Extensions/Nodes
Extension catalog

ComfyUI Custom Extensions

Browse 9,446 ComfyUI extensions and 73,215 custom nodes.

🏷️ Tag Autocomplete (Booru)

Booru style tag autocompletion for ComfyUI CLIP text encoder nodes (port of a1111-sd-webui-tagcomplete)

2
NodeSimpleExecutor

This node package contains automatic sampler setting according to model name in ComfyUI, adjusting image size according to specific constraints and some other nodes.

2
ComfyUI-list-filter

Custom nodes for convenient filtering image or string lists in ComfyUI workflow.

2
ComfyUI-CNCC (ControlNet Control Center)

Nodes: CNCC ControlNet, CNCC Apply ControlNet. Saves comfyui_controlnet_aux preprocessors as reusable presets, and lets a single node run the preprocessor and apply the result as a ControlNet (a drop-in alternative to the native Apply ControlNet node). Includes a settings modal for creating/managing presets from a thumbnail gallery.

2
Mask Editor One

A layer-based modal mask editor for ComfyUI with Photoshop-like controls. Features paint, color selection, alpha extraction, vector (Catmull-Rom spline), shape, and text tools, SAM3 AI segmentation, BiRefNet background removal, layer management with Undo/Redo (30 levels), ABR brush import, brush library, and multilingual UI (en/ja/zh).

2
Prompt Tag Editor

Interactive prompt tag editor: tag chips with hover weight/delete, double-click edit, press-and-drag reorder, click to disable tags, Tencent Hy-MT2-1.8B GGUF translation, load image from path, and a multi reroute node (1-20 pass-through rows with type auto-naming).

2
ComfyUI-SaturnNodes

Essential workflow controls: mid-generation pause, persistent queue auto-recovery, visual LoRA/image loaders, prompt queue iterator, interactive decision nodes, and local file runner.

2
ComfyUI_jxl_support

Load and save JPEG XL images in ComfyUI with lossy/lossless compression and optional workflow metadata compression.

2
ComfyUI-NebulaPromptManager

A clean, project-based prompt manager for ComfyUI that lets you store/load positive/negative prompts and typed variables per project.

2
Color-Light-FineTune

Color & light grading node for ComfyUI with a built-in live preview, color wheels, per-zone color balance, tone curves, film grain and picked-color adjustments; works with images and videos (frame batches).

2
ComfyUI-Diff2Flow

Unofficial Implementation of Diff2Flow Method for ComfyUI.

2
Kraken Tools

15 productivity nodes: Kraken Unbound Prompt (vision-enabled prompt builder with Qwen2-VL), WAN Prompt Splitter (cinematic styling), Ollama Prompt Chat (LLM enhancement), LoRA Loader with CivitAI trigger fetching, Dual CLIP Loader (Flux/SD3/SDXL), smart KSampler (AMP handling for WAN/Flow/FP8), Empty Latent with aspect presets, Upscale & Tile Calculator for Ultimate SD Upscale, Resolution Helper, Image Processor, WAN Helper, and more.

2
ComfyUI-GroupBypasser

A small ComfyUI custom node that provides a lightweight bypass for grouped nodes.

2
HunyuanWorld 3D World Generation

ComfyUI custom nodes for immersive 3D world generation using Tencent HunyuanWorld 1.0

2
ComfyUI Equirectangular Tools

Tools for processing equirectangular images, supporting conversion from equirectangular format to cubemap.

2
ComfyUI-Flux2KontextConditioner

Advanced conditioning node for Flux2 Klein Kontext image editing workflows. Encodes up to 3 reference images via the Flux2 VAE and attaches them as reference latents for Kontext attention. Text is encoded through the Qwen3-8B LLM-based text encoder with optional instruct prompt wrapping. Supports per-image strength and resolution control, VAE tiling for high-resolution encoding, and bakes the Flux2 guidance scale directly into the conditioning.

2
LoRA Txt Loader

Automatically loads trigger words from a .txt file with the same name as the LoRA. Supports offline use and custom-trained models.

2
ComfyUI_PuLID_Flux_ll_FaceNet

Same Function as original ComfyUI_PuLID_Flux_ll repository, with FaceNet Implementation that is safe for commercial usage.

2
Load Image With Filename

Drop-in replacement for Load Image that outputs the original filename as a string. Wire it into Save Image to auto-name your outputs. Preserves the real filename even after mask-editor / clipspace painting.

