ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
Intelligent video frame selection node powered by Qwen3-VL-235B vision model. Automatically analyzes and selects the best quality frames from videos for further creative work.
ComfyUI node suite for faster SDXL image generation on Apple Silicon with MLX.
Given min/max resolution constraints, this automatically suggests optimal dimensions while preserving aspect ratio. Ideal for Image to Image (I2I) and Image to Video (I2V) workflows!
An universal media loader for ComfyUI (Size, Image, Audio, Video)
A standalone ComfyUI custom node for creating animated shapes that follow user-drawn paths.
FL PixelGen - Pixel-space diffusion text-to-image generation and LoRA training nodes for ComfyUI
ComfyUI nodes for Mistral Voxtral-4B TTS with direct PyTorch inference. Supports 20 preset voices across 9 languages on CUDA, MPS, and CPU.
ComfyUI custom nodes to interact with the Finegrain API.
Join video clips end-to-end — instant, lossless, zero VRAM. Editor-style transitions: cut, dissolve, fades, wipes, slides. Works with loaded files or clips generated in-workflow.
This repository provides custom nodes for ComfyUI that enable pixel art style image processing, including downscaling, upscaling, color quantization, and resolution adjustments.
A ComfyUI node pack containing nodes for basic programming logic.
This repository provides custom nodes for ComfyUI that enable pixel art style image processing, including downscaling, upscaling, color quantization, and resolution adjustments.
Tired of OOM errors and tedious file management? The AIIA Node Suite delivers the ultimate workflow overhaul, headlined by the AIIA Media Browser: a high-performance file hub fully integrated into ComfyUI. Instantly preview images, videos, and audio, and experience ultimate smoothness thanks to smart caching and virtual scrolling, even with tens of thousands of files. It also features a powerful fullscreen viewer, rich tooltip previews, and flexible sorting. Alongside the browser, our Video Combine node fundamentally solves memory bottlenecks in long video generation. By streaming frames from disk, you can create videos of virtually unlimited length, making OOM errors a thing of the past. The suite also includes OOM-safe FLOAT video generation, advanced audio processing, and other utilities, providing a complete end-to-end solution from content creation to asset management.
a [a/Facefusion](https://github.com/facefusion/facefusion)'s wrapper for ComfyUI custom node.
A custom node for ComfyUI that integrates OneReward model for high-quality image inpainting, outpainting, and object removal.
A custom ComfyUI node integrating DW-Pose (Denoising Whole-Body Pose Estimation) for high-quality pose detection with CPU (ONNX) and GPU (TensorRT) support. Features 20x faster performance with TensorRT acceleration, automatic model downloading, customizable pose visualization, keypoint conversion, and video workflow integration.
Tag completion with a1111-style wildcard sub-selection, CSV database support (Danbooru, e621), multiple wildcard sources, and smart parsing for professional prompt engineering in ComfyUI.
Add more endpoints to make easy for utilizing ComfyUI API.
A collection of post processing nodes for ComfyUI, dds image post-processing adjustment capabilities to the ComfyUI.
These are ComfyUI nodes to assist in converting images to paintings and to assist the Inspyrenet Rembg node to totally remove, or replace with a color, the original background from images so that the background does not reappear in videos or in nodes that do not retain the alpha channel in rgba images.
Save and load MiniMax H3 AV NestedTensor latents, avoiding the built-in Save Latent limitation for H3 video/audio latent pairs.
This node pack integrates the core capabilities of the Canary-1b-v2 model, providing three main features: it can transcribe audio in any of 25 supported languages into text in the same language, translate audio from 24 source languages directly into English, and translate English audio directly into one of the 24 other supported languages.
INT4 weight-only quantization (W4A16) via torchao. Activations remain FP16 — zero quality loss. Full LoRA: standard + LoKr, multi-LoRA stack (≤8), SHA256 JSON cache (<1s hit), GPU pre-hook bake-in. Auto-detects device on startup and installs correct torchao build (Intel XPU / NVIDIA CUDA / AMD ROCm). Verified: Krea2 Turbo, Flux2 Klein 9B, Z-Image, Boogu, Qwen-Image. Includes model analysis CLI.
