ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
[a/PuLID](https://github.com/ToTheBeginning/PuLID) ComfyUI native implementation.
Film grain and color match nodes designed for high-quality frame-by-frame video enhancement in ComfyUI.
ComfyUI Wrapper for TRELLIS.2 - Microsoft's image-to-3D generation model. (Description by CC)
Custom ComfyUI Nodes for interacting with [a/Ollama](https://ollama.com/) using the [a/ollama python client](https://github.com/ollama/ollama-python). Integrate the power of LLMs into CompfyUI workflows easily.
Custom nodes introducing particle simulations, optical flow, audio manipulation & reactivity, and temporal masks
Custom nodes for easier use of SDXL in ComfyUI including an img2img workflow that utilizes both the base and refiner checkpoints.
A collection of utility nodes for Qwen-based image editing in ComfyUI.
A plugin offering supplementary Chinese translations for ComfyUI custom nodes.
[a/BizyAir](https://github.com/siliconflow/BizyAir) Comfy Nodes that can run in any environment.
ComfyUI custom nodes for refiners models
This extension provides various nodes to support Lora Block Weight and the Impact Pack. Provides many easily applicable regional features and applications for Variation Seed.
Unofficial implementation of BRIA RMBG Model for ComfyUI.
Unofficial implementation of [a/YOLO-World + EfficientSAM](https://huggingface.co/spaces/SkalskiP/YOLO-World) & [a/YOLO-World](https://github.com/AILab-CVC/YOLO-World) for ComfyUI NOTE: Install the efficient_sam model from the Install models menu. [w/When installing or updating this custom node, many installation packages may be downgraded due to the installation of requirements. !! python3.12 is incompatible.]
Lucy Edit is a video editing model that performs instruction-guided edits on videos using free-text prompts — it supports a variety of edits, such as clothing & accessory changes, character changes, object insertions, and scene replacements while preserving the motion and composition perfectly.
Running FlashVSR on lower VRAM without any artifacts.
Unofficial implementation of [a/PhotoMaker](https://github.com/TencentARC/PhotoMaker) for ComfyUI
This is an experimental project focused on Stable Diffusion (SD) models. In a single generated image, the same object or character consistently maintains a very high level of consistency. I had already attempted to address this issue in the SDXL model.
Using Gemini-pro & Gemini-pro-vision in ComfyUI.
Krea 2 Identity Edit — in-context instruction-edit nodes for the Krea 2 model: source-image appearance preservation (VAE reference tokens + 3D-RoPE), image-grounded instruction encoding, a reference-fidelity dial (ref_boost), and the training-matched FIT reference geometry.
A visual timeline and material planner for native MiniMax H3 video generation, with ordered image/video/audio references, editable Guides, prompt-planning integration, and long-video segment workflows.
NODES: An industrial-grade zero-shot text-to-speech synthesis system with a ComfyUI interface.
I love GoYounJung!Most Cheap API to my fans friedns!Bilibili:https://space.bilibili.com/385085361,website:https://ai.t8star.org/register?aff=dP7j
ComfyUI nodes for VFX professionals This extension provides GPU-accelerated nodes powered by Nvidia RTX technology, including super resolution, frame generation and SDR-to-HDR conversion.
NVIDIA RTX Nodes for ComfyUI\nThis extension provides GPU-accelerated nodes powered by NVIDIA RTX technology, including RTX Video Super Resolution.
ComfyUI node for background removal, implementing [a/InSPyReNet](https://github.com/plemeri/InSPyReNet)
AnimateDiff integration for ComfyUI, adapts from sd-webui-animatediff. [w/You only need to download one of [a/mm_sd_v14.ckpt](https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v14.ckpt) | [a/mm_sd_v15.ckpt](https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v15.ckpt). Put the model weights under %%ComfyUI/custom_nodes/comfyui-animatediff/models%%. DO NOT change model filename.]
AnimateDiff integration for ComfyUI, adapts from sd-webui-animatediff. [w/You only need to download one of [a/mm_sd_v14.ckpt](https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v14.ckpt) | [a/mm_sd_v15.ckpt](https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v15.ckpt). Put the model weights under %%ComfyUI/custom_nodes/comfyui-animatediff/models%%. DO NOT change model filename.]
