ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
The Wav2Lip node is a custom node for ComfyUI that allows you to perform lip-syncing on videos using the Wav2Lip model. It takes an input video and an audio file and generates a lip-synced output video.
An all-in-one, multi-pass generative upscaling and post-processing node designed to simplify complex workflows and add a professional finish to your images.
Calculate the execution time of all nodes.
A Text To Speech node using Step-Audio-TTS in ComfyUI. Can speak, rap, sing, or clone voice.
A custom node for ComfyUI designed to facilitate the real-time transmission of rendered images, videos, or 3D models to TouchDesigner.
Preliminary use of SVD in ComfyUI. NOTE: Quick Implementation, Unstable. See details on repositories.
A ComfyUI custom node extension integrating Meta's Segment Anything Model 3 (SAM 3) for advanced image and video segmentation with text-prompt, point-based, and mask-driven capabilities. Provides production-ready nodes compatible with ComfyUI's Impact Pack SEGS format, depth map generation, and support for Python 3.13+ with CUDA and CPU support.
A prompt-generator or prompt-improvement node for ComfyUI, utilizing the power of a language model to turn a provided text-to-image prompt into a more detailed and improved prompt.
FreeLong spectral blending for consistent motion and prompt adherence in Wan 2.2 video generation with chunked generation support.
A ComfyUI node for 3D lighting angle control, outputs lighting prompts for relighting image generation
Powerful ComfyUI custom node built on the FlashVSR model, facilitating real-time diffusion-based video super-resolution for streaming applications.
Comfy Nodes that make utilizing resources from Civitas easy as copying and pasting
Run FP8 and INT8 quantized models (FLUX, SD3.5, Ideogram 4, Krea2) on Apple Silicon / MPS — compatibility fixes plus bit-exact fp8/int8 Metal matmul kernels, plus a psutil fix for recent macOS betas.
[a/SongGeneration](https://github.com/tencent-ailab/SongGeneration):High-Quality Song Generation with Multi-Preference Alignment (SOTA),you can try VRAM>12G
Upscaling stable diffusion latents using a small neural network.
Port of [a/https://github.com/huchenlei/sd-webui-openpose-editor](https://github.com/huchenlei/sd-webui-openpose-editor) in ComfyUI
ComfyUI InstantMesh is custom nodes that running InstantMesh into ComfyUI
Node to use [a/DDColor](https://github.com/piddnad/DDColor) in ComfyUI.
Nodes to generate noise from video for https://github.com/Eyeline-Research/Go-with-the-Flow
This project implements the comfyui for long-clip, currently supporting the replacement of clip-l. For SD1.5, the SeaArtLongClip module can be used to replace the original clip in the model, expanding the token length from 77 to 248.
A very simple ComfyUI node to remove item with mask.
About TBG Enhanced Tiled Upscaler and Refiner Pro! We at TBG Think. Build. Generate. Pro AI upscaling & image enrichment are excited to make our TBG Enhanced Tiled Upscaler and Refiner Pro available to you for free non-commercial use. We believe in empowering creators and innovators, which is why anything you create or generate using our software
Jerry Davos Custom Nodes for Saving Latents in Directory (BatchLatentSave) , Importing Latent from directory (BatchLatentLoadFromDir) , List to string, string to list, get any file list from directory which give filepath, filename, move any files from any directory to any other directory, VHS Video combine file mover, rebatch list of strings, batch image load from any dir, load image batch from any directory and other custom nodes.
A MiniMax H3 video studio inside ComfyUI, with inspectable prompts, official H3 workflow generation, segment planning, and a built-in clip editor.
Turn a description into a finished MiniMax H3 video without leaving ComfyUI, prompt, segments, continuity and final cut in one workbench.
Scan workflows for required models and download them automatically from HuggingFace, CivitAI, and other sources. Features include filter dropdowns, Tavily AI-powered advanced search, metadata caching, and automatic URL restoration.
Creating subgraph and Calling subgraphs.
a wrap-up of ComfyUI nodes for converting pixels to raster, sent out to [a/Vtracer](https://github.com/visioncortex/vtracer)!
ComfyUI Implementaion of ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
[a/DenseDiffusion](https://github.com/naver-ai/DenseDiffusion) custom node for ComfyUI.
Professional audio processing and mastering suite for ComfyUI.
Enhanced features with flexible choice of inputs and outputs, fine control for pose plotting, freedom to composite poses and fast local pose editting.
一个打包comfyui节点,用于把像素转矢量 a wrap-up comfyui nodes for concerting pix to raster
Run Local and API LLMs, Features Conditioning manipulation via Omost, supports Ollama, LlamaCPP LMstudio, Koboldcpp, TextGen, Transformers or via APIs Anthropic, Groq, OpenAI, Google Gemini, Mistral, xAI and create your own charcters assistants (SystemPrompts) with custom presets and muchmore
Breeze TTS 2 nodes for ComfyUI: voice clone, voice design, and voice direction with INT8 ConvRot support.
