Extensions/Nodes
Extension catalog

ComfyUI Custom Extensions

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

BV Nodes

This repository contains a user-defined node for ComfyUI, currently there are nodes for capturing captions. But will be expanded in the future.

3
ComfyUI-NodeReset

An extension for ComyUI that allows resetting a node's inputs to their default values

3
ComfyUI NodeReset

An extension for ComyUI to allow resetting a node's inputs to their default values. NOTE:Right click any node and choose 'Reset' from the context menu.

3
Prompt & Dimensions from LLM

ComfyUI custom node that resolves a Qwen Image 2.1 Prompt Enhancer JSON hint (rewritten prompt + aspect ratio/size) into a ready-to-use prompt and exact width/height.

3
ComfyUI_video-image-motion-transfer

Introduces a node that tries to approximate the entire video using it's first frame (that we stylize) by warping it using optical flow extracted from the video. First we do image-to-image using the reference video's first frame and a depth controlnet. The generated object doesn't have to closely resemble the reference like on the demo. Then the generated image and the video frames are fed into the node and it returns a warped video. No ai models are used by the node. The example workflow uses SDXL but you can get it to work with any arch if you manage i2i.

3
comfyUI_SillyNodes

Using rgthree's fast_group_muter and bookmark nodes, introduce the pyautogui library to simulate clicks and hotkeys, and run groups in sequence. screen manipulation is involved

3
CoMPaSS-ComfyUI

A ComfyUI custom node that implements CoMPaSS for FLUX.1-dev models. CoMPaSS enhances the spatial understanding capabilities of text-to-image diffusion models.

3
ComfyUI-EvalSampler

ComfyUI node for running evaluation after collecting latents with the EvalSampler, comparing against baseline BF16 latents. (Description by CC)

3
ComfyUI-OpenSoraPlan

Another comfy implementation for the short video generation project PKU-YuanGroup/Open-Sora-Plan, supporting latest 1.3.0 and 1.2.0 and image to video feature, etc.

3
ComfyUI-AI-CustomURL

A comprehensive ComfyUI extension that enables text, image, video, and speech generation using any OpenAI-compatible API endpoint with custom URLs.

3
Splat Loader

In-node Gaussian splat viewport (Spark) for ComfyUI with WYSIWYG image capture.

3
Vintage Effect

ComfyUI node that applies vintage/retro effects through JPG compression, color grading, film grain, vignette, and more to emulate more realistic photo aesthetics.

3
FMJ-LLM

Advanced nodes for interaction with Olama (text, vision, image editing), with dynamic management of prompts via CSV.

3
buqi-qwen-image-2.1-multigpu

ComfyUI-native Ulysses sequence-parallel inference for Qwen-Image 2.1 across 1/2/4/8 GPUs, including text-to-image, multi-reference editing, and distributed prefix caching. Requires ComfyUI commit c194dd00 or newer and Linux or WSL2 with NCCL; native Windows is not supported.

3
ComfyUI-Gradual-IC-LoRA

Gradual IC-LoRA time-curve nodes for LTX-2.3 (ComfyUI). Modulate IC-LoRA strength over the output clip via a user-drawn curve, applied as a per-token runtime adapter.

3
ComfyUI-InstantIDUtils

Nodes:Multi-ControlNet Converter, List of Images, Convert PIL to Tensor (NHWC), Convert Tensor (NHWC) to (NCHW), Convert Tensor (NHWC) to PIL

3
FreezeFrame

Modifed Sampler nodes that allow you to pause/resume generations. For those with older hardware running in CPU mode or old GPUs. Useful for managing thermals.

3
ComfyUI_OmniAvatar

A ComfyUI custom node developed based on OmniAvatar, capable of generating video sequences with synchronized lip movements and facial expressions by inputting a portrait image, audio, and text prompt. The node parameters and invocation method are fully consistent with the official OmniAvatar inference.

3
ComfyUI-TostAI

NODES: SendToTostAI

3
ComfyUI-DiT360

Implement circular padding VAE in ComfyUI from DiT 360 Paper

3
comfyui-last-frame-extractor

This is a ComfyUI custom node that extracts the last frame (image) from an input image batch. It is particularly useful when you want to obtain the final scene or frame in a video generation workflow.

3
ComfyUI_Spectral

ComfyUI Spectral is a ComfyUI custom nodes library based on the spectral, mainly used for visual processing of spectral files

3
ComfyUI NSFW Filter

A simple and effective ComfyUI custom node for filtering inappropriate text content, automatically detecting and replacing prohibited words while preserving the original format.

