Compare commits

...

10 Commits

Author SHA1 Message Date
Yousef R. Gamaleldin
fe07092de6
Merge 96d0cfe0d7 into 7bbf1e8169 2026-05-09 13:17:55 +08:00
Alexander Piskun
7bbf1e8169
[Partner Nodes] Tripo3D 3.1 model (#13788)
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
* feat(api-nodes): add Tripo3D 3.1 model

Signed-off-by: bigcat88 <bigcat88@icloud.com>

* fix: price badges algo

Signed-off-by: bigcat88 <bigcat88@icloud.com>

* [Partner Nodes] deprecate "quad" param for the TripoMultiviewToModel node

Signed-off-by: bigcat88 <bigcat88@icloud.com>

---------

Signed-off-by: bigcat88 <bigcat88@icloud.com>
2026-05-08 21:38:17 -07:00
lin-bot23
8b08bfdcbe
Add description field to blueprint subgraphs (#13797)
* Add description field to all blueprint subgraphs

Sets the 'description' field on every subgraph blueprint node,
which will show on the node preview and tooltip. Covers all 51
blueprint files under blueprints/.

* Update blueprint descriptions with researched model info

* Refine blueprint descriptions with researched model specs from docs

Updates subgraph descriptions across all 51 blueprints with accurate
model details drawn from ComfyUI docs, including:
- Flux.1 Dev: 12B open-weights, Pro-level quality
- Flux.2 Klein 4B: fastest Flux, distilled architecture
- Qwen-Image: 20B MMDiT, multilingual text rendering
- Z-Image-Turbo: distilled 6B DiT, sub-second inference
- LTX-2/2.3: 19B DiT audio-video foundation model
- Wan2.2: open-source, 14B/1.3B variants
- ACE-Step 1.5: ~1s full-song generation
- GPU shader nodes consistently labeled as fragment shaders

* Strip marketing fluff and license info from descriptions

* Fix Canny to Video (LTX 2.0) description

* Remove 'local-' prefix from subgraph names

* Preserve UTF-8 encoding in JSON files (ensure_ascii=False)

* Apply review suggestions from alexisrolland

- Rename 'Image to Model (Hunyuan3d 2.1)' -> 'Image to 3D Model (Hunyuan3d 2.1)'
- Rename 'Image Upscale(Z-image-Turbo)' -> 'Image Upscale (Z-image-Turbo)'
- Rename 'Video Inpaint(Wan2.1 VACE)' -> 'Video Inpaint (Wan 2.1 VACE)'
- Use 'Black Forest Labs' branding in Flux descriptions
- Use 'Google's Gemini' with possessive in captioning nodes
- Normalize 'Wan 2.2' and 'Wan 2.1' spacing in descriptions

* fix: revert Color Adjustment.json to preserve original GLSL shader content

Only adds the 'description' field without modifying the shader code
(which contained Unicode escape \\u2192 that should be preserved).

* Apply CodeRabbit review suggestions

- Color Adjustment: include vibrance in description
- Image Blur: expand to Gaussian/Box/Radial modes
- Flux.2 Klein 4B: narrow to image edit only (no T2I)
- NetaYume Lumina: correct model base (Neta Lumina, not Lumina-Next)

---------

Co-authored-by: linmoumou <linmoumou@linmoumoudeMac-mini.local>
Co-authored-by: Daxiong (Lin) <contact@comfyui-wiki.com>
2026-05-09 11:26:13 +08:00
Matt Miller
4e823431cc
Add cloud-runtime experiment node-schema endpoints to spec (#13806)
* Add cloud-runtime experiment node-schema endpoints to spec

Replace the GET operations at /api/experiment/nodes and
/api/experiment/nodes/{id} with getNodeInfoSchema and getNodeByID —
the optimized, ETag-tagged object_info schema endpoints the cloud
frontend depends on for the workflow editor.

Each operation is tagged x-runtime: [cloud] and uses the runtime-only
tag for cloud-side codegen exclusion. Response headers document the
ETag and Cache-Control validators; 304 Not Modified is declared for
RFC 7232 conditional GETs.

Remove the now-unused CloudNodeList schema to keep Spectral clean.

Co-authored-by: Matt Miller <MillerMedia@users.noreply.github.com>

* spec: document If-None-Match header on conditional GET endpoints

Both `getNodeInfoSchema` and `getNodeByID` advertise `ETag` response
headers and a `304 Not Modified` response, but the spec didn't declare
the `If-None-Match` request header that triggers conditional validation.
Adding it as an optional header parameter on both ops so client codegen
exposes the conditional-GET pattern.
2026-05-08 19:14:23 -07:00
comfyanonymous
66669b2ded
I don't think there was any because nobody complained. (#13807)
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
2026-05-08 17:32:14 -07:00
Alexander Piskun
65045730a6
[Partner Nodes] additionally use Baidu server to detect the accessibility of internet (#13803)
Signed-off-by: bigcat88 <bigcat88@icloud.com>
2026-05-08 13:11:52 -07:00
Matt Miller
87878f354f
Add cloud-runtime FE-facing operations to spec (#13734)
* Add cloud-runtime FE-facing operations to openapi.yaml

Add ~67 cloud-runtime FE-facing path operations to the core OpenAPI spec,
each tagged with x-runtime: [cloud] at the operation level. These operations
are served by the cloud runtime; the local runtime returns 404 for all of
these paths.

