Extensions/Nodes
Extension catalog

ComfyUI Custom Extensions

Browse 9,420 ComfyUI extensions and 73,215 custom nodes.

Euler_A2_Sampler-ComfyUI

ComfyUI custom sampler node implementing Euler A2 sampling algorithm. (Description by CC)

7
ComfyUI Color Profile Reader

A comprehensive collection of color manipulation and analysis nodes for ComfyUI

7
Artfat Face Consistency

Face-identity consistency scoring for ComfyUI (cv2 YuNet+SFace, CPU). Inline pass/fail sort + batch contact-sheet.

7
Mutiny

Unofficial Midjourney integration for ComfyUI

7
YALLM-LlamaVision

A set of nodes for basic Llama 3.2 Vision support in ComfyUI. Give it an image and query and it will output a text response.

7
ComfyUI_Delay

Simple custom node for ComfyUI to artificially delay a workflow at any point.

7
ComfyUI Mask Area Condition

Calculates the percentage of a mask area compared to the total image size and outputs a boolean based on a defined threshold.

7
ComfyUI-flux_fill_patcher

flux patcher for Fill Flux.Dev lora [a/https://civitai.com/models/981615/fluxfill-inpaint-lora](https://civitai.com/models/981615/fluxfill-inpaint-lora)

7
MBQ Wedge

Compare ComfyUI parameter values without contact sheets — sweep numerics, samplers, or schedulers, then inspect each result full-res in MBQ Viewer.

7
seriesmith

Write the show, get the episodes: an AI video editor inside ComfyUI. Script your shots, keep characters and places consistent with reference pictures, render each shot on any model (your GPU, Comfy Cloud or Router), then cut, upscale and master.

7
ComfyUI_CSM

ComfyUI node of Conversational Speech Model (CSM).

7
Comfyui_Hunyuan3D_EX

This is a custom node designed to simplify the use of Hunyuan3D in ComfyUI

7
DynamicPose-ComfyUI

NODES:pose_extraction, Load_reference_unet, Load_denoising_unet, Load_Pose_Guider, Pose_Guider_Encode, DynamicPose_Sampler, load_pose_model, align

7
ComfyUI_Text2PixelCharacter

A custom ComfyUI node for generating cozy fantasy JRPG-style pixel characters from text prompts.

7
Qwen-llm-loader

Local Qwen loader and prompt refiner for ComfyUI

7
ComfyUI-SCStepFun

To use stepfun's library, you need an official api that supports multimodal inputs such as video and pictures [a/https://platform.stepfun.com/request-restriction](https://platform.stepfun.com/request-restriction)

7
comfyui-EncryptSave

comfyui image encrypt and save.

7
EmbeddingsCurveEditor_ComfyUI

Edit embeddings with a curve. Actually should work on any 1D input tensor. Tested with IPAdapter-Plus.

7
URN_AudioTools_Yue2

Yue2 Cover Music Auto Download Lyrics

7
MOSS-TTS

ComfyUI custom nodes for OpenMOSS MOSS-TTS v1.5 — three variants: Local-Transformer (Qwen3-4B backbone, 48 kHz stereo), Delay (8B, 24 kHz) and VoiceGenerator (1.7B, 24 kHz, voice design). Reference-free TTS, zero-shot voice cloning, continuation, duration control, 31 languages.

7
ComfyUI-WanAnimalPreprocess

ComfyUI nodes for animal pose estimation and preprocessing using AP10k/APT36k ViTPose models

7
Soda H3 Tools

MiniMax H3 segmented video helpers for ComfyUI: project and segment control, continuation decoding, per-segment saving and three-segment audio-video merging.

7
Image Uploader

Upload images automatically to image hosting sites.

7
comfy_http_request

Nodes:Send Http Request. You can use this node to save full size images through the websocket.

7
ComfyUI-Image-Vector

modify the original node instruction of image vector, add ‘imagemagick’ which is the key base Python library of ‘wand’ library.

7
ComfyUI-OmniGenX

OmniGen Unified Image Generation Model Integration.

7
ComfyUI HunyuanVideo-Foley Custom Node

This custom node integrates the HunyuanVideo-Foley model for generating audio from video frames and text prompts in ComfyUI. It's built for use in generating Foley sounds from video and text inputs.