3
Logo Generator Node for ComfyUI

This custom node allows you to generate logo images using Google Fonts.

3
ComfyUI-SeaCache

SeaCache for native ComfyUI FLUX, HunyuanVideo, Wan2.1, and MiniMax H3 models

3
comfyui_EncryptPreview

ComfyUI's non-persistent (in-memory) image preview feature

3
ComfyUI-Line-counter

This custom node package for ComfyUI is designed to streamline your workflow with powerful file-counting capabilities.

3
google-image-comfyui-node

Provide a prompt and get google image search results

3
painting-by-colors-generator

Create a painting by colors image from an image

3
ComfyUI-ClarkAirSana

Run Clark Air Sana 1.6B (ternary ~1.58-bit, GemLite INT2 kernels) natively under ComfyUI's KSampler.

3
ComfyUI-Jtils

An extension for ComfyUI that adds utility functions and nodes not available in the default setup.

3
ComfyUI-ToriiGate-Reforged

A ComfyUI custom node pack for image captioning and text generation with ToriiGate-0.5, a fine-tuned Qwen3.5-4B model.

3
PSD Layers

Load PSD / save PSD nodes with an interactive layer panel: load PSD or PSB files layer by layer (composite + per-layer image/mask outputs, all Photoshop blend modes), and save ByteDance Seedream layer PSD files with embedded smart-object layers. No Photoshop required.

3
JH XMP Metadata Nodes

These are custom nodes for ComfyUI for the loading and saving of metadata in XMP format. XMP metadata is embedded in the images created by these nodes; it travels along wherever the image does. Both macOS and Windows index XMP metadata automatically, making it searchable from the Finder on the Mac or the File Explorer in Windows. Apps like Photoshop or Lightroom (and presumably many others) expose XMP metadata and allow it to be edited.

3
ComfyUI-Topaz-Upscaler

A custom node for ComfyUI that integrates the Topaz Labs API for AI-powered image upscaling and enhancement.

3
ComfyUI_Qwen_chat_models

ComfyUI custom nodes for Qwen text and vision-language models. Supports Qwen2.5/Qwen3, 4-/8-bit quantization, deterministic seeding, auto model download, and shared caching to improve workflow performance.

3
ComfyUI CoolB Nodes

A simple pack of utility nodes for ComfyUI featuring saving/loading speakers with transcripts (useful alongside TTS packs), execution flow control (muting/bypassing nodes and groups on trigger to actively change the workflow state from run to run), some useful text file utilities (including save/load text file) and data type conversion.

3
ComfyUI-llama-multimodal

ComfyUI Ollama node for image list

3
ComfyUI-CraftKit

Smart resize, batch resize, resolution multiplier and prompt controller nodes for ComfyUI

3
ComfyUI-WorkflowOrganizer

Drag-and-drop workflow organization for the ComfyUI sidebar

3
[Unofficial] ComfyUI-Veo3-Experimental

A custom node extension for ComfyUI that integrates Google's Veo 3 text-to-video generation capabilities.

3
ComfyUI-Trellis2 Multi-View Refiner

Multi-view mesh refiner node for ComfyUI-Trellis2 with spatial blending across front/back/left/right views.

3
CyberKrea Sampler

A preset-driven Krea 2 Turbo sampler and 16-channel empty latent node for ComfyUI, with direct manual tuning and NegPiP-friendly model wiring.

3
ComfyUI-AdvancedLivePortrait-Universal

Maintained AdvancedLivePortrait fork with universal device support (Intel XPU, Apple MPS, CUDA, ROCm, CPU) and other improvements.

3
Prompt Composer

Build, organize, and randomize prompts from a disk-backed, drag-and-droppable library of reusable prompt entries, with sections, presets, and queue-time randomization.

3
ComfyUI GLM-OCR

Load and run GLM-OCR (zai-org/GLM-OCR) locally in ComfyUI. Supports text recognition, formula recognition, table extraction, and general image description. Picks up models from any ComfyUI checkpoint directory.

3
comfyui-checkpoint-automatic-config
3
ComfyUI-Visual-LoRA-Loader

Visual interface for LoRA management with tabs, drag-and-drop, and automatic CivitAI metadata fetching.

3
Comfy DV Nodes

Quality of life ComfyUI nodes: dynamic string formatting with Python f-strings or Jinja2 templates, seed-controlled random input selection, and workflow circuit-breaker for conditional queue interruption.