Domain groups added:
- Jobs / prompts: /api/job/*, /api/jobs/*/cancel, /api/prompt/*, etc.
- History v2: /api/history_v2, /api/history_v2/{prompt_id}
- Cloud logs: /api/logs
- Asset extensions: /api/assets/download, export, import, etc.
- Custom nodes: /api/experiment/nodes (cloud install/uninstall)
- Hub: /api/hub/profiles, /api/hub/workflows, /api/hub/labels, etc.
- Workflows: /api/workflows CRUD, versioning, fork, publish
- Auth/session: /api/auth/session, /api/auth/token, /.well-known/jwks.json
- Billing: /api/billing/balance, plans, subscribe, topup, etc.
- Workspace: /api/workspace/*, /api/workspaces/*
- User/settings/misc: /api/user, /api/secrets, /api/feedback, etc.

Also adds corresponding cloud-only component schemas (CloudJob, CloudWorkflow,
BillingPlan, Workspace, HubProfile, AuthSession, etc.), all tagged with
x-runtime: [cloud].

Spectral lint passes under the existing ruleset with zero new warnings.

* Add job_id field to Asset schema and deprecate prompt_id (#13736)

- Add job_id as a nullable UUID field to the Asset schema
- Mark prompt_id as deprecated with note pointing to job_id
- No x-runtime tag needed as both runtimes populate the field

* Add hash field to Asset schemas and deprecate asset_hash (#13738)

- Add 'hash' as a nullable string field to Asset and AssetUpdated schemas
- Mark 'asset_hash' as deprecated with a note pointing to 'hash'
- AssetCreated inherits 'hash' via allOf from Asset
- Spectral lint clean (no new warnings)

* Fix method drift on cloud-runtime endpoints

Three PUT operations were added that should be PATCH (cloud serves
PATCH for partial updates):

- /api/workflows/{workflow_id}
- /api/workspaces/{id}
- /api/workspace/members/{userId}

Two POST operations were added that should be GET (cloud serves GET
with query params):

- /api/assets/remote-metadata (url moves to query param)
- /api/files/mask-layers (response shape replaced — operation queries
  related mask layer filenames, not file uploads)

* Add missing cloud-runtime operations and schemas

PR review surfaced operations the cloud runtime serves that weren't
covered by the initial spec push, plus one path family missed entirely.

New methods on existing paths:

- /api/auth/session: add POST (create session cookie) and DELETE (logout)
- /api/secrets/{id}: add GET (read metadata) and PATCH (update)
- /api/hub/profiles: add POST (create profile)
- /api/hub/workflows: add POST (publish to hub)
- /api/hub/workflows/{share_id}: add DELETE (unpublish)
- /api/workspaces/{id}: add DELETE (soft-delete workspace)
- /api/workspace/members/{user_id}/api-keys: add DELETE (bulk revoke)
- /api/workflows/{workflow_id}/versions: add POST (create new version)
- /api/userdata/{file}/publish: add GET (read publish info)

New path family:

- /api/tasks (GET list) and /api/tasks/{task_id} (GET detail) for the
  background task framework

New component schemas (all tagged x-runtime: [cloud]):

CreateSessionResponse, DeleteSessionResponse, UpdateSecretRequest,
BulkRevokeAPIKeysResponse, CreateHubProfileRequest, PublishHubWorkflowRequest,
HubWorkflowDetail, AssetInfo, CreateWorkflowVersionRequest,
WorkflowVersionResponse, WorkflowPublishInfo, TaskEntry, TaskResponse,
TasksListResponse. Existing SecretMeta extended with provider and
last_used_at fields the cloud runtime actually returns.

New tag: task. Spectral lint passes with zero errors.

* Add job_id and prompt_id to AssetUpdated schema

Mirrors the Asset schema's deprecation pattern: prompt_id is marked
deprecated with a description pointing to job_id; job_id is the new
preferred field. PUT /api/assets/{id} responses can now carry both fields
consistent with the other Asset-returning endpoints.

* feat: add width and height fields to Asset schema (#13745)

Add nullable integer fields 'width' and 'height' to the Asset schema
in openapi.yaml. These expose original image dimensions in pixels for
clients that need pre-thumbnail size info. Both fields are null for
non-image assets or assets ingested before dimension extraction.

Co-authored-by: Matt Miller <MillerMedia@users.noreply.github.com>

* Remove /api/job/{job_id} and /api/job/{job_id}/outputs

These two paths are not actually served by the cloud runtime — they
return 404 with a redirect message pointing callers to the canonical
`/api/jobs/{job_id}` (plural). Declaring them with `x-runtime: [cloud]`
and a 200 response schema is incorrect.

`/api/job/{job_id}/status` stays — it is a real cloud-served endpoint.

Also drops the now-orphaned `CloudJob` and `CloudJobOutputs` component
schemas. `CloudJobStatus` is retained.
2026-05-08 12:39:16 -07:00
Alexis Rolland
c5ecd231a2
fix: Fix bug when mask not on same device (CORE-181) (#13801)
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
2026-05-08 23:06:29 +08:00
drozbay
9864f5ac86
fix: Stop LTXVImgToVideoInplace from mutating input latents and dropping noise_mask (#13793) 2026-05-08 23:02:17 +08:00
drozbay
05cd076bc1
fix: Make LTXVAddGuide center-crop guide images to match other LTXV nodes (#13794) 2026-05-08 22:48:59 +08:00
59 changed files with 4929 additions and 189 deletions

View File

@ -431,9 +431,10 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Adjusts image brightness and contrast using a real-time GPU fragment shader."
}
]
},
"extra": {}
}
}

