wangbo/ComfyUI-Manager
1
0
Fork 0
mirror of https://github.com/Comfy-Org/ComfyUI-Manager.git synced 2025-12-16 18:02:58 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
7d636c4118
ComfyUI-Manager/node_db/new/custom-node-list.json
Dr.Lt.Data 7d636c4118 update DB
2024-06-20 21:40:01 +09:00

744 lines
36 KiB
JSON
Raw Blame History

{
"custom_nodes": [
{
"author": "#NOTICE_1.13",
"title": "NOTICE: This channel is not the default channel.",
"reference": "https://github.com/ltdrdata/ComfyUI-Manager","files": [],
"install_type": "git-clone",
"description": "If you see this message, your ComfyUI-Manager is outdated.\nRecent channel provides only the list of the latest nodes. If you want to find the complete node list, please go to the Default channel.\nMaking LoRA has never been easier!"
},
{
"author": "asagi4",
"title": "Adaptive Guidance for ComfyUI",
"id": "asagi-nodes",
"reference": "https://github.com/asagi4/ComfyUI-Adaptive-Guidance",
"files": [
"https://github.com/asagi4/ComfyUI-Adaptive-Guidance"
],
"install_type": "git-clone",
"description": "An implementation of adaptive guidance for ComfyUI\nSee [a/https://bcv-uniandes.github.io/adaptiveguidance-wp/](https://bcv-uniandes.github.io/adaptiveguidance-wp/)"
},
{
"author": "kijai",
"title": "ComfyUI-Florence2",
"id": "florence2-kijai",
"reference": "https://github.com/kijai/ComfyUI-Florence2",
"files": [
"https://github.com/kijai/ComfyUI-Florence2"
],
"install_type": "git-clone",
"description": "ComfyUI nodes to use Microsoft's Florence2 vision model. Supports captioning, object detection and segmentation"
},
{
"author": "spacepxl",
"title": "ComfyUI-Florence-2",
"id": "florence2-spacepxl",
"reference": "https://github.com/spacepxl/ComfyUI-Florence-2",
"files": [
"https://github.com/spacepxl/ComfyUI-Florence-2"
],
"install_type": "git-clone",
"description": "[a/https://huggingface.co/microsoft/Florence-2-large-ft](https://huggingface.co/microsoft/Florence-2-large-ft)\nLarge or base model, support for captioning and bbox task modes, more coming soon."
},
{
"author": "kijai",
"title": "ComfyUI-LuminaWrapper",
"id": "lumina",
"reference": "https://github.com/kijai/ComfyUI-LuminaWrapper",
"files": [
"https://github.com/kijai/ComfyUI-LuminaWrapper"
],
"install_type": "git-clone",
"description": "ComfyUI wrapper nodes for Lumina models"
},
{
"author": "kadirnar",
"title": "ComfyUI-YOLO",
"id": "comfy-yolo",
"reference": "https://github.com/kadirnar/ComfyUI-YOLO",
"files": [
"https://github.com/kadirnar/ComfyUI-YOLO"
],
"install_type": "git-clone",
"description": "Nodes:Load Ultralytics Model, Ultralytics Inference, Ultralytics Visualization, Convert to Dictionary, BBox to XYWH"
},
{
"author": "chris-the-wiz",
"title": "EmbeddingsCurveEditor_ComfyUI",
"id": "embeddings-curve-editor",
"reference": "https://github.com/chris-the-wiz/EmbeddingsCurveEditor_ComfyUI",
"files": [
"https://github.com/chris-the-wiz/EmbeddingsCurveEditor_ComfyUI"
],
"install_type": "git-clone",
"description": "Edit embeddings with a curve. Actually should work on any 1D input tensor. Tested with IPAdapter-Plus."
},
{
"author": "AustinMroz",
"title": "ComfyUI-WorkflowCheckpointing",
"id": "workflowcheckpointing",
"reference": "https://github.com/AustinMroz/ComfyUI-WorkflowCheckpointing",
"files": [
"https://github.com/AustinMroz/ComfyUI-WorkflowCheckpointing"
],
"install_type": "git-clone",
"description": "Automatically creates checkpoints during workflow execution. If If an workflow is canceled or ComfyUI crashes mid-execution, then these checkpoints are used when the workflow is re-queued to resume execution with minimal progress loss."