3
ComfyUI-LoadFiles

The primary goal of these nodes is to provide a way to access files generated by ComfyUI workflows, local to the machine running ComfyUI. These nodes should always return an updated list of files when triggered.

3
Prompt History

ComfyUI custom node for saving, searching, and reusing prompts across sessions.

3
Dazzle KSampler

Enhanced KSampler for ComfyUI with SmartResCalc noise passthrough and DazzleCommand integration. Based on RES4LYF's ClownsharKSampler.

3
Preview Bridge Extended

Enhanced Preview Bridge node for ComfyUI with LayerCache architecture, dual-layer mask editing, and instant preview refresh. Extends Impact Pack's Preview Bridge with optional MASK input, mode selection, and WYSIWYG preview display.

3
DemonAlone-nodes-ComfyUI

A set of lightweight utility nodes for ComfyUI that were originally crafted to support XYZ‑plot pipelines but are broadly useful in any workflow.

3
ComfyUI Needle 2

Cactus Needle 2 in ComfyUI: a 45M-parameter CPU model that turns text into typed graph parameters, plus nodes that read a ComfyUI workflow back out of a PNG.

3
comfyui-daz-tools

A collection of ComfyUI utility nodes. The Workflow Config nodes (WAN2.2 and LTX2.3) let you store multiple named presets — models, LoRA stacks, prompts, dimensions, and sampling parameters — and switch between them from a single dropdown, making it easy to test variations, manage scene setups, and iterate across versions without rebuilding your workflow or creating and maintaining multiple copies of it. Additional nodes: Lora Inspector (scans and displays safetensors metadata for any LoRA in your library), Check Null (detects null, None, NaN, or empty values), Null Audio Checker (detects silent/missing audio tracks from video inputs), and Abs Int (absolute value for integers).

3
ComfyUI Caching Embeddings

This repository simply caches the CLIP embeddings and subtly accelerates the inference process by bypassing unnecessary computations.

3
ComfyUI-basic-pitch

Audio to midi functionality within ComfyUI

3
Comfy-INT4-HIPtest

AMD/HIP native Triton W4A4 ConvRot nodes for ComfyUI.

3
PureRef Connector

Send Save Image outputs to an editable PureRef board without adding nodes. Windows only.

3
ComfyUI_Dragos_Nodes

Nodes:File Padding, Image Info, VAE Loader With Name

3
ComfyUI_show_seed

A custom node that saves images while displaying the seed value used in generation

3
ComfyUI-FastImageSequence

Fast parallel PNG image-sequence saver for ComfyUI. Multithreaded 8/16-bit PNG encoding with first-frame-only metadata — a big speedup over Save Image (Advanced) for video/frame dumps.

3
Dropdown Switch

A frontend-only ComfyUI node that routes one of several inputs to the output based on a dropdown selection.

3
ComfyUI-DesignPack

A ComfyUI custom node package for generating professional interior design presentations using AI. This package integrates with Gemini/Ollama/OpenAI API to analyze floor plans and automatically generate PowerPoint presentations and PDF with AI-generated content and images. (Currently Support Chinese Only)

3
Auto Mask

Automatic mask refinement and histogram-based multi-threshold nodes for ComfyUI by easygoing0114

3
FlexPainter ComfyUI Wrapper

ComfyUI FlexPainter Wrapper

3
MOSS-TTS 1.5

ComfyUI custom nodes for OpenMOSS MOSS-TTS v1.5 — both the 1.7B Local-Transformer (48 kHz) and the 8B full model (24 kHz). Reference-free TTS, zero-shot voice cloning, audio continuation, hard duration control, 31 languages, stereo output.

3
ComfyUI-Manufnode

Custom ComfyUI nodes integrating Ollama to generate and enhance positive/negative prompts for Stable Diffusion workflows.

3
Livepeer AI Streaming

Real-time streaming for ComfyUI using the Livepeer gateway trickle protocol. Frames are published directly to orchestrators and outputs are pulled via trickle subscribe.

3
ComfyUI-SweepGrid

Sweep ComfyUI parameters and combine labeled frame batches into one comparison video.

3
YuE2 Native

Composable ComfyUI V3 nodes for YuE2 music generation

3
comfy-modelopt

NVIDIA ModelOpt integration for ComfyUI - Quantize and optimize diffusion models with INT8/FP8/INT4

3
SageAttention Opt-out Custom Nodes

Minimal ComfyUI custom node for per-model SageAttention opt-out and attention overrides.

