, crop_w = cy2 - cy1, cx2 - cx1 + + # Crop coarse mask and refine via SAM on the cropped image + mask_h, mask_w = coarse_mask.shape[-2:] + mx1, my1 = int(cx1 / W * mask_w), int(cy1 / H * mask_h) + mx2, my2 = int(cx2 / W * mask_w), int(cy2 / H * mask_h) + if mx2 <= mx1 or my2 <= my1: + return _coarse_fallback() + mask_logit = coarse_mask[..., my1:my2, mx1:mx2].unsqueeze(0).unsqueeze(0) + for _ in range(iterations): + coarse_input = F.interpolate(mask_logit, size=(1008, 1008), mode="bilinear", align_corners=False) + mask_logit = sam3_model.forward_segment(crop_frame, mask_inputs=coarse_input) + + refined_crop = F.interpolate(mask_logit, size=(crop_h, crop_w), mode="bilinear", align_corners=False) + full_mask = torch.zeros(1, 1, H, W, device=device, dtype=dtype) + full_mask[:, :, cy1:cy2, cx1:cx2] = refined_crop + coarse_full = F.interpolate(coarse_mask.unsqueeze(0).unsqueeze(0), size=(H, W), mode="bilinear", align_corners=False) + return ((full_mask[0] > 0) | (coarse_full[0] > 0)).float() + + + +class SAM3_Detect(io.ComfyNode): + """Open-vocabulary detection and segmentation using text, box, or point prompts.""" + + @classmethod + def define_schema(cls): + return io.Schema( + node_id="SAM3_Detect", + display_name="SAM3 Detect", + category="detection/", + search_aliases=["sam3", "segment anything", "open vocabulary", "text detection", "segment"], + inputs=[ + io.Model.Input("model", display_name="model"), + io.Image.Input("image", display_name="image"), + io.Conditioning.Input("conditioning", display_name="conditioning", optional=True, tooltip="Text conditioning from CLIPTextEncode"), + io.BoundingBox.Input("bboxes", display_name="bboxes", force_input=True, optional=True, tooltip="Bounding boxes to segment within"), + io.String.Input("positive_coords", display_name="positive_coords", force_input=True, optional=True, tooltip="Positive point prompts as JSON [{\"x\": int, \"y\": int}, ...] (pixel coords)"), + io.String.Input("negative_coords", display_name="negative_coords", force_input=True, optional=True, tooltip="Negative point prompts as JSON [{\"x\": int, \"y\": int}, ...] (pixel coords)"), + io.Float.Input("threshold", display_name="threshold", default=0.5, min=0.0, max=1.0, step=0.01), + io.Int.Input("refine_iterations", display_name="refine_iterations", default=2, min=0, max=5, tooltip="SAM decoder refinement passes (0=use raw detector masks)"), + io.Boolean.Input("individual_masks", display_name="individual_masks", default=False, tooltip="Output per-object masks instead of union"), + ], + outputs=[ + io.Mask.Output("masks"), + io.BoundingBox.Output("bboxes"), + ], + ) + + @classmethod + def execute(cls, model, image, conditioning=None, bboxes=None, positive_coords=None, negative_coords=None, threshold=0.5, refine_iterations=2, individual_masks=False) -> io.NodeOutput: + B, H, W, C = image.shape + image_in = comfy.utils.common_upscale(image[..., :3].movedim(-1, 1), 1008, 1008, "bilinear", crop="disabled") + + # Convert bboxes to normalized cxcywh format, per-frame list of [1, N, 4] tensors. + # Supports: single dict (all frames), list[dict] (all frames), list[list[dict]] (per-frame). + def _boxes_to_tensor(box_list): + coords = [] + for d in box_list: + cx = (d["x"] + d["width"] / 2) / W + cy = (d["y"] + d["height"] / 2) / H + coords.append([cx, cy, d["width"] / W, d["height"] / H]) + return torch.tensor([coords], dtype=torch.float32) # [1, N, 4] + + per_frame_boxes = None + if bboxes is not None: + if isinstance(bboxes, dict): + # Single box → same for all frames + shared = _boxes_to_tensor([bboxes]) + per_frame_boxes = [shared] * B + elif isinstance(bboxes, list) and len(bboxes) > 0 and isinstance(bboxes[0], list): + # list[list[dict]] → per-frame boxes + per_frame_boxes = [_boxes_to_tensor(frame_boxes) if frame_boxes else None for frame_boxes in bboxes] + # Pad to B if fewer frames provided + while len(per_frame_boxes) < B: + per_frame_boxes.append(per_frame_boxes[-1] if per_frame_boxes else None) + elif isinstance(bboxes, list) and len(bboxes) > 0: + # list[dict] → same boxes for all frames + shared = _boxes_to_tensor(bboxes) + per_frame_boxes = [shared] * B + + # Parse point prompts from JSON (KJNodes PointsEditor format: [{"x": int, "y": int}, ...]) + pos_pts = json.loads(positive_coords) if positive_coords else [] + neg_pts = json.loads(negative_coords) if negative_coords else [] + has_points = len(pos_pts) > 0 or len(neg_pts) > 0 + + comfy.model_management.load_model_gpu(model) + device = comfy.model_management.get_torch_device() + dtype = model.model.get_dtype() + sam3_model = model.model.diffusion_model + + # Build point inputs for tracker SAM decoder path + point_inputs = None + if has_points: + all_coords = [[p["x"] / W * 1008, p["y"] / H * 1008] for p in pos_pts] + \ + [[p["x"] / W * 1008, p["y"] / H * 1008] for p in neg_pts] + all_labels = [1] * len(pos_pts) + [0] * len(neg_pts) + point_inputs = { + "point_coords": torch.tensor([all_coords], dtype=dtype, device=device), + "point_labels": torch.tensor([all_labels], dtype=torch.int32, device=device), + } + + cond_list = _extract_text_prompts(conditioning, device, dtype) if conditioning is not None and len(conditioning) > 0 else [] + has_text = len(cond_list) > 0 + + # Run per-image through detector (text/boxes) and/or tracker (points) + all_bbox_dicts = [] + all_masks = [] + pbar = comfy.utils.ProgressBar(B) + + for b in range(B): + frame = image_in[b:b+1].to(device=device, dtype=dtype) + b_boxes = None + if per_frame_boxes is not None and per_frame_boxes[b] is not None: + b_boxes = per_frame_boxes[b].to(device=device, dtype=dtype) + + frame_bbox_dicts = [] + frame_masks = [] + + # Point prompts: tracker SAM decoder path with iterative refinement + if point_inputs is not None: + mask_logit = sam3_model.forward_segment(frame, point_inputs=point_inputs) + for _ in range(max(0, refine_iterations - 1)): + mask_logit = sam3_model.forward_segment(frame, mask_inputs=mask_logit) + mask = F.interpolate(mask_logit, size=(H, W), mode="bilinear", align_corners=False) + frame_masks.append((mask[0] > 0).float()) + + # Box prompts: SAM decoder path (segment inside each box) + if b_boxes is not None and not has_text: + for box_cxcywh in b_boxes[0]: + cx, cy, bw, bh = box_cxcywh.tolist() + # Convert cxcywh normalized → xyxy in 1008 space → [1, 2, 2] corners + sam_box = torch.tensor([[[(cx - bw/2) * 1008, (cy - bh/2) * 1008], + [(cx + bw/2) * 1008, (cy + bh/2) * 1008]]], + device=device, dtype=dtype) + mask_logit = sam3_model.forward_segment(frame, box_inputs=sam_box) + for _ in range(max(0, refine_iterations - 1)): + mask_logit = sam3_model.forward_segment(frame, mask_inputs=mask_logit) + mask = F.interpolate(mask_logit, size=(H, W), mode="bilinear", align_corners=False) + frame_masks.append((mask[0] > 0).float()) + + # Text prompts: run detector per text prompt (each detects one category) + for text_embeddings, text_mask, max_det in cond_list: + results = sam3_model( + frame, text_embeddings=text_embeddings, text_mask=text_mask, + boxes=b_boxes, threshold=threshold, orig_size=(H, W)) + + pred_boxes = results["boxes"][0] + scores = results["scores"][0] + masks = results["masks"][0] + + probs = scores.sigmoid() + keep = probs > threshold + kept_boxes = pred_boxes[keep].cpu() + kept_scores = probs[keep].cpu() + kept_masks = masks[keep] + + order = kept_scores.argsort(descending=True)[:max_det] + kept_boxes = kept_boxes[order] + kept_scores = kept_scores[order] + kept_masks = kept_masks[order] + + for box, score in zip(kept_boxes, kept_scores): + frame_bbox_dicts.append({ + "x": float(box[0]), "y": float(box[1]), + "width": float(box[2] - box[0]), "height": float(box[3] - box[1]), + "score": float(score), + }) + for m, box in zip(kept_masks, kept_boxes): + frame_masks.append(_refine_mask( + sam3_model, image[b], m, box, H, W, device, dtype, refine_iterations)) + + all_bbox_dicts.append(frame_bbox_dicts) + if len(frame_masks) > 0: + combined = torch.cat(frame_masks, dim=0) # [N_obj, H, W] + if individual_masks: + all_masks.append(combined) + else: + all_masks.append((combined > 0).any(dim=0).float()) + else: + if individual_masks: + all_masks.append(torch.zeros(0, H, W, device=comfy.model_management.intermediate_device())) + else: + all_masks.append(torch.zeros(H, W, device=comfy.model_management.intermediate_device())) + pbar.update(1) + + idev = comfy.model_management.intermediate_device() + all_masks = [m.to(idev) for m in all_masks] + mask_out = torch.cat(all_masks, dim=0) if individual_masks else torch.stack(all_masks) + return io.NodeOutput(mask_out, all_bbox_dicts) + + +SAM3TrackData = io.Custom("SAM3_TRACK_DATA") + +class SAM3_VideoTrack(io.ComfyNode): + """Track objects across video frames using SAM3's memory-based tracker.""" + + @classmethod + def define_schema(cls): + return io.Schema( + node_id="SAM3_VideoTrack", + display_name="SAM3 Video Track", + category="detection/", + search_aliases=["sam3", "video", "track", "propagate"], + inputs=[ + io.Image.Input("images", display_name="images", tooltip="Video frames as batched images"), + io.Model.Input("model", display_name="model"), + io.Mask.Input("initial_mask", display_name="initial_mask", optional=True, tooltip="Mask(s) for the first frame to track (one per object)"), + io.Conditioning.Input("conditioning", display_name="conditioning", optional=True, tooltip="Text conditioning for detecting new objects during tracking"), + io.Float.Input("detection_threshold", display_name="detection_threshold", default=0.5, min=0.0, max=1.0, step=0.01, tooltip="Score threshold for text-prompted detection"), + io.Int.Input("max_objects", display_name="max_objects", default=0, min=0, tooltip="Max tracked objects (0=unlimited). Initial masks count toward this limit."), + io.Int.Input("detect_interval", display_name="detect_interval", default=1, min=1, tooltip="Run detection every N frames (1=every frame). Higher values save compute."), + ], + outputs=[ + SAM3TrackData.Output("track_data", display_name="track_data"), + ], + ) + + @classmethod + def execute(cls, images, model, initial_mask=None, conditioning=None, detection_threshold=0.5, max_objects=0, detect_interval=1) -> io.NodeOutput: + N, H, W, C = images.shape + + comfy.model_management.load_model_gpu(model) + device = comfy.model_management.get_torch_device() + dtype = model.model.get_dtype() + sam3_model = model.model.diffusion_model + + frames = images[..., :3].movedim(-1, 1) + frames_in = comfy.utils.common_upscale(frames, 1008, 1008, "bilinear", crop="disabled").to(device=device, dtype=dtype) + + init_masks = None + if initial_mask is not None: + init_masks = initial_mask.unsqueeze(1).to(device=device, dtype=dtype) + + pbar = comfy.utils.ProgressBar(N) + + text_prompts = None + if conditioning is not None and len(conditioning) > 0: + text_prompts = [(emb, mask) for emb, mask, _ in _extract_text_prompts(conditioning, device, dtype)] + elif initial_mask is None: + raise ValueError("Either initial_mask or conditioning must be provided") + + result = sam3_model.forward_video( + images=frames_in, initial_masks=init_masks, pbar=pbar, text_prompts=text_prompts, + new_det_thresh=detection_threshold, max_objects=max_objects, + detect_interval=detect_interval) + result["orig_size"] = (H, W) + return io.NodeOutput(result) + + +class SAM3_TrackPreview(io.ComfyNode): + """Visualize tracked objects with distinct colors as a video preview. No tensor output — saves to temp video.""" + + @classmethod + def define_schema(cls): + return io.Schema( + node_id="SAM3_TrackPreview", + display_name="SAM3 Track Preview", + category="detection/", + inputs=[ + SAM3TrackData.Input("track_data", display_name="track_data"), + io.Image.Input("images", display_name="images", optional=True), + io.Float.Input("opacity", display_name="opacity", default=0.5, min=0.0, max=1.0, step=0.05), + io.Float.Input("fps", display_name="fps", default=24.0, min=1.0, max=120.0, step=1.0), + ], + is_output_node=True, + ) + + COLORS = [ + (0.12, 0.47, 0.71), (1.0, 0.5, 0.05), (0.17, 0.63, 0.17), (0.84, 0.15, 0.16), + (0.58, 0.4, 0.74), (0.55, 0.34, 0.29), (0.89, 0.47, 0.76), (0.5, 0.5, 0.5), + (0.74, 0.74, 0.13), (0.09, 0.75, 0.81), (0.94, 0.76, 0.06), (0.42, 0.68, 0.84), + ] + + # 5x3 bitmap font atlas for digits 0-9 [10, 5, 3] + _glyph_cache = {} # (device, scale) -> (glyphs, outlines, gh, gw, oh, ow) + + @staticmethod + def _get_glyphs(device, scale=3): + key = (device, scale) + if key in SAM3_TrackPreview._glyph_cache: + return SAM3_TrackPreview._glyph_cache[key] + atlas = torch.tensor([ + [[1,1,1],[1,0,1],[1,0,1],[1,0,1],[1,1,1]], + [[0,1,0],[1,1,0],[0,1,0],[0,1,0],[1,1,1]], + [[1,1,1],[0,0,1],[1,1,1],[1,0,0],[1,1,1]], + [[1,1,1],[0,0,1],[1,1,1],[0,0,1],[1,1,1]], + [[1,0,1],[1,0,1],[1,1,1],[0,0,1],[0,0,1]], + [[1,1,1],[1,0,0],[1,1,1],[0,0,1],[1,1,1]], + [[1,1,1],[1,0,0],[1,1,1],[1,0,1],[1,1,1]], + [[1,1,1],[0,0,1],[0,0,1],[0,0,1],[0,0,1]], + [[1,1,1],[1,0,1],[1,1,1],[1,0,1],[1,1,1]], + [[1,1,1],[1,0,1],[1,1,1],[0,0,1],[1,1,1]], + ], dtype=torch.bool) + glyphs, outlines = [], [] + for d in range(10): + g = atlas[d].repeat_interleave(scale, 0).repeat_interleave(scale, 1) + padded = F.pad(g.float().unsqueeze(0).unsqueeze(0), (1,1,1,1)) + o = (F.max_pool2d(padded, 3, stride=1, padding=1)[0, 0] > 0) + glyphs.append(g.to(device)) + outlines.append(o.to(device)) + gh, gw = glyphs[0].shape + oh, ow = outlines[0].shape + SAM3_TrackPreview._glyph_cache[key] = (glyphs, outlines, gh, gw, oh, ow) + return SAM3_TrackPreview._glyph_cache[key] + + @staticmethod + def _draw_number_gpu(frame, number, cx, cy, color, scale=3): + """Draw a number on a GPU tensor [H, W, 3] float 0-1 at (cx, cy) with outline.""" + H, W = frame.shape[:2] + device = frame.device + glyphs, outlines, gh, gw, oh, ow = SAM3_TrackPreview._get_glyphs(device, scale) + color_t = torch.tensor(color, device=device, dtype=frame.dtype) + digs = [int(d) for d in str(number)] + total_w = len(digs) * (gw + scale) - scale + x0 = cx - total_w // 2 + y0 = cy - gh // 2 + for i, d in enumerate(digs): + dx = x0 + i * (gw + scale) + # Black outline + oy0, ox0 = y0 - 1, dx - 1 + osy1, osx1 = max(0, -oy0), max(0, -ox0) + osy2, osx2 = min(oh, H - oy0), min(ow, W - ox0) + if osy2 > osy1 and osx2 > osx1: + fy1, fx1 = oy0 + osy1, ox0 + osx1 + frame[fy1:fy1+(osy2-osy1), fx1:fx1+(osx2-osx1)][outlines[d][osy1:osy2, osx1:osx2]] = 0 + # Colored fill + sy1, sx1 = max(0, -y0), max(0, -dx) + sy2, sx2 = min(gh, H - y0), min(gw, W - dx) + if sy2 > sy1 and sx2 > sx1: + fy1, fx1 = y0 + sy1, dx + sx1 + frame[fy1:fy1+(sy2-sy1), fx1:fx1+(sx2-sx1)][glyphs[d][sy1:sy2, sx1:sx2]] = color_t + + @classmethod + def execute(cls, track_data, images=None, opacity=0.5, fps=24.0) -> io.NodeOutput: + + from comfy.ldm.sam3.tracker import unpack_masks + packed = track_data["packed_masks"] + H, W = track_data["orig_size"] + if images is not None: + H, W = images.shape[1], images.shape[2] + if packed is None: + N, N_obj = track_data["n_frames"], 0 + else: + N, N_obj = packed.shape[0], packed.shape[1] + + import uuid + gpu = comfy.model_management.get_torch_device() + temp_dir = folder_paths.get_temp_directory() + filename = f"sam3_track_preview_{uuid.uuid4().hex[:8]}.mp4" + filepath = os.path.join(temp_dir, filename) + with av.open(filepath, mode='w') as output: + stream = output.add_stream('h264', rate=Fraction(round(fps * 1000), 1000)) + stream.width = W + stream.height = H + stream.pix_fmt = 'yuv420p' + + frame_cpu = torch.empty(H, W, 3, dtype=torch.uint8) + frame_np = frame_cpu.numpy() + if N_obj > 0: + colors_t = torch.tensor([cls.COLORS[i % len(cls.COLORS)] for i in range(N_obj)], + device=gpu, dtype=torch.float32) + grid_y = torch.arange(H, device=gpu).view(1, H, 1) + grid_x = torch.arange(W, device=gpu).view(1, 1, W) + for t in range(N): + if images is not None and t < images.shape[0]: + frame = images[t].clone() + else: + frame = torch.zeros(H, W, 3) + + if N_obj > 0: + frame_binary = unpack_masks(packed[t:t+1].to(gpu)) # [1, N_obj, H, W] bool + frame_masks = F.interpolate(frame_binary.float(), size=(H, W), mode="nearest")[0] + frame_gpu = frame.to(gpu) + bool_masks = frame_masks > 0.5 + any_mask = bool_masks.any(dim=0) + if any_mask.any(): + obj_idx_map = bool_masks.to(torch.uint8).argmax(dim=0) + color_overlay = colors_t[obj_idx_map] + mask_3d = any_mask.unsqueeze(-1) + frame_gpu = torch.where(mask_3d, frame_gpu * (1 - opacity) + color_overlay * opacity, frame_gpu) + area = bool_masks.sum(dim=(-1, -2)).clamp_(min=1) + cy = (bool_masks * grid_y).sum(dim=(-1, -2)) // area + cx = (bool_masks * grid_x).sum(dim=(-1, -2)) // area + has = area > 1 + scores = track_data.get("scores", []) + for obj_idx in range(N_obj): + if has[obj_idx]: + _cx, _cy = int(cx[obj_idx]), int(cy[obj_idx]) + color = cls.COLORS[obj_idx % len(cls.COLORS)] + SAM3_TrackPreview._draw_number_gpu(frame_gpu, obj_idx, _cx, _cy, color) + if obj_idx < len(scores) and scores[obj_idx] < 1.0: + SAM3_TrackPreview._draw_number_gpu(frame_gpu, int(scores[obj_idx] * 100), + _cx, _cy + 5 * 3 + 3, color, scale=2) + frame_cpu.copy_(frame_gpu.clamp_(0, 1).mul_(255).byte()) + else: + frame_cpu.copy_(frame.clamp_(0, 1).mul_(255).byte()) + + vframe = av.VideoFrame.from_ndarray(frame_np, format='rgb24') + output.mux(stream.encode(vframe.reformat(format='yuv420p'))) + output.mux(stream.encode(None)) + return io.NodeOutput(ui=ui.PreviewVideo([ui.SavedResult(filename, "", io.FolderType.temp)])) + + +class SAM3_TrackToMask(io.ComfyNode): + """Select tracked objects by index and output as mask.""" + + @classmethod + def define_schema(cls): + return io.Schema( + node_id="SAM3_TrackToMask", + display_name="SAM3 Track to Mask", + category="detection/", + inputs=[ + SAM3TrackData.Input("track_data", display_name="track_data"), + io.String.Input("object_indices", display_name="object_indices", default="", + tooltip="Comma-separated object indices to include (e.g. '0,2,3'). Empty = all objects."), + ], + outputs=[ + io.Mask.Output("masks", display_name="masks"), + ], + ) + + @classmethod + def execute(cls, track_data, object_indices="") -> io.NodeOutput: + from comfy.ldm.sam3.tracker import unpack_masks + packed = track_data["packed_masks"] + H, W = track_data["orig_size"] + + if packed is None: + N = track_data["n_frames"] + return io.NodeOutput(torch.zeros(N, H, W, device=comfy.model_management.intermediate_device())) + + N, N_obj = packed.shape[0], packed.shape[1] + + if object_indices.strip(): + indices = [int(i.strip()) for i in object_indices.split(",") if i.strip().isdigit()] + indices = [i for i in indices if 0 <= i < N_obj] + else: + indices = list(range(N_obj)) + + if not indices: + return io.NodeOutput(torch.zeros(N, H, W, device=comfy.model_management.intermediate_device())) + + selected = packed[:, indices] + binary = unpack_masks(selected) # [N, len(indices), Hm, Wm] bool + union = binary.any(dim=1, keepdim=True).float() + mask_out = F.interpolate(union, size=(H, W), mode="bilinear", align_corners=False)[:, 0] + return io.NodeOutput(mask_out) + + +class SAM3Extension(ComfyExtension): + @override + async def get_node_list(self) -> list[type[io.ComfyNode]]: + return [ + SAM3_Detect, + SAM3_VideoTrack, + SAM3_TrackPreview, + SAM3_TrackToMask, + ] + + +async def comfy_entrypoint() -> SAM3Extension: + return SAM3Extension() diff --git a/comfy_extras/nodes_sd3.py b/comfy_extras/nodes_sd3.py index c43844a1a..6655c1ba7 100644 --- a/comfy_extras/nodes_sd3.py +++ b/comfy_extras/nodes_sd3.py @@ -54,7 +54,7 @@ class EmptySD3LatentImage(io.ComfyNode): @classmethod def execute(cls, width, height, batch_size=1) -> io.NodeOutput: - latent = torch.zeros([batch_size, 16, height // 8, width // 8], device=comfy.model_management.intermediate_device()) + latent = torch.zeros([batch_size, 16, height // 8, width // 8], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype()) return io.NodeOutput({"samples": latent, "downscale_ratio_spacial": 8}) generate = execute # TODO: remove diff --git a/comfy_extras/nodes_sdpose.py b/comfy_extras/nodes_sdpose.py index 46b5fb226..96b6821bd 100644 --- a/comfy_extras/nodes_sdpose.py +++ b/comfy_extras/nodes_sdpose.py @@ -1,5 +1,6 @@ import torch import comfy.utils +import comfy.model_management import numpy as np import math import colorsys @@ -410,7 +411,9 @@ class SDPoseDrawKeypoints(io.ComfyNode): pose_outputs.append(canvas) pose_outputs_np = np.stack(pose_outputs) if len(pose_outputs) > 1 else np.expand_dims(pose_outputs[0], 0) - final_pose_output = torch.from_numpy(pose_outputs_np).float() / 255.0 + final_pose_output = torch.from_numpy(pose_outputs_np).to( + device=comfy.model_management.intermediate_device(), + dtype=comfy.model_management.intermediate_dtype()) / 255.0 return io.NodeOutput(final_pose_output) class SDPoseKeypointExtractor(io.ComfyNode): @@ -456,8 +459,25 @@ class SDPoseKeypointExtractor(io.ComfyNode): total_images = image.shape[0] captured_feat = None - model_h = int(head.heatmap_size[0]) * 4 # e.g. 192 * 4 = 768 - model_w = int(head.heatmap_size[1]) * 4 # e.g. 256 * 4 = 1024 + model_w = int(head.heatmap_size[0]) * 4 # 192 * 4 = 768 + model_h = int(head.heatmap_size[1]) * 4 # 256 * 4 = 1024 + + def _resize_to_model(imgs): + """Stretch BHWC images to (model_h, model_w), model expects no aspect preservation.""" + h, w = imgs.shape[-3], imgs.shape[-2] + method = "area" if (model_h <= h and model_w <= w) else "bilinear" + chw = imgs.permute(0, 3, 1, 2).float() + scaled = comfy.utils.common_upscale(chw, model_w, model_h, upscale_method=method, crop="disabled") + return scaled.permute(0, 2, 3, 1), model_w / w, model_h / h + + def _remap_keypoints(kp, scale_x, scale_y, offset_x=0, offset_y=0): + """Remap keypoints from model space back to original image space.""" + kp = kp.copy() if isinstance(kp, np.ndarray) else np.array(kp, dtype=np.float32) + invalid = kp[..., 0] < 0 + kp[..., 0] = kp[..., 0] / scale_x + offset_x + kp[..., 1] = kp[..., 1] / scale_y + offset_y + kp[invalid] = -1 + return kp def _run_on_latent(latent_batch): """Run one forward pass and return (keypoints_list, scores_list) for the batch.""" @@ -504,36 +524,19 @@ class SDPoseKeypointExtractor(io.ComfyNode): if x2 <= x1 or y2 <= y1: continue - crop_h_px, crop_w_px = y2 - y1, x2 - x1 crop = img[:, y1:y2, x1:x2, :] # (1, crop_h, crop_w, C) - - # scale to fit inside (model_h, model_w) while preserving aspect ratio, then pad to exact model size. - scale = min(model_h / crop_h_px, model_w / crop_w_px) - scaled_h, scaled_w = int(round(crop_h_px * scale)), int(round(crop_w_px * scale)) - pad_top, pad_left = (model_h - scaled_h) // 2, (model_w - scaled_w) // 2 - - crop_chw = crop.permute(0, 3, 1, 2).float() # BHWC → BCHW - scaled = comfy.utils.common_upscale(crop_chw, scaled_w, scaled_h, upscale_method="bilinear", crop="disabled") - padded = torch.zeros(1, scaled.shape[1], model_h, model_w, dtype=scaled.dtype, device=scaled.device) - padded[:, :, pad_top:pad_top + scaled_h, pad_left:pad_left + scaled_w] = scaled - crop_resized = padded.permute(0, 2, 3, 1) # BCHW → BHWC + crop_resized, sx, sy = _resize_to_model(crop) latent_crop = vae.encode(crop_resized) kp_batch, sc_batch = _run_on_latent(latent_crop) - kp, sc = kp_batch[0], sc_batch[0] # (K, 2), coords in model pixel space - - # remove padding offset, undo scale, offset to full-image coordinates. - kp = kp.copy() if isinstance(kp, np.ndarray) else np.array(kp, dtype=np.float32) - kp[..., 0] = (kp[..., 0] - pad_left) / scale + x1 - kp[..., 1] = (kp[..., 1] - pad_top) / scale + y1 - + kp = _remap_keypoints(kp_batch[0], sx, sy, x1, y1) img_keypoints.append(kp) - img_scores.append(sc) + img_scores.append(sc_batch[0]) else: - # No bboxes for this image – run on the full image - latent_img = vae.encode(img) + img_resized, sx, sy = _resize_to_model(img) + latent_img = vae.encode(img_resized) kp_batch, sc_batch = _run_on_latent(latent_img) - img_keypoints.append(kp_batch[0]) + img_keypoints.append(_remap_keypoints(kp_batch[0], sx, sy)) img_scores.append(sc_batch[0]) all_keypoints.append(img_keypoints) @@ -541,19 +544,16 @@ class SDPoseKeypointExtractor(io.ComfyNode): pbar.update(1) else: # full-image mode, batched - tqdm_pbar = tqdm(total=total_images, desc="Extracting keypoints") - for batch_start in range(0, total_images, batch_size): - batch_end = min(batch_start + batch_size, total_images) - latent_batch = vae.encode(image[batch_start:batch_end]) - + for batch_start in tqdm(range(0, total_images, batch_size), desc="Extracting keypoints"): + batch_resized, sx, sy = _resize_to_model(image[batch_start:batch_start + batch_size]) + latent_batch = vae.encode(batch_resized) kp_batch, sc_batch = _run_on_latent(latent_batch) for kp, sc in zip(kp_batch, sc_batch): - all_keypoints.append([kp]) + all_keypoints.append([_remap_keypoints(kp, sx, sy)]) all_scores.append([sc]) - tqdm_pbar.update(1) - pbar.update(batch_end - batch_start) + pbar.update(len(kp_batch)) openpose_frames = _to_openpose_frames(all_keypoints, all_scores, height, width) return io.NodeOutput(openpose_frames) @@ -723,13 +723,13 @@ class CropByBBoxes(io.ComfyNode): scale = min(output_width / crop_w, output_height / crop_h) scaled_w = int(round(crop_w * scale)) scaled_h = int(round(crop_h * scale)) - scaled = comfy.utils.common_upscale(crop_chw, scaled_w, scaled_h, upscale_method="bilinear", crop="disabled") + scaled = comfy.utils.common_upscale(crop_chw, scaled_w, scaled_h, upscale_method="area", crop="disabled") pad_left = (output_width - scaled_w) // 2 pad_top = (output_height - scaled_h) // 2 resized = torch.zeros(1, num_ch, output_height, output_width, dtype=image.dtype, device=image.device) resized[:, :, pad_top:pad_top + scaled_h, pad_left:pad_left + scaled_w] = scaled else: # "stretch" - resized = comfy.utils.common_upscale(crop_chw, output_width, output_height, upscale_method="bilinear", crop="disabled") + resized = comfy.utils.common_upscale(crop_chw, output_width, output_height, upscale_method="area", crop="disabled") crops.append(resized) if not crops: diff --git a/comfy_extras/nodes_string.py b/comfy_extras/nodes_string.py index b4e5f148a..604076c4e 100644 --- a/comfy_extras/nodes_string.py +++ b/comfy_extras/nodes_string.py @@ -1,4 +1,5 @@ import re +import json from typing_extensions import override from comfy_api.latest import ComfyExtension, io @@ -9,9 +10,9 @@ class StringConcatenate(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="StringConcatenate", - display_name="Concatenate", + display_name="Text Concatenate", category="utils/string", - search_aliases=["text concat", "join text", "merge text", "combine strings", "concat", "concatenate", "append text", "combine text", "string"], + search_aliases=["Concatenate", "text concat", "join text", "merge text", "combine strings", "concat", "concatenate", "append text", "combine text", "string"], inputs=[ io.String.Input("string_a", multiline=True), io.String.Input("string_b", multiline=True), @@ -32,8 +33,8 @@ class StringSubstring(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="StringSubstring", - search_aliases=["extract text", "text portion"], - display_name="Substring", + search_aliases=["Substring", "extract text", "text portion"], + display_name="Text Substring", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -55,8 +56,8 @@ class StringLength(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="StringLength", - search_aliases=["character count", "text size"], - display_name="Length", + search_aliases=["character count", "text size", "string length"], + display_name="Text Length", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -76,8 +77,8 @@ class CaseConverter(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="CaseConverter", - search_aliases=["text case", "uppercase", "lowercase", "capitalize"], - display_name="Case Converter", + search_aliases=["Case Converter", "text case", "uppercase", "lowercase", "capitalize"], + display_name="Text Case Converter", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -109,8 +110,8 @@ class StringTrim(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="StringTrim", - search_aliases=["clean whitespace", "remove whitespace"], - display_name="Trim", + search_aliases=["Trim", "clean whitespace", "remove whitespace", "strip"], + display_name="Text Trim", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -140,8 +141,8 @@ class StringReplace(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="StringReplace", - search_aliases=["find and replace", "substitute", "swap text"], - display_name="Replace", + search_aliases=["Replace", "find and replace", "substitute", "swap text"], + display_name="Text Replace", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -163,8 +164,8 @@ class StringContains(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="StringContains", - search_aliases=["text includes", "string includes"], - display_name="Contains", + search_aliases=["Contains", "text includes", "string includes"], + display_name="Text Contains", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -191,8 +192,8 @@ class StringCompare(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="StringCompare", - search_aliases=["text match", "string equals", "starts with", "ends with"], - display_name="Compare", + search_aliases=["Compare", "text match", "string equals", "starts with", "ends with"], + display_name="Text Compare", category="utils/string", inputs=[ io.String.Input("string_a", multiline=True), @@ -227,8 +228,8 @@ class RegexMatch(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="RegexMatch", - search_aliases=["pattern match", "text contains", "string match"], - display_name="Regex Match", + search_aliases=["Regex Match", "regex", "pattern match", "text contains", "string match"], + display_name="Text Match", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -268,8 +269,8 @@ class RegexExtract(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="RegexExtract", - search_aliases=["pattern extract", "text parser", "parse text"], - display_name="Regex Extract", + search_aliases=["Regex Extract", "regex", "pattern extract", "text parser", "parse text"], + display_name="Text Extract Substring", category="utils/string", inputs=[ io.String.Input("string", multiline=True), @@ -343,8 +344,8 @@ class RegexReplace(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="RegexReplace", - search_aliases=["pattern replace", "find and replace", "substitution"], - display_name="Regex Replace", + search_aliases=["Regex Replace", "regex", "pattern replace", "regex replace", "substitution"], + display_name="Text Replace (Regex)", category="utils/string", description="Find and replace text using regex patterns.", inputs=[ @@ -375,6 +376,39 @@ class RegexReplace(io.ComfyNode): return io.NodeOutput(result) +class JsonExtractString(io.ComfyNode): + @classmethod + def define_schema(cls): + return io.Schema( + node_id="JsonExtractString", + display_name="Extract String from JSON", + category="utils/string", + search_aliases=["json", "extract json", "parse json", "json value", "read json"], + inputs=[ + io.String.Input("json_string", multiline=True), + io.String.Input("key", multiline=False), + ], + outputs=[ + io.String.Output(), + ] + ) + + @classmethod + def execute(cls, json_string, key): + try: + data = json.loads(json_string) + if isinstance(data, dict) and key