},
{
"author": "TRI3D-LC",
"title": "ComfyUI-MiroBoard",
"id": "miroboard",
"reference": "https://github.com/TRI3D-LC/ComfyUI-MiroBoard",
"files": [
"https://github.com/TRI3D-LC/ComfyUI-MiroBoard"
],
"install_type": "git-clone",
"description": "Nodes: add-image-miro-board."
},
{
"author": "SamKhoze",
"title": "DeepFuze",
"id": "deepfuze",
"reference": "https://github.com/SamKhoze/ComfyUI-DeepFuze",
"files": [
"https://github.com/SamKhoze/ComfyUI-DeepFuze"
],
"install_type": "git-clone",
"description": "DeepFuze is a state-of-the-art deep learning tool that seamlessly integrates with ComfyUI to revolutionize facial transformations, lipsyncing, video generation, voice cloning, face swapping, and lipsync translation. Leveraging advanced algorithms, DeepFuze enables users to combine audio and video with unparalleled realism, ensuring perfectly synchronized facial movements. This innovative solution is ideal for content creators, animators, developers, and anyone seeking to elevate their video editing projects with sophisticated AI-driven features."
},
{
"author": "AIFSH",
"title": "ComfyUI-UniAnimate",
"id": "unianimate",
"reference": "https://github.com/AIFSH/ComfyUI-UniAnimate",
"files": [
"https://github.com/AIFSH/ComfyUI-UniAnimate"
],
"install_type": "git-clone",
"description": "a comfyui custom node for [a/UniAnimate](https://github.com/ali-vilab/UniAnimate)"
},
{
"author": "AIFSH",
"title": "ComfyUI-Hallo",
"id": "hallo",
"reference": "https://github.com/AIFSH/ComfyUI-Hallo",
"files": [
"https://github.com/AIFSH/ComfyUI-Hallo"
],
"install_type": "git-clone",
"description": "a comfyui custom node for [a/hallo](https://github.com/fudan-generative-vision/hallo)"
},
{
"author": "superyoman",
"title": "comfyui_lumaAPI",
"id": "luma",
"reference": "https://github.com/superyoman/comfyui_lumaAPI",
"files": [
"https://github.com/superyoman/comfyui_lumaAPI"
],
"install_type": "git-clone",
"description": "Unofficial Luma API-ComfyUI version.[w/WARN: This project is for learning purpose only!]"
},
{
"author": "nuanarchy",
"title": "ComfyUI-NuA-BIRD",
"id": "nua-bird",
"reference": "https://github.com/nuanarchy/ComfyUI-NuA-BIRD",
"files": [
"https://github.com/nuanarchy/ComfyUI-NuA-BIRD"
],
"install_type": "git-clone",
"description": "ComfyUI implementation of '[a/Blind Image Restoration via Fast Diffusion Inversion](https://github.com/hamadichihaoui/BIRD)' Original [a/article](https://arxiv.org/abs/2405.19572)"
},
{
"author": "SuperMasterBlasterLaser",
"title": "ComfyUI_YOLO_Classifiers",
"id": "yolo-classifier",
"reference": "https://github.com/SuperMasterBlasterLaser/ComfyUI_YOLO_Classifiers",
"files": [
"https://github.com/SuperMasterBlasterLaser/ComfyUI_YOLO_Classifiers"
],
"install_type": "git-clone",
"description": "Nodes:YOLO Classifier Model Loader, YOLO Classify."
},
{
"author": "kijai",
"title": "ComfyUI-B-LoRA",
"id": "b-lora",
"reference": "https://github.com/liusida/ComfyUI-B-LoRA",
"files": [
"https://github.com/liusida/ComfyUI-B-LoRA"
],
"install_type": "git-clone",
"description": "Load and apply B-LoRA models, currently B-LoRA models only works with SDXL (sdxl_base_1.0)."
