ComfyUI Custom Extensions
Browse 8,530 ComfyUI extensions and 65,510 custom nodes.
ANIMA_BOOSTER is a high-performance optimization suite for the Anima DiT 2B model in ComfyUI.
Power Noise Suite contains nodes centered around latent noise input, and diffusion, as well as latent adjustments.
Unofficial implementation of [a/SegMoE: Segmind Mixture of Diffusion Experts](https://github.com/segmind/segmoe) for ComfyUI
A lightweight ComfyUI custom node pack for Qwen3-ASR, providing simple speech‑to‑text workflows with local model caching and optional timestamp output. Supports Qwen/Qwen3‑ASR‑1.7B and 0.6B, with HuggingFace/ModelScope download options and clean integration for ComfyUI pipelines.
A set of ComfyUI custom nodes for video workflows.
UniVidX intrinsic & alpha video decomposition for ComfyUI
Node to use APISR upscale models in ComfyUI
Enhance your prompts using the Qwen LLM to align the behavior and capabilities of the Qwen-Image/Edit online version.
Dynamic prompt expansion, powered by GPT-2 locally on your device.
Actively maintained fork of ComfyUI-GGUF node pack with support for new models, INT8/INT4 GGUFs and optionally ComfyUI Dynamic VRAM
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.
The best way to run, share, & discover thousands of ComfyUI workflows.
小珠光 - ComfyUI节点美化增强插件，提供节点收藏、工作流管理、主题美化、田字格对齐、视觉编组等功能
ComfyUI nodes for multi-image processing and data manipulation in InfiniteTalk workflows. (Description by CC)
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.
MiniMax H3 FL2VA long-video continuation for ComfyUI with freeze-safe native masked video context, independent audio-tail preservation, flexible Qwen conditioning, and memory-bounded stitching
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.
Nodes:YouTube Video Loader. Custom ComfyUI Nodes for video generation
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.
Custom Nodes to work with SAM3
This extension has some useful nodes, loops, wechat public number +AI chat drawing, distributed cluster
Enhancing Image Restoration. (ref:[a/InstructIR](https://github.com/mv-lab/InstructIR))
HY-World 2.0 ComfyUI nodes — WorldMirror V1 & V2 3D reconstruction
Python interpreter to embed scripts into workflows and debug custom nodes.
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.
This is a collection of nodes created to aid when managing area conditionings.
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, ...
An extension for merging LoRAs. Offers a wide range of LoRA merge techniques (including dare) and XY plots. XY plots require efficiency nodes.
Paint3D Nodes is a custom ComfyUI node for 3D model texture inpainting based on [a/Paint3D](https://arxiv.org/pdf/2312.13913).
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.
A continuous, real-time runtime diagnostics suite for ComfyUI. Automatic error interception, intelligent fix suggestions, and deep data flow inspection.
ComfyUI integration of the LongCat-Image pipeline for text-to-image generation and image editing with excellent Chinese text rendering capabilities. (Description by CC)
A collection of batch operation toolkits suitable for ComfyUI
Image Manipulation and Prompt Generation Nodes
An unofficial implementation of PixelSmile workflow in ComfyUI that enables fine-grained expression editing using natural language prompts.
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.
Load and apply B-LoRA models, currently B-LoRA models only works with SDXL (sdxl_base_1.0).
ComfyUI Custom Node for [a/Step1X-Edit](https://github.com/stepfun-ai/Step1X-Edit/). Noted this node may consume large VRAMs!
Nodes: Base64Image Input Node, Base64Image Output Node. [a/A8R8](https://github.com/ramyma/a8r8) supporting nodes to integrate with ComfyUI
This Node provides a method for fuzzy searching Danbooru tags. Users can find corresponding tags in the Danbooru dataset using fuzzy linguistic descriptions.
A node suite for ComfyUI that allows you to load image sequence and generate new image sequence with different styles or content.
I love GoYounJung!Most Cheap API to my fans friedns!Bilibili:https://space.bilibili.com/385085361,website:https://ai.t8star.cn/register?aff=dP7j
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.
The LLM_Node enhances ComfyUI by integrating advanced language model capabilities, enabling a wide range of NLP tasks such as text generation, content summarization, question answering, and more. This flexibility is powered by various transformer model architectures from the transformers library, allowing for the deployment of models like T5, GPT-2, and others based on your project's needs.
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.
Go to the top menu>Workflow>Browse Templates. This is a collection of my Inpainting workflows for Flux (expanded and COMPACT) + others. Previously called: 'Proper Flux Control-Net inpainting and/or outpainting with batch size - Alimama or Flux Fill'. Works with Kontext now! By installing this 'node' you can always keep them up to date by updating on the manager. This is not a new custom node. You will still need to install all other custom nodes used on the workflows. You will also find my 'Flux LoRA Block Weights Preset Tester' here.
This is a bunch of nodes for ComfyUI to help with sound work.
Encrypt your comfyui workflow, and share it with key
Removes the 2px pixel grid artifact from Qwen Image VAE decoded images with auto-calibration.
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
ComfyUI custom nodes for Higgs Audio v3 TTS with native inference, voice cloning, multi-speaker dialogue, longform chunking, and AIMDO DynamicVRAM support
A collection of custom nodes for ComfyUI providing video manipulation, LoRA loading, path animation, and visual drawing tools for WanVideo workflows.
A collection of custom nodes for ComfyUI providing video manipulation, LoRA loading, path animation, and visual drawing tools for WanVideo workflows.