View File

@ -162,7 +162,7 @@
},
"revision": 0,
"config": {},
"name": "local-Canny to Image (Z-Image-Turbo)",
"name": "Canny to Image (Z-Image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1553,7 +1553,8 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Canny to image"
"category": "Image generation and editing/Canny to image",
"description": "Generates an image from a Canny edge map using Z-Image-Turbo, with text conditioning."
}
]
},
@ -1574,4 +1575,4 @@
}
},
"version": 0.4
}
}

View File

@ -192,7 +192,7 @@
},
"revision": 0,
"config": {},
"name": "local-Canny to Video (LTX 2.0)",
"name": "Canny to Video (LTX 2.0)",
"inputNode": {
"id": -10,
"bounding": [
@ -3600,7 +3600,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Canny to video"
"category": "Video generation and editing/Canny to video",
"description": "Generates video from Canny edge maps using LTX-2, with optional synchronized audio."
}
]
},
@ -3616,4 +3617,4 @@
}
},
"version": 0.4
}
}

View File

@ -377,8 +377,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Adds lens-style chromatic aberration (color fringing) using a real-time GPU fragment shader."
}
]
}
}
}

View File

@ -596,7 +596,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Adjusts saturation, temperature, tint, and vibrance using a real-time GPU fragment shader."
}
]
}

View File

@ -1129,7 +1129,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Balances colors across shadows, midtones, and highlights using a real-time GPU fragment shader."
}
]
}

View File

@ -608,7 +608,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Fine-tunes tone and color with per-channel curve adjustments using a real-time GPU fragment shader."
}
]
}

View File

@ -1609,7 +1609,8 @@
}
],
"extra": {},
"category": "Image Tools/Crop"
"category": "Image Tools/Crop",
"description": "Splits an image into a 2×2 grid of four equal tiles."
}
]
},

View File

@ -2946,7 +2946,8 @@
}
],
"extra": {},
"category": "Image Tools/Crop"
"category": "Image Tools/Crop",
"description": "Splits an image into a 3×3 grid of nine equal tiles."
}
]
},

View File

@ -1579,7 +1579,8 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Depth to image"
"category": "Image generation and editing/Depth to image",
"description": "Generates an image from a depth map using Z-Image-Turbo with text conditioning."
},
{
"id": "458bdf3c-4b58-421c-af50-c9c663a4d74c",
@ -2461,7 +2462,8 @@
]
},
"workflowRendererVersion": "LG"
}
},
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
}
]
},

View File

@ -4233,7 +4233,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Depth to video"
"category": "Video generation and editing/Depth to video",
"description": "Generates video from depth maps using LTX-2, with optional synchronized audio."
},
{
"id": "38b60539-50a7-42f9-a5fe-bdeca26272e2",
@ -5192,7 +5193,8 @@
],
"extra": {
"workflowRendererVersion": "LG"
}
},
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
}
]
},

View File

@ -450,9 +450,10 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Blur"
"category": "Image Tools/Blur",
"description": "Applies bilateral (edge-preserving) blur to soften images while retaining detail."
}
]
},
"extra": {}
}
}

View File

@ -580,8 +580,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Adds procedural film grain texture for a cinematic look via GPU fragment shader."
}
]
}
}
}

View File

@ -3350,7 +3350,8 @@
}
],
"extra": {},
"category": "Video generation and editing/First-Last-Frame to Video"
"category": "Video generation and editing/First-Last-Frame to Video",
"description": "Generates a video interpolating between first and last keyframes using LTX-2.3."
}
]
},

View File

@ -575,8 +575,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Adds a glow/bloom effect around bright image areas via GPU fragment shader."
}
]
}
}
}

View File

@ -752,8 +752,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Adjusts hue, saturation, and lightness of an image using a real-time GPU fragment shader."
}
]
}
}
}

View File

@ -374,7 +374,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Blur"
"category": "Image Tools/Blur",
"description": "Applies Gaussian, Box, or Radial blur to soften images and create stylized depth or motion effects."
}
]
}

View File

@ -310,7 +310,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Text generation/Image Captioning"
"category": "Text generation/Image Captioning",
"description": "Generates descriptive captions for images using Google's Gemini multimodal LLM."
}
]
}

View File

@ -315,8 +315,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Manipulates individual RGBA channels for masking, compositing, and channel effects."
}
]
}
}
}

View File

@ -2138,7 +2138,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Edit image"
"category": "Image generation and editing/Edit image",
"description": "Edits images via text instructions using FireRed Image Edit 1.1, a diffusion-based instruction-following editing model."
}
]
},

View File

@ -1472,7 +1472,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Edit image"
"category": "Image generation and editing/Edit image",
"description": "Edits an input image via text instructions using FLUX.2 [klein] 4B."
},
{
"id": "6007e698-2ebd-4917-84d8-299b35d7b7ab",
@ -1821,7 +1822,8 @@
],
"extra": {
"workflowRendererVersion": "LG"
}
},
"description": "Applies reference image conditioning for style/identity transfer (Flux.2 Klein 4B)."
}
]
},
@ -1837,4 +1839,4 @@
}
},
"version": 0.4
}
}

View File

@ -1417,7 +1417,8 @@
}
],
"extra": {},
"category": "Image generation and editing/Edit image"
"category": "Image generation and editing/Edit image",
"description": "Edits images via text instructions using LongCat Image Edit, an instruction-following image editing diffusion model."
}
]
},

View File

@ -132,7 +132,7 @@
},
"revision": 0,
"config": {},
"name": "local-Image Edit (Qwen 2511)",
"name": "Image Edit (Qwen 2511)",
"inputNode": {
"id": -10,
"bounding": [
@ -1468,7 +1468,8 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Edit image"
"category": "Image generation and editing/Edit image",
"description": "Edits images via text instructions using Qwen-Image-Edit-2511 with improved character consistency and integrated LoRA."
}
]
},
@ -1489,4 +1490,4 @@
}
},
"version": 0.4
}
}