},
{
"author": "koopke",
"title": "ComfyUI-websocket-data-channel",
"id": "websocket-data-channel",
"reference": "https://github.com/koopke/ComfyUI-websocket-data-channel",
"files": [
"https://github.com/koopke/ComfyUI-websocket-data-channel"
],
"install_type": "git-clone",
"description": "Sending Data from a ComfyUI workflow to the websocket."
},
{
"author": "baicai99",
"title": "ComfyUI-FrameSkipping",
"id": "FrameSkipping",
"reference": "https://github.com/baicai99/ComfyUI-FrameSkipping",
"files": [
"https://github.com/baicai99/ComfyUI-FrameSkipping"
],
"install_type": "git-clone",
"description": "Used to process video redrawing, frame skipping, frame ending early, etc."
},
{
"author": "AIFSH",
"title": "ComfyUI-MimicBrush",
"id": "mimicbrush",
"reference": "https://github.com/AIFSH/ComfyUI-MimicBrush",
"files": [
"https://github.com/AIFSH/ComfyUI-MimicBrush"
],
"install_type": "git-clone",
"description": "a comfyui custom node for [a/MimicBrush](https://github.com/ali-vilab/MimicBrush),then inpainting with reference image."
},
{
"author": "dicksondickson",
"title": "ComfyUI-Dickson-Nodes",
"id": "dicksonnodes",
"reference": "https://github.com/dicksondickson/ComfyUI-Dickson-Nodes",
"files": [
"https://github.com/dicksondickson/ComfyUI-Dickson-Nodes"
],
"install_type": "git-clone",
"description": "Custom nodes for ComfyUI by DicksonDickson."
},
{
"author": "G-370",
"title": "ComfyUI-SD3-Powerlab",
"id": "sd3-powerlab",
"reference": "https://github.com/G-370/ComfyUI-SD3-Powerlab",
"files": [
"https://github.com/G-370/ComfyUI-SD3-Powerlab"
],
"install_type": "git-clone",
"description": "Nodes:Render SD3 Attention, SD3 Attention To Image, SD3 Image Into Attention."
},
{
"author": "TylerZoro",
"title": "SD3-Scaling",
"id": "sd3-scaling",
"reference": "https://github.com/TylerZoro/SD3-Scaling",
"files": [
"https://github.com/TylerZoro/SD3-Scaling"
],
"install_type": "git-clone",
"description": "Tools for scaling images and latents appropriate to SD3 in ComfyUI."
},
{
"author": "ShmuelRonen",
"title": "ComfyUI_Gemini_Flash",
"id": "gemini-flash",
"reference": "https://github.com/ShmuelRonen/ComfyUI_Gemini_Flash",
"files": [
"https://github.com/ShmuelRonen/ComfyUI_Gemini_Flash"
],
"install_type": "git-clone",
"description": "ComfyUI_Gemini_Flash is a custom node for ComfyUI, integrating the capabilities of the Gemini 1.5 Flash model. This node supports text and vision-based prompts, allowing users to analyze and adapt images to text prompts for text2image tasks."
},
{
"author": "nagolinc",
"title": "comfyui_openai_node",
"reference": "https://github.com/nagolinc/comfyui_openai_node",
"files": [
"https://github.com/nagolinc/comfyui_openai_node"
],
"install_type": "git-clone",
"description": "This provides a single node openai > Open AI query node\nthat takes a system prompt and user message and sends them to chatGPT 3.5\nNote, you MUST have an OPEN AI API key stored in the environment variable OPENAI_API_KEY in order for this to work."
},
{
"author": "juehackr",
"title": "comfyui_fk_server",
"id": "fk-server",
"reference": "https://github.com/juehackr/comfyui_fk_server",
"files": [
"https://github.com/juehackr/comfyui_fk_server"
],
"install_type": "git-clone",
"description": "🤗🤗🤗Comfyui Universal Translation Plugin (no longer requires adding various nodes, directly add translation function on the existing nodes), allowing Comfyui to support Chinese input and automatic translation for any long text input box, while adding error translation function (calling Baidu Translate), achieving translation freedom!"
