ComfyUI Custom Extensions

In-workflow Nodes for ComfyUI - Heavy interaction and streaming capabilities

Nodes:VideoLaVITLoader, VideoLaVITT2V, VideoLaVITI2V, VideoLaVITI2VLong, VideoLaVITT2VLong, VideoLaVITI2I

Add caching to any custom node

comfyui-default-values-manager

This is a ComfyUI node that allows you to translate subtitles using the Whisper. Now support for multiple languages: ['zh', 'en', 'ja', 'ko', 'ru', 'fr', 'de', 'es', 'pt', 'it', 'ar'] You may need to put fonts in the 'fonts' folder to support different languages.

DiffHDR (LDR to HDR reconstruction for images, videos and HDRI panoramas) on ComfyUI's native Wan2.1-VACE.

A powerful ComfyUI multi-image composition node that supports real-time adjustment of image position, size, and rotation angle on an interactive Canvas, with freehand drawing capabilities and real-time preview of composition effects.

This is a version of [a/sd-d2-prompt-selector](https://github.com/da2el-ai/sd-d2-prompt-selector) reworked for ComfyUI. It's just a prototype that I've put together for now. The random syntax of sd-d2-prompt-selector cannot be used; instead, the DynamicPrompt syntax is used

A small collection of custom nodes for use with ComfyUI, by [a/Discopixel](https://discopixel.studio)

ComfyUI Custom Node for HeartMuLa AI Music Generation and Transcript Text (Low VRAM optimized)

Nodes: Images_Converter, Show_Text, Strings_From_List, Save_Text, Random_Images, Load_Images_From_Paths, JSPaint.

Collection of one or more custom nodes for ComfyUI made mainly for personal use (GitHub README for more info). Nodes: live Token Counter on any node, switch nodes with fallback functionality and FLOAT/INT nodes (and maybe more).

A ComfyUI node for producing stereoscopic and autostereogram (magic eye) images and videos.

Comfyui [a/BPT](https://github.com/whaohan/bpt) Wrapper (Trimesh in/out connections)

This custom node for ComfyUI allows you to use the Doubutsu small VLM model to describe images. Credit and further information on Doubutsu: [a/https://huggingface.co/qresearch/doubutsu-2b-pt-756](https://huggingface.co/qresearch/doubutsu-2b-pt-756)

A comprehensive collection of advanced image processing nodes for ComfyUI, featuring state-of-the-art denoising, enhancement, and restoration techniques with GPU acceleration and specialized film grain processing.

ComfyUI-AutoLabel is a custom node for ComfyUI that uses BLIP (Bootstrapping Language-Image Pre-training) to generate detailed descriptions of the main object in an image. This node leverages the power of BLIP to provide accurate and context-aware captions for images. by Fexploit.

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.

Nodes:Save Image Without Metadata

Various nodes related to audio.

Nodes to make ComfyUI-Image-Saver and rgthree-comfy more compatible. Allowing Power Lora Loader node to be used with Image Saver node. Also adding nodes to extract Image Saver compatible strings to simplify workflows.

Partial MPS support for ComfyUI nodes for LivePortrait to use them on a MacBook

This plugin integrates the Janus-Pro multi-modal model into ComfyUI, enabling advanced image understanding and text-to-image generation capabilities. It supports both image analysis and creative image generation workflows.

Simple camera prompt builder node for Qwen-Edit-2509 Multiple-Angles in ComfyUI.

Unofficial implementation of [a/dreamtalk](https://github.com/ali-vilab/dreamtalk) for ComfyUI

Custom nodes pack provided by [a/HiFORCE](https://www.hiforce.net/) for ComfyUI. This custom node helps to conveniently enhance images through Sampler, Upscaler, Mask, and more. NOTE:You should install [a/ComfyUI-Impact-Pack](https://github.com/ltdrdata/ComfyUI-Impact-Pack). Many optimizations are built upon the foundation of ComfyUI-Impact-Pack.

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.