2
ComfyUI-CharacterPromptBuffer

Nodes for generating multiple character prompt variations in a single queue run. Includes Character Prompt Manager and Variation Buffer.

2
AnimaTagCompleter

The extension is designed for Anima and offers simultaneous searching and tagcomplete across multiple tag sources. See the README in the repository for details.

2
comfyui-latent-astronaut-suite

ComfyUI nodes for batch processing, loops, and iteration workflows

2
Touch Node Manager

Touch-first node/extension manager for ComfyUI: check updates, update nodes and core, install from a GitHub URL, select versions, fuzzy search — mobile-friendly.

2
Touch Resize

Big corner grab-handles for resizing ComfyUI nodes and groups on touch devices.

2
ComfyUI-LLMLink

A lightweight multimodal LLM node for ComfyUI: Ollama and OpenAI-compatible APIs over plain HTTP. SDK-free, zero extra dependencies.

2
comfyui_psd_smart_object

ComfyUI nodes for working with Photoshop mockup files - automatically project images onto PSD smart objects while preserving perspective, rotation, and scale transforms for seamless mockup rendering.

2
ComfyUI-VideoChatWrapper

Nodes related to video chat workflows

2
ComfyUI_ChatGen

ComfyUI nodes to use [a/ChatGen](https://github.com/chengyou-jia/ChatGen)

2
ComfyUI_Cogview4

The latest DIT architecture-based image generation model from Zhipu that supports Chinese text generation.

2
ComfyUI_Qwen3Omni

The ComfyUI version of [a/Qwen3-Omini](https://github.com/QwenLM/Qwen3-Omni)

2
ComfyUI_QWQ32B

ComfyUI nodes to use [a/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B)

2
ComfyUI-Chinese-CLIP

Support for directly inputting Chinese characters in the CLIP text box. The system will automatically translate them into English and replace the punctuation marks as well.

2
ComfyUI-GG

ComfyUI-GG is a collection of ComfyUI nodes designed to enhance productivity in image processing workflows. This plugin provides a set of custom nodes that perform various image manipulations and metadata extractions to streamline your tasks.

2
ComfyUI_Base64_IO

any to base64, and base64 to any.

2
ComfyUI-PechaKucha

Nodes to generate a pecha-kucha presentation in ComfyUI

2
Computational LSNet

把 LSNet / Kaloscope 的画师风格张量变成可计算、可存档、可读回、可进化的对象:张量反推画师串、画师串反推张量、106 函数的向量表达式运算、b64 逐比特存档,附画师串遗传算法(GA)工作流。

2
ComfyUI-Lumina-DiMOO

ComfyUI wrapper nodes for Lumina-DiMOO. Please see the README for model weight download instructions.

2
Auto Crop Black Borders

Auto crop continuous black borders from images

2
ComfyUI-Subtitle-Effects

Dynamic subtitle effect nodes for ComfyUI - CapCut-style animated subtitles, CPU rendering with zero VRAM

2
ComfyUI Image Browser

Browse, search and manage ComfyUI's generated images with Hanaikada inside ComfyUI.

2
ComfyUI-Qwen-Canvas

Enforces Qwen's training resolution buckets for precise Latent space generation.

2
ComfyUI-LivePortraitNode (Replicate API)

Two simple to install nodes to get Live Portrait working in ComfyUI without the need for a fancy GPU (Replicate account needed).

2
ComfyUI-Canvas-Snapshots

Save multiple snapshots for each workflow tab in ComfyUI and switch between them instantly.

2
ComfyUI-Custom-Scripts_extend

Feature extension package for ComfyUI-Custom-Scripts.

2
ComfyUI-Leputen-Utils

Game development toolkit for ComfyUI with DDS (DirectDraw Surface) support, PBR map generation and batch processing

2
comfyUI_Vertex_API
2
Comfy-IndexTTSLocalAPI

ComfyUI node for local IndexTTS: multi-role, multi-emotion script dubbing with frame-accurate subtitles

2
ComfyUI-AI2Go-Utils

ComfyUI utility nodes by AIKnowledge2Go.

2
ComfyUI In-N-Out Bucket

Store and load ComfyUI media (image / audio / video) in an S3-compatible bucket, passing keys instead of asset bytes — built for using ComfyUI as an API across distributed installs. Great for building applications off of ComfyUI. Configure your bucket connection — copy `.env.example` to `.env` and fill it in.

