ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
Implementation of X-Portrait nodes for ComfyUI, animate portraits with an input video and a reference image.
ANIMA_BOOSTER is a high-performance optimization suite for the Anima DiT 2B model in ComfyUI.
Nodes: Latent Diffusion Mega Modifier. ComfyUI nodes which modify the latent during the diffusion process. (Sharpness, Tonemap, Rescale, Extra Noise)
A collection of prompt managent nodes with advanced tag parsing. Prompt tag cloud, mutiselect, toggle list, randomizer, filter, autocompete.
Tell your dream and it interprets it and puts you inside your dream
A node for ComfyUI that allows you to overlay text on an image in an area defined by a mask, with support for text rotation, custom fonts, line breaks and transparency.
These nodes are for real-time applications of ComfyUI.
This is an (very) advanced and (very) experimental custom node for the ComfyUI. It allows you to iteratively change the blocks weights of Flux models and check the difference each value makes.
Nodes: Pixel Sort, Swap Color Mode, Solid Color, Glitch This, Add Text To Image, Play Sound, Prettify Prompt, Generate Noise, Flatten Colors
Qwen multi-image editing enhancement node supporting 8-image input, dual conditional output, and background layer priority for coordinated image composition workflows. (Description by CC)
HY-World 2.0 ComfyUI nodes — WorldMirror V1 & V2 3D reconstruction
ComfyUI diffusers wrapper nodes for [a/NormalCrafter](https://github.com/Binyr/NormalCrafter)
Nodes: Download the weights of MotionCtrl-SVD [a/motionctrl_svd.ckpt](https://huggingface.co/TencentARC/MotionCtrl/blob/main/motionctrl_svd.ckpt) and put it to ComfyUI/models/checkpoints
This repository is a collection of open-source nodes and workflows for ComfyUI, a dev tool that allows users to create node-based workflows often powered by various AI models to do pretty much anything. Our mission is to seamlessly connect people and organizations with the world’s foremost AI innovations, anywhere, anytime. Our vision is to foster a flourishing AI ecosystem where the world’s best developers can build and share their work, thereby redefining how software is made, pushing innovation forward, and ensuring as many people as possible can benefit from the positive promise of AI technologies. We believe that ComfyUI is a powerful tool that can help us achieve our mission and vision, by enabling anyone to explore the possibilities and limitations of AI models in a visual and interactive way, without coding if desired. We hope that by sharing our nodes and workflows, we can inspire and empower more people to create amazing AI-powered content with ComfyUI.
Node to use [a/APISR](https://github.com/Kiteretsu77/APISR) upscale models in ComfyUI.[w/NOTE: repo name is changed from ComfyUI-APISR -> ComfyUI-APISR-KJ]
[a/https://huggingface.co/microsoft/Florence-2-large-ft](https://huggingface.co/microsoft/Florence-2-large-ft) Large or base model, support for captioning and bbox task modes, more coming soon.
GPU-native NVIDIA enhancement with in-process DLSS Neural Rendering, native DLSS Frame Generation, and high-throughput NVENC/ProRes video output nodes for ComfyUI.
Custom ComfyUI Nodes for interacting with [a/Ollama](https://ollama.com/) using the [a/ollama python client](https://github.com/ollama/ollama-python). Meanwhile it will provide better prompt descriptor for stable diffusion.
请使用Github安装,桌面端会缺少中文文件
Yet Another Node Collection. Adds some useful nodes, check out the GitHub page for more details.
A set of ComfyUI custom nodes for video workflows.
Quickly and easily build a GUI on top of your workflow. Gather just the nodes that you want to see, with no spaghetti, onto controller panels, leaving your workflow untouched in the background.
ComfyUI Custom Sampler nodes that implement Zheng et al.'s Trajectory Consistency Distillation based on [a/https://mhh0318.github.io/tcd](https://mhh0318.github.io/tcd)
⚠️ ARCHIVED PROJECT: This project has evolved into TTS Audio Suite (https://github.com/diodiogod/TTS-Audio-Suite). This legacy v3.x version is maintained for compatibility only. For new projects, use TTS Audio Suite v4.0.0+ which provides a unified multi-engine TTS platform with ChatterBox, F5-TTS, Higgs Audio, and RVC support.
Start and end frames video generation node that supports native ComfyUI.
Multi-shot chaining for MiniMax-H3 audio+video: carry identity, voice and framing across shots so a sequence reads as one take.