NODES: Face Swap, Film Interpolation, Latent Lerp, Int To Number, Bounding Box, Crop, Uncrop, ImageBlur, Denoise, ImageCompare, RGV to HSV, HSV to RGB, Color Correct, Modulo, Deglaze Image, Smart Step, ...
The nodes detached from ComfyUI Layer Style are mainly those with complex requirements for dependency packages.
NODES:Joy Caption Two, Joy Caption Two Advanced, Joy Caption Two Load, Joy Caption Extra Options
A ComfyUI custom node implementing Spectrum spectral feature forecasting for native MiniMax H3 audio-video generation.
Audio Reactive nodes for AI animations 🔊 Analyze audio, extract drums, bass, vocals. Compatible with IPAdapter, ControlNets, AnimateDiff... Generate reactive masks and weights. Create audio-driven visuals. Produce weight graphs and audio masks. Ideal for music videos and reactive animations. Features audio scheduling and waveform analysis
This node was created to send a webcam to ComfyUI in real time. This node is recommended for use with LCM.
ComfyUI-IF_AI_tools is a set of custom nodes for ComfyUI that allows you to generate prompts using a local Large Language Model (LLM) via Ollama. This tool enables you to enhance your image generation workflow by leveraging the power of language models.
This node enables the best performance on NVIDIA RTX™ Graphics Cards (GPUs) for Stable Diffusion by leveraging NVIDIA TensorRT.
You can using EchoMimic in comfyui,please using pip install install miss module
Provides nodes and server API extensions geared towards using ComfyUI as a backend for external tools.
This is an image/video/workflow browser and manager for ComfyUI. You could add image/video/workflow to collections and load it to ComfyUI. You will be able to use your collections everywhere.
Separate audio track into stems (vocals, bass, drums, other). Along with tools to recombine, tempo match, slice/crop audio.
Wrapper nodes to use DynamiCrafter image2video and frame interpolation models in ComfyUI And this extension supports ToonCrafter as well
Fill-Nodes is a versatile collection of custom nodes for ComfyUI that extends functionality across multiple domains. Features include advanced image processing (pixelation, slicing, masking), visual effects generation (glitch, halftone, pixel art), comprehensive file handling (PDF creation/extraction, Google Drive integration), AI model interfaces (GPT, DALL-E, Hugging Face), utility nodes for workflow enhancement, and specialized tools for video processing, captioning, and batch operations. The pack provides both practical workflow solutions and creative tools within a unified node collection.
A custom node extension for ComfyUI that enables distributed image generation across multiple GPUs through a master-worker architecture.
This extension offers a new Apply-Style node for Redux that allows for changing the influence of the conditioning image on the final outcome. This effectively allows for changing the style or content of an image using a prompt while using Redux.
ComfyUI Lumi Batcher is a batch processing extension plugin designed for ComfyUI, aiming to improve workflow debugging efficiency. Traditional debugging methods require adjusting parameters one by one, while this tool significantly enhances work efficiency through batch processing capabilities.
ComfyUI nodes for Janus-Pro, a unified multimodal understanding and generation framework.
ComfyUI native implementation of [a/IC-Light](https://github.com/lllyasviel/IC-Light).
A general extension to utilize TIPO or DanTagGen to do 'text-presampling' based on KGen library: [a/https://github.com/KohakuBlueleaf/KGen](https://github.com/KohakuBlueleaf/KGen)
An enhanced Wan2.2 Image-to-Video node specifically designed to fix the slow-motion issue in 4-step LoRAs (like lightx2v).
pass up to 8 images and visually place, rotate and scale them to build the perfect composition. group move and group rescale. remember their position and scaling value across generations to easy swap images. use the buffer zone to to park an asset you don't want to use or easily reach transformations controls
Extract, save and combine reusable MiniMax H3 image, video and audio references as RefMod safetensors, with a unified Master extractor, library, inspector and strength curves.