2
ComfyUI_Lora_List_With_Url_Loader

Nodes:ComfyUI_Lora_List_With_Url_Loader. Load loras from urls and auto fetch them on web if they are missing.

2
ComfyUI-LZNodes

Custom nodes for ComfyUI

2
comfyui_imgutils

Image tool kit for comfyui with dghs-imgutils

2
Agate

ComfyUI nodes for Agate, LogoLabs' 260M-parameter text-to-image model: a single-file loader, a sampler that outputs SD 1.x LATENTs (img2img, live previews), an all-in-one 256x256 generator and a plan viewer that shows the thinker's 16x16 layout plan evolving over the denoising steps.

2
ComfyUI-Better-Flow

Nodes for controlling workflow and reducing VRAM fingerprint.

2
ComfyUI-Offload-Models

Custom nodes to offload and rapatriate models from cpu.

2
comfyui-ComfyUI-Basic-Drawing

The Basic Drawing Board is a hybrid creative tool designed for ComfyUI.

2
ComfyUI Simple Batch

Batch-process every image, audio, or video file in a folder tree through an existing single-item ComfyUI workflow (📥 Batch Load / 📤 Batch Save + execution watchdog), without reloading models between items.

2
Local-Translator

A text translation node for ComfyUI using a local SLM (Microsoft Phi-4)

2
Fix: Flash Attention Schema Bug

Bypass ComfyUI's torch.library.custom_op schema-registration bug that causes Flash Attention to silently fall back to SDPA (schema_.has_value() INTERNAL ASSERT FAILED).

2
ComfyUI HealthCheck

A lightweight health check plugin for ComfyUI that monitors custom node import status and provides colorful summary reports

2
ComfyUI-TorchMonitor
2
Comfyui-LTXCondReplace

A ComfyUI custom node for combining LTXV conditioning latents from different sources.

2
LUNA Z-Image Qwen3-VL

ComfyUI nodes for GGUF-based Qwen3/Qwen3-VL text encoding and VLM inference for Z-Image

2
Egregora Frames Animation Nodes for ComfyUI

Advanced image list animation toolkit for ComfyUI with batch processing, AI-powered frame interpolation, and multi-format video encoding.

2
comfyui_EdgeTAM

A ComfyUI custom node implementation of EdgeTAM (On-Device Track Anything Model) for efficient, interactive video object tracking.

2
ComfyUI_NativeBlockSwap

Native block swap node for ComfyUI WAN models (2.1 & 2.2), reduces VRAM by swapping up to 40 transformer blocks to CPU.

2
Lyonir Studio

Lyonir Studio nodes for ComfyUI: multi-model sampler, resolution, image comparison, persistent image/video galleries and Qwen3-TTS.

2
ComfyUI-OtherVAEs

Nodes: TAESD VAE Decode

2
DriveSend Node

Automatically upload ComfyUI output files to Google Drive with optional encryption. Supports OAuth and service accounts, real-time monitoring, cloud setups (RunPod), and includes cross-platform decryption scripts.

2
DropSend Node

Automatically upload ComfyUI output files to Dropbox with optional encryption. Supports real-time monitoring, cloud setups (RunPod), and includes cross-platform decryption scripts.

2
ComfyUI-Happyhorse-Wrapper

ComfyUI custom nodes for HappyHorse 1.0 video generation, including text-to-video, image-to-video, reference-to-video, video editing, and preview nodes.

2
ComfyUI-MiniMax-H3-API

ComfyUI custom nodes for the MiniMax H3 Video V2 API, supporting text-to-video, first/last-frame generation, multimodal references, H3-Context-IR, 2K regeneration, task management, download, and preview.

2
Gemma 4 - Multimodal AI

ComfyUI custom nodes for Gemma 4 multimodal AI

2
ComfyUI-Sa2VA

Sa2VA-8B 的 ComfyUI 插件:图像 / 视频反推提示词,并在同一次推理里拿到 grounded 分割掩码。

2
ComfyUI-BucketCrop

Crop an image to the nearest training bucket ratio, centered on a detected region.