},
{
"author": "Yanick112",
"title": "ComfyUI-ToSVG",
"id": "tosvg",
"reference": "https://github.com/Yanick112/ComfyUI-ToSVG",
"files": [
"https://github.com/Yanick112/ComfyUI-ToSVG"
],
"install_type": "git-clone",
"description": "This project converts raster images into SVG format using the [a/VTracer](https://github.com/visioncortex/vtracer) library. It's a handy tool for designers and developers who need to work with vector graphics programmatically."
},
{
"author": "logtd",
"title": "ComfyUI-FLATTEN",
"id": "flatten",
"reference": "https://github.com/logtd/ComfyUI-FlattenFlow",
"files": [
"https://github.com/logtd/ComfyUI-FlattenFlow"
],
"install_type": "git-clone",
"description": "An alternate trajectory processor for ComfyUI-FLATTEN\nNOTE:When using this trajectory type FLATTEN will use roughly 1/4 VRAM and be ~20% faster at the cost of some consistency (especially when injection_steps are low)."
},
{
"author": "toxicwind",
"title": "TTools for ComfyUI",
"id": "ttools",
"reference": "https://github.com/toxicwind/ComfyUI-TTools",
"files": [
"https://github.com/toxicwind/ComfyUI-TTools"
],
"install_type": "git-clone",
"description": "Text Randomization and Formatting, JSON Extraction and Processing, SD3 Resolution Solver"
},
{
"author": "ljleb",
"title": "Mecha Merge Node Pack",
"id": "mecha",
"reference": "https://github.com/ljleb/comfy-mecha",
"files": [
"https://github.com/ljleb/comfy-mecha"
],
"install_type": "git-clone",
"description": "Model merging node pack with a focus on low memory footprint."
},
{
"author": "Michael Standen",
"title": "Ollama Prompt Encode",
"id": "ollamapromptencode",
"reference": "https://github.com/ScreamingHawk/comfyui-ollama-prompt-encode",
"files": [
"https://github.com/ScreamingHawk/comfyui-ollama-prompt-encode"
],
"install_type": "git-clone",
"description": "A prompt generator and CLIP encoder using AI provided by Ollama."
},
{
"author": "smthemex",
"title": "ComfyUI_Pops",
"id": "pops",
"reference": "https://github.com/smthemex/ComfyUI_Pops",
"files": [
"https://github.com/smthemex/ComfyUI_Pops"
],
"install_type": "git-clone",
"description": "You can use [a/Popspaper](https://popspaper.github.io/pOps/) method in comfyUI"
},
{
"author": "Late Night Labs",
"title": "LNL Frame Selector",
"id": "lnlframeselector",
"reference": "https://github.com/latenightlabs/ComfyUI-LNL",
"files": [
"https://github.com/latenightlabs/ComfyUI-LNL"
],
"install_type": "git-clone",
"description": "Frame Selector & Sequence Selection Node for ComfyUI."
},
{
"author": "shobhitic",
"title": "PlusMinusTextClip - Single node for Positive and Negative Prompts",
"id": "plusminustextclip",
"reference": "https://github.com/shobhitic/ComfyUI-PlusMinusTextClip",
"files": [
"https://github.com/shobhitic/ComfyUI-PlusMinusTextClip"
],
"install_type": "git-clone",
"description": "This adds a node that has both the positive and negative prompts as input in one node. You can just add one node and be done with both Positive and Negative prompts, in place of adding two different nodes for them."
},
{
"author": "huchenlei",
"title": "ComfyUI_omost",
"id": "omost",
"reference": "https://github.com/huchenlei/ComfyUI_omost",
"files": [
"https://github.com/huchenlei/ComfyUI_omost"
],
"install_type": "git-clone",
"description": "ComfyUI implementation of [a/Omost](https://github.com/lllyasviel/Omost), and everything about regional prompt.\nNOTE: You need to install ComfyUI_densediffusion to use this node."