7
comfyui-workflow-prettier

Auto-arrange workflow nodes with 4 layout algorithms, group-aware positioning, alignment tools, and undo

7
Flux 3 API

ComfyUI nodes for the BFL Flux 3 video API, with an OpenRouter-backed prompt helper.

7
Comfyui SDAPI Request / NovelAI

A Novel AI / SD-WebUI request node, support nai3/nai4, use NovelAI model in Your Comfyui.

7
ComfyUI-Raw-Image

Comfyui-raw-image provides the ability to load raw image files for ComfyUI

7
Comfyui FOCUS nodes

A collection of nodes designed for efficiency and the reduction of screen-clutter. Includes a Global Seed controller with boolean toggles, SDXL All-in-One conditioner, a custom SDXL control module, Wildcard processor, Style Injector, and more. [w/WARNING: Updating this node-pack wil overwrite any changes you've made to the included wildcards and styles. Please backup your folders before updating.]

7
ComfyUI_e621_booru_toolkit

WIP. Nodes: Fetch e621/danbooru image and/or tags etc from a given URL; Get the Wiki entry for a tag through a button press.

7
comfyui-dreambait-nodes

A collection of forks, QoL nodes and utilities for ComfyUI

7
ComfyUI-Thread

A ComfyUI custom node package for seamless integration with Threads (Meta's social platform). This package allows you to publish posts, manage images, and retrieve post history directly from your ComfyUI workflows.

7
Seedream Image Generate ComfyUI Node

A ComfyUI custom node based on the Volcano Engine Doubao large model Seedream API, designed for high-quality image generation.

7
Powder Nodes

ComfyUI nodes for prompts, styles, LoRAs, sampling, visual canvas editing and image grids. Includes 44 example workflows and English/Russian documentation.

7
ComfyUI-mflux2

ComfyUI custom nodes for mflux, including FLUX.2 workflows optimized for Apple Silicon.

7
ComfyUI Custom API

Custom model APIs for text, vision, image generation and editing. Provider management, model discovery, request templates, authenticated management, public-network access with explicit local-service grants or a strict origin allow-list, and English UI with native ComfyUI localization.

7
ComfyUI-Eagle-Autosend

A seamless, node-independent way to automatically send your ComfyUI generations to Eagle, complete with full metadata annotation and tags.

7
ER VFX Nodepack

ER VFX Nodepack: film-grade VFX tools for ComfyUI — generative editing (FLUX.2 klein/Kontext/Qwen-Edit), lens flares, defocus/bokeh, glow, grain, camera dirt, color correction with vectorscope, relighting, layer compositing, wedge sequencing and more. GPU live previews on every node.

7
ComfyUI-Omnivoice

ComfyUI nodes for OmniVoice — multilingual zero-shot TTS with voice cloning, voice design, EPUB loading, and voice mixing.

7
SAM2Matting Video

Video-first temporal foreground matting for ComfyUI using FudanCVL SAM2Matting with SAM2.1 and SAM3 variants.

7
ComfyUI-Krea2-attention-tweak

A tiny patch altering Krea2 Turbo's attention mechanism based on the Krea-2-Turbo-Projector-Scale-LoRA for improved balance between creativity and prompt following.

7
ComfyUI-AutoTrimBG

ComfyUI-AutoCropBgTrim is a powerful tool designed to automatically clean up the background of your images. This tool trims unnecessary spaces and pixels, leaving only the main subject of the image. It generates both a mask and an image output, making it easy to focus on the essential elements. Perfect for enhancing your photos and preparing them for professional use.

7
ComfyUI_Fill-Example-Nodes

An example node pack for ComfyUI to demonstrate custom node creation.

7
ComfyUI Seed API Integration

ComfyUI custom nodes for Seed AI APIs including video generation, image generation, and chat models

7
ComfyUI LoRA adaLN Patcher Node

A simple but powerful custom node for ComfyUI that patches LoRA models by adding dummy adaLN_modulation_1 weights. This solves compatibility errors when using LoRAs with newer model architectures that expect these keys to be present in the final_layer.

7
ComfyUI-drag-ghost

A premium visual enhancement for ComfyUI that adds a smooth 'ghost' effect when dragging nodes and groups.