2
ComfyUI-Mango-Random

🥭 Mango Random Nodes - A collection of random file nodes for ComfyUI

2
ComfyUI-Cog

This is a custom node aiming to run CogView4 on diffusers while there is no official implementation on ComfyUI. NOTE: You will need a updated version of diffusers and I don't know if updating it my break other stuff, so I advise you to make in a new instance of ComfyUI

2
ComfyUI_LFM2-350M

A custom node for ComfyUI to load and use the LFM2-350M model trained to work as a prompt enhancer for z-image turbo or any other long token model.

2
ComfyUI-Liebs-Toast

A node to display a toast notification. Use it to send a toast when your prompt is complete. Also pairs well with [a/ComfyUI-Liebs_Picker](https://github.com/marklieberman/ComfyUI-Liebs-Picker) and [a/cg-image-filter](https://github.com/chrisgoringe/cg-image-filter) to be notified when the picker is waiting.

2
ComfyUI Conditioning Resizer

A custom node for ComfyUI that allows resizing of conditioning tensors, particularly useful for fixing size mismatches between CLIP Text Encode and CLIP Vision Encode outputs in SD3 workflows.

2
ComfyUI-MDSNodes

A collection of lightweight utility nodes for workflow automation and model routing.

2
Native Looper

Multi-loop video generation with sharp output and character consistency

2
milan-nodes-comfyui

NODES: 'Load One Image with Name, Title, Description', 'Load Multiple Images with Name, Directory, Title, Description'

2
ComfyUI-GIMM-VFI-Registry

This node is a registry version of Kijais https://github.com/kijai/ComfyUI-GIMM-VFI

2
Metadata manager for various generation services

MetaMan bridges the metadata gap between AI image generation services, enabling seamless workflow sharing and model dependency tracking across platforms.

2
ComfyUI Find Models

Find and adapt missing models in the current ComfyUI workflow

2
ComfyUI-OneForOne

Node:Image Fit Calculator

2
MegaPotato AI Upscaler

#1 of 18 AI upscalers in our reproducible 2026 benchmark and the cheapest of the leaders (megapotato.app/blog/best-ai-image-upscalers-2026). The MegaPotato AI upscaler (megapotato.app) as one node: photo super-resolution x1-x8 on cloud GPUs through the API, IMAGE in, IMAGE out, real detail and nothing invented. No model download, no VRAM; pay per photo with your own API key, test keys are free.

2
ComfyUI-Demucs-AudioSeparator

Custom ComfyUI node for audio source separation using Meta Demucs v4 technology to extract voices, drums, bass, and other instruments with high fidelity. (Description by CC)

2
ComfyUI-Easy-Image-Nodes

Dataset-oriented image load and save nodes for ComfyUI with filename metadata and auto-incrementing support.

2
M3D photo effects

A set of photo effects for ComfyUI, for the moment, only Bleach Bypass effect is provided, but more to come!

2
Infinite Movie

Beta - feedback welcome. Turn a few still images into one seamless, looping film with video models (MiniMax H3, LTX 2.5, Wan 2.2): auto prompts from the images, A/B shot review, motion-evened assembly, upscale, model download with size check.

2
Useful-Meti

Useful custom nodes for ComfyUI by Meti: Outputs the total execution time (Generation Time) of your Nodes or workflow , Keeps a history of your generated images (up to 10) and shows them in a live-updating grid , Saves images with custom path and outputs filename & full path or Just Preview

2
comfyui_met_suit

Nodes:BBOXPadding, BBOXResize, ResizeKeepRatio.

2
comfyui_met_suite

Nodes: Primitive BBOX, BBOX Padding, BBOX Resize, ImageResize KeepRatio.

2
ComfyUI-VLMPrompt

ComfyUI custom nodes for local VLM prompt generation with GGUF and Hugging Face backends.

2
StyledCLIPTextEncode

StyledCLIPTextEncode is a node that enables you to build your prompts(both postive and negative) based on the selected style. It provides up-to 77 styles currently and has been tested on SDXL and SD1.5 checkpoints. It's ported from project [a/Style Selector for SDXL 1.0](https://github.com/ahgsql/StyleSelectorXL), which is only availabe on WebUI.

2
ComfyUI_Workflow_Timer

A simple workflow timer node for ComfyUI.

2
Transparent-background-comfyUI

Removes background using Transparent Background

2
ComfyUI-seamless_latent_tiling

Generates perfectly tileable/repeating patterns by circular-padding the latent tensor at every denoising step.

2