},
{
"author": "huchenlei",
"title": "ComfyUI DenseDiffusion",
"id": "densediffusion",
"reference": "https://github.com/huchenlei/ComfyUI_densediffusion",
"files": [
"https://github.com/huchenlei/ComfyUI_densediffusion"
],
"install_type": "git-clone",
"description": "[a/DenseDiffusion](https://github.com/naver-ai/DenseDiffusion) custom node for ComfyUI."
},
{
"author": "ZHO-ZHO-ZHO",
"title": "ComfyUI-Qwen-2",
"id": "qwen-2",
"reference": "https://github.com/ZHO-ZHO-ZHO/ComfyUI-Qwen-2",
"files": [
"https://github.com/ZHO-ZHO-ZHO/ComfyUI-Qwen-2"
],
"install_type": "git-clone",
"description": "Using Qwen-2 in ComfyUI"
},
{
"author": "BenNarum",
"title": "SigmaWaveFormNodes",
"id": "sigmawaveform",
"reference": "https://github.com/BenNarum/SigmaWaveFormNode",
"files": [
"https://github.com/BenNarum/SigmaWaveFormNode"
],
"install_type": "git-clone",
"description": "A set of tools for generating and altering sigmas in ComfyUI."
},
{
"author": "alessandrozonta",
"title": "OpenPose Node",
"id": "openpose-alessandrozonta",
"reference": "https://github.com/alessandrozonta/ComfyUI-OpenPose",
"files": [
"https://github.com/alessandrozonta/ComfyUI-OpenPose"
],
"install_type": "git-clone",
"description": "This extension contains a custom node for ComfyUI. The node, called 'Bounding Box Crop', is designed to compute the top-left coordinates of a cropped bounding box based on input coordinates and dimensions of the final cropped image. It does so computing the center of the cropping area and then computing where the top-left coordinates would be."
},
{
"author": "GavChap",
"title": "ComfyUI-SD3LatentSelectRes",
"id": "sd3latent-select-res",
"reference": "https://github.com/GavChap/ComfyUI-SD3LatentSelectRes",
"files": [
"https://github.com/GavChap/ComfyUI-SD3LatentSelectRes"
],
"install_type": "git-clone",
"description": "You'll get a new node called SD3 Latent Select Resolution, you can pick the x and y sizes from a list."
},
{
"author": "Jin Liu",
"title": "ComfyUI-LJNodes",
"id": "ComfyUI-LJNodes",
"reference": "https://github.com/coolzilj/ComfyUI-LJNodes",
"files": [
"https://github.com/coolzilj/ComfyUI-LJNodes"
],
"install_type": "git-clone",
"description": "A variety of custom nodes to enhance ComfyUI for a buttery smooth experience."
},
{
"author": "marduk191",
"title": "marduk191 workflow settings",
"id": "marnodes",
"reference": "https://github.com/marduk191/comfyui-marnodes",
"files": [
"https://github.com/marduk191/comfyui-marnodes"
],
"install_type": "git-clone",
"description": "A node to set workflow settings."
},
{
"author": "denfrost",
"title": "Den_ComfyUI_Workflows",
"id": "den",
"reference": "https://github.com/denfrost/Den_ComfyUI_Workflow",
"files": [
"https://github.com/denfrost/Den_ComfyUI_Workflow"
],
"install_type": "git-clone",
"description": "Custom nodes make easy Advanced Workflows. Focus on Image/Video and ControlNet efficiency and performances. Manipulation of Latent Space, Automatic pipeline with a bit efforts."