View File

@ -1188,7 +1188,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Inpaint image"
"category": "Image generation and editing/Inpaint image",
"description": "Inpaints masked image regions using Flux.1 fill [dev], Black Forest Labs' inpainting/outpainting model."
}
]
},
@ -1202,4 +1203,4 @@
},
"ue_links": []
}
}
}

View File

@ -1548,7 +1548,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Inpaint image"
"category": "Image generation and editing/Inpaint image",
"description": "Inpaints masked regions using Qwen-Image, extending its multilingual text rendering to inpainting tasks."
},
{
"id": "56a1f603-fbd2-40ed-94ef-c9ecbd96aca8",
@ -1907,7 +1908,8 @@
],
"extra": {
"workflowRendererVersion": "LG"
}
},
"description": "Expands and softens mask edges to reduce visible seams after image processing."
}
]
},

View File

@ -742,9 +742,10 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
"category": "Image Tools/Color adjust",
"description": "Adjusts black point, white point, and gamma for tonal range control via GPU shader."
}
]
},
"extra": {}
}
}

View File

@ -1919,7 +1919,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Outpaint image"
"category": "Image generation and editing/Outpaint image",
"description": "Outpaints beyond image boundaries using Qwen-Image's outpainting capabilities."
},
{
"id": "f93c215e-c393-460e-9534-ed2c3d8a652e",
@ -2278,7 +2279,8 @@
],
"extra": {
"workflowRendererVersion": "LG"
}
},
"description": "Expands and softens mask edges to reduce visible seams after image processing."
},
{
"id": "2a4b2cc0-db37-4302-a067-da392f38f06b",
@ -2733,7 +2735,8 @@
],
"extra": {
"workflowRendererVersion": "LG"
}
},
"description": "Scales both image and mask together while preserving alignment for editing workflows."
}
]
},

View File

@ -141,7 +141,7 @@
},
"revision": 0,
"config": {},
"name": "local-Image Upscale(Z-image-Turbo)",
"name": "Image Upscale (Z-image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1302,7 +1302,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Enhance"
"category": "Image generation and editing/Enhance",
"description": "Upscales images to higher resolution using Z-Image-Turbo."
}
]
},

View File

@ -99,7 +99,7 @@
},
"revision": 0,
"config": {},
"name": "local-Image to Depth Map (Lotus)",
"name": "Image to Depth Map (Lotus)",
"inputNode": {
"id": -10,
"bounding": [
@ -948,7 +948,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Depth to image"
"category": "Image generation and editing/Depth to image",
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
}
]
},
@ -964,4 +965,4 @@
"workflowRendererVersion": "LG"
},
"version": 0.4
}
}

View File

@ -1586,7 +1586,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Image to layers"
"category": "Image generation and editing/Image to layers",
"description": "Decomposes an image into variable-resolution RGBA layers for independent editing using Qwen-Image-Layered."
}
]
},

View File

@ -72,7 +72,7 @@
},
"revision": 0,
"config": {},
"name": "local-Image to Model (Hunyuan3d 2.1)",
"name": "Image to 3D Model (Hunyuan3d 2.1)",
"inputNode": {
"id": -10,
"bounding": [
@ -765,7 +765,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "3D/Image to 3D Model"
"category": "3D/Image to 3D Model",
"description": "Generates 3D mesh models from a single input image using Hunyuan3D 2.0/2.1."
}
]
},

View File

@ -4223,7 +4223,8 @@
"extra": {
"workflowRendererVersion": "Vue-corrected"
},
"category": "Video generation and editing/Image to video"
"category": "Video generation and editing/Image to video",
"description": "Generates video from a single input image using LTX-2.3."
}
]
},

View File

@ -206,7 +206,7 @@
},
"revision": 0,
"config": {},
"name": "local-Image to Video (Wan 2.2)",
"name": "Image to Video (Wan 2.2)",
"inputNode": {
"id": -10,
"bounding": [
@ -2027,7 +2027,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Image to video"
"category": "Video generation and editing/Image to video",
"description": "Generates video from an image and text prompt using Wan 2.2, supporting T2V and I2V."
}
]
},

View File

@ -134,7 +134,7 @@
},
"revision": 0,
"config": {},
"name": "local-Pose to Image (Z-Image-Turbo)",
"name": "Pose to Image (Z-Image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1298,7 +1298,8 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Pose to image"
"category": "Image generation and editing/Pose to image",
"description": "Generates an image from pose keypoints using Z-Image-Turbo with text conditioning."
}
]
},
@ -1319,4 +1320,4 @@
}
},
"version": 0.4
}
}

View File

@ -3870,7 +3870,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Pose to video"
"category": "Video generation and editing/Pose to video",
"description": "Generates video from pose reference frames using LTX-2, with optional synchronized audio."
}
]
},

View File

@ -270,9 +270,10 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Text generation/Prompt enhance"
"category": "Text generation/Prompt enhance",
"description": "Expands short text prompts into detailed descriptions using a text generation model for better generation quality."
}
]
},
"extra": {}
}
}

View File

@ -302,8 +302,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Sharpen"
"category": "Image Tools/Sharpen",
"description": "Sharpens image details using a GPU fragment shader for enhanced clarity."
}
]
}
}
}