7
ComfyUI-PNGInfo

A1111-style PNG Info for ComfyUI: load an image, read its generation metadata as human-readable text (A1111 parameters and ComfyUI embedded workflows), and reuse positive/negative/seed/steps/cfg as typed outputs.

7
ComfyUI-BDsInfiniteYou

ComfyUI custom_node for [a/ByteDance's InfiniteYou](https://github.com/bytedance/InfiniteYou).

7
ComfyUI-UltimateUpsacaler

Geekatplay Studio tiled generative upscale helpers for ComfyUI

7
ComfyUI Geeky AudioMixer

Audio Mixing node for ComfyUI

7
ComfyUI-iterator-nodes

Here are several ComfyUI nodes that traverse specific folders to sequentially deliver images, prompts, video files (split into image sequences), entire video files, and video files first split into keyframe sequences at specific intervals to subsequent nodes, which then upload them to the corresponding large models via an API (OpenAI format).

7
GF_translate

These custom nodes for ComfyUI provide advanced text translation capabilities using Google Translate. They are designed for seamless integration into the ComfyUI environment, offering users powerful tools for text and JSON file translation tasks.

7
ComfyUI-Lumina-Video

This is a video generation plugin implementation for ComfyUI based on the Lumina Video model.

7
ComfyUI DashuaiTools

A practical and lightweight collection of custom nodes for ComfyUI, providing utility tools and convenient workflow functions.

7
ComfyUI DDColor

Unofficial implementation of [a/DDColor](https://github.com/piddnad/DDColor) for ComfyUI

7
ComfyUI-ToolBox

Nodes:commonly_node.

7
comfyui_LLM_schools

ComfyUI node library for fine-tuning LLMs

7
ComfyUI-Prompt_Library

A ComfyUI node pack for management of larger prompt amounts and prompt variations.

7
ComfyUI_RH_mammothmoda

ComfyUI custom nodes for MammothModa2 text-to-image generation.

7
Ghost2_Comfyui

ComfyUI adaptation of [a/GHOST 2.0](https://github.com/ai-forever/ghost-2.0).

7
ComfyUI_LiteLLM

Nodes for calling LLMs, enabled by LiteLLM

7
ComfyUI-MusePose-Remaster

MusePose Remaster is a remaster version of ComfyUI MusePose node. It supports auto weights download, remove most necessary dependencies, etc.

7
ComfyUI-Pt-Wrapper

PyTorch extension for ComfyUI featuring extensive PyTorch wrapper nodes for seamless tensor operations and PyTorch model training.

7
ComfyUI-RIFE-TensorRT-Auto

Ultra fast video frame interpolation for ComfyUI using RIFE with TensorRT acceleration. Auto-detects CUDA version, installs matching TensorRT wheels, and downloads RIFE models automatically.

7
AspectAwareTiling

This is an extension script for Stable Diffusion WebUI, modified based on the original functionality. It now supports fixing FLUX panorama seams. It allows users to independently configure seamless image tiling for both the X and Y axes while also being capable of handling FLUX panorama seam issues.

7
ComfyUI-ZipDepth

A simple implementation of ZipDepth. monocular depth estimation for ComfyUI.

7
ComfyUI-PackedPipes

Custom nodes that organize ComfyUI workflow connections by combining multiple links into single pipeline links. (Description by CC)

7
Lenient Switch

A switcher that allows specify conditions and inputs/outputs individually

7
ComfyUI-FairyTaler

This package provides ComfyUI nodes for creating 3-scene storyboards from Ollama text output.

7
ComfyUI-LoraTags

A powerful, sleek, and highly optimized LoRA loader for ComfyUI with modern tag management, automated Civitai metadata fetching, and seamless multi-LoRA stacking.

7
ComfyUI-JH-PixelPro

GPU-powered pro-grade image suite cho retouch chân dung. v0.1.0 alpha: Frequency Separation (N-01) + Sub-Pixel Mask Refiner (N-02). Kornia core, tensor thuần không rời VRAM.

7
ComfyUI Gemini Nodes

A collection of custom nodes for integrating Google Gemini API with ComfyUI, providing powerful AI capabilities for text generation, image generation, and video analysis. Nodes: Gemini Text API, Gemini Image Editor, Gemini Image Gen Advanced, Gemini Video Captioner.