},
{
"author": "seghier",
"title": "ComfyUI_LibreTranslate",
"reference": "https://github.com/seghier/ComfyUI_LibreTranslate",
"files": [
"https://github.com/seghier/ComfyUI_LibreTranslate/raw/main/translate_node.py"
],
"install_type": "copy",
"description": "Use LibreTranslation in ComfyUI [a/https://github.com/LibreTranslate/LibreTranslate](https://github.com/LibreTranslate/LibreTranslate)"
},
{
"author": "Limbicnation",
"title": "ComfyUIDepthEstimation",
"reference": "https://github.com/Limbicnation/ComfyUIDepthEstimation",
"files": [
"https://github.com/Limbicnation/ComfyUIDepthEstimation/raw/main/depth_estimation_node.py"
],
"pip": ["transformers"],
"install_type": "copy",
"description": "A custom depth estimation node for ComfyUI using transformer models. It integrates depth estimation with automatic gamma correction, contrast adjustment, and edge detection, based on the [a/TransformDepth](https://github.com/Limbicnation/TransformDepth) repository."
},
{
"author": "shadowcz007",
"title": "comfyui-sound-lab",
"id": "soundlab",
"reference": "https://github.com/shadowcz007/comfyui-sound-lab",
"files": [
"https://github.com/shadowcz007/comfyui-sound-lab"
],
"install_type": "git-clone",
"description": "Nodes:Music Gen, Audio Play, Stable Audio"
},
{
"author": "DannyStone1999",
"title": "ComfyUI-Depth2Mask",
"reference": "https://github.com/DannyStone1999/ComfyUI-Depth2Mask",
"files": [
"https://github.com/DannyStone1999/ComfyUI-Depth2Mask/raw/main/Depth2Mask.py"
],
"install_type": "copy",
"description": "Nodes:Depth2Mask"
},
{
"author": "smthemex",
"title": "ComfyUI_StableAudio_Open",
"id": "stable-audio-open-1.0",
"reference": "https://github.com/smthemex/ComfyUI_StableAudio_Open",
"files": [
"https://github.com/smthemex/ComfyUI_StableAudio_Open"
],
"install_type": "git-clone",
"description": "You can use stable-audio-open-1.0 in comfyUI"
},
{
"author": "nuanarchy",
"title": "ComfyUI-NuA-FlashFace",
"id": "nua-flashface",
"reference": "https://github.com/nuanarchy/ComfyUI-NuA-FlashFace",
"files": [
"https://github.com/nuanarchy/ComfyUI-NuA-FlashFace"
],
"install_type": "git-clone",
"description": "ComfyUI implementation of [a/FlashFace: Human Image Personalization with High-fidelity Identity Preservation](https://github.com/ali-vilab/FlashFace)\nNOTE: You need to downalod models manually."
},
{
"author": "FrankChieng",
"title": "ComfyUI_llm_easyanimiate",
"id": "llm-easyanimate",
"nodename_pattern": "^FrankChiengEasyAnimate",
"reference": "https://github.com/frankchieng/ComfyUI_llm_easyanimiate",
"files": [
"https://github.com/frankchieng/ComfyUI_llm_easyanimiate"
],
"install_type": "git-clone",
"description": "implementation easyanimate with llama3-8b-6bit instruction LLM generation prompt help"
},
{
"author": "chakib-belgaid",
"title": "ComfyUI-autosize",
"id": "autosize",
"reference": "https://github.com/chakib-belgaid/ComfyUI-autosize",
"files": [
"https://github.com/chakib-belgaid/ComfyUI-autosize"
],
"install_type": "git-clone",
"description": "A ComfyUI utility plugin designed to optimize the latent space for generating high-quality results. It approximates the closest size model for better generation results."