ComfyUI node for fast neural style transfer. This is a simple conversion based on this: [a/https://github.com/rrmina/fast-neural-style-pytorch](https://github.com/rrmina/fast-neural-style-pytorch) Only basic inference functionality is ported for now.
Unofficial implementation of [a/DepthFM](https://github.com/CompVis/depth-fm) for ComfyUI
ComfyUI-ReduxFineTune is a custom node for ComfyUI that enables advanced style fine-tuning using the Flux Redux approach. It offers multiple unified fusion modes for precise and consistent control over style transfer, allowing users to fine-tune image styles with high flexibility and detail.
TTS with Zyphra Zonos
A modern, powerful, and easy-to-use Storyboard extension for ComfyUI.
A custom node for ComfyUI to integrate GPT API.
InstantX's Flux union ControlNet loader and implementation
A collection of custom nodes for ComfyUI, originally focused on workflow parsing, now expanded to provide advanced file loading features like 'Load Latent (Advanced)' for drag-and-drop latent file uploads and 'WorkflowImageFileLoader' for parsing prompts from image metadata. It also adds a js extension for a better UI experience.
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.
ComfyUI-RIFE is an inference wrapper for RIFE designed for use with ComfyUI.
Enjoy the latest GEMINI V2 API for ComfyUI - generate images, analyze content, and use multimodal capabilities with Google's Gemini models
Use ComfyUI with RTX Remix to remaster classic games [a/https://github.com/NVIDIAGameWorks/rtx-remix](https://github.com/NVIDIAGameWorks/rtx-remix)
A ComfyUI extension to apply better nodes layout algorithm to ComfyUI workflow (mostly for visualization purpose)
True single-frame stills from MiniMax H3: a one-frame latent and a decode that renders it cleanly, at any size. Two nodes, no extra models.
Long-Duration and High-Resolution Audio-driven Portrait Image Animation,
JoyTag is a state of the art AI vision model for tagging images, with a focus on sex positivity and inclusivity. It uses the Danbooru tagging schema, but works across a wide range of images, from hand drawn to photographic. Download the weight and put it under checkpoints: [a/https://huggingface.co/fancyfeast/joytag/tree/main](https://huggingface.co/fancyfeast/joytag/tree/main)
Prompt Edit is a custom node designed for ComfyUI that allows you to pause, edit text prompts, and then continue during workflow execution. This is extremely useful for scenarios where prompts need to be dynamically adjusted during the generation process.
DragAnything
Works with any Depth Map and visualizes the applied version it inside ComfyUI
This custom node is based on the [a/rembg-comfyui-node](https://github.com/Jcd1230/rembg-comfyui-node) but provides additional functionality to select ONNX models.
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.
Professional AI Interior Design Toolkit for ComfyUI. Custom Qwen-VL nodes with 4 design modes: Text-to-Design, Mood Board, Reference Control, and Room Cleaning. Includes 5 optimized nodes with advanced strength controls and 23 preferred aspect ratios.
This is a set of nodes to interact with llama-cpp-python
This extension adds nodes that allow you to easily serve your workflow (for example using a discord bot)
This custom node for ComfyUI provides a powerful and flexible dynamic layering system, similar to what you would find in image editing software like Photoshop.
Kalman-Inspired Feature Propagation for Video Face Super-Resolution
阿组小助手（Group Assistant）可以让组自动包裹组节点，实现自动调整组边界，让组功能更好用。Group Assistant can automatically wrap group nodes, achieve automatic adjustment of group boundaries, making group functions more useful.
a custom comfyui node for [a/coqui-ai/TTS](https://github.com/coqui-ai/TTS.git)'s xtts module! support 17 languages voice cloning and tts
A Text To Speech node using Kokoro TTS in ComfyUI.
This custom node offers the following functionalities: API support for setting up API requests, computer vision primarily for masking or collages, and general utility to streamline workflow setup or implement essential missing features.
Maintained by Eden.art, this is a very fast, well tuned trainer for SDXL and SD15
A collection of prompt managent nodes with advanced tag parsing. Prompt tag cloud, mutiselect, toggle list, randomizer, filter, autocompete.
ComfyUI music production with YuE2 audio cover versions, SheetSage2 score-aware prompts, YuE2 and MiniMax Music 3 song generation, restoration, mastering, artwork and release metadata.
ComfyUI wrapper for [a/StableX normal](https://github.com/Stable-X/StableNormal)/[a/delight](https://github.com/Stable-X/StableDelight) models
High-performance Video Super Resolution for ComfyUI with VRAM optimization.
Nodes for NSFW content filtering
ComfyUI custom node integrating SPEED (Spectral Progressive Diffusion) for faster sampling with progressive resolution growth during diffusion denoising.
ComfyUI custom nodes for HiDream O1 Image generation with reference images, BF16/FP16/FP8 loading, FlashAttention, SageAttention, and DynamicVRAM support
A node for ComfyUI that performs GPEN face restoration on the input image(s). Significantly faster than other implementations of GPEN.
This is a collection of custom nodes that make ComfyUI slightly more convenient.
Neural Network Toolkit (NNT) for ComfyUI is an extensive set of custom ComfyUI nodes for designing, training, and fine-tuning neural networks. This toolkit allows defining models, layers, training workflows, transformers, and tensor operations in a visual manner using nodes.
[DEPRECATED] ComfyUI Extension for Advanced Security. Implements login, multi-user registration, IP filtering, and user-specific input/output directories.
本插件为 ComfyUI 提供本地 RAG 工作流节点，支持文档构建向量库、检索增强问答，以及 LM Studio 本地多模态对话。