A custom node pack for ComfyUI that allows you to run Large Language Models (LLMs) locally and use them for prompt generation and other text tasks directly within your ComfyUI workflows.
AI music generation node (for HeartMuLa) that auto-generates style tags and lyrics from keywords, supporting OpenAI/Claude/local LLM APIs and multilingual lyrics (Japanese, English, Chinese, Korean, Spanish). (Description by CC)
Top-bar button that reads a workflow's Markdown notes, downloads the models it needs into the right folder, and relinks loader nodes to copies you already own.
A custom nodes for OmniVoice K2-FSA. A fast TTS diffusion audio model with cloning capabilities, and 600 languages
This is a repository for using LoRTnoC (LoRA with hint block of ControlNet) on ComfyUI. NOTE:Please place the model file in the same location as controlnet. (Is this too arbitrary?)
LiquidTime is a simple yet powerful frame interpolation node for ComfyUI. Just input your sequence and desired frame count - the node handles all complex calculations and generates smooth in-between frames for you. A must-have tool for AI animation and video creation that lets you shape time like liquid.
ComfyUI Ultimate SD Upscale nodes with FLS tile sampling and optional Anima LLLite tile repair.
ComfyUI for [a/InternVL](https://github.com/OpenGVLab/InternVL)
Nodes:TCL EbSynth, TCL Extract Frames (From File), TCL Extract Frames (From Video), TCL Combine Frames, TCL Save Video (From Frames)
Checkpoint Discovery Hub — An advanced browser for your ComfyUI models. Easily explore, filter, and load your checkpoints, manage presets, favorites, and Civitai metadata — all from a sleek and intuitive interface.
NODES: String Formatter, String List
ComfyUI nodes to use RAVE attention as a temporal attention mechanism. This differs from other implementations in that it does not concatenate the images together, but within the UNet's Self-Attention mechanism performs the RAVE technique. By not altering the images/latents throughout the UNet, this method does not affect other temporal techniques, style mechanisms, or other UNet modifications. For example, it can be combined with AnimateDiff, ModelScope/ZeroScope, or FLATTEN.
ComfyUI nodes to use [a/ViewCrafter](https://github.com/Drexubery/ViewCrafter/tree/main) for novel view synthesis.
ComfyUI LC Modelbuilder Nodes by lonecatone23 — checkpoint/model merging tools. Starts with LC Krea2 Block Merge Advanced (per-block ratio curve + named-region sliders, reuses ComfyUI's own block-merge patching), checkpoint savers, LC Face Variety Scorer (same-face test with InsightFace buffalo_l via onnxruntime), and LC Krea2 LoRA Editor + LC LoRA Save + LC Krea2 LoRA Block Scan + LC Krea2 LoRA Merge (find a LoRA's face-lock blocks, edit them per block, attention / MLP and spikes, merge two LoRAs per block, save as a standard LoRA). Companion to ComfyUI_LC123_nodes; separate Registry name.
ComfyUI-Hive/Club - Github: https://github.com/luguoli - A community plugin for ComfyUI users: Real-time communication, Share、Browse、Search workflows、nodes、models,one-click download models and install nodes. Right-click to use expand prompt, random prompt, photo prompt generator, prompt favorite, AI chat, translate, reverse prompt, and fix node
Restoring the ComfyUI frontend pre-vue update queue functionality, drag&drop support, quicksave, and more in a clean design that respects your screen area.