DyPE for FLUX. Artifact-free 4K+ image generation.
4-step turbo sampler + LoRA loader for MiniMax-H3 joint video + audio generation.
AICG3D 短剧工作台:面向 MiniMax H3 的无限时长视频、智能分段、独立素材库与无缝合成 ComfyUI 工作流。
Recommended based on comfyui node pictures:Joy_caption + MiniCPMv2_6-prompt-generator + florence2
VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio
This extension offers various pipe nodes, extensive XYZ plotting, fullscreen image viewer based on node history, dynamic widgets, interface customization, and more.
Refine and improve the quality of small faces in MiniMax H3 video: per-frame face tracking, normalised crops, AV-latent injection and feathered stitch-back.
Conditioning enhancement node for FLUX.2 Klein 9B in ComfyUI. Controls prompt adherence and image edit behavior by modifying the active text embedding region.
ComfyUI adaptation of [a/IDM-VTON](https://github.com/yisol/IDM-VTON) for virtual try-on.
A selection of nodes for Stable Diffusion ComfyUI
Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.
implementation of MagicClothing with garment and prompt in ComfyUI
Custom Nodes for Vision Language Models (VLM) , Large Language Models (LLM), Image Captioning, Automatic Prompt Generation, Creative and Consistent Prompt Suggestion, Keyword Extraction
Rudimentary wrapper that runs [a/Kwai-Kolors](https://huggingface.co/Kwai-Kolors/Kolors) text2image pipeline using diffusers.
Run LLM/VLM models natively in ComfyUI based on llama.cpp
This is an implementation of [a/Qwen2-VL-Instruct](https://github.com/QwenLM/Qwen2-VL) by [a/ComfyUI](https://github.com/comfyanonymous/ComfyUI), which includes, but is not limited to, support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.
This is an implementation of [Qwen3-VL-Instruct](https://github.com/QwenLM/Qwen3-VL) by [ComfyUI](https://github.com/comfyanonymous/ComfyUI), which includes, but is not limited to, support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.
🤗🤗🤗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!
Quick connections, Circuit board connections
A free, open-source AI design canvas that runs fully on your own ComfyUI
ComfyUI integration for Meta's SAM3 model enabling open-vocabulary image segmentation using natural language text prompts, with automatic model download, geometric refinement, and flexible confidence thresholds.
A simple sidebar for ComfyUI.
Nodes to generate audio for vide with: [a/https://github.com/hkchengrex/MMAudio](https://github.com/hkchengrex/MMAudio)
Warning, uses experimental package `comfy-env` to attempt a one click isolated install. Will download and use pixi package manager. ComfyUI nodes for TRELLIS.2 - Microsoft's image-to-3D generation model. Generate high-quality 3D meshes with PBR materials from a single image. Models autodownload from HuggingFace.
Train, analyze, selectively load, and extract/merge LoRAs inside ComfyUI. Supports Z-Image, Qwen Image, Qwen Image Edit, SDXL, FLUX, FLUX Klein, Wan 2.2, and SD 1.5. Includes LoRA layer analyzers, selective block loaders, model layer editors, and text-encoder debiasing/inspection tools.
Multi-frame reference conditioning nodes for Wan2.2 A14B I2V models.
Implementation of Kolors on ComfyUI Reference from [a/https://github.com/kijai/ComfyUI-KwaiKolorsWrapper](https://github.com/kijai/ComfyUI-KwaiKolorsWrapper) Using ComfyUI Native Sampling
Flow is a custom node designed to provide a more user-friendly interface for ComfyUI by acting as an alternative user interface for running workflows. It is not a replacement for workflow creation. Flow is currently in the early stages of development, so expect bugs and ongoing feature enhancements. With your support and feedback, Flow will settle into a steady stream.
Recursive MiniMax H3 scene loops with motion and audio continuity, visual planning, review gates, atomic checkpoints, resume, and final video assembly.
This is a wrapper node for Marigold depth estimation: [https://github.com/prs-eth/Marigold](https://github.com/kijai/ComfyUI-Marigold). Currently using the same diffusers pipeline as in the original implementation, so in addition to the custom node, you need the model in diffusers format. NOTE: See details in repo to install.