This project is designed to detect whether images generated by ComfyUI are Not Safe For Work (NSFW). It uses a machine learning model to classify images as either safe or not safe for work and returns a confidence score for the NSFW classification.

Direct Higgsfield API integration for ComfyUI — multi-model image and video generation with Soul 2.0, Seedream 4, Kling 2.1, Seedance, and more. Use your own API key.

Automatically display context-aware notes based on workflow state, selected nodes, and node attributes in ComfyUI.

Plenio Music Production System: song writing, YuE2 and MiniMax Music 3 generation, editable scores and release export for ComfyUI.

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.

NOTE: Concatenate Strings, Format Datetime String, Integer Caster, Multiline String, Truncate String. Yet Another Node Collection, a repository of simple nodes for ComfyUI. This repository eases the addition or removal of custom nodes to itself.

Interactive 3D pose editor inside ComfyUI. Load VRM/GLB/GLTF models, drag bones to pose, control shape keys/expressions, and capture as IMAGE. All Three.js dependencies are bundled locally (no CDN required).

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

ComfyUI custom nodes for Riemannian geometry and Bayesian latent space manipulation

ComfyUI version of https://github.com/laksjdjf/pfg-webui. (To use this extension, you need to download the required model file from **Install Models**)

Nodes to run nodes on remote ComfyUI instances.

A custom node for ComfyUI that enables integration with Google Sheets. It allows reading from and writing to Google Sheets directly from ComfyUI workflows, making it easy to import and export data.

ComfyUI for [a/M3Net](https://github.com/I2-Multimedia-Lab/M3Net)

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.

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

A unified ComfyUI custom node that integrates all Reve API endpoints (Create, Edit, Remix) into a single, dynamic node with operation-specific inputs and seamless operation switching.

A ComfyUI node for creating human character prompts with guided fields for gender, age, ethnicity, body type, hair, clothing, accessories, pose, camera, lighting, and art style. (Description by CC)

A general comfyui model loading plugin that supports loading unet models quantized in bnb-4bit (nf4 and fp4) format

Convert PoseKeypoint to mask, please refer to the example workflow for usage instructions.

Add a node that outputs width and height of the size selected from the preset (.csv).

Nodes: Noxin Complete Chime, Noxin Scaled Resolutions, Load from Noxin Prompt Library, Save to Noxin Prompt Library

ComfyUI-Mosaic-Mask is an automatic tool designed to detect and mask mosaic areas in input images.

An interactive color balance adjustment node for ComfyUI, featuring a clean interface and realtime preview.

Client-side nodes for enabling/disabling parts of your graph - by hand or from a wired boolean. A more flexible take on rgthree's Fast Group Bypasser. Two nodes, identical behaviour, different target.

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.

This project is a custom node for ComfyUI that integrates the power of the Google Gemini 2.5 Flash Image (“Nano Banana”) API. It provides a single versatile node, the Gemini Nano Banana, which allows you to perform image generation and editing operations directly within your workflows.

Generative Paint is a custom node for ComfyUI that adds an advanced painting interface directly usable from the browser.

An advanced, high-productivity prompt engineering suite for ComfyUI.

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.

This is a Google Gemini Pro API integration node for ComfyUI, supporting text, image, video, and audio inputs.

Custom ComfyUI nodes for loading and saving images to a PixlStash vault.

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

UI Decorators is a set of 4 nodes to enhance frontside SubGraph usability and organization. A Note, a Divider, an editable Spacer, and a Title node. Includes color pickers for fonts, font sizing, bold/non-bold text, and background color picker for the note

A custom node for ComfyUI that performs speaker diarization to isolate individual speaker audio tracks from a single audio source.

A custom node for ComfyUI to parse and extract data from JSON strings.

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.

ComfyUI loaders for MiniMax-H3 NF4 weights, plus prompt, canvas, audio reroll, and AV latent tools.