in data: + value = data[key] + if value is None: + return io.NodeOutput("") + + return io.NodeOutput(str(value)) + + return io.NodeOutput("") + + except (json.JSONDecodeError, TypeError): + return io.NodeOutput("") + class StringExtension(ComfyExtension): @override async def get_node_list(self) -> list[type[io.ComfyNode]]: @@ -390,6 +424,7 @@ class StringExtension(ComfyExtension): RegexMatch, RegexExtract, RegexReplace, + JsonExtractString, ] async def comfy_entrypoint() -> StringExtension: diff --git a/comfy_extras/nodes_textgen.py b/comfy_extras/nodes_textgen.py index f1aeb63fa..1661a1011 100644 --- a/comfy_extras/nodes_textgen.py +++ b/comfy_extras/nodes_textgen.py @@ -32,9 +32,12 @@ class TextGenerate(io.ComfyNode): io.Clip.Input("clip"), io.String.Input("prompt", multiline=True, dynamic_prompts=True, default=""), io.Image.Input("image", optional=True), + io.Image.Input("video", optional=True, tooltip="Video frames as image batch. Assumed to be 24 FPS; subsampled to 1 FPS internally."), + io.Audio.Input("audio", optional=True), io.Int.Input("max_length", default=256, min=1, max=2048), io.DynamicCombo.Input("sampling_mode", options=sampling_options, display_name="Sampling Mode"), io.Boolean.Input("thinking", optional=True, default=False, tooltip="Operate in thinking mode if the model supports it."), + io.Boolean.Input("use_default_template", optional=True, default=True, tooltip="Use the built in system prompt/template if the model has one.", advanced=True), ], outputs=[ io.String.Output(display_name="generated_text"), @@ -42,9 +45,9 @@ class TextGenerate(io.ComfyNode): ) @classmethod - def execute(cls, clip, prompt, max_length, sampling_mode, image=None, thinking=False) -> io.NodeOutput: + def execute(cls, clip, prompt, max_length, sampling_mode, image=None, thinking=False, use_default_template=True, video=None, audio=None) -> io.NodeOutput: - tokens = clip.tokenize(prompt, image=image, skip_template=False, min_length=1, thinking=thinking) + tokens = clip.tokenize(prompt, image=image, skip_template=not use_default_template, min_length=1, thinking=thinking, video=video, audio=audio) # Get sampling parameters from dynamic combo do_sample = sampling_mode.get("sampling_mode") == "on" @@ -69,7 +72,8 @@ class TextGenerate(io.ComfyNode): seed=seed ) - generated_text = clip.decode(generated_ids, skip_special_tokens=True) + generated_text = clip.decode(generated_ids) + return io.NodeOutput(generated_text) @@ -160,12 +164,12 @@ class TextGenerateLTX2Prompt(TextGenerate): ) @classmethod - def execute(cls, clip, prompt, max_length, sampling_mode, image=None, thinking=False) -> io.NodeOutput: + def execute(cls, clip, prompt, max_length, sampling_mode, image=None, thinking=False, use_default_template=True, video=None, audio=None) -> io.NodeOutput: if image is None: formatted_prompt = f"system\n{LTX2_T2V_SYSTEM_PROMPT.strip()}\nuser\nUser Raw Input Prompt: {prompt}.\nmodel\n" else: formatted_prompt = f"system\n{LTX2_I2V_SYSTEM_PROMPT.strip()}\nuser\n\n\n\nUser Raw Input Prompt: {prompt}.\nmodel\n" - return super().execute(clip, formatted_prompt, max_length, sampling_mode, image, thinking) + return super().execute(clip, formatted_prompt, max_length, sampling_mode, image=image, thinking=thinking, use_default_template=use_default_template, video=video, audio=audio) class TextgenExtension(ComfyExtension): diff --git a/comfy_extras/nodes_upscale_model.py b/comfy_extras/nodes_upscale_model.py index db4f9d231..d3ee3f1c1 100644 --- a/comfy_extras/nodes_upscale_model.py +++ b/comfy_extras/nodes_upscale_model.py @@ -6,6 +6,7 @@ import comfy.utils import folder_paths from typing_extensions import override from comfy_api.latest import ComfyExtension, io +import comfy.model_management try: from spandrel_extra_arches import EXTRA_REGISTRY @@ -78,13 +79,15 @@ class ImageUpscaleWithModel(io.ComfyNode): tile = 512 overlap = 32 + output_device = comfy.model_management.intermediate_device() + oom = True try: while oom: try: steps = in_img.shape[0] * comfy.utils.get_tiled_scale_steps(in_img.shape[3], in_img.shape[2], tile_x=tile, tile_y=tile, overlap=overlap) pbar = comfy.utils.ProgressBar(steps) - s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar) + s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a.float()), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar, output_device=output_device) oom = False except Exception as e: model_management.raise_non_oom(e) @@ -94,7 +97,7 @@ class ImageUpscaleWithModel(io.ComfyNode): finally: upscale_model.to("cpu") - s = torch.clamp(s.movedim(-3,-1), min=0, max=1.0) + s = torch.clamp(s.movedim(-3,-1), min=0, max=1.0).to(comfy.model_management.intermediate_dtype()) return io.NodeOutput(s) upscale = execute # TODO: remove diff --git a/comfyui_version.py b/comfyui_version.py index 61d7672ca..53e7156e3 100644 --- a/comfyui_version.py +++ b/comfyui_version.py @@ -1,3 +1,3 @@ # This file is automatically generated by the build process when version is # updated in pyproject.toml. -__version__ = "0.18.1" +__version__ = "0.20.1" diff --git a/execution.py b/execution.py index 5e02dffb2..654db8426 100644 --- a/execution.py +++ b/execution.py @@ -15,6 +15,7 @@ import torch from comfy.cli_args import args import comfy.memory_management import comfy.model_management +import comfy.model_prefetch import comfy_aimdo.model_vbar from latent_preview import set_preview_method @@ -537,6 +538,7 @@ async def execute(server, dynprompt, caches, current_item, extra_data, executed, if args.verbose == "DEBUG": comfy_aimdo.control.analyze() comfy.model_management.reset_cast_buffers() + comfy.model_prefetch.cleanup_prefetch_queues() comfy_aimdo.model_vbar.vbars_reset_watermark_limits() if has_pending_tasks: @@ -779,7 +781,7 @@ class PromptExecutor: if self.cache_type == CacheType.RAM_PRESSURE: comfy.model_management.free_memory(0, None, pins_required=ram_headroom, ram_required=ram_headroom) - comfy.memory_management.extra_ram_release(ram_headroom) + ram_release_callback(ram_headroom, free_active=True) else: # Only execute when the while-loop ends without break # Send cached UI for intermediate output nodes that weren't executed @@ -811,11 +813,30 @@ class PromptExecutor: self._notify_prompt_lifecycle("end", prompt_id) -async def validate_inputs(prompt_id, prompt, item, validated): +async def validate_inputs(prompt_id, prompt, item, validated, visiting=None): + if visiting is None: + visiting = [] + unique_id = item if unique_id in validated: return validated[unique_id] + if unique_id in visiting: + cycle_path_nodes = visiting[visiting.index(unique_id):] + [unique_id] + cycle_nodes = list(dict.fromkeys(cycle_path_nodes)) + cycle_path = " -> ".join(f"{node_id} ({prompt[node_id]['class_type']})" for node_id in cycle_path_nodes) + for node_id in cycle_nodes: + validated[node_id] = (False, [{ + "type": "dependency_cycle", + "message": "Dependency cycle detected", + "details": cycle_path, + "extra_info": { + "node_id": node_id, + "cycle_nodes": cycle_nodes, + } + }], node_id) + return validated[unique_id] + inputs = prompt[unique_id]['inputs'] class_type = prompt[unique_id]['class_type'] obj_class = nodes.NODE_CLASS_MAPPINGS[class_type] @@ -899,7 +920,11 @@ async def validate_inputs(prompt_id, prompt, item, validated): errors.append(error) continue try: - r = await validate_inputs(prompt_id, prompt, o_id, validated) + visiting.append(unique_id) + try: + r = await validate_inputs(prompt_id, prompt, o_id, validated, visiting) + finally: + visiting.pop() if r[0] is False: # `r` will be set in `validated[o_id]` already valid = False @@ -1048,10 +1073,13 @@ async def validate_inputs(prompt_id, prompt, item, validated): errors.append(error) continue - if len(errors) > 0 or valid is not True: - ret = (False, errors, unique_id) - else: - ret = (True, [], unique_id) + ret = validated.get(unique_id, (True, [], unique_id)) + # Recursive cycle detection may have already populated an error on us. Join it. + ret = ( + ret[0] and valid is True and not errors, + ret[1] + [error for error in errors if error not in ret[1]], + unique_id, + ) validated[unique_id] = ret return ret diff --git a/folder_paths.py b/folder_paths.py index 9c96540e3..80f4b291a 100644 --- a/folder_paths.py +++ b/folder_paths.py @@ -52,6 +52,8 @@ folder_names_and_paths["model_patches"] = ([os.path.join(models_dir, "model_patc folder_names_and_paths["audio_encoders"] = ([os.path.join(models_dir, "audio_encoders")], supported_pt_extensions) +folder_names_and_paths["frame_interpolation"] = ([os.path.join(models_dir, "frame_interpolation")], supported_pt_extensions) + output_directory = os.path.join(base_path, "output") temp_directory = os.path.join(base_path, "temp") input_directory = os.path.join(base_path, "input") diff --git a/main.py b/main.py index 12b04719d..dbaf2745c 100644 --- a/main.py +++ b/main.py @@ -9,6 +9,8 @@ import folder_paths import time from comfy.cli_args import args, enables_dynamic_vram from app.logger import setup_logger +setup_logger(log_level=args.verbose, use_stdout=args.log_stdout) + from app.assets.seeder import asset_seeder from app.assets.services import register_output_files import itertools @@ -27,8 +29,6 @@ if __name__ == "__main__": os.environ['HF_HUB_DISABLE_TELEMETRY'] = '1' os.environ['DO_NOT_TRACK'] = '1' -setup_logger(log_level=args.verbose, use_stdout=args.log_stdout) - faulthandler.enable(file=sys.stderr, all_threads=False) import comfy_aimdo.control diff --git a/manager_requirements.txt b/manager_requirements.txt index f770ec933..a079d3492 100644 --- a/manager_requirements.txt +++ b/manager_requirements.txt @@ -1 +1 @@ -comfyui_manager==4.1 +comfyui_manager==4.2.1 diff --git a/models/frame_interpolation/put_frame_interpolation_models_here b/models/frame_interpolation/put_frame_interpolation_models_here new file mode 100644 index 000000000..e69de29bb diff --git a/node_helpers.py b/node_helpers.py index d3d834516..cac4e88dd 100644 --- a/node_helpers.py +++ b/node_helpers.py @@ -86,6 +86,6 @@ def image_alpha_fix(destination, source): if destination.shape[-1] < source.shape[-1]: source = source[...,:destination.shape[-1]] elif destination.shape[-1] > source.shape[-1]: - destination = torch.nn.functional.pad(destination, (0, 1)) - destination[..., -1] = 1.0 + source = torch.nn.functional.pad(source, (0, 1)) + source[..., -1] = 1.0 return destination, source diff --git a/nodes.py b/nodes.py index 299b3d758..710cccffe 100644 --- a/nodes.py +++ b/nodes.py @@ -32,7 +32,7 @@ import comfy.controlnet from comfy.comfy_types import IO, ComfyNodeABC, InputTypeDict, FileLocator from comfy_api.internal import register_versions, ComfyAPIWithVersion from comfy_api.version_list import supported_versions -from comfy_api.latest import io, ComfyExtension +from comfy_api.latest import io, ComfyExtension, InputImpl import comfy.clip_vision @@ -728,50 +728,26 @@ class LoraLoaderModelOnly(LoraLoader): class VAELoader: video_taes = ["taehv", "lighttaew2_2", "lighttaew2_1", "lighttaehy1_5", "taeltx_2"] - image_taes = ["taesd", "taesdxl", "taesd3", "taef1"] + image_taes = ["taesd", "taesdxl", "taesd3", "taef1", "taef2"] + @staticmethod def vae_list(s): vaes = folder_paths.get_filename_list("vae") approx_vaes = folder_paths.get_filename_list("vae_approx") - sdxl_taesd_enc = False - sdxl_taesd_dec = False - sd1_taesd_enc = False - sd1_taesd_dec = False - sd3_taesd_enc = False - sd3_taesd_dec = False - f1_taesd_enc = False - f1_taesd_dec = False - + have_img_encoder, have_img_decoder = set(), set() for v in approx_vaes: - if v.startswith("taesd_decoder."): - sd1_taesd_dec = True - elif v.startswith("taesd_encoder."): - sd1_taesd_enc = True - elif v.startswith("taesdxl_decoder."): - sdxl_taesd_dec = True - elif v.startswith("taesdxl_encoder."): - sdxl_taesd_enc = True - elif v.startswith("taesd3_decoder."): - sd3_taesd_dec = True - elif v.startswith("taesd3_encoder."): - sd3_taesd_enc = True - elif v.startswith("taef1_encoder."): - f1_taesd_dec = True - elif v.startswith("taef1_decoder."): - f1_taesd_enc = True - else: + parts = v.split("_", 1) + if len(parts) != 2 or parts[0] not in s.image_taes: for tae in s.video_taes: if v.startswith(tae): vaes.append(v) - - if sd1_taesd_dec and sd1_taesd_enc: - vaes.append("taesd") - if sdxl_taesd_dec and sdxl_taesd_enc: - vaes.append("taesdxl") - if sd3_taesd_dec and sd3_taesd_enc: - vaes.append("taesd3") - if f1_taesd_dec and f1_taesd_enc: - vaes.append("taef1") + break + continue + if parts[1].startswith("encoder."): + have_img_encoder.add(parts[0]) + elif parts[1].startswith("decoder."): + have_img_decoder.add(parts[0]) + vaes += [k for k in have_img_decoder if k in have_img_encoder] vaes.append("pixel_space") return vaes @@ -827,6 +803,11 @@ class VAELoader: else: vae_path = folder_paths.get_full_path_or_raise("vae", vae_name) sd, metadata = comfy.utils.load_torch_file(vae_path, return_metadata=True) + if vae_name == "taef2": + if metadata is None: + metadata = {"tae_latent_channels": 128} + else: + metadata["tae_latent_channels"] = 128 vae = comfy.sd.VAE(sd=sd, metadata=metadata) vae.throw_exception_if_invalid() return (vae,) @@ -1713,22 +1694,27 @@ class LoadImage: RETURN_TYPES = ("IMAGE", "MASK") FUNCTION = "load_image" + def load_image(self, image): image_path = folder_paths.get_annotated_filepath(image) + dtype = comfy.model_management.intermediate_dtype() + device = comfy.model_management.intermediate_device() + + components = InputImpl.VideoFromFile(image_path).get_components() + if components.images.shape[0] > 0: + return (components.images.to(device=device, dtype=dtype), (1.0 - components.alpha[..., -1]).to(device=device, dtype=dtype) if components.alpha is not None else torch.zeros((components.images.shape[0], 64, 64), dtype=dtype, device=device)) + + # This code is left here to handle animated webp which pyav does not support loading img = node_helpers.pillow(Image.open, image_path) output_images = [] output_masks = [] w, h = None, None - dtype = comfy.model_management.intermediate_dtype() - for i in ImageSequence.Iterator(img): i = node_helpers.pillow(ImageOps.exif_transpose, i) - if i.mode == 'I': - i = i.point(lambda i: i * (1 / 255)) image = i.convert("RGB") if len(output_images) == 0: @@ -1743,25 +1729,15 @@ class LoadImage: if 'A' in i.getbands(): mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0 mask = 1. - torch.from_numpy(mask) - elif i.mode == 'P' and 'transparency' in i.info: - mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0 - mask = 1. - torch.from_numpy(mask) else: - mask = torch.zeros((64,64), dtype=torch.float32, device="cpu") + mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu") output_images.append(image.to(dtype=dtype)) output_masks.append(mask.unsqueeze(0).to(dtype=dtype)) - if img.format == "MPO": - break # ignore all frames except the first one for MPO format + output_image = torch.cat(output_images, dim=0) + output_mask = torch.cat(output_masks, dim=0) - if len(output_images) > 1: - output_image = torch.cat(output_images, dim=0) - output_mask = torch.cat(output_masks, dim=0) - else: - output_image = output_images[0] - output_mask = output_masks[0] - - return (output_image, output_mask) + return (output_image.to(device=device, dtype=dtype), output_mask.to(device=device, dtype=dtype)) @classmethod def IS_CHANGED(s, image): @@ -2457,7 +2433,9 @@ async def init_builtin_extra_nodes(): "nodes_number_convert.py", "nodes_painter.py", "nodes_curve.py", - "nodes_rtdetr.py" + "nodes_rtdetr.py", + "nodes_frame_interpolation.py", + "nodes_sam3.py", ] import_failed = [] diff --git a/openapi.yaml b/openapi.yaml new file mode 100644 index 000000000..77d0e2318 --- /dev/null +++ b/openapi.yaml @@ -0,0 +1,3231 @@ +openapi: 3.1.0 +info: + title: ComfyUI API + description: | + API for ComfyUI - A powerful and modular stable diffusion GUI and backend. + + This API allows you to interact with ComfyUI programmatically, including: + - Submitting and managing workflow executions + - Querying node/object information + - Uploading and viewing files + - Managing user settings and data + - Asset management (feature-gated) + + ## Dual-path routing + Every route registered via `self.routes` in the ComfyUI server is available at + both its bare path (e.g. `/prompt`) and an `/api`-prefixed path (e.g. `/api/prompt`). + This spec uses the `/api`-prefixed versions as canonical. + + ## Multi-user mode + When ComfyUI is started with `--multi-user`, the `Comfy-User` header identifies + the active user for settings, userdata, and history isolation. This is **not** a + security mechanism — it is an organisational convenience with no authentication + or authorisation behind it. + version: 1.0.0 + license: + name: GNU General Public License v3.0 + url: https://github.com/comfyanonymous/ComfyUI/blob/master/LICENSE + +servers: + - url: / + description: Default ComfyUI server (typically http://127.0.0.1:8188) + +tags: + - name: prompt + description: Workflow submission and prompt info + - name: queue + description: Queue inspection and management + - name: history + description: Execution history + - name: upload + description: File upload endpoints + - name: view + description: File viewing / download + - name: system + description: System stats and feature flags + - name: node + description: Node / object_info definitions + - name: model + description: Model folder and file listing + - name: user + description: User management (multi-user mode) + - name: userdata + description: Per-user file storage + - name: settings + description: Per-user settings + - name: extensions + description: Frontend extension JS files + - name: subgraph + description: Global subgraph blueprints + - name: internal + description: Internal / debug endpoints + - name: assets + description: Asset management (feature-gated behind enable-assets) + +paths: + # --------------------------------------------------------------------------- + # WebSocket + # --------------------------------------------------------------------------- + /ws: + get: + operationId: connectWebSocket + tags: [system] + summary: WebSocket connection for real-time updates + description: | + Upgrades to a WebSocket connection that streams execution progress, + node status, and output messages. The server sends an initial `status` + message with the session ID (SID) on connect. + + ## Message types (server → client) + The server sends JSON messages with a `type` field. See the + `x-websocket-messages` list below for the schema of each message type. + parameters: + - name: clientId + in: query + required: false + schema: + type: string + description: Client identifier. If omitted the server assigns one. + responses: + "101": + description: WebSocket upgrade successful + x-websocket-messages: + - type: status + schema: + $ref: "#/components/schemas/StatusWsMessage" + - type: progress + schema: + $ref: "#/components/schemas/ProgressWsMessage" + - type: progress_text + schema: + $ref: "#/components/schemas/ProgressTextWsMessage" + - type: progress_state + schema: + $ref: "#/components/schemas/ProgressStateWsMessage" + - type: executing + schema: + $ref: "#/components/schemas/ExecutingWsMessage" + - type: executed + schema: + $ref: "#/components/schemas/ExecutedWsMessage" + - type: execution_start + schema: + $ref: "#/components/schemas/ExecutionStartWsMessage" + - type: execution_success + schema: + $ref: "#/components/schemas/ExecutionSuccessWsMessage" + - type: execution_cached + schema: + $ref: "#/components/schemas/ExecutionCachedWsMessage" + - type: execution_interrupted + schema: + $ref: "#/components/schemas/ExecutionInterruptedWsMessage" + - type: execution_error + schema: + $ref: "#/components/schemas/ExecutionErrorWsMessage" + - type: logs + schema: + $ref: "#/components/schemas/LogsWsMessage" + - type: notification + schema: + $ref: "#/components/schemas/NotificationWsMessage" + - type: feature_flags + schema: + $ref: "#/components/schemas/FeatureFlagsWsMessage" + - type: asset_download + schema: + $ref: "#/components/schemas/AssetDownloadWsMessage" + - type: asset_export + schema: + $ref: "#/components/schemas/AssetExportWsMessage" + + # --------------------------------------------------------------------------- + # Prompt + # --------------------------------------------------------------------------- + /api/prompt: + get: + operationId: getPromptInfo + tags: [prompt] + summary: Get queue status + description: Returns how many items remain in the execution queue. + responses: + "200": + description: Queue info + content: + application/json: + schema: + $ref: "#/components/schemas/PromptInfo" + post: + operationId: executePrompt + tags: [prompt] + summary: Submit a workflow for execution + description: Submits a workflow for execution. The server validates the graph, assigns a `prompt_id`, and enqueues it. Clients listen on `/ws` for execution progress and output messages. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/PromptRequest" + responses: + "200": + description: Prompt accepted + content: + application/json: + schema: + $ref: "#/components/schemas/PromptResponse" + "400": + description: Validation or node errors + content: + application/json: + schema: + $ref: "#/components/schemas/PromptErrorResponse" + + # --------------------------------------------------------------------------- + # Queue + # --------------------------------------------------------------------------- + /api/queue: + get: + operationId: getQueue + tags: [queue] + summary: Get running and pending queue items + description: Returns the server's current execution queue, split into the currently-running prompt and the list of pending prompts. + responses: + "200": + description: Queue contents + content: + application/json: + schema: + $ref: "#/components/schemas/QueueInfo" + post: + operationId: manageQueue + tags: [queue] + summary: Clear or delete items from the queue + description: Mutates the execution queue. Supports clearing all queued prompts or deleting individual prompts by ID. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/QueueManageRequest" + responses: + "200": + description: Queue updated + + /api/interrupt: + post: + operationId: interruptExecution + tags: [queue] + summary: Interrupt current execution + description: Interrupts the prompt that is currently executing. The next queued prompt (if any) will start immediately after. + requestBody: + required: false + content: + application/json: + schema: + type: object + properties: + prompt_id: + type: string + format: uuid + description: "If provided, only interrupts this specific running prompt. Otherwise interrupts all." + responses: + "200": + description: Interrupt signal sent + + /api/free: + post: + operationId: freeMemory + tags: [queue] + summary: Free GPU memory and/or unload models + description: Frees GPU memory by unloading models and/or freeing the resident model cache, controlled by the request flags. + requestBody: + required: false + content: + application/json: + schema: + type: object + properties: + unload_models: + type: boolean + description: Unload all models from VRAM/RAM + free_memory: + type: boolean + description: Run garbage collection and free cached memory + responses: + "200": + description: Memory freed + + # --------------------------------------------------------------------------- + # Jobs + # --------------------------------------------------------------------------- + /api/jobs: + get: + operationId: listJobs + tags: [queue] + summary: List jobs with filtering and pagination + description: Returns a paginated list of completed prompt executions, newest first. + parameters: + - name: status + in: query + schema: + type: string + description: Filter by job status + - name: workflow_id + in: query + schema: + type: string + description: Filter by workflow ID + - name: sort_by + in: query + schema: + type: string + description: Field to sort by + - name: sort_order + in: query + schema: + type: string + enum: [asc, desc] + description: Sort direction + - name: limit + in: query + schema: + type: integer + description: Maximum number of results (default is unlimited/None) + - name: offset + in: query + schema: + type: integer + default: 0 + description: Pagination offset + responses: + "200": + description: Jobs list + content: + application/json: + schema: + type: object + properties: + jobs: + type: array + items: + $ref: "#/components/schemas/JobEntry" + pagination: + $ref: "#/components/schemas/PaginationInfo" + + /api/jobs/{job_id}: + get: + operationId: getJob + tags: [queue] + summary: Get a single job by ID + description: Returns the full record for a single completed prompt execution, including its outputs, status, and metadata. + parameters: + - name: job_id + in: path + description: The job (prompt) ID to fetch. + required: true + schema: + type: string + format: uuid + responses: + "200": + description: Job detail + content: + application/json: + schema: + $ref: "#/components/schemas/JobDetailResponse" + "404": + description: Job not found + + # --------------------------------------------------------------------------- + # History + # --------------------------------------------------------------------------- + /api/history: + get: + operationId: getHistory + tags: [history] + summary: Get execution history + deprecated: true + description: | + **Deprecated.** Superseded by `GET /api/jobs`, which returns the same + execution records in a paginated, filterable format. Planned for removal + no earlier than a future major release; sunset timeline TBD. + + Returns a dictionary keyed by prompt_id. Each value is a HistoryEntry + containing prompt metadata, outputs, status, and node meta. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: max_items + in: query + schema: + type: integer + description: Maximum number of history entries to return + - name: offset + in: query + schema: + type: integer + description: Pagination offset (number of entries to skip) + responses: + "200": + description: History dictionary keyed by prompt_id + content: + application/json: + schema: + type: object + additionalProperties: + $ref: "#/components/schemas/HistoryEntry" + post: + operationId: manageHistory + tags: [history] + summary: Clear or delete history entries + deprecated: true + description: | + **Deprecated.** Superseded by the forthcoming job-management endpoints + under `/api/jobs`. Planned for removal no earlier than a future major + release; sunset timeline TBD. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/HistoryManageRequest" + responses: + "200": + description: History updated + + /api/history/{prompt_id}: + get: + operationId: getHistoryByPromptId + tags: [history] + summary: Get history for a specific prompt + deprecated: true + description: | + **Deprecated.** Superseded by `GET /api/jobs/{job_id}`, which returns + the same execution record. Planned for removal no earlier than a future + major release; sunset timeline TBD. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: prompt_id + in: path + description: The prompt ID to fetch history for. + required: true + schema: + type: string + format: uuid + responses: + "200": + description: Single-entry history dictionary. Returns an empty object `{}` if the prompt_id is not found. + content: + application/json: + schema: + type: object + additionalProperties: + $ref: "#/components/schemas/HistoryEntry" + + # --------------------------------------------------------------------------- + # Upload + # --------------------------------------------------------------------------- + /api/upload/image: + post: + operationId: uploadImage + tags: [upload] + summary: Upload an image file + description: Uploads an image file into one of the input/output/temp directories so it can be referenced by workflow nodes. + requestBody: + required: true + content: + multipart/form-data: + schema: + type: object + required: + - image + properties: + image: + type: string + format: binary + description: Image file to upload + type: + type: string + enum: [input, temp, output] + default: input + description: Target directory type + overwrite: + type: string + description: 'Set to "true" to overwrite existing files' + subfolder: + type: string + description: Subfolder within the target directory + responses: + "200": + description: Upload result + content: + application/json: + schema: + $ref: "#/components/schemas/UploadResult" + "400": + description: No file provided or invalid request + + /api/upload/mask: + post: + operationId: uploadMask + tags: [upload] + summary: Upload a mask image + description: Uploads a mask image associated with a previously-uploaded reference image. + requestBody: + required: true + content: + multipart/form-data: + schema: + type: object + required: + - image + - original_ref + properties: + image: + type: string + format: binary + description: Mask image (alpha channel is used) + original_ref: + type: object + description: Reference to the original image file + required: + - filename + properties: + filename: + type: string + description: Filename of the original image + additionalProperties: true + type: + type: string + enum: [input, temp, output] + default: input + description: Target directory type + overwrite: + type: string + description: 'Set to "true" to overwrite existing files' + subfolder: + type: string + description: Subfolder within the target directory + responses: + "200": + description: Upload result + content: + application/json: + schema: + $ref: "#/components/schemas/UploadResult" + "400": + description: No file provided or invalid request + + # --------------------------------------------------------------------------- + # View + # --------------------------------------------------------------------------- + /api/view: + get: + operationId: viewFile + tags: [view] + summary: View or download a file + description: Serves a file (image, audio, or video) from the input/output/temp directory identified by the query parameters. + parameters: + - name: filename + in: query + required: true + schema: + type: string + description: Name of the file to view + - name: type + in: query + schema: + type: string + enum: [input, output, temp] + default: output + description: Directory type + - name: subfolder + in: query + schema: + type: string + description: Subfolder within the directory + - name: preview + in: query + schema: + type: string + description: Preview format hint (e.g. "webp;90") + - name: channel + in: query + schema: + type: string + enum: [rgba, rgb, a] + description: Channel extraction mode + responses: + "200": + description: File content + content: + image/*: + schema: + type: string + format: binary + video/*: + schema: + type: string + format: binary + audio/*: + schema: + type: string + format: binary + application/octet-stream: + schema: + type: string + format: binary + "404": + description: File not found + + /api/view_metadata/{folder_name}: + get: + operationId: viewMetadata + tags: [view] + summary: Get metadata for a file (e.g. safetensors header) + description: Returns embedded metadata parsed from a file in the given folder — for example, the header of a safetensors model. + parameters: + - name: folder_name + in: path + required: true + schema: + type: string + description: Folder type (output, input, temp, etc.) + - name: filename + in: query + required: true + schema: + type: string + description: Filename to read metadata from + responses: + "200": + description: File metadata + content: + application/json: + schema: + type: object + additionalProperties: true + "404": + description: File or metadata not found + + # --------------------------------------------------------------------------- + # System + # --------------------------------------------------------------------------- + /api/system_stats: + get: + operationId: getSystemStats + tags: [system] + summary: Get system statistics + description: Returns hardware, Python, VRAM, and runtime statistics for the running ComfyUI process. + responses: + "200": + description: System stats + content: + application/json: + schema: + $ref: "#/components/schemas/SystemStatsResponse" + + /api/features: + get: + operationId: getFeatures + tags: [system] + summary: Get enabled feature flags + description: Returns a dictionary of feature flag names to their enabled state. + responses: + "200": + description: Feature flags + content: + application/json: + schema: + type: object + additionalProperties: + type: boolean + + # --------------------------------------------------------------------------- + # Node / Object Info + # --------------------------------------------------------------------------- + /api/object_info: + get: + operationId: getObjectInfo + tags: [node] + summary: Get all node definitions + description: | + Returns a dictionary of every registered node class, keyed by class name. + Each value is a NodeInfo object describing inputs, outputs, category, etc. + responses: + "200": + description: All node definitions + content: + application/json: + schema: + type: object + additionalProperties: + $ref: "#/components/schemas/NodeInfo" + + /api/object_info/{node_class}: + get: + operationId: getObjectInfoByClass + tags: [node] + summary: Get a single node definition + description: Returns the `NodeInfo` definition for a single registered node class. + parameters: + - name: node_class + in: path + required: true + schema: + type: string + description: Node class name (e.g. "KSampler") + responses: + "200": + description: Single node definition + content: + application/json: + schema: + type: object + additionalProperties: + $ref: "#/components/schemas/NodeInfo" + "404": + description: Node class not found + + /api/embeddings: + get: + operationId: getEmbeddings + tags: [node] + summary: List available embedding names + description: Returns the list of text-encoder embeddings available on disk. + responses: + "200": + description: Embedding names + content: + application/json: + schema: + type: array + items: + type: string + + # --------------------------------------------------------------------------- + # Models + # --------------------------------------------------------------------------- + /api/models: + get: + operationId: getModelTypes + tags: [model] + summary: List model folder type names + description: Returns an array of model type names (e.g. checkpoints, loras, vae). + responses: + "200": + description: Model type names + content: + application/json: + schema: + type: array + items: + type: string + + /api/models/{folder}: + get: + operationId: getModelsByFolder + tags: [model] + summary: List model filenames in a folder + description: Returns the names of model files in the given folder. This endpoint predates `/api/experiment/models/{folder}` and returns names only — prefer the experiment endpoint for new integrations. + parameters: + - name: folder + in: path + required: true + schema: + type: string + description: Model folder type name + responses: + "200": + description: Model filenames + content: + application/json: + schema: + type: array + items: + type: string + "404": + description: Unknown folder type + + /api/experiment/models: + get: + operationId: getExperimentModels + tags: [model] + summary: List model folders with paths + description: Returns an array of model folder objects with name and folder paths. + responses: + "200": + description: Model folders + content: + application/json: + schema: + type: array + items: + $ref: "#/components/schemas/ModelFolder" + + /api/experiment/models/{folder}: + get: + operationId: getExperimentModelsByFolder + tags: [model] + summary: List model files with metadata + description: Returns the model files in the given folder with richer metadata (path index, mtime, size) than the legacy `/api/models/{folder}` endpoint. + parameters: + - name: folder + in: path + required: true + schema: + type: string + description: Model folder type name + responses: + "200": + description: Model files with metadata + content: + application/json: + schema: + type: array + items: + $ref: "#/components/schemas/ModelFile" + "404": + description: Unknown folder type + + /api/experiment/models/preview/{folder}/{path_index}/{filename}: + get: + operationId: getModelPreview + tags: [model] + summary: Get model preview image + description: Returns the preview image associated with a model file, if one exists alongside the model on disk. + parameters: + - name: folder + in: path + required: true + schema: + type: string + description: Model folder type name + - name: path_index + in: path + required: true + schema: + type: integer + description: Path index within the folder + - name: filename + in: path + required: true + schema: + type: string + description: Model filename + responses: + "200": + description: Preview image (WebP) + content: + image/webp: + schema: + type: string + format: binary + "404": + description: Preview not found + + # --------------------------------------------------------------------------- + # Users + # --------------------------------------------------------------------------- + /api/users: + get: + operationId: getUsers + tags: [user] + summary: Get user storage info + description: | + Returns user storage configuration. In single-user mode returns + `{"storage": "server", "migrated": true/false}`. In multi-user mode + returns `{"storage": "server", "users": {"user_id": "user_dir", ...}}`. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + responses: + "200": + description: User info + content: + application/json: + schema: + type: object + properties: + storage: + type: string + description: Storage backend type (always "server") + migrated: + type: boolean + description: Whether migration from browser storage is complete (single-user) + users: + type: object + additionalProperties: + type: string + description: Map of user_id to directory name (multi-user) + post: + operationId: createUser + tags: [user] + summary: Create a new user (multi-user mode) + description: Creates a new user entry. Only meaningful when ComfyUI is running in multi-user mode. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - username + properties: + username: + type: string + description: Username for the new user + responses: + "200": + description: Created user ID + content: + application/json: + schema: + type: string + description: The generated user_id + "400": + description: Username already exists or invalid + + # --------------------------------------------------------------------------- + # Userdata + # --------------------------------------------------------------------------- + /api/userdata: + get: + operationId: listUserdata + tags: [userdata] + summary: List files in a userdata directory + description: Lists files in the authenticated user's data directory. Returns either filename strings or full objects depending on the `full_info` query parameter. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: dir + in: query + required: true + schema: + type: string + description: Directory path relative to the user's data folder + - name: recurse + in: query + schema: + type: boolean + description: Recurse into subdirectories + - name: full_info + in: query + schema: + type: boolean + description: Return full file info objects instead of just names + - name: split + in: query + schema: + type: boolean + description: Split paths into directory components + responses: + "200": + description: File listing + content: + application/json: + schema: + $ref: "#/components/schemas/ListUserdataResponse" + "404": + description: Directory not found + + /api/v2/userdata: + get: + operationId: listUserdataV2 + tags: [userdata] + summary: List files in userdata (v2 format) + description: Lists files in the authenticated user's data directory using the v2 response shape, which always returns full objects. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: path + in: query + schema: + type: string + description: Directory path relative to user data root + responses: + "200": + description: File listing with metadata + content: + application/json: + schema: + type: array + items: + type: object + properties: + name: + type: string + path: + type: string + type: + type: string + enum: [file, directory] + size: + type: integer + modified: + type: number + description: Unix timestamp + + /api/userdata/{file}: + get: + operationId: getUserdataFile + tags: [userdata] + summary: Read a userdata file + description: Reads the contents of a file from the authenticated user's data directory. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: file + in: path + required: true + schema: + type: string + description: File path relative to user data directory + responses: + "200": + description: File content + content: + application/octet-stream: + schema: + type: string + format: binary + "404": + description: File not found + post: + operationId: writeUserdataFile + tags: [userdata] + summary: Write or create a userdata file + description: Writes (creates or replaces) a file in the authenticated user's data directory. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: file + in: path + required: true + schema: + type: string + description: File path relative to user data directory + - name: overwrite + in: query + schema: + type: boolean + description: Allow overwriting existing files + - name: full_info + in: query + schema: + type: boolean + description: Return full file info in response + requestBody: + required: true + content: + application/octet-stream: + schema: + type: string + format: binary + application/json: + schema: {} + responses: + "200": + description: File written + content: + application/json: + schema: + $ref: "#/components/schemas/UserDataResponse" + "409": + description: File exists and overwrite not set + delete: + operationId: deleteUserdataFile + tags: [userdata] + summary: Delete a userdata file + description: Deletes a file from the authenticated user's data directory. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: file + in: path + required: true + schema: + type: string + description: File path relative to user data directory + responses: + "204": + description: File deleted + "404": + description: File not found + + /api/userdata/{file}/move/{dest}: + post: + operationId: moveUserdataFile + tags: [userdata] + summary: Move or rename a userdata file + description: Renames or moves a file within the authenticated user's data directory. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: file + in: path + required: true + schema: + type: string + description: Source file path + - name: dest + in: path + required: true + schema: + type: string + description: Destination file path + - name: overwrite + in: query + schema: + type: boolean + description: Allow overwriting at destination + - name: full_info + in: query + schema: + type: boolean + description: Return full file info in response + responses: + "200": + description: File moved + content: + application/json: + schema: + $ref: "#/components/schemas/UserDataResponse" + "404": + description: Source file not found + "409": + description: Destination exists and overwrite not set + + # --------------------------------------------------------------------------- + # Settings + # --------------------------------------------------------------------------- + /api/settings: + get: + operationId: getSettings + tags: [settings] + summary: Get all user settings + description: Returns all settings for the authenticated user. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + responses: + "200": + description: Settings object + content: + application/json: + schema: + type: object + additionalProperties: true + post: + operationId: updateSettings + tags: [settings] + summary: Update user settings (partial merge) + description: Replaces the authenticated user's settings with the provided object. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + requestBody: + required: true + content: + application/json: + schema: + type: object + additionalProperties: true + description: Partial settings to merge + responses: + "200": + description: Settings updated + + /api/settings/{id}: + get: + operationId: getSetting + tags: [settings] + summary: Get a single setting by key + description: Returns the value of a single setting, identified by key. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: id + in: path + required: true + schema: + type: string + description: Setting key + responses: + "200": + description: Setting value (null if the setting does not exist) + content: + application/json: + schema: + nullable: true + description: The setting value (any JSON type), or null if not set + post: + operationId: updateSetting + tags: [settings] + summary: Set a single setting value + description: Sets the value of a single setting, identified by key. + parameters: + - $ref: "#/components/parameters/ComfyUserHeader" + - name: id + in: path + required: true + schema: + type: string + description: Setting key + requestBody: + required: true + content: + application/json: + schema: + description: The setting value (any JSON type) + responses: + "200": + description: Setting updated + + # --------------------------------------------------------------------------- + # Extensions / Templates / i18n + # --------------------------------------------------------------------------- + /api/extensions: + get: + operationId: getExtensions + tags: [extensions] + summary: List frontend extension JS file paths + description: Returns the list of frontend extension JS URLs registered by custom nodes, to be loaded by the frontend on startup. + responses: + "200": + description: Array of JS file paths + content: + application/json: + schema: + type: array + items: + type: string + description: Relative path to extension JS file + + /api/workflow_templates: + get: + operationId: getWorkflowTemplates + tags: [extensions] + summary: Get workflow template mappings + description: Returns a map of custom node names to their provided workflow template names. + responses: + "200": + description: Template mappings + content: + application/json: + schema: + type: object + additionalProperties: + type: array + items: + type: string + description: Map of node pack name to array of template names + + /api/i18n: + get: + operationId: getI18n + tags: [extensions] + summary: Get internationalisation translation strings + description: Returns the URLs of translation files contributed by custom nodes, keyed by locale. + responses: + "200": + description: Translation map + content: + application/json: + schema: + type: object + additionalProperties: true + description: Nested map of locale to translation key-value pairs + + # --------------------------------------------------------------------------- + # Subgraphs + # --------------------------------------------------------------------------- + /api/global_subgraphs: + get: + operationId: getGlobalSubgraphs + tags: [subgraph] + summary: List global subgraph blueprints + description: Returns a dictionary of subgraph IDs to their metadata. + responses: + "200": + description: Subgraph metadata dictionary + content: + application/json: + schema: + type: object + additionalProperties: + $ref: "#/components/schemas/GlobalSubgraphInfo" + + /api/global_subgraphs/{id}: + get: + operationId: getGlobalSubgraph + tags: [subgraph] + summary: Get a global subgraph with full data + description: Returns the blueprint for a globally-registered subgraph, used by the frontend to materialize the subgraph node. + parameters: + - name: id + in: path + required: true + schema: + type: string + description: Subgraph identifier + responses: + "200": + description: Full subgraph data + content: + application/json: + schema: + $ref: "#/components/schemas/GlobalSubgraphData" + "404": + description: Subgraph not found + + # --------------------------------------------------------------------------- + # Node Replacements + # --------------------------------------------------------------------------- + /api/node_replacements: + get: + operationId: getNodeReplacements + tags: [node] + summary: Get node replacement mappings + description: | + Returns a dictionary mapping deprecated or replaced node class names + to their replacement node information. + responses: + "200": + description: Replacement mappings + content: + application/json: + schema: + type: object + additionalProperties: true + + # --------------------------------------------------------------------------- + # Internal (x-internal: true) + # --------------------------------------------------------------------------- + /internal/logs: + get: + operationId: getInternalLogs + tags: [internal] + summary: Get server logs as text + description: Returns structured ComfyUI log entries from the in-memory log buffer. + x-internal: true + responses: + "200": + description: Log text + content: + text/plain: + schema: + type: string + + /internal/logs/raw: + get: + operationId: getInternalLogsRaw + tags: [internal] + summary: Get raw structured log entries + description: Returns the raw ComfyUI log buffer as text, together with metadata about the current size limit. + x-internal: true + responses: + "200": + description: Structured log data + content: + application/json: + schema: + type: object + properties: + entries: + type: array + items: + type: object + properties: + t: + type: number + description: Timestamp + m: + type: string + description: Message + size: + type: object + properties: + cols: + type: integer + rows: + type: integer + + /internal/logs/subscribe: + patch: + operationId: subscribeToLogs + tags: [internal] + summary: Subscribe or unsubscribe a WebSocket client to log streaming + description: Subscribes or unsubscribes the current client from live log streaming over the WebSocket. + x-internal: true + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - clientId + - enabled + properties: + clientId: + type: string + description: WebSocket client ID + enabled: + type: boolean + description: Enable or disable log streaming for this client + responses: + "200": + description: Subscription updated + + /internal/folder_paths: + get: + operationId: getInternalFolderPaths + tags: [internal] + summary: Get configured folder paths + description: Returns the filesystem paths ComfyUI is configured to load models and other assets from, keyed by folder type. + x-internal: true + responses: + "200": + description: Dictionary of folder type to paths + content: + application/json: + schema: + type: object + additionalProperties: + type: array + items: + type: array + items: + type: string + description: Map of folder type name to list of [path, ...] entries + + /internal/files/{directory_type}: + get: + operationId: getInternalFiles + tags: [internal] + summary: List files in a directory type + description: Lists the files present in one of ComfyUI's known directories (input, output, or temp). + x-internal: true + parameters: + - name: directory_type + in: path + required: true + schema: + type: string + description: Directory type (e.g. output, input, temp) + responses: + "200": + description: Array of filenames + content: + application/json: + schema: + type: array + items: + type: string + + # --------------------------------------------------------------------------- + # Assets (x-feature-gate: enable-assets) + # --------------------------------------------------------------------------- + /api/assets/hash/{hash}: + head: + operationId: checkAssetByHash + tags: [assets] + summary: Check if an asset with the given hash exists + description: Returns 204 if an asset with the given content hash already exists, 404 otherwise. Used by clients to deduplicate uploads before transferring bytes. + x-feature-gate: enable-assets + parameters: + - name: hash + in: path + required: true + schema: + type: string + description: "Blake3 hash of the asset (e.g. blake3:abc123...)" + responses: + "200": + description: Asset exists + "404": + description: No asset with this hash + + /api/assets: + get: + operationId: listAssets + tags: [assets] + summary: List assets with filtering and pagination + description: Returns a paginated list of assets, optionally filtered by tags, name, or other query parameters. + x-feature-gate: enable-assets + parameters: + - name: limit + in: query + schema: + type: integer + default: 50 + - name: offset + in: query + schema: + type: integer + default: 0 + - name: include_tags + in: query + schema: + type: array + items: + type: string + style: form + explode: true + description: Tags that assets must have (AND logic) + - name: exclude_tags + in: query + schema: + type: array + items: + type: string + style: form + explode: true + description: Tags that assets must not have + - name: name_contains + in: query + schema: + type: string + description: Filter assets whose name contains this substring + - name: metadata_filter + in: query + schema: + type: string + description: JSON-encoded metadata key/value filter + - name: sort + in: query + schema: + type: string + description: Field to sort by + - name: order + in: query + schema: + type: string + enum: [asc, desc] + description: Sort direction + responses: + "200": + description: Asset list + content: + application/json: + schema: + $ref: "#/components/schemas/ListAssetsResponse" + post: + operationId: createAsset + tags: [assets] + summary: Upload a new asset + description: Uploads a new asset (binary content plus metadata) and registers it in the asset database. + x-feature-gate: enable-assets + requestBody: + required: true + content: + multipart/form-data: + schema: + type: object + required: + - file + properties: + file: + type: string + format: binary + description: Asset file to upload + name: + type: string + description: Display name for the asset + tags: + type: string + description: Comma-separated tags + user_metadata: + type: string + description: JSON-encoded user metadata + hash: + type: string + description: "Blake3 hash of the file content (e.g. blake3:abc123...)" + mime_type: + type: string + description: MIME type of the file (overrides auto-detected type) + preview_id: + type: string + format: uuid + description: ID of an existing asset to use as the preview image + responses: + "201": + description: Asset created + content: + application/json: + schema: + $ref: "#/components/schemas/AssetCreated" + + /api/assets/from-hash: + post: + operationId: createAssetFromHash + tags: [assets] + summary: Create an asset reference from an existing hash + description: Registers a new asset that references existing content by hash, without re-uploading the bytes. + x-feature-gate: enable-assets + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - hash + - name + properties: + hash: + type: string + description: Blake3 hash of existing content + name: + type: string + description: Display name + tags: + type: array + items: + type: string + user_metadata: + type: object + additionalProperties: true + responses: + "201": + description: Asset created from hash + content: + application/json: + schema: + $ref: "#/components/schemas/AssetCreated" + + /api/assets/{id}: + get: + operationId: getAsset + tags: [assets] + summary: Get asset metadata + description: Returns the metadata for a single asset. + x-feature-gate: enable-assets + parameters: + - name: id + in: path + description: The asset ID. + required: true + schema: + type: string + format: uuid + responses: + "200": + description: Asset metadata + content: + application/json: + schema: + $ref: "#/components/schemas/Asset" + "404": + description: Asset not found + put: + operationId: updateAsset + tags: [assets] + summary: Update asset metadata + description: Updates the mutable metadata of an asset (name, tags, etc.). Binary content is immutable. + x-feature-gate: enable-assets + parameters: + - name: id + in: path + description: The asset ID. + required: true + schema: + type: string + format: uuid + requestBody: + required: true + content: + application/json: + schema: + type: object + properties: + name: + type: string + description: New display name for the asset + user_metadata: + type: object + additionalProperties: true + description: Custom user metadata to set + preview_id: + type: string + format: uuid + description: ID of the asset to use as the preview + responses: + "200": + description: Asset updated + content: + application/json: + schema: + $ref: "#/components/schemas/AssetUpdated" + delete: + operationId: deleteAsset + tags: [assets] + summary: Delete an asset + description: Removes an asset entry. Depending on the server configuration, the underlying content may also be deleted. + x-feature-gate: enable-assets + parameters: + - name: id + in: path + description: The asset ID. + required: true + schema: + type: string + format: uuid + - name: delete_content + in: query + schema: + type: boolean + description: Also delete the underlying content file + responses: + "204": + description: Asset deleted + + /api/assets/{id}/content: + get: + operationId: getAssetContent + tags: [assets] + summary: Download asset file content + description: Returns the binary content of an asset. Supports range requests. + x-feature-gate: enable-assets + parameters: + - name: id + in: path + description: The asset ID. + required: true + schema: + type: string + format: uuid + responses: + "200": + description: Asset file content + content: + application/octet-stream: + schema: + type: string + format: binary + "404": + description: Asset not found + + /api/assets/{id}/tags: + post: + operationId: addAssetTags + tags: [assets] + summary: Add tags to an asset + description: Adds one or more tags to an asset. + x-feature-gate: enable-assets + parameters: + - name: id + in: path + description: The asset ID. + required: true + schema: + type: string + format: uuid + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - tags + properties: + tags: + type: array + items: + type: string + responses: + "200": + description: Tags added + content: + application/json: + schema: + $ref: "#/components/schemas/TagsModificationResponse" + delete: + operationId: removeAssetTags + tags: [assets] + summary: Remove tags from an asset + description: Removes one or more tags from an asset. + x-feature-gate: enable-assets + parameters: + - name: id + in: path + description: The asset ID. + required: true + schema: + type: string + format: uuid + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - tags + properties: + tags: + type: array + items: + type: string + responses: + "200": + description: Tags removed + content: + application/json: + schema: + $ref: "#/components/schemas/TagsModificationResponse" + + /api/tags: + get: + operationId: listTags + tags: [assets] + summary: List all known tags with counts + description: Returns the list of all tags known to the asset database, with counts. + x-feature-gate: enable-assets + parameters: + - name: limit + in: query + schema: + type: integer + - name: offset + in: query + schema: + type: integer + - name: search + in: query + schema: + type: string + description: Search term for tag name + responses: + "200": + description: Tag list + content: + application/json: + schema: + $ref: "#/components/schemas/ListTagsResponse" + + /api/assets/tags/refine: + get: + operationId: refineAssetTags + tags: [assets] + summary: Get tag counts for assets matching current filters + description: Returns suggested additional tags that would refine a filtered asset query, together with the count of assets each tag would select. + x-feature-gate: enable-assets + parameters: + - name: include_tags + in: query + schema: + type: array + items: + type: string + style: form + explode: true + description: Tags that assets must have (AND logic) + - name: exclude_tags + in: query + schema: + type: array + items: + type: string + style: form + explode: true + description: Tags that assets must not have + - name: name_contains + in: query + schema: + type: string + description: Filter assets whose name contains this substring + - name: metadata_filter + in: query + schema: + type: string + description: JSON-encoded metadata key/value filter + - name: limit + in: query + schema: + type: integer + - name: offset + in: query + schema: + type: integer + - name: sort + in: query + schema: + type: string + description: Field to sort by + - name: order + in: query + schema: + type: string + enum: [asc, desc] + description: Sort direction + responses: + "200": + description: Tag histogram + content: + application/json: + schema: + $ref: "#/components/schemas/AssetTagHistogramResponse" + + /api/assets/seed: + post: + operationId: seedAssets + tags: [assets] + summary: Trigger asset scan/seed from filesystem + description: Starts a background job that scans the configured directories and registers any assets not yet present in the asset database. + x-feature-gate: enable-assets + requestBody: + required: false + content: + application/json: + schema: + type: object + properties: + roots: + type: array + items: + type: string + description: Root folder paths to scan (if omitted, scans all) + responses: + "200": + description: Seed started + content: + application/json: + schema: + type: object + properties: + status: + type: string + + /api/assets/seed/status: + get: + operationId: getAssetSeedStatus + tags: [assets] + summary: Get asset scan progress + description: Returns the progress and status of the most recently-started asset seed job. + x-feature-gate: enable-assets + responses: + "200": + description: Scan progress + content: + application/json: + schema: + type: object + additionalProperties: true + description: Scan progress details (files scanned, total, status, etc.) + + /api/assets/seed/cancel: + post: + operationId: cancelAssetSeed + tags: [assets] + summary: Cancel an in-progress asset scan + description: Requests cancellation of the currently-running asset seed job. + x-feature-gate: enable-assets + responses: + "200": + description: Scan cancelled + content: + application/json: + schema: + type: object + properties: + status: + type: string + + /api/assets/prune: + post: + operationId: pruneAssets + tags: [assets] + summary: Mark assets whose backing files no longer exist on disk + description: Starts a background job that removes asset entries whose underlying content no longer exists on disk. + x-feature-gate: enable-assets + responses: + "200": + description: Prune result + content: + application/json: + schema: + type: object + properties: + status: + type: string + marked: + type: integer + description: Number of assets marked as missing + +components: + parameters: + ComfyUserHeader: + name: Comfy-User + in: header + required: false + schema: + type: string + description: | + Identifies the active user in multi-user mode. Used for settings, + userdata, and history isolation. This is not a security mechanism — + it is an organisational convenience with no authentication behind it. + + schemas: + # ------------------------------------------------------------------- + # Prompt + # ------------------------------------------------------------------- + PromptRequest: + type: object + description: A workflow submission. Wraps the prompt graph plus optional client identifier and extra per-request data. + required: + - prompt + properties: + prompt: + type: object + description: | + The workflow graph to execute. Keys are node IDs (strings); + values are objects with class_type and inputs. + additionalProperties: true + number: + type: number + description: Priority number for the queue (lower numbers have higher priority) + front: + type: boolean + description: If true, adds the prompt to the front of the queue + extra_data: + type: object + description: Extra data associated with the prompt (e.g. extra_pnginfo) + additionalProperties: true + client_id: + type: string + description: WebSocket client ID to receive progress updates + prompt_id: + type: string + format: uuid + description: "Client-supplied prompt ID. Server generates a UUID if omitted." + partial_execution_targets: + type: array + items: + type: string + description: List of node IDs to execute (partial graph execution) + + PromptResponse: + type: object + description: Server acknowledgement of a workflow submission. Includes the assigned `prompt_id` and current queue position. + properties: + prompt_id: + type: string + format: uuid + description: Unique identifier for the prompt execution + number: + type: number + description: Priority number in the queue + node_errors: + type: object + description: Validation errors keyed by node ID + additionalProperties: + $ref: "#/components/schemas/NodeError" + error: + description: Top-level prompt error (string message or structured error) + oneOf: + - type: string + - $ref: "#/components/schemas/PromptError" + + PromptErrorResponse: + type: object + description: Error response when prompt validation fails + additionalProperties: true + + PromptError: + type: object + description: Structured prompt validation error + properties: + type: + type: string + message: + type: string + details: + type: string + + Error: + type: object + description: Detailed node-level error + properties: + type: + type: string + message: + type: string + details: + type: string + extra_info: + type: object + properties: + input_name: + type: string + additionalProperties: true + + NodeError: + type: object + description: Error details for a single node + properties: + errors: + type: array + items: + $ref: "#/components/schemas/Error" + class_type: + type: string + description: The node's class type + dependent_outputs: + type: array + items: {} + + PromptInfo: + type: object + description: Summary of a queued or recently-executed prompt, as returned by the queue and history endpoints. + properties: + exec_info: + type: object + properties: + queue_remaining: + type: integer + description: Number of items remaining in the queue + + # ------------------------------------------------------------------- + # Queue + # ------------------------------------------------------------------- + QueueInfo: + type: object + description: Queue information with pending and running items + properties: + queue_running: + type: array + description: Currently running queue items + items: + type: array + description: | + Queue item tuple: [number, prompt_id, prompt, extra_data, outputs_to_execute, sensitive] + items: {} + prefixItems: + - type: number + description: Priority number + - type: string + format: uuid + description: prompt_id + - type: object + description: prompt graph + additionalProperties: true + - type: object + description: extra_data + additionalProperties: true + - type: array + description: outputs_to_execute (list of output node IDs) + items: + type: string + - type: object + description: sensitive data (may be omitted) + additionalProperties: true + queue_pending: + type: array + description: Pending queue items (oldest first) + items: + type: array + description: | + Queue item tuple: [number, prompt_id, prompt, extra_data, outputs_to_execute, sensitive] + items: {} + prefixItems: + - type: number + description: Priority number + - type: string + format: uuid + description: prompt_id + - type: object + description: prompt graph + additionalProperties: true + - type: object + description: extra_data + additionalProperties: true + - type: array + description: outputs_to_execute (list of output node IDs) + items: + type: string + - type: object + description: sensitive data (may be omitted) + additionalProperties: true + + QueueManageRequest: + type: object + description: Request to clear or delete from queue + properties: + clear: + type: boolean + description: If true, clear all pending items + delete: + type: array + items: + type: string + description: Array of prompt IDs to delete from queue + + # ------------------------------------------------------------------- + # History + # ------------------------------------------------------------------- + HistoryEntry: + type: object + description: A single execution history entry + properties: + prompt: + type: array + description: | + Prompt tuple: [number, prompt_id, prompt_graph, extra_data, output_node_ids] + items: {} + outputs: + type: object + description: Output data from execution keyed by node ID + additionalProperties: true + status: + type: object + description: Execution status (status_str, completed, messages, etc.) + additionalProperties: true + meta: + type: object + description: Metadata about the execution and nodes + additionalProperties: true + + HistoryManageRequest: + type: object + description: Request to clear or delete history entries + properties: + clear: + type: boolean + description: If true, clear all history + delete: + type: array + items: + type: string + description: Array of prompt IDs to delete from history + + # ------------------------------------------------------------------- + # Jobs + # ------------------------------------------------------------------- + JobEntry: + type: object + description: Lightweight job data for list views + required: + - id + - status + properties: + id: + type: string + format: uuid + description: Unique job identifier (same as prompt_id) + status: + type: string + description: Current job status + create_time: + type: number + description: Job creation timestamp + execution_start_time: + type: number + description: Workflow execution start timestamp + execution_end_time: + type: number + description: Workflow execution end timestamp + preview_output: + type: object + additionalProperties: true + description: Primary preview output + outputs_count: + type: integer + description: Total number of output files + + JobDetailResponse: + type: object + description: Full job details including workflow and outputs + required: + - id + - status + properties: + id: + type: string + format: uuid + status: + type: string + workflow: + type: object + additionalProperties: true + description: Full ComfyUI workflow + outputs: + type: object + additionalProperties: true + description: Full outputs object from execution + execution_error: + $ref: "#/components/schemas/ExecutionError" + create_time: + type: number + update_time: + type: number + execution_start_time: + type: number + execution_end_time: + type: number + preview_output: + type: object + additionalProperties: true + outputs_count: + type: integer + execution_status: + type: object + additionalProperties: true + execution_meta: + type: object + additionalProperties: true + + ExecutionError: + type: object + description: Detailed execution error from ComfyUI + properties: + node_id: + type: string + description: ID of the node that failed + node_type: + type: string + description: Type name of the node + exception_message: + type: string + description: Human-readable error message + exception_type: + type: string + description: Python exception type + traceback: + type: array + items: + type: string + description: Traceback lines + current_inputs: + type: object + additionalProperties: true + current_outputs: + type: object + additionalProperties: true + + PaginationInfo: + type: object + description: Pagination metadata returned alongside list responses. + properties: + offset: + type: integer + limit: + type: integer + total: + type: integer + has_more: + type: boolean + + # ------------------------------------------------------------------- + # Upload / View + # ------------------------------------------------------------------- + UploadResult: + type: object + description: Response body returned by the image/mask upload endpoints, describing where the uploaded file now lives. + properties: + name: + type: string + description: Saved filename (may be renamed to avoid collisions) + subfolder: + type: string + description: Subfolder the file was saved to + type: + type: string + description: Directory type (input, temp) + + # ------------------------------------------------------------------- + # System + # ------------------------------------------------------------------- + DeviceStats: + type: object + description: GPU/compute device statistics + required: + - name + - type + - index + properties: + name: + type: string + description: Device name + type: + type: string + description: Device type (cuda, mps, cpu, etc.) + index: + type: number + description: Device index + vram_total: + type: number + description: Total VRAM in bytes + vram_free: + type: number + description: Free VRAM in bytes + torch_vram_total: + type: number + description: Total PyTorch-managed VRAM in bytes + torch_vram_free: + type: number + description: Free PyTorch-managed VRAM in bytes + + SystemStatsResponse: + type: object + description: Hardware, VRAM, Python, and ComfyUI version information for the running process. + required: + - system + - devices + properties: + system: + type: object + required: + - os + - python_version + - embedded_python + - comfyui_version + - pytorch_version + - argv + - ram_total + - ram_free + properties: + os: + type: string + description: Operating system + python_version: + type: string + description: Python version + embedded_python: + type: boolean + description: Whether using embedded Python + comfyui_version: + type: string + description: ComfyUI version string + pytorch_version: + type: string + description: PyTorch version + required_frontend_version: + type: string + description: Required frontend version + argv: + type: array + items: + type: string + description: Command line arguments + ram_total: + type: number + description: Total RAM in bytes + ram_free: + type: number + description: Free RAM in bytes + installed_templates_version: + type: string + nullable: true + description: Version of the currently installed workflow templates + required_templates_version: + type: string + nullable: true + description: Minimum required workflow templates version for this ComfyUI build + devices: + type: array + items: + $ref: "#/components/schemas/DeviceStats" + + # ------------------------------------------------------------------- + # Node / Object Info + # ------------------------------------------------------------------- + NodeInfo: + type: object + description: 'Definition of a registered node class: its inputs, outputs, category, and display metadata.' + properties: + input: + type: object + description: Input specifications (required and optional groups) + additionalProperties: true + input_order: + type: object + description: Ordered input names per group + additionalProperties: + type: array + items: + type: string + output: + type: array + items: + type: string + description: Output type names + output_is_list: + type: array + items: + type: boolean + description: Whether each output is a list + output_name: + type: array + items: + type: string + description: Display names of outputs + name: + type: string + description: Internal class name + display_name: + type: string + description: Human-readable display name + description: + type: string + description: Node description + python_module: + type: string + description: Python module implementing the node + category: + type: string + description: Node category path + output_node: + type: boolean + description: Whether this is an output node + output_tooltips: + type: array + items: + type: string + description: Tooltips for each output + deprecated: + type: boolean + description: Whether the node is deprecated + experimental: + type: boolean + description: Whether the node is experimental + api_node: + type: boolean + description: Whether this is an API node + is_input_list: + type: boolean + description: Whether the node accepts list inputs + dev_only: + type: boolean + description: Whether the node is developer-only (hidden in production UI) + has_intermediate_output: + type: boolean + description: Whether the node emits intermediate output during execution + search_aliases: + type: array + items: + type: string + description: Alternative search terms for finding this node + essentials_category: + type: string + description: Category override used by the essentials pack + + # ------------------------------------------------------------------- + # Models + # ------------------------------------------------------------------- + ModelFolder: + type: object + description: A configured model folder and the list of disk paths it resolves to. + required: + - name + - folders + properties: + name: + type: string + description: Model folder type name (e.g. "checkpoints") + folders: + type: array + items: + type: string + description: Filesystem paths for this model type + + ModelFile: + type: object + description: A single model file in a folder, with filesystem metadata. + required: + - name + - pathIndex + properties: + name: + type: string + description: Model filename + pathIndex: + type: integer + description: Index into the folder's paths array + modified: + type: number + description: File modification timestamp + created: + type: number + description: File creation timestamp + size: + type: integer + format: int64 + description: File size in bytes + + # ------------------------------------------------------------------- + # Subgraphs + # ------------------------------------------------------------------- + GlobalSubgraphInfo: + type: object + description: Metadata for a global subgraph blueprint (without full data) + required: + - source + - name + - info + properties: + source: + type: string + description: Source type ("templates" or "custom_node") + name: + type: string + description: Display name of the subgraph blueprint + info: + type: object + description: Additional information about the subgraph + required: + - node_pack + properties: + node_pack: + type: string + description: The node pack/module providing this subgraph + data: + type: string + description: The full subgraph JSON data (may be empty in list view) + + GlobalSubgraphData: + type: object + description: Full data for a global subgraph blueprint + required: + - source + - name + - info + - data + properties: + source: + type: string + description: Source type ("templates" or "custom_node") + name: + type: string + description: Display name of the subgraph blueprint + info: + type: object + description: Additional information about the subgraph + required: + - node_pack + properties: + node_pack: + type: string + description: The node pack/module providing this subgraph + data: + type: string + description: The full subgraph JSON data as a string + + # ------------------------------------------------------------------- + # Userdata + # ------------------------------------------------------------------- + UserDataResponse: + description: | + Response body for the POST endpoints `/api/userdata/{file}` and + `/api/userdata/{file}/move/{dest}`. Returns a single item whose + shape depends on the `full_info` query parameter. + x-variant-selector: + full_info=true: file-info object (`GetUserDataResponseFullFile`) + default: relative path string + oneOf: + - $ref: "#/components/schemas/GetUserDataResponseFullFile" + - type: string + description: Relative path of the written or moved file. Returned when `full_info` is absent or false. + + ListUserdataResponse: + description: | + Response body for `GET /api/userdata`. The array item shape is + determined by the `full_info` and `split` query parameters. + x-variant-selector: + full_info=true: array of file-info objects (`GetUserDataResponseFullFile`) + split=true: array of `[relative_path, ...path_components]` arrays + default: array of relative path strings + oneOf: + - type: array + items: + $ref: "#/components/schemas/GetUserDataResponseFullFile" + description: Returned when `full_info=true`. + - type: array + items: + type: array + items: + type: string + minItems: 2 + description: | + Returned when `split=true` and `full_info=false`. Each inner + array is `[relative_path, ...path_components]`. + - type: array + items: + type: string + description: Default shape — array of file paths relative to the user data root. + + GetUserDataResponseFullFile: + type: object + description: A single entry in a full-info user data listing. + properties: + path: + type: string + description: File name or path relative to the user directory + created: + type: number + description: Unix timestamp of file creation + size: + type: integer + description: File size in bytes + modified: + type: integer + format: int64 + description: Unix timestamp of last modification in milliseconds + + # ------------------------------------------------------------------- + # Assets + # ------------------------------------------------------------------- + Asset: + type: object + description: A registered asset — an input/output file tracked in the asset database with content hash and metadata. + required: + - id + - name + - size + - created_at + - updated_at + properties: + id: + type: string + format: uuid + description: Unique identifier for the asset + name: + type: string + description: Name of the asset file + asset_hash: + type: string + description: Blake3 hash of the asset content + pattern: "^blake3:[a-f0-9]{64}$" + size: + type: integer + format: int64 + description: Size of the asset in bytes + mime_type: + type: string + description: MIME type of the asset + tags: + type: array + items: + type: string + description: Tags associated with the asset + user_metadata: + type: object + description: Custom user metadata + additionalProperties: true + metadata: + type: object + description: System-managed metadata (read-only) + additionalProperties: true + readOnly: true + preview_url: + type: string + format: uri + description: URL for asset preview/thumbnail + preview_id: + type: string + format: uuid + description: ID of the preview asset if available + prompt_id: + type: string + format: uuid + description: ID of the prompt that created this asset + created_at: + type: string + format: date-time + updated_at: + type: string + format: date-time + last_access_time: + type: string + format: date-time + is_immutable: + type: boolean + description: Whether this asset is immutable + + AssetCreated: + description: Response body returned after successfully registering a new asset. + allOf: + - $ref: "#/components/schemas/Asset" + - type: object + required: + - created_new + properties: + created_new: + type: boolean + description: Whether this was a new creation (true) or returned existing (false) + + AssetUpdated: + type: object + description: Response body returned after updating an asset's metadata. + required: + - id + - updated_at + properties: + id: + type: string + format: uuid + name: + type: string + asset_hash: + type: string + pattern: "^blake3:[a-f0-9]{64}$" + tags: + type: array + items: + type: string + mime_type: + type: string + user_metadata: + type: object + additionalProperties: true + updated_at: + type: string + format: date-time + + ListAssetsResponse: + type: object + description: Paginated list of assets. + required: + - assets + - total + - has_more + properties: + assets: + type: array + items: + $ref: "#/components/schemas/Asset" + total: + type: integer + has_more: + type: boolean + + TagInfo: + type: object + description: A tag known to the asset database, with the number of assets bearing it. + required: + - name + - count + properties: + name: + type: string + count: + type: integer + + ListTagsResponse: + type: object + description: Flat list of all tags, with counts. + required: + - tags + - total + - has_more + properties: + tags: + type: array + items: + $ref: "#/components/schemas/TagInfo" + total: + type: integer + has_more: + type: boolean + + AssetTagHistogramResponse: + type: object + description: Tags that would refine a filtered asset query, with the count of assets each tag would additionally select. + required: + - tag_counts + properties: + tag_counts: + type: object + additionalProperties: + type: integer + description: Map of tag names to occurrence counts + + TagsModificationResponse: + type: object + description: Response body returned after adding or removing tags on an asset. + required: + - total_tags + properties: + added: + type: array + items: + type: string + description: Tags successfully added + removed: + type: array + items: + type: string + description: Tags successfully removed + already_present: + type: array + items: + type: string + description: Tags already present (for add) + not_present: + type: array + items: + type: string + description: Tags not present (for remove) + total_tags: + type: array + items: + type: string + description: All tags on the asset after the operation + + # ------------------------------------------------------------------- + # Result / Output types + # ------------------------------------------------------------------- + ResultItem: + type: object + description: A single output file reference + properties: + filename: + type: string + subfolder: + type: string + type: + type: string + enum: [input, output, temp] + display_name: + type: string + + NodeOutputs: + type: object + description: | + Outputs from a single node execution. Known keys are listed below, + but custom nodes may add arbitrary keys (additionalProperties). + properties: + images: + type: array + items: + $ref: "#/components/schemas/ResultItem" + audio: + type: array + items: + $ref: "#/components/schemas/ResultItem" + video: + type: array + items: + $ref: "#/components/schemas/ResultItem" + animated: + type: array + items: + type: boolean + text: + oneOf: + - type: string + - type: array + items: + type: string + additionalProperties: true + + TerminalSize: + type: object + description: Terminal dimensions + properties: + cols: + type: number + row: + type: number + + LogEntry: + type: object + description: A single log entry + properties: + t: + type: string + description: Timestamp + m: + type: string + description: Log message + + StatusWsMessageStatus: + type: object + description: Inner payload of a `status` WebSocket message, describing the execution queue state. + properties: + exec_info: + type: object + required: + - queue_remaining + properties: + queue_remaining: + type: integer + + StatusWsMessage: + type: object + description: Initial status message sent on connect + queue status updates + properties: + status: + $ref: "#/components/schemas/StatusWsMessageStatus" + sid: + type: string + description: Session ID assigned by the server + + ProgressWsMessage: + type: object + description: Node execution progress (step N of M) + required: + - value + - max + - prompt_id + - node + properties: + value: + type: integer + description: Current step + max: + type: integer + description: Total steps + prompt_id: + type: string + node: + type: string + description: Node ID currently executing + + ProgressTextWsMessage: + type: object + description: Text-based progress update from a node + properties: + nodeId: + type: string + text: + type: string + prompt_id: + type: string + + NodeProgressState: + type: object + description: Progress state for a single node + properties: + value: + type: number + max: + type: number + state: + type: string + enum: [pending, running, finished, error] + node_id: + type: string + prompt_id: + type: string + display_node_id: + type: string + parent_node_id: + type: string + real_node_id: + type: string + + ProgressStateWsMessage: + type: object + description: Bulk progress state for all nodes in a prompt + required: + - prompt_id + - nodes + properties: + prompt_id: + type: string + nodes: + type: object + description: Map of node ID to progress state + additionalProperties: + $ref: "#/components/schemas/NodeProgressState" + + ExecutingWsMessage: + type: object + description: Fired when a node begins execution + required: + - node + - display_node + - prompt_id + properties: + node: + type: string + description: Node ID + display_node: + type: string + description: Display node ID (may differ for subgraphs) + prompt_id: + type: string + + ExecutedWsMessage: + type: object + description: Fired when a node completes execution with output + required: + - node + - display_node + - prompt_id + - output + properties: + node: + type: string + display_node: + type: string + prompt_id: + type: string + output: + $ref: "#/components/schemas/NodeOutputs" + merge: + type: boolean + description: Whether to merge with existing output + + ExecutionWsMessageBase: + type: object + description: Base fields for execution lifecycle messages + required: + - prompt_id + - timestamp + properties: + prompt_id: + type: string + timestamp: + type: integer + description: Unix timestamp in milliseconds + + ExecutionStartWsMessage: + allOf: + - $ref: "#/components/schemas/ExecutionWsMessageBase" + description: Fired when prompt execution begins + + ExecutionSuccessWsMessage: + allOf: + - $ref: "#/components/schemas/ExecutionWsMessageBase" + description: Fired when prompt execution completes successfully + + ExecutionCachedWsMessage: + allOf: + - $ref: "#/components/schemas/ExecutionWsMessageBase" + - type: object + properties: + nodes: + type: array + items: + type: string + description: List of node IDs that were cached + description: Fired when nodes are served from cache + + ExecutionInterruptedWsMessage: + allOf: + - $ref: "#/components/schemas/ExecutionWsMessageBase" + - type: object + properties: + node_id: + type: string + node_type: + type: string + executed: + type: array + items: + type: string + description: Node IDs that completed before interruption + description: Fired when execution is interrupted by user + + ExecutionErrorWsMessage: + allOf: + - $ref: "#/components/schemas/ExecutionWsMessageBase" + - type: object + properties: + node_id: + type: string + node_type: + type: string + executed: + type: array + items: + type: string + exception_message: + type: string + exception_type: + type: string + traceback: + type: array + items: + type: string + current_inputs: {} + current_outputs: {} + description: Fired when a node throws an exception during execution + + LogsWsMessage: + type: object + description: Streaming log entries from the server + properties: + size: + $ref: "#/components/schemas/TerminalSize" + entries: + type: array + items: + $ref: "#/components/schemas/LogEntry" + + NotificationWsMessage: + type: object + description: Server notification (e.g. model download complete) + properties: + value: + type: string + id: + type: string + + FeatureFlagsWsMessage: + type: object + description: Feature flags sent on connect + additionalProperties: true + + AssetDownloadWsMessage: + type: object + description: Asset download progress + required: + - task_id + - asset_name + - bytes_total + - bytes_downloaded + - progress + - status + properties: + task_id: + type: string + asset_name: + type: string + bytes_total: + type: number + bytes_downloaded: + type: number + progress: + type: number + description: 0.0 to 1.0 + status: + type: string + enum: [created, running, completed, failed] + asset_id: + type: string + error: + type: string + + AssetExportWsMessage: + type: object + description: Bulk asset export progress + required: + - task_id + - assets_total + - assets_attempted + - assets_failed + - bytes_total + - bytes_processed + - progress + - status + properties: + task_id: + type: string + export_name: + type: string + assets_total: + type: number + assets_attempted: + type: number + assets_failed: + type: number + bytes_total: + type: number + bytes_processed: + type: number + progress: + type: number + description: 0.0 to 1.0 + status: + type: string + enum: [created, running, completed, failed] + error: + type: string diff --git a/pyproject.toml b/pyproject.toml index 1fc9402a1..633dac517 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "ComfyUI" -version = "0.18.1" +version = "0.20.1" readme = "README.md" license = { file = "LICENSE" } requires-python = ">=3.10" diff --git a/requirements.txt b/requirements.txt index 6f0659a00..32826e25a 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,6 +1,6 @@ -comfyui-frontend-package==1.42.8 -comfyui-workflow-templates==0.9.39 -comfyui-embedded-docs==0.4.3 +comfyui-frontend-package==1.42.15 +comfyui-workflow-templates==0.9.68 +comfyui-embedded-docs==0.4.4 torch torchsde torchvision @@ -19,11 +19,11 @@ scipy tqdm psutil alembic -SQLAlchemy +SQLAlchemy>=2.0.0 filelock av>=14.2.0 comfy-kitchen>=0.2.8 -comfy-aimdo>=0.2.12 +comfy-aimdo==0.3.0 requests simpleeval>=1.0.0 blake3 diff --git a/server.py b/server.py index 27b14825e..881da8e66 100644 --- a/server.py +++ b/server.py @@ -146,6 +146,10 @@ def is_loopback(host): def create_origin_only_middleware(): @web.middleware async def origin_only_middleware(request: web.Request, handler): + if 'Sec-Fetch-Site' in request.headers: + sec_fetch_site = request.headers['Sec-Fetch-Site'] + if sec_fetch_site == 'cross-site': + return web.Response(status=403) #this code is used to prevent the case where a random website can queue comfy workflows by making a POST to 127.0.0.1 which browsers don't prevent for some dumb reason. #in that case the Host and Origin hostnames won't match #I know the proper fix would be to add a cookie but this should take care of the problem in the meantime diff --git a/utils/install_util.py b/utils/install_util.py index 34489aec5..fdba23a8f 100644 --- a/utils/install_util.py +++ b/utils/install_util.py @@ -39,7 +39,7 @@ def get_required_packages_versions(): if len(s) == 2: version_str = s[-1] if not is_valid_version(version_str): - logging.error(f"Invalid version format in requirements.txt: {version_str}") + logging.debug(f"Invalid version format for {s[0]} in requirements.txt: {version_str}") continue out[s[0]] = version_str return out.copy()