Nodes: RawText, RawTextCLIPEncode, RawTextCombine, RawTextReplace, Extension: m957ymj75urz.colors
Nodes:TextualInversionTrainingSDXL, TextualInversionTraining
OpenImageIO plugin for ComfyUI
A general comfyui model loading plugin that supports loading unet models quantized in bnb-4bit (nf4 and fp4) format
Essential nodes. Fork from ComfyUI_essentials
A ComfyUI custom node plugin for DiffSynth-Studio, enabling low-VRAM inference through configurable VRAM management, NF4 quantization, and model offloading. Supports image, video, and audio generation and editing across 20+ diffusion models.
This extension provides image generation features based on Fooocus.
A pack of nodes(only 2 for now) to make my life easier and hopefully yours ;)
A comprehensive node for ComfyUI that implements an image reference mechanism for Flux2-based image generation models.
Bilibili IndexTTS2 ComfyUI Version - Auto-downloads models, simple to use.
Custom javascript extensions for better UX for ComfyUI. Double click on image to open. It's convenient for checking images.
Native ComfyUI v3 nodes for the pixel-space AsymFLUX.2-klein 9B model from LakonLab (Asymmetric Flow Models, arXiv 2605.12964).
NK2E — experimental, unofficial in-context image editing for Krea 2 (community project; not affiliated with Krea).
ComfyUI-Mosaic-Mask is an automatic tool designed to detect and mask mosaic areas in input images.
ComfyUI_DAO_master is a collection of custom nodes for ComfyUI. These nodes provide additional tools for image creation, manipulation, and visual experimentation, with a focus on vector workflows (DXF & SVG) and production utilities.
Updated version of IPAdapter Plus. ComfyUI reference implementation for the IPAdapter models. The IPAdapter are very powerful models for image conditioning. The style and composition of a reference can be easily transferred to the generation. Think of it as a 1-image lora.
A collection of custom nodes for ComfyUI
A fully automated ComfyUI custom node that uses Joy Caption Alpha Two to generate high-quality image captions. Perfect for: LoRA/model training dataset preparation, Image tagging and organization, NSFW content captioning, Batch processing large image collections
Mute or bypass any node by its ID, with no wires. Includes a Single node (up to 20 targets), an A/B switch (up to 10 pairs), and a Stacker for global control of several Remote nodes, plus legacy Triple and AA/BB nodes. Pick targets from a node picker, work across subgraphs, and promote toggles and pickers to a subgraph node as front-panel switches. Compatible with the current ComfyUI frontend, including promoted widgets on 1.52+.
Simple REST API interfaces for ComfyUI with dynamic parameter replacement and output management
Chinese end-to-end MOSS-Image prompt studio for ComfyUI: canvas draft editing, LLM translation, official compile, and image reverse.
This nodepack contains custom nodes for ComfyUI designed specifically for handling Reallusion-related assets such as Character Creator and iClone image and video files. These nodes are intended to be used as backend components that communicate and operate through the AI Render Plugin interface of iClone or Character Creator, enabling a seamless integration between ComfyUI's powerful image/video generation capabilities and Reallusion’s animation tools. By bridging ComfyUI with iClone/Character Creator’s AI Render Plugin, these nodes facilitate workflows where AI-assisted content generation can be controlled, customized, and rendered directly from within Reallusion software environments.
This plugin is compatible with the ComfyUI audio nodes.
MiniMax H3 latent spatial upscale nodes for ComfyUI two-pass video workflows
This repository packages the latest BiRefNet model as a ComfyUI node for use, supporting chunked loading on both CPU and GPU, as well as model caching features.
This repository packages the latest BiRefNet model as a ComfyUI node for use, supporting chunked loading on both CPU and GPU, as well as model caching features.
An empty latent size picker with support for Qwen Image, SDXL, and Flux models.
ComfyUI custom nodes for Ideogram 4 Magic Prompt and Ideogram 4 resolution selection
Native ComfyUI nodes for Zyphra ZONOS2 text-to-speech and voice cloning with AIMDO memory tracking
This is a collection of tools that I use to make my life easier when developing ComfyUI applications. It is a collection of tools that I have created to help me with my development process. I have decided to share these tools with the community in the hopes that they will be useful to others as well. I use this tools to further develop features for [a/https://shibiko.ai](https://shibiko.ai)
ComfyUI node for Semantic-aware Guidance based on the [a/paper](https://arxiv.org/abs/2404.05384) 'Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance'
Custom Loader for scaled_fp8 models with hybrid precision layers.