},
{
"author": "DataCTE",
"title": "Prompt Injection Node for ComfyUI",
"id": "prompt-injection",
"reference": "https://github.com/DataCTE/prompt_injection",
"files": [
"https://github.com/DataCTE/prompt_injection"
],
"install_type": "git-clone",
"description": "This custom node for ComfyUI allows you to inject specific prompts at specific blocks of the Stable Diffusion UNet, providing fine-grained control over the generated image. It is based on the concept that the content/subject understanding of the model is primarily contained within the MID0 and MID1 blocks, as demonstrated in the B-Lora (Content Style implicit separation) paper. Features.\nInject different prompts into specific UNet blocks Three different node variations for flexible workflow integration Customize the learning rate of specific blocks to focus on content, lighting, style, or other aspects Potential for developing a 'Mix of Experts' approach by swapping blocks on-the-fly based on prompt content"
},
{
"author": "lks-ai",
"title": "ComfyUI Stable Audio Open 1.0 Sampler",
"id": "stableaudiosampler",
"reference": "https://github.com/lks-ai/ComfyUI-StableAudioSampler",
"files": [
"https://github.com/lks-ai/ComfyUI-StableAudioSampler"
],
"install_type": "git-clone",
"description": "Nodes: StableAudioSampler. Wraps the new Stable Audio Open Model in the sampler that dropped Jun 5th. See Github for Features"
},
{
"author": "luandev",
"title": "ComfyUI CrewAI",
"id": "crewai",
"reference": "https://github.com/luandev/ComfyUI-CrewAI",
"files": [
"https://github.com/luandev/ComfyUI-CrewAI"
],
"install_type": "git-clone",
"description": "ComfyUI-CrewAI aims to integrate Crew AI's multi-agent collaboration framework into the ComfyUI environment. By combining the strengths of Crew AI's role-based, collaborative AI agent system with ComfyUI's intuitive interface, we will create a robust platform for managing and executing complex AI tasks seamlessly"
},
{
"author": "Tool Of North america",
"title": "Easy automatic (square) image cropper using Yolo",
"id": "tooldigital",
"reference": "https://github.com/tooldigital/ComfyUI-Yolo-Cropper",
"files": [
"https://github.com/tooldigital/ComfyUI-Yolo-Cropper"
],
"install_type": "git-clone",
"description": "A very simple and easy to use node to automaticaaly create (square) image crops and masks using YoloV8. This can be very useful when using controlnet and ip adapters"
},
{
"author": "11dogzi",
"title": "Comfyui-ergouzi-samplers",
"id": "ergouzi-samplers",
"reference": "https://github.com/11dogzi/Comfyui-ergouzi-samplers",
"files": [
"https://github.com/11dogzi/Comfyui-ergouzi-samplers"
],
"install_type": "git-clone",
"description": "Partial redraw sampler and variant seed sampler"
},
{
"author": "prodogape",
"title": "ComfyUI-OmDet",
"id": "omdet",
"reference": "https://github.com/prodogape/ComfyUI-OmDet",
"files": [
"https://github.com/prodogape/ComfyUI-OmDet"
],
"install_type": "git-clone",
"description": "This node is mainly based on [a/OmDet](https://github.com/om-ai-lab/OmDet) for object detection, and it outputs related images, masks, and Labelme JSON information."
},
{
"author": "risunobushi",
"title": "comfyUI_FrequencySeparation_RGB-HSV",
"id": "freq-sep",
"reference": "https://github.com/risunobushi/comfyUI_FrequencySeparation_RGB-HSV",
"files": [
"https://github.com/risunobushi/comfyUI_FrequencySeparation_RGB-HSV"
],
"install_type": "git-clone",
"description": "A collection of simple nodes for Frequency Separation / Frequency Recombine with RGB and HSV methods"
},
{
"author": "chandlergis",
"title": "ComfyUI_EmojiOverlay",
"id": "emoji-overlay",
"reference": "https://github.com/chandlergis/ComfyUI_EmojiOverlay",
"files": [
"https://github.com/chandlergis/ComfyUI_EmojiOverlay"
],
"install_type": "git-clone",
"description": "Nodes:Image Emoji Overlay"
},
{
"author": "JayLyu",
"title": "ComfyUI_BaiKong_Node",
"id": "baikong",
"reference": "https://github.com/JayLyu/ComfyUI_BaiKong_Node",
"files": [
"https://github.com/JayLyu/ComfyUI_BaiKong_Node"
],
"install_type": "git-clone",
"description": "Nodes:BK Img To Color, BK Color Selector"
},
{
"author": "zohac",
"title": "ComfyUI_ZC_DrawShape",
"id": "drawshape",
"reference": "https://github.com/zohac/ComfyUI_ZC_DrawShape",
"files": [
"https://github.com/zohac/ComfyUI_ZC_DrawShape"
],
"install_type": "git-clone",
"description": "Nodes:ZC DrawShape Node"
},
{
"author": "ThereforeGames",
"title": "ComfyUI-Unprompted",
"id": "unprompted",
"reference": "https://github.com/ThereforeGames/ComfyUI-Unprompted",
"files": [
"https://github.com/ThereforeGames/ComfyUI-Unprompted"
],
"install_type": "git-clone",
"description": "This is a ComfyUI node that processes your input text with the [a/Unprompted templating language](https://github.com/ThereforeGames/unprompted). Early alpha release.\n"
},
{
"author": "Scorpinaus",
"title": "Loaders for Diffusers-format checkpoints",
"id": "diffusersloader",
"reference": "https://github.com/Scorpinaus/ComfyUI-DiffusersLoader",
"files": [
"https://github.com/Scorpinaus/ComfyUI-DiffusersLoader"
],
"install_type": "git-clone",
"description": "This node pack allows loading of CLIP, MODEL, VAE aspects for both SD1.5 and SDXL checkpoints that is converted to diffusers format."