View File

@ -222,7 +222,7 @@
},
"revision": 0,
"config": {},
"name": "local-Text to Audio (ACE-Step 1.5)",
"name": "Text to Audio (ACE-Step 1.5)",
"inputNode": {
"id": -10,
"bounding": [
@ -1502,7 +1502,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Audio/Music generation"
"category": "Audio/Music generation",
"description": "Generates audio/music from text prompts using ACE-Step 1.5, a diffusion-based audio generation model."
}
]
},
@ -1518,4 +1519,4 @@
}
},
"version": 0.4
}
}

View File

@ -1029,7 +1029,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Text to image"
"category": "Image generation and editing/Text to image",
"description": "Generates images from text prompts using Flux.1 [dev], Black Forest Labs' 12B diffusion model."
}
]
},
@ -1043,4 +1044,4 @@
},
"ue_links": []
}
}
}

View File

@ -1023,7 +1023,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Text to image"
"category": "Image generation and editing/Text to image",
"description": "Generates images from text prompts using Flux.1 Krea Dev, a Black Forest Labs × Krea collaboration variant."
}
]
},
@ -1037,4 +1038,4 @@
},
"ue_links": []
}
}
}

View File

@ -1104,7 +1104,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Text to image"
"category": "Image generation and editing/Text to image",
"description": "Generates images from text prompts using NetaYume Lumina, fine-tuned from Neta Lumina for anime-style and illustration generation."
},
{
"id": "a07fdf06-1bda-4dac-bdbd-63ee8ebca1c9",
@ -1458,11 +1459,12 @@
],
"extra": {
"workflowRendererVersion": "LG"
}
},
"description": "Encodes a negative text prompt via CLIP for classifier-free guidance in anime-style generation (NetaYume Lumina)."
}
]
},
"extra": {
"ue_links": []
}
}
}

View File

@ -1941,7 +1941,8 @@
"extra": {
"workflowRendererVersion": "Vue-corrected"
},
"category": "Image generation and editing/Text to image"
"category": "Image generation and editing/Text to image",
"description": "Generates images from text prompts using Qwen-Image-2512, with enhanced human realism and finer natural detail over the base version."
}
]
},

View File

@ -1873,7 +1873,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Text to image"
"category": "Image generation and editing/Text to image",
"description": "Generates images from text prompts using Qwen-Image, Alibaba's 20B MMDiT model with excellent multilingual text rendering."
}
]
},

View File

@ -149,7 +149,7 @@
},
"revision": 0,
"config": {},
"name": "local-Text to Image (Z-Image-Turbo)",
"name": "Text to Image (Z-Image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1054,7 +1054,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Text to image"
"category": "Image generation and editing/Text to image",
"description": "Generates images from text prompts using Z-Image-Turbo, Alibaba's distilled 6B DiT model."
}
]
},
@ -1075,4 +1076,4 @@
}
},
"version": 0.4
}
}

View File

@ -4286,7 +4286,8 @@
"extra": {
"workflowRendererVersion": "Vue-corrected"
},
"category": "Video generation and editing/Text to video"
"category": "Video generation and editing/Text to video",
"description": "Generates video from text prompts using LTX-2.3, Lightricks' video diffusion model."
}
]
},

View File

@ -1572,7 +1572,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Text to video"
"category": "Video generation and editing/Text to video",
"description": "Generates video from text prompts using Wan2.2, Alibaba's diffusion video model."
}
]
},
@ -1586,4 +1587,4 @@
"VHS_KeepIntermediate": true
},
"version": 0.4
}
}

View File

@ -434,8 +434,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Sharpen"
"category": "Image Tools/Sharpen",
"description": "Enhances edge contrast via unsharp masking for a sharper image appearance."
}
]
}
}
}

View File

@ -307,7 +307,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Text generation/Video Captioning"
"category": "Text generation/Video Captioning",
"description": "Generates descriptive captions for video input using Google's Gemini multimodal LLM."
}
]
}

View File

@ -165,7 +165,7 @@
},
"revision": 0,
"config": {},
"name": "local-Video Inpaint(Wan2.1 VACE)",
"name": "Video Inpaint (Wan 2.1 VACE)",
"inputNode": {
"id": -10,
"bounding": [
@ -2368,7 +2368,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Inpaint video"
"category": "Video generation and editing/Inpaint video",
"description": "Inpaints masked regions in video frames using Wan 2.1 VACE."
}
]
},

View File

@ -584,8 +584,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video Tools/Stitch videos"
"category": "Video Tools/Stitch videos",
"description": "Stitches multiple video clips into a single sequential video file."
}
]
}
}
}

View File

@ -412,9 +412,10 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Enhance video"
"category": "Video generation and editing/Enhance video",
"description": "Upscales video to 4× resolution using a GAN-based upscaling model."
}
]
},
"extra": {}
}
}

View File

@ -47,7 +47,7 @@ class BackgroundRemovalModel():
out = self.model(pixel_values=pixel_values)
out = torch.nn.functional.interpolate(out, size=(H, W), mode="bicubic", antialias=False)
mask = out.sigmoid()
mask = out.sigmoid().to(device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
if mask.ndim == 3:
mask = mask.unsqueeze(0)
if mask.shape[1] != 1:

View File

@ -1390,7 +1390,7 @@ def convert_old_quants(state_dict, model_prefix="", metadata={}):
k_out = "{}.weight_scale".format(layer)
if layer is not None:
layer_conf = {"format": "float8_e4m3fn"} # TODO: check if anyone did some non e4m3fn scaled checkpoints
layer_conf = {"format": "float8_e4m3fn"}
if full_precision_matrix_mult:
layer_conf["full_precision_matrix_mult"] = full_precision_matrix_mult
layers[layer] = layer_conf