ComfyUI custom nodes for OmniVoice TTS | voice clone, multi-speaker, voice design, text-to-speech
The successful integration of Qwen3-VL-Instruct series into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to) text-based queries, video queries, single-image queries, and multi-image queries for generating captions or responses.
Improved AnimateAnyone implementation that allows you to use the opse image sequence and reference image to generate stylized video. The current goal of this project is to achieve desired pose2video result with 1+FPS on GPUs that are equal to or better than RTX 3080!🚀 [w/The torch environment may be compromised due to version issues as some torch-related packages are being reinstalled.]
quickly use the prompt word tool in ComfyUI
This extension uses [a/DLib](http://dlib.net/) to calculate the Euclidean and Cosine distance between two faces. NOTE: Install the Shape Predictor, Face Recognition model from the Install models menu.
Prompt Visualization | Art Gallery [w/WARN: Installation requires 2GB of space, and it will involve a long download time.]
Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️
IndexTTS Voice Cloning Nodes for ComfyUI. High-quality voice cloning, very fast, supports Chinese and English, and allows custom voice styles.
ComfyUI nodes for WanAnimate input processing
Nodes: Ollama, Green Screen to Transparency, Save image for Bjornulf LobeChat, Text with random Seed, Random line from input, Combine images (Background+Overlay alpha), Image to grayscale (black & white), Remove image Transparency (alpha), Resize Image, ...
Custom nodes for various visual generation and editing tasks using Scepter.
Conditioning optimizer nodes with per layer weighting that offers IP-Adapter-like features for Krea 2 image reference editing along with bypassing the built in quality diluation from the trained safety filter and also works as a means to unfilter the model.
A set of evolving nodes that balance ComfyUI for the best user experience. foundational: Omni Node, Input, Load Images, Load Image Newest, Load Image Full, Color Image, Concatenate, String (Inline), String to List, List String Index, Float Exact, Float 1.00, Float 10.00, Any, Switch utility: Image Resolution Cap, Image Aspect Ratio Crop, Mask Aspect Ratio Crop, Mask Uncrop, Image Uncrop, Border Mask, Mask Opacity, conditioning: Conditioning Merge, Conditioning Merge Multi, Qwen VL List Encode Rebalance, Conditioning Freeze, Conditioning Unfreeze model specific: Load LoRA (Block), Conditioning Krea 2 Rebalance, Krea 2 Edit Rebalance, Krea 2 Encode Rebalance, Conditioning Ideogram 4 Rebalance, Ideogram 4 Edit Rebalance, Ideogram 4 Encode Rebalance
This is a custom node that lets you use TripoSR right from ComfyUI. [a/TripoSR](https://github.com/VAST-AI-Research/TripoSR) is a state-of-the-art open-source model for fast feedforward 3D reconstruction from a single image, collaboratively developed by Tripo AI and Stability AI. (TL;DR it creates a 3d model from an image.)
The extension enables large image drawing & upscaling with limited VRAM via the following techniques: 1.Two SOTA diffusion tiling algorithms: [a/Mixture of Diffusers](https://github.com/albarji/mixture-of-diffusers) and [a/MultiDiffusion](https://github.com/omerbt/MultiDiffusion) 2.pkuliyi2015's Tiled VAE algorithm.
Nodes: AnyNode. Nodes that can be anything you ask. Auto-Generate functional nodes using LLMs. Create impossible workflows. API Compatibility: (OpenAI, LocalLLMs, Gemini).
If you see this message, your ComfyUI-Manager is outdated. Recent channel provides only the list of the latest nodes. If you want to find the complete node list, please go to the Default channel. Making LoRA has never been easier!
This extension aims to add support for various random image diffusion models to ComfyUI.
Nodes to use Florence2 VLM for image tagging and captioning
MiniMax H3 character-sheet prompt and layout designer for ComfyUI with selectable multi-view panels, deterministic Ref2VA prompts, automatic output sizing, and a local graphical UI.