ComfyUI custom nodes for AI image and video generation through MuAPI, including Seedance, Kling, Veo3, Flux, HiDream, GPT-image, and Imagen4. Requires a MuAPI API key from https://muapi.ai.
A powerful ComfyUI custom node for text-based image editing using Black Forest Labs' Flux Kontext API. Transform your images with simple text instructions while maintaining character consistency and quality.
First/Last Frame control for SVI 2 PRO
A custom node for ComfyUI that dynamically manages RAM usage by intelligently controlling cache purging based on available system memory.
ComfyUI-EdgeTTS is a powerful text-to-speech node for ComfyUI, leveraging Microsoft's Edge TTS capabilities. It enables seamless conversion of text into natural-sounding speech, supporting multiple languages and voices. Ideal for enhancing user interactions, this node is easy to integrate and customize, making it perfect for various applications.
ComfyUI custom node pack for loading SDNQ quantized models
A ComfyUI custom node that generates Image-to-LoRA (I2L) LoRA from training images using DiffSynth-Studio Qwen-Image i2L pipelines.
Nodes: Plasma Noise, Random Noise, Greyscale Noise, Pink Noise, Brown Noise, Plasma KSampler
Just like when your pizza is ready and the oven goes 'Ding! 🍕', this plugin lets your ComfyUI notify you when your AI creations are done baking! A ComfyUI custom node that sends you a friendly 'ding-dong' notification when your workflows are fully cooked and ready to serve. No more staring at the screen waiting - let the AI kitchen tell you when dinner's ready! 👨🍳
The comfyui supported version of the [a/Magic Clothing](https://github.com/ShineChen1024/MagicClothing) project, not the diffusers version, allows direct integration with modules such as ipadapter.[w/comfyui-oms-diffusion is renamed to comfyui-magic-clothing. You may need to reinstall this.]
ShineChen1024/MagicClothing comfyui support .
Agent-driven video editing with Studio, ComfyUI Apps and CLI/MCP
A ComfyUI custom node for Google's Gemini 2.5 Flash Image (aka 'Nano Banana') model - the state-of-the-art image generation and editing AI.
Offline Chinese costume gallery (服装图库) with 1,407 outfits, image outputs and bilingual keywords for ComfyUI
ComfyUI nodes for multi-image processing and data manipulation in InfiniteTalk workflows. (Description by CC)
Support multi-task parallel queue.
Encrypt your comfyui workflow, and share it with key
AspectSize and 100 more nodes
NODES: ComfyUI-YuE2-Trainer - Experimental trainer nodes for YuE2
The easiest way to run & share ComfyUI workflows.
Group switching control, one click control to ignore and disable multiple groups, as well as wired switch combination nodes, allowing for arbitrary switching of annotation names
UniVidX intrinsic & alpha video decomposition for ComfyUI
A prompt helper for ComfyUI, based on [a/prompter.fofr.ai](https://prompter.fofr.ai)
A custom node for ComfyUI that integrates DreamOmni2 for image generation and editing with multi-modal understanding.
The LoRA Caption custom nodes, just like their name suggests, allow you to caption images so they are ready for LoRA training.
An extension for merging LoRAs. Offers a wide range of LoRA merge techniques (including dare) and XY plots. XY plots require efficiency nodes.
Hair transfer
Some tools to help with [a/Flex.1-alpha](https://huggingface.co/ostris/Flex.1-alpha) inference on Comfy UI.
ComfyUI nodes for the roop A1111 webui script.
A collection of nodes to facilitate the creation of explicit NSFW scenes in ComfyUI.
Kalman-Inspired Feature Propagation for Video Face Super-Resolution
Use ComfyUI with RTX Remix to remaster classic games [a/https://github.com/NVIDIAGameWorks/rtx-remix](https://github.com/NVIDIAGameWorks/rtx-remix)
MOSS-Image edit (reference image) nodes for LoRAs trained with ai-toolkit. Encodes prompts + reference images through the MOSS-Image Qwen3.5 text encoder and patches the model to consume reference latents, with KV-cache conditioning on by default.
For loading and running Pixtral models
For loading and running Pixtral, Llama 3.2 Vision, and Molmo models. Put models in the models/LLM folder.
For loading and running Pixtral, Llama 3.2 Vision, and Molmo models. Put models in the models/LLM folder.
HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters,try it in comfyUI ,if your VRAM >24G.
Power Noise Suite contains nodes centered around latent noise input, and diffusion, as well as latent adjustments.