View File

@ -1,10 +1,11 @@
from __future__ import annotations
from enum import Enum
from typing import Optional, List, Dict, Any, Union
from typing import Optional, Any
from pydantic import BaseModel, Field, RootModel
class TripoModelVersion(str, Enum):
v3_1_20260211 = 'v3.1-20260211'
v3_0_20250812 = 'v3.0-20250812'
v2_5_20250123 = 'v2.5-20250123'
v2_0_20240919 = 'v2.0-20240919'
@ -142,7 +143,7 @@ class TripoFileEmptyReference(BaseModel):
pass
class TripoFileReference(RootModel):
root: Union[TripoFileTokenReference, TripoUrlReference, TripoObjectReference, TripoFileEmptyReference]
root: TripoFileTokenReference | TripoUrlReference | TripoObjectReference | TripoFileEmptyReference
class TripoGetStsTokenRequest(BaseModel):
format: str = Field(..., description='The format of the image')
@ -183,7 +184,7 @@ class TripoImageToModelRequest(BaseModel):
class TripoMultiviewToModelRequest(BaseModel):
type: TripoTaskType = TripoTaskType.MULTIVIEW_TO_MODEL
files: List[TripoFileReference] = Field(..., description='The file references to convert to a model')
files: list[TripoFileReference] = Field(..., description='The file references to convert to a model')
model_version: Optional[TripoModelVersion] = Field(None, description='The model version to use for generation')
orthographic_projection: Optional[bool] = Field(False, description='Whether to use orthographic projection')
face_limit: Optional[int] = Field(None, description='The number of faces to limit the generation to')
@ -251,27 +252,13 @@ class TripoConvertModelRequest(BaseModel):
with_animation: Optional[bool] = Field(None, description='Whether to include animations')
pack_uv: Optional[bool] = Field(None, description='Whether to pack the UVs')
bake: Optional[bool] = Field(None, description='Whether to bake the model')
part_names: Optional[List[str]] = Field(None, description='The names of the parts to include')
part_names: Optional[list[str]] = Field(None, description='The names of the parts to include')
fbx_preset: Optional[TripoFbxPreset] = Field(None, description='The preset for the FBX export')
export_vertex_colors: Optional[bool] = Field(None, description='Whether to export the vertex colors')
export_orientation: Optional[TripoOrientation] = Field(None, description='The orientation for the export')
animate_in_place: Optional[bool] = Field(None, description='Whether to animate in place')
class TripoTaskRequest(RootModel):
root: Union[
TripoTextToModelRequest,
TripoImageToModelRequest,
TripoMultiviewToModelRequest,
TripoTextureModelRequest,
TripoRefineModelRequest,
TripoAnimatePrerigcheckRequest,
TripoAnimateRigRequest,
TripoAnimateRetargetRequest,
TripoStylizeModelRequest,
TripoConvertModelRequest
]
class TripoTaskOutput(BaseModel):
model: Optional[str] = Field(None, description='URL to the model')
base_model: Optional[str] = Field(None, description='URL to the base model')
@ -283,12 +270,13 @@ class TripoTask(BaseModel):
task_id: str = Field(..., description='The task ID')
type: Optional[str] = Field(None, description='The type of task')
status: Optional[TripoTaskStatus] = Field(None, description='The status of the task')
input: Optional[Dict[str, Any]] = Field(None, description='The input parameters for the task')
input: Optional[dict[str, Any]] = Field(None, description='The input parameters for the task')
output: Optional[TripoTaskOutput] = Field(None, description='The output of the task')
progress: Optional[int] = Field(None, description='The progress of the task', ge=0, le=100)
create_time: Optional[int] = Field(None, description='The creation time of the task')
running_left_time: Optional[int] = Field(None, description='The estimated time left for the task')
queue_position: Optional[int] = Field(None, description='The position in the queue')
consumed_credit: int | None = Field(None)
class TripoTaskResponse(BaseModel):
code: int = Field(0, description='The response code')
@ -296,7 +284,7 @@ class TripoTaskResponse(BaseModel):
class TripoGeneralResponse(BaseModel):
code: int = Field(0, description='The response code')
data: Dict[str, str] = Field(..., description='The task ID data')
data: dict[str, str] = Field(..., description='The task ID data')
class TripoBalanceData(BaseModel):
balance: float = Field(..., description='The account balance')