7
ComfyUI-JaRue

A collection of nodes powering a tensor oracle on a home network with automation

7
Bawk Nodes Collection

A complete collection of FLUX-optimized ComfyUI nodes for enhanced AI image generation workflows.

7
ComfyUI-JoyCaption-beta-one-hf-llava-Prompt_node

Prompt node for the [a/JoyCaption-beta-one-hf-llava](https://huggingface.co/mradermacher/llama-joycaption-beta-one-hf-llava-GGUF) model, to use JoyCaption-beta-one-hf-llava with Ollama

7
ComfyUI-multiple-inputs

A collection of utility nodes for ComfyUI, focusing on batch processing, stitching, and visualization.

7
ComfyUI Multi-Analysis Heatmaps

A custom ComfyUI node for visual comparison of two images using multiple perceptual and mathematical methods. The goal: make hidden differences visible as colorful heatmaps, so you can see where an upscaler, denoiser, or diffusion model changed your image — even when your eyes can’t tell at first glance.

7
ComfyUI-MemoryManagement

Advanced memory management custom nodes for ComfyUI

7
ComfyUI Load and Save file to S3

Nodes:Load From S3, Save To S3.

7
ComfyUI-FastVideo
7
ComfyUI-TextGenerateGemma3Prompt

ComfyUI custom node for LTX Video 2.3 that uses Gemma3-12b-it LLM for text generation with support for LTX-2.3 prompt extensions and custom system prompts. (Description by CC)

7
KurdKnight ComfyUI System Check Node

A comprehensive system information node for ComfyUI that provides detailed information about your system, GPU, CUDA, and AI libraries configuration. Works on both Windows and Linux systems.

7
ComfyUI-Drawer

A mobile-friendly drawer-style gadget platform for ComfyUI with Deck, Gallery, Model Viewer, XYZ Plot, and utility nodes.

7
Image Browser

Full-canvas file explorer for browsing and managing images across ComfyUI's input, output, temp and arbitrary paths — thumbnails plus delete, rename and move.

7
VideoClipGenerator - by PabloGFX

Vibe Music Engine is a custom node that processes audio input using OpenAI's Whisper models. It provides transcription, translation, and precise word-level timing—perfect for generating subtitles and edit decision lists (EDL) for video editing workflows. In addition, it features beat detection to synchronize video cuts with the music rhythm. You can generate full-lenght video based on song words with Automatic prompting the img2video i2v or text2video.

7
MiniMax H3 Context IR - leoleexh

Multimodal Context IR prompt builder for MiniMax H3 video generation in ComfyUI

7
comfyui_kj

comfyui_kj, A tool that can package workflows into projects and publish them to a WeChat Mini Program named Kaji, allowing charges to be collected from users.

7
ComfyUI-GiftHelperSuite

Fast utility nodes for ComfyUI gift and livestream animation pipelines, optimized for high-speed processing of short video frame sequences. (Description by CC)

7
comfyui-llm-assistant

Nodes:Generate Stable Diffsution Prompt With LLM, Translate Text With LLM, Chat With LLM

7
AUN ComfyUI Nodes

A collection of workflow helper nodes focused on organization + control (bypass/mute/collapse/group control), prompt/text utilities, file/path helpers, and image/video save helpers (optional VHS integration).

7
comfyui-image-annotator

A professional image annotation node for ComfyUI, featuring Point, Rectangle, and Polygon annotations with real-time rendering and WYSIWYG editing.

7
ComfyUI OpenAI Compatible LLM Node

A ComfyUI custom node that provides integration with OpenAI-compatible Large Language Model APIs, including OpenAI, local models, and other compatible endpoints. Supports both text-only and multimodal (text + image) interactions.

7
KepPromptLang

Nodes: Build Gif, Special CLIP Loader. It offers various manipulation capabilities for the internal operations of the prompt.

7
Qwen3-ASR - Voice to Text

ComfyUI custom nodes for Qwen3-ASR

7
ComfyUI-RVC-Trainer

在 ComfyUI 内训练 RVC(Retrieval-based Voice Conversion)音色模型。导出*.pth、*.npy和*.index。

7
ComfyUI-Koolook

This repository provides custom nodes for ComfyUI tailored for VFX and AI image/video generation workflows

7
Basix Image Filters

A handful of image filters for ComfyUI (darken, lighten, levels, saturate, hue)

7