This extension has some useful nodes, loops, wechat public number +AI chat drawing, distributed cluster
Unofficial implementation of [a/SegMoE: Segmind Mixture of Diffusion Experts](https://github.com/segmind/segmoe) for ComfyUI
Node to use APISR upscale models in ComfyUI
New UI on the sidebar that allows for quick and easy navigation of images to help build styles, characters, backgrounds, etc. or even entire random prompts.
Dynamic prompt expansion, powered by GPT-2 locally on your device.
This Node provides a method for fuzzy searching Danbooru tags. Users can find corresponding tags in the Danbooru dataset using fuzzy linguistic descriptions.
Custom Nodes to work with SAM3
This is a project that generates videos frame by frame based on IPAdapter+ControlNet. Unlike [a/Steerable-motion](https://github.com/banodoco/Steerable-Motion), we do not rely on AnimateDiff. This decision is primarily due to the fact that the videos generated by AnimateDiff are often blurry. Through frame-by-frame control using IPAdapter+ControlNet, we can produce higher definition and more controllable videos.
The ListHelper collection is a comprehensive set of custom nodes for ComfyUI that provides powerful list manipulation capabilities. This collection includes audio processing, text splitting, and number generation tools for enhanced workflow automation.
A collection of batch operation toolkits suitable for ComfyUI
ComfyUI-RIFE is an inference wrapper for RIFE designed for use with ComfyUI.
Nodes:YouTube Video Loader. Custom ComfyUI Nodes for video generation
Paint3D Nodes is a custom ComfyUI node for 3D model texture inpainting based on [a/Paint3D](https://arxiv.org/pdf/2312.13913).
I love GoYounJung!Most Cheap API to my fans friedns!Bilibili:https://space.bilibili.com/385085361,website:https://ai.t8star.cn/register?aff=dP7j
The best way to run, share, & discover thousands of ComfyUI workflows.
Enhancing Image Restoration. (ref:[a/InstructIR](https://github.com/mv-lab/InstructIR))
A quality-of-life node for ComfyUI that lets you browse anime artists, Animadex styles, character tags, visual previews, prompt autocomplete, and configurable Auto Cycle prompt testing.
This is a collection of nodes created to aid when managing area conditionings.
Image Manipulation and Prompt Generation Nodes
Nodes:Any List, Image Accumulator Start, Image Accumulator End, Load Lines From Text File, XY Grid Helper, Slice List, Axis To String/Int/Float/Model, ...
Enhance your prompts using the Qwen LLM to align the behavior and capabilities of the Qwen-Image/Edit online version.
Load and apply B-LoRA models, currently B-LoRA models only works with SDXL (sdxl_base_1.0).
An advanced chat node integrating LLMs, real-time web search, image handling, and image scraping. Supports APIs from OpenAI, Google, Anthropic, Grok, DeepSeek, and local Ollama. Includes custom node finder, smart assistant tools, and growing subnodes like text masking and concept eraser.
Interactive sigma schedule editor for ComfyUI — NURBS spline curve widget
Real-time input output node for ComfyUI by NDI. Leveraging the powerful linking capabilities of NDI, you can access NDI video stream frames and send images generated by the model to NDI video streams.
GlitchNodes is a collection of image processing nodes designed for ComfyUI that specializes in creating glitch art and retro effects.
Recraft AI API Custom Nodes
A continuous, real-time runtime diagnostics suite for ComfyUI. Automatic error interception, intelligent fix suggestions, and deep data flow inspection.
ComfyUI custom node integrating SPEED (Spectral Progressive Diffusion) for faster sampling with progressive resolution growth during diffusion denoising.
ComfyUI custom nodes for Higgs Audio v3 TTS with native inference, voice cloning, multi-speaker dialogue, longform chunking, and AIMDO DynamicVRAM support
ComfyUI preset and per-layer Base+SFT merge node for MOSS-Image
ComfyUI integration of the LongCat-Image pipeline for text-to-image generation and image editing with excellent Chinese text rendering capabilities. (Description by CC)
This extension allows users to load styles from a CSV file, primarily for migration purposes from the automatic1111 Stable Diffusion web UI.
A comprehensive toolkit based on ComfyUI, providing image, mask, audio, and tools nodes, fully modular and v3 compatible.
This is simplified implementation of the [a/DiffusionLight](https://github.com/DiffusionLight/DiffusionLight) method of creating light probes. You will need the included LoRA, place it in ComfyUI/loras folder like usual, it's converted from the original diffusers one.
Nodes for NSFW content filtering