3
comfyui-immich

ComfyUI custom nodes for Immich integration — upload, metadata, album management

3
Photoshop Bridge

Round-trip images between ComfyUI and Photoshop: right-click any image, edit it in Photoshop, and your save lands back on the originating node automatically.

3
Eric Composer Studio

High-quality pose detection plus interactive multi-layer image, depth, and pose compositing for ComfyUI. Uses RTMW-x / DWPose via rtmlib ONNX, and adds canvas-based image, depth, and text-layer composers with blend modes, drop shadows, and per-layer transforms.

3
Eric UniPic3 Nodes

ComfyUI nodes for UniPic3 multi-image composition and HOI

3
Eric ERNIE-Image Real Diffusers

High-fidelity ComfyUI nodes for ERNIE-Image (SFT) and ERNIE-Image-Turbo using the native diffusers pipeline, with all critical text encoder and attention weight patches applied.

3
ComfyUI-Erosdiffusion-LTX2

Custom ComfyUI nodes for extending video scenes with synchronized audio generation using LTXAVModel.

3
Eternal Nodes

Eternal Nodes for ComfyUI by EternalShade3D: ▶ Panorama 360 Viewer(Load & inspect equirectangular panoramas with drag-to-orbit, scroll zoom, live FOV write-back, & seam/pole/horizon tilt checks) ▶ Flat Shade (GPU flat shading with split and crease modes) ▶ Mesh Bridge & Trimesh to Model3D (Types.MESH ⇄ trimesh conversion and GLB export) ▶ Tile Pipeline Eternal (Split, Source, Save, and Merge pipeline for high-res outpainting) ▶ Video Sizes & Aspect Ratio Size Picker

3
comfyui-nodes-agents

In-graph ComfyUI nodes + MCP bridge for external coding agents (Claude Code / Codex)

3
Comfyui-JSON-Manager

A visual dashboard for managing, versioning, and batch-processing JSON configuration files for AI video generation workflows with Streamlit web interface and ComfyUI custom nodes.

3
Info Utils

Nodes that facilitate simpler information providing and gathering, such as Text Box, Show Data and Token Counter nodes.

3
String Utils

Nodes dedicated to the analysis and transformation of text strings, such as for formatting and conversions between types.

3
ComfyUI-EmbeddingPipelineAnalytics

this repo is to capture end-to-end data, metadata, and embeddings for ComfyUI workflows, specifically HunyuanVideo to start.

3
fexli-util-node-comfyui

A set of Fe's Util nodes for ComfyUI

3
FiL_LLM

ComfyUI custom nodes for image understanding, prompt control, and generation-ready prompt packaging.

3
FL Search Box

Restores and enhances the legacy node search experience in ComfyUI. Shows a type-filtered connection menu when dropping links on the canvas, forces the legacy search box on double-click regardless of settings, and increases the search results display height.

3
FL UI Addons

UI enhancements for ComfyUI: type-filtered connection menu on link drop, forced legacy search box, taller search results, shift+drag link cutting, and trackpad pan/pinch-zoom navigation.

3
ComfyUI-Basic-Auth

A basic auth middleware for ComfyUI

3
FrameThrower Reference

Search the FrameThrower film-still library from inside ComfyUI. Outputs the frame, its scene description, its credit line, and optional depth / pose / lineart — all three computed locally.

3
Nukomfy Suite

Server-side companion custom nodes for the Nukomfy Nuke plugin.

3
NX_HuggingFace_Flux

Nodes:Hugging Face Flux

3
NX_Translator

A custom node for translating prompts with Google Translate or DeeplL directly in ComfyUI.

3
comfyui-fb-utils

Nodes:FBStringJoin, FBStringSplit, FBMultilineStringList, FBMultilineString

3
ComfyUI-Dummy_Node_Pack

Custom node pack creating fake/dummy nodes to replace missing, obsolete, or cloud-specific nodes, allowing legacy workflows to load visually without errors while preserving connections. (Description by CC)

3
comfyui-minimal-workflow-image

Fixed implementation of the export workflow image utility from [a/pythongosssss/ComfyUI-Custom-Scripts](https://github.com/pythongosssss/ComfyUI-Custom-Scripts). All nodes should display and all node links should be visible and render 1:1 to their actual states in ComfyUI.

3
comfyui_ui_render

ComfyUI HTML Renderer Node - Display rich HTML content within ComfyUI nodes

3
Spectrum LTX

Feature-level Spectrum acceleration for native ComfyUI LTXV / LTXAV models.

3