},
{
"author": "chakib-belgaid",
"title": "ComfyUI Style Plugin",
"id": "style-plugin",
"reference": "https://github.com/chakib-belgaid/Comfyui_Prompt_styler",
"files": [
"https://github.com/chakib-belgaid/Comfyui_Prompt_styler"
],
"install_type": "git-clone",
"description": "This is a simple plugin for ComfyUI that allows you to import A1111 CSV styles into ComfyUI prompts."
},
{
"author": "tiankuan93",
"title": "V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation",
"id": "v-express",
"reference": "https://github.com/tiankuan93/ComfyUI-V-Express",
"files": [
"https://github.com/tiankuan93/ComfyUI-V-Express"
],
"install_type": "git-clone",
"description": "[Original] In the field of portrait video generation, the use of single images to generate portrait videos has become increasingly prevalent. A common approach involves leveraging generative models to enhance adapters for controlled generation. However, control signals can vary in strength, including text, audio, image reference, pose, depth map, etc. Among these, weaker conditions often struggle to be effective due to interference from stronger conditions, posing a challenge in balancing these conditions. In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as pose and original image. However, direct training with weak signals often leads to difficulties in convergence. To address this, we propose V-Express, a simple method that balances different control signals through a series of progressive drop operations. Our method gradually enables effective control by weak conditions, thereby achieving generation capabilities that simultaneously take into account pose, input image, and audio.\nNOTE: You need to downdload [a/model_ckpts](https://huggingface.co/tk93/V-Express/tree/main) manually."
},
{
"author": "CMonk",
"title": "Stable Projectorz Bridge",
"id": "projectorz",
"reference": "https://github.com/tianlang0704/ComfyUI-StableProjectorzBridge",
"files": [
"https://github.com/tianlang0704/ComfyUI-StableProjectorzBridge"
],
"install_type": "git-clone",
"description": "This custom nodes enables Stable Projectorz to work with ComfyUI Directly."
},
{
"author": "comfyanonymous",
"title": "TensorRT Node for ComfyUI",
"id": "tensorrt",
"reference": "https://github.com/comfyanonymous/ComfyUI_TensorRT",
"files": [
"https://github.com/comfyanonymous/ComfyUI_TensorRT"
],
"install_type": "git-clone",
"description": "This node enables the best performance on NVIDIA RTX™ Graphics Cards (GPUs) for Stable Diffusion by leveraging NVIDIA TensorRT."
},
{
"author": "fexploit",
"title": "ComfyUI-Classifier",
"id": "classifier",
"reference": "https://github.com/fexploit/ComfyUI-Classifier",
"files": [
"https://github.com/fexploit/ComfyUI-Classifier"
],
"install_type": "git-clone",
"description": "ComfyUI-Classifier is a custom node for ComfyUI that uses a zero-shot classification model to classify text inputs based on a set of candidate labels. This node leverages the power of Hugging Face Transformers to provide accurate and flexible text classification."
}
]
}
Reference in New Issue View Git Blame Copy Permalink