This repository provides a temporary ComfyUI node implementation of the Stand-In preprocessor, aiming to correct the misunderstanding of Stand-In’s preprocessing logic in [a/ComfyUI-WanVideoWrapper](https://github.com/kijai/ComfyUI-WanVideoWrapper). [w/We strongly recommend using the workflows provided in this repo to ensure proper compatibility and the best identity-preserving performance.]
A ComfyUI node that intelligently composites a generated (AI-edited) image back onto an original image by detecting only what actually changed between the two images and blending the generated content in cleanly.
Save as AVIF, WebP, JPEG, customize the folder, sub-folders, and filenames of your images!
ComfyUI MuseV
FL AceStep Training - LoRA Training nodes for ACE-Step 1.5 in ComfyUI
This is a custom node that lets you use Convolutional Reconstruction Models right from ComfyUI. [a/CRM](https://ml.cs.tsinghua.edu.cn/~zhengyi/CRM/) is a high-fidelity feed-forward single image-to-3D generative model.
Kytra's MatAnyone (Video Matting) implementation for ComfyUI - Based on pq-yang/MatAnyone
One node for AI video and stills across seven model families: MiniMax H3, LTX 2.5, Krea 2, Ideogram 4.0, Qwen Image Edit, Flux 2 Klein and Qwen Image 2.1. Write a prompt, attach media with @, press Render. Everything renders locally from open weights. The optional prompt refiner can run in-process or on your own server or API provider.
One node for MiniMax H3 video, one shot or twenty: write a sentence, attach media with @, press Run — get a finished clip with sound. Local open weights only, no API key.
A ComfyUI custom node for MiniCPM vision-language models, enabling high-quality image captioning and analysis.
Paint on the first frame of a plate to erase, add or relight, watch the edit carry through the shot, and export it in the plate's own format, layers and untouched pixels.
Better TAESD previews, BlehHyperTile.
This is a simple implementation StreamDiffusion(A Pipeline-Level Solution for Real-Time Interactive Generation) for ComfyUI
Multi-reference and scheduled SCAIL-2 workflow helpers for ComfyUI.
Qwen3 TTS for ComfyUI - High-quality text-to-speech with voice cloning, voice design, and custom voices
CRT-Nodes is a collection of custom nodes for ComfyUI
Supported by anima_lora trainer daemon, this introduces simplified comfyui ui for training in background.
This extension provides various utility nodes. Inputs(prompt, styles, dynamic, merger, ...), Outputs(style pile), Dashboard(selectors, loader, switch, ...), Networks(LORA, Embedding, Hypernetwork), Visuals(visual selectors, )
FL CosyVoice3 - Advanced Text-to-Speech nodes for ComfyUI. Features zero-shot voice cloning, cross-lingual synthesis, instruction-based control, and voice conversion using the CosyVoice3 model family. Supports 9 languages and 18+ Chinese dialects with automatic model downloading and caching.
ComfyUI-FreeMemory is a custom node extension for ComfyUI that provides advanced memory management capabilities within your image generation workflows. It aims to help prevent out-of-memory errors and optimize resource usage during complex operations.
Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation. A node for ComfyUI.
Custom Node for comfyUI for virtual lighting based on normal map. You can use normal maps to add virtual lighting effects to your images.
Encapsulate the commonly used functions of FFmpeg into ComfyUI nodes, making it convenient for users to perform various video processing tasks within ComfyUI.
A universal swap node that supports ComfyUI native workflow, allowing 4_6G users to experience Klein9B or other large models
Generate MiniMax H3 prompts and general multimodal Qwen answers locally in ComfyUI.
ComfyUI nodes for ID-LoRA-2.3 one-stage audio+video generation with speaker identity transfer
A ComfyUI extension providing nodes for generating 3D models from images and rendering/visualizing 3D assets within your workflow.
This repository provides a custom ComfyUI node for running object detection with the [a/Qwen 2.5 VL](https://github.com/QwenLM/Qwen2.5-VL) model. The node downloads the selected model on demand, runs a detection prompt and outputs bounding boxes that can be used with segmentation nodes such as [a/SAM2](https://github.com/kijai/ComfyUI-segment-anything-2).
A project for pose alignment and human body proportion mapping based on SDPose.
All-in-one Civitai integration center for ComfyUI — browse online models, manage local assets,analyze community trends, and instantly apply full recipes within your workflow.
A ComfyUI workflow customization by Jake.
ComfyUI wrapper nodes to use the Diffusers implementation of BrushNet
Divide and Conquer Node Suite: It calculates the optimal upscale resolution and seamlessly divides the image into tiles, ready for individual processing using your preferred workflow. After processing, the tiles are seamlessly merged into a larger image, offering sharper and more detailed visuals.