ComfyUI nodes for KRAFTON Raon-OpenTTS (F5-TTS-style CFM/DiT) with INT8 ConvRot quantization support via comfy-kitchen

Native ComfyUI nodes for Zyphra ZONOS2 text-to-speech and voice cloning with AIMDO memory tracking

Nodes: SRL Conditional Interrupt, SRL Format String, SRL Eval, SRL Filter Image List. This is a collection of nodes I find useful. Note that at least one module allows execution of arbitrary code. Do not use any of these nodes on a system that allow untrusted users to control workflows or inputs.[w/WARNING: The custom nodes in this extension are vulnerable to **security risks** because they allow the execution of arbitrary code through the workflow]

This comfyUI node intializes at startup automatically and displays the clock in CMD console when Process starts and ends.

Use LoRAs, model merges and ControlNets (LLLite/VACE) across Anima generations (Anima, 2.9B, 3.8B/Pro52 and beyond) with automatic block-index remapping

This project adds high-quality Text-to-Speech capabilities to ComfyUI using the Orpheus TTS model. Create natural-sounding voices with emotional expressions, multilingual support, and audio effects.

Using Demucs in comfyUI, make Music Source Separation

using [a/StreamV2V](https://github.com/Jeff-LiangF/streamv2v) in ComfyUI

TRELLIS.2:Native and Compact Structured Latents for 3D Generation,load single dinov3

DAVE (DC Attenuation for diVersity Enhancement) as a drop-in MODEL patch for Anima / Cosmos-predict2 DiT: recover same-prompt sample diversity by attenuating the DC component of early-mid blocks over the first tau fraction of steps. Self-contained — bundles the shipped block-pool mask, pulls no training-repo code.

NODES: Dynamic Prompts Text Encode, Feeling Lucky Text Encode, Output String

ComfyUI-SVGFullfill is a custom node for ComfyUI that handles SVG file processing. Key features: - SVG file upload and preview - Replace images (up to 3) and text elements (up to 10) in SVG - Chinese font support - Real-time canvas preview - PNG export

This extension provides nodes for [a/DeepCache: Accelerating Diffusion Models for Free](https://arxiv.org/abs/2312.00858) NOTE:Original code can be found [a/here](https://gist.github.com/laksjdjf/435c512bc19636e9c9af4ee7bea9eb86). Full credit to laksjdjf for sharing the code.

Three custom ComfyUI nodes: Empty Image RGB, Text Line Break, and Random Chars (Append) for convenient utilities. (Description by CC)

Nodes:Prompt editing, Word as Image

krea.ai-style moodboard and vibe transfer for identity-preserving editing using Krea 2 model, as ComfyUI nodes for style and composition control.

A versatile LoRA merger for Flux (4B/9B/Dev), Z-Image, and SDXL. Features cross-architecture scaling, weight normalization, and live model baking.

A node that processes input text with the [a/Unprompted templating language](https://github.com/ThereforeGames/unprompted).

A custom node for ComfyUI that enables Large Language Model (LLM) chat interactions with optional image input support.

An elegant, premium, remote bypass and wire-management nodes suite for ComfyUI.

A small set of JavaScript files I created for myself. The scripts provide Quality of Life enhancements to the ComfyUI interface, such as changing fonts and font sizes.

This project is a ComfyUI version of [a/sd-webui-segment-anything](https://github.com/continue-revolution/sd-webui-segment-anything). At present, only the most core functionalities have been implemented. I would like to express my gratitude to [a/continue-revolution](https://github.com/continue-revolution) for their preceding work on which this is based.

A manager for the whole ComfyUI workspace: custom nodes, themes, models, downloads, a resource monitor and a desktop.

This extension provides tag completion feature in textbox.

This node provides a simple way to view the output of many nodes, without leaving ComfyUI.

Faithful FLUX-focused ComfyUI port of Spectrum spectral feature forecasting.

Drop-in TorchCompile node that preserves LoRA patches.

Standalone ComfyUI node pack for RealRestorer image restoration with self-contained model code and no vendored dependencies.

Support input of Chinese prompts.

Make AudioX avialbe in ComfyUI.