Run retro games inside ComfyUI via EmulatorJS and capture their screens for image generation workflows.
Just a reroute node with a tiny twist.
the sampler introduced by [a/hallatore](https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/8457) code extracted from [a/smZNodes](https://github.com/shiimizu/ComfyUI_smZNodes).[w/NOTE:ComfyUI-dpmpp_2m_alt-Sampler is renamed to StableDiffusion-dpmpp_2m_alt-Sampler. Please reinstall.]
lynx:Towards High-Fidelity Personalized Video Generation, you can use this node in comfyUI with origin pipeline
Visual control and creative tools for ComfyUI: 3D posing, image-and-FBX animation, OpenPose, canvas editing, and model workflows.
Maintained VNCCS Utils fork with corrected Pose Studio, OpenPose, capture, and morph execution.
A versatile LoRA merger for Flux (4B/9B/Dev), Z-Image, and SDXL. Features cross-architecture scaling, weight normalization, and live model baking.
An elegant, premium, remote bypass and wire-management nodes suite for ComfyUI.
ComfyUI workflow for VEnhancer Inference
Makes every ComfyUI job take the GPU through vhotseat first, so ComfyUI and a local LLM take turns on one GPU instead of loading on top of each other. Needs the vhotseat CLI.
ComfyUI custom nodes for LoRA management (stack, recipe, Civitai fill, backup) and a Live2D desktop pet.
A ComfyUI custom node that loads and stacks regular LoRAs and DoRA LoRAs with Flux/Flux2 and OneTrainer compatibility fixes.
Faithful FLUX-focused ComfyUI port of Spectrum spectral feature forecasting.
Standalone ComfyUI node pack for RealRestorer image restoration with self-contained model code and no vendored dependencies.
Nodes: String, Int, Float, Short String, CLIP Text Encode (With Variables), String Format, Short String Format. This extension introduces quality of life improvements by providing variable nodes and shared global variables.
ComfyUI-SkyworkUniPic is now available in ComfyUI, Skywork-UniPic is a unified autoregressive multimodal model with 1.5 billion parameters that natively integrates image understanding, text-to-image generation, and image editing capabilities within a single architecture.
Nodes: PhotoMakerLoaderV2,PhotoMakerEncodeV2
This is a custom node for ComfyUI. Features:Removes white areas in the input image by making them transparent based on brightness, Outputs in black and transparent, Outputs in gray and transparent. This is a simple node with the above functionalities implemented. It also supports sequential processing.
A barebones ComfyUI wrapper for [a/PixelOE](https://github.com/KohakuBlueleaf/PixelOE). I cannot promise any support, if there is someone who wants to make a proper node, please do.
A properly implemented lycoris loader for comfyui.
API call node for Third-party platforms both official and local. Support VLMs LLMs Dalle3 Flux-Pro SD3 etc. And some little tools: img to b64 url, b64 url to img, b64 url to b64 data, reg text to word and ',' only, etc.
A ComfyUI chat node based on SemiUI.
This node allows you to cache/caching/store and reuse resized images, ControlNet images, masks, and texts. It avoids repeating heavy operations by loading previously saved files — saving time, memory, and processing power in future executions.
The CLIPSeg node generates a binary mask for a given input image and text prompt.
Simple implementation of [a/ByteDance Sa2VA](https://github.com/bytedance/Sa2VA) nodes for ComfyUI.
Using image caption models to extract prompts in ComfyUI
Colorize ComfyUI nodes with defaults per node, node category or via regex filtering.
Custom ComfyUI utility nodes for workflow enhancements.
A set of nodes for interfacing with the FastSDCPU webserver.