Custom nodes to improve flow control and logic + several utilities to enhance capabilities
A comfyui node that provides translation and image reverse push functions(JoyTag & JoyCaption).
ComfyUI Qwen2-VL wrapper that supports text-based and single-image queries.
Better user experience plugin for ComfyUI.
Additional UI focused on inference. Stable UI states; presets; and advanced queue. Based on Gradio
An execution-scoped F1B0 residual block cache for ComfyUI's native MiniMax H3 model.
Nodes: Checkpoint Loader with Name, Save Prompt Info, Outpaint to Image, CLIP Positive-Negative, SDXL Quick Empty Latent, Empty Latent by Ratio, Time String, SDXL Steps, SDXL Resolutions ...
The Ultimate Local File Manager for Images, Videos, and Audio in ComfyUI
An easy-to-use ComfyUI plugin for LLM integration supporting DeepSeek, OpenAI API-compatible models, with video reverse-prompt (captioning) capabilities. (Description by CC)
The official ComfyUI version of facechain greatly improves the speed of reasoning and has great custom process controls.
Unofficial implementation of [a/UltraEdit](https://github.com/HaozheZhao/UltraEdit) (Diffusers) for ComfyUI
Instantly explore Civitai community hits for your local AI models and apply full recipes with one click — or dive deep to uncover the best prompts, parameters, and LoRA combos.
ComfyUI custom node of OmniGen project.
ComfyUI plugin that integrates Pascal 3D architectural editor
Extension to show random cat GIFs while queueing prompt.
Warning, uses experimental package `comfy-env` to attempt a one click isolated install. Will download and use pixi package manager. ComfyUI wrapper for LiTo: single-image to 3D Gaussian Splat generation
ComfyUI nodes for Viggle-Animate (MiniMax-H3 ref2va finetune): character replacement in video from a driving clip and a reference still
Nodes:Music Gen, Audio Play, Stable Audio
A reference-aware MiniMax H3 still-image studio for ComfyUI
Multi-artist mixing for Anima through cross-attention or post-adapter embedding projection.
Bundle multiple wires into one wire. Create customizable Presets nodes. Compose ref images in one node. ComfyUI nodes to save time and keep your workflows tidy.
Multi-segment MiniMax H3 video director for ComfyUI with continuity, selective reruns, asset management, post-processing, and live preview.
Nodes:LCMScheduler, SamplerLCMAlternative, SamplerLCMCycle. ComfyUI Custom Sampler nodes that add a new improved LCM sampler functions
An advanced Assets manager for ComfyUI outputs with gallery, metadata inspection, ratings, and tags.
Implement Region Attention for Flux model. Add node RegionAttention that takes a regions - mask + condition, mask could be set from comfyui masks or bbox in FluxRegionBBOX node. This code is not optimized and has a memory leak. If you caught a OOM just try run a query againg - works on my RTX3080. For generation it uses a usual prompt that have influence to all picture and a regions that have their own prompts. Base prompt good for setup background and style of image. This is train-free technique and results not always stable - sometimes need to try several seeds or change prompt.
InfiniteTalk lip-sync node optimized for Wan2.2 dual-model workflow with first/last frame precision control and FPS synchronization. (Description by CC)
Nodes:LoadImageWithSwitch, ImageBatchOneOrMore, GenderControlOutput, ImageCompositeMaskedWithSwitch, ImageCompositeMaskedOneByOne, ColorCorrectOfUtils, SplitMask, MaskFastGrow, CheckpointLoaderSimpleWithSwitch, ImageResizeTo8x, MatchImageRatioToPreset, MaskFromFaceModel, MaskCoverFourCorners, DetectorForNSFW, DeepfaceAnalyzeFaceAttributes, VolcanoOutpainting, VolcanoImageEdit, ReplicateRequstNode etc.
Agent sidebar panel for ComfyUI — chat with an autonomous agent (Claude, Codex/GPT, Gemini, or local Ollama) that builds, runs, and debugs workflows on your live canvas. UI-only pack (also on the Comfy Registry as comfyui-agent-panel); pairs with the comfyui-mcp orchestrator: npx -y comfyui-mcp@latest --panel-orchestrator
A ComfyUI extension for chatting with your images. Runs on your own system, no external services used, no filter. Uses the [a/LLaVA multimodal LLM](https://llava-vl.github.io/) so you can give instructions or ask questions in natural language. It's maybe as smart as GPT3.5, and it can see.
Nodes: Download the weights of MotionCtrl [a/motionctrl.pth](https://huggingface.co/TencentARC/MotionCtrl/blob/main/motionctrl.pth) and put it to ComfyUI/models/checkpoints
ComfyUI node that pixelizes images.
ComfyUI custom nodes for LongCat-AudioDiT TTS - zero-shot and voice cloning diffusion TTS