View File

@ -60,6 +60,7 @@ async def poll_until_finished(
],
status_extractor=lambda x: x.data.status,
progress_extractor=lambda x: x.data.progress,
price_extractor=lambda x: x.data.consumed_credit * 0.01 if x.data.consumed_credit else None,
estimated_duration=average_duration,
)
if response_poll.data.status == TripoTaskStatus.SUCCESS:
@ -113,7 +114,6 @@ class TripoTextToModelNode(IO.ComfyNode):
depends_on=IO.PriceBadgeDepends(
widgets=[
"model_version",
"style",
"texture",
"pbr",
"quad",
@ -124,20 +124,17 @@ class TripoTextToModelNode(IO.ComfyNode):
expr="""
(
$isV14 := $contains(widgets.model_version,"v1.4");
$style := widgets.style;
$hasStyle := ($style != "" and $style != "none");
$isV3OrLater := $contains(widgets.model_version,"v3.");
$withTexture := widgets.texture or widgets.pbr;
$isHdTexture := (widgets.texture_quality = "detailed");
$isDetailedGeometry := (widgets.geometry_quality = "detailed");
$baseCredits :=
$isV14 ? 20 : ($withTexture ? 20 : 10);
$credits :=
$baseCredits
+ ($hasStyle ? 5 : 0)
$credits := $isV14 ? 20 : (
($withTexture ? 20 : 10)
+ (widgets.quad ? 5 : 0)
+ ($isHdTexture ? 10 : 0)
+ ($isDetailedGeometry ? 20 : 0);
{"type":"usd","usd": $round($credits * 0.01, 2)}
+ (($isDetailedGeometry and $isV3OrLater) ? 20 : 0)
);
{"type":"usd","usd": $round($credits * 0.01, 2), "format": {"approximate": true}}
)
""",
),
@ -239,7 +236,6 @@ class TripoImageToModelNode(IO.ComfyNode):
depends_on=IO.PriceBadgeDepends(
widgets=[
"model_version",
"style",
"texture",
"pbr",
"quad",
@ -250,20 +246,17 @@ class TripoImageToModelNode(IO.ComfyNode):
expr="""
(
$isV14 := $contains(widgets.model_version,"v1.4");
$style := widgets.style;
$hasStyle := ($style != "" and $style != "none");
$isV3OrLater := $contains(widgets.model_version,"v3.");
$withTexture := widgets.texture or widgets.pbr;
$isHdTexture := (widgets.texture_quality = "detailed");
$isDetailedGeometry := (widgets.geometry_quality = "detailed");
$baseCredits :=
$isV14 ? 30 : ($withTexture ? 30 : 20);
$credits :=
$baseCredits
+ ($hasStyle ? 5 : 0)
$credits := $isV14 ? 30 : (
($withTexture ? 30 : 20)
+ (widgets.quad ? 5 : 0)
+ ($isHdTexture ? 10 : 0)
+ ($isDetailedGeometry ? 20 : 0);
{"type":"usd","usd": $round($credits * 0.01, 2)}
+ (($isDetailedGeometry and $isV3OrLater) ? 20 : 0)
);
{"type":"usd","usd": $round($credits * 0.01, 2), "format": {"approximate": true}}
)
""",
),
@ -358,7 +351,7 @@ class TripoMultiviewToModelNode(IO.ComfyNode):
"texture_alignment", default="original_image", options=["original_image", "geometry"], optional=True, advanced=True
),
IO.Int.Input("face_limit", default=-1, min=-1, max=500000, optional=True, advanced=True),
IO.Boolean.Input("quad", default=False, optional=True, advanced=True),
IO.Boolean.Input("quad", default=False, optional=True, advanced=True, tooltip="This parameter is deprecated and does nothing."),
IO.Combo.Input("geometry_quality", default="standard", options=["standard", "detailed"], optional=True, advanced=True),
],
outputs=[
@ -379,7 +372,6 @@ class TripoMultiviewToModelNode(IO.ComfyNode):
"model_version",
"texture",
"pbr",
"quad",
"texture_quality",
"geometry_quality",
],
@ -387,17 +379,16 @@ class TripoMultiviewToModelNode(IO.ComfyNode):
expr="""
(
$isV14 := $contains(widgets.model_version,"v1.4");
$isV3OrLater := $contains(widgets.model_version,"v3.");
$withTexture := widgets.texture or widgets.pbr;
$isHdTexture := (widgets.texture_quality = "detailed");
$isDetailedGeometry := (widgets.geometry_quality = "detailed");
$baseCredits :=
$isV14 ? 30 : ($withTexture ? 30 : 20);
$credits :=
$baseCredits
+ (widgets.quad ? 5 : 0)
$credits := $isV14 ? 30 : (
($withTexture ? 30 : 20)
+ ($isHdTexture ? 10 : 0)
+ ($isDetailedGeometry ? 20 : 0);
{"type":"usd","usd": $round($credits * 0.01, 2)}
+ (($isDetailedGeometry and $isV3OrLater) ? 20 : 0)
);
{"type":"usd","usd": $round($credits * 0.01, 2), "format": {"approximate": true}}
)
""",
),
@ -457,7 +448,7 @@ class TripoMultiviewToModelNode(IO.ComfyNode):
geometry_quality=geometry_quality,
texture_alignment=texture_alignment,
face_limit=face_limit if face_limit != -1 else None,
quad=quad,
quad=None,
),
)
return await poll_until_finished(cls, response, average_duration=80)
@ -498,7 +489,7 @@ class TripoTextureNode(IO.ComfyNode):
expr="""
(
$tq := widgets.texture_quality;
{"type":"usd","usd": ($contains($tq,"detailed") ? 0.2 : 0.1)}
{"type":"usd","usd": ($contains($tq,"detailed") ? 0.2 : 0.1), "format": {"approximate": true}}
)
""",
),
@ -555,7 +546,7 @@ class TripoRefineNode(IO.ComfyNode):
is_api_node=True,
is_output_node=True,
price_badge=IO.PriceBadge(
expr="""{"type":"usd","usd":0.3}""",
expr="""{"type":"usd","usd":0.3, "format": {"approximate": true}}""",
),
)
@ -592,7 +583,7 @@ class TripoRigNode(IO.ComfyNode):
is_api_node=True,
is_output_node=True,
price_badge=IO.PriceBadge(
expr="""{"type":"usd","usd":0.25}""",
expr="""{"type":"usd","usd":0.25, "format": {"approximate": true}}""",
),
)
@ -652,7 +643,7 @@ class TripoRetargetNode(IO.ComfyNode):
is_api_node=True,
is_output_node=True,
price_badge=IO.PriceBadge(
expr="""{"type":"usd","usd":0.1}""",
expr="""{"type":"usd","usd":0.1, "format": {"approximate": true}}""",
),
)
@ -761,19 +752,10 @@ class TripoConversionNode(IO.ComfyNode):
"face_limit",
"texture_size",
"texture_format",
"force_symmetry",
"flatten_bottom",
"flatten_bottom_threshold",
"pivot_to_center_bottom",
"scale_factor",
"with_animation",
"pack_uv",
"bake",
"part_names",
"fbx_preset",
"export_vertex_colors",
"export_orientation",
"animate_in_place",
],
),
expr="""
@ -783,28 +765,16 @@ class TripoConversionNode(IO.ComfyNode):
$flatThresh := (widgets.flatten_bottom_threshold != null) ? widgets.flatten_bottom_threshold : 0;
$scale := (widgets.scale_factor != null) ? widgets.scale_factor : 1;
$texFmt := (widgets.texture_format != "" ? widgets.texture_format : "jpeg");
$part := widgets.part_names;
$fbx := (widgets.fbx_preset != "" ? widgets.fbx_preset : "blender");
$orient := (widgets.export_orientation != "" ? widgets.export_orientation : "default");
$advanced :=
widgets.quad or
widgets.force_symmetry or
widgets.flatten_bottom or
widgets.pivot_to_center_bottom or
widgets.with_animation or
widgets.pack_uv or
widgets.bake or
widgets.export_vertex_colors or
widgets.animate_in_place or
($face != -1) or
($texSize != 4096) or
($flatThresh != 0) or
($scale != 1) or
($texFmt != "jpeg") or
($part != "") or
($fbx != "blender") or
($orient != "default");
{"type":"usd","usd": ($advanced ? 0.1 : 0.05)}
($texFmt != "jpeg");
{"type":"usd","usd": ($advanced ? 0.1 : 0.05), "format": {"approximate": true}}
)
""",
),

View File

@ -488,10 +488,30 @@ async def _diagnose_connectivity() -> dict[str, bool]:
"api_accessible": False,
}
timeout = aiohttp.ClientTimeout(total=5.0)
# Probe Google and Baidu in parallel: Google is blocked by the GFW in mainland China, so a Baidu probe is required
# to correctly detect that Chinese users with working internet do have working internet.
internet_probe_urls = ("https://www.google.com", "https://www.baidu.com")
async with aiohttp.ClientSession(timeout=timeout) as session:
with contextlib.suppress(ClientError, OSError):
async with session.get("https://www.google.com") as resp:
results["internet_accessible"] = resp.status < 500
async def _probe(url: str) -> bool:
try:
async with session.get(url) as resp:
return resp.status < 500
except (ClientError, OSError, asyncio.TimeoutError):
return False
probe_tasks = [asyncio.create_task(_probe(u)) for u in internet_probe_urls]
try:
for fut in asyncio.as_completed(probe_tasks):
if await fut:
results["internet_accessible"] = True
break
finally:
for t in probe_tasks:
if not t.done():
t.cancel()
await asyncio.gather(*probe_tasks, return_exceptions=True)
if not results["internet_accessible"]:
return results

View File

@ -203,7 +203,7 @@ class JoinImageWithAlpha(io.ComfyNode):
@classmethod
def execute(cls, image: torch.Tensor, alpha: torch.Tensor) -> io.NodeOutput:
batch_size = max(len(image), len(alpha))
alpha = 1.0 - resize_mask(alpha, image.shape[1:])
alpha = 1.0 - resize_mask(alpha.to(image), image.shape[1:])
alpha = comfy.utils.repeat_to_batch_size(alpha, batch_size)
image = comfy.utils.repeat_to_batch_size(image, batch_size)
return io.NodeOutput(torch.cat((image[..., :3], alpha.unsqueeze(-1)), dim=-1))

View File

@ -106,12 +106,12 @@ class LTXVImgToVideoInplace(io.ComfyNode):
if bypass:
return (latent,)
samples = latent["samples"]
samples = latent["samples"].clone()
_, height_scale_factor, width_scale_factor = (
vae.downscale_index_formula
)
batch, _, latent_frames, latent_height, latent_width = samples.shape
_, _, _, latent_height, latent_width = samples.shape
width = latent_width * width_scale_factor
height = latent_height * height_scale_factor
@ -124,11 +124,7 @@ class LTXVImgToVideoInplace(io.ComfyNode):
samples[:, :, :t.shape[2]] = t
conditioning_latent_frames_mask = torch.ones(
(batch, 1, latent_frames, 1, 1),
dtype=torch.float32,
device=samples.device,
)
conditioning_latent_frames_mask = get_noise_mask(latent)
conditioning_latent_frames_mask[:, :, :t.shape[2]] = 1.0 - strength
return io.NodeOutput({"samples": samples, "noise_mask": conditioning_latent_frames_mask})
@ -236,7 +232,7 @@ class LTXVAddGuide(io.ComfyNode):
def encode(cls, vae, latent_width, latent_height, images, scale_factors):
time_scale_factor, width_scale_factor, height_scale_factor = scale_factors
images = images[:(images.shape[0] - 1) // time_scale_factor * time_scale_factor + 1]
pixels = comfy.utils.common_upscale(images.movedim(-1, 1), latent_width * width_scale_factor, latent_height * height_scale_factor, "bilinear", crop="disabled").movedim(1, -1)
pixels = comfy.utils.common_upscale(images.movedim(-1, 1), latent_width * width_scale_factor, latent_height * height_scale_factor, "bilinear", crop="center").movedim(1, -1)
encode_pixels = pixels[:, :, :, :3]
t = vae.encode(encode_pixels)
return encode_pixels, t

File diff suppressed because it is too large Load Diff