ComfyUI Custom Extensions

An interactive sketching and drawing node for ComfyUI with stylus/pen support – built for fast, intuitive scribbling directly inside your workflows, geared towards ControlNet-style workflows which utilize scribbles and line art.

you can using anydoor ,change clothes,object

train your lora in Diffusion_pipe_in_ComfyUI in wsl2

Capture window content from other programs, easyway combined with LCM for real-time painting

ComfyUI-Documents is a powerful extension for ComfyUI that enhances workflows with advanced document processing capabilities. It includes nodes for loading and parsing various document types (PDF, TXT, DOC, DOCX), converting PDF pages to images, splitting PDFs into individual pages, and selecting specific images from batches. Features include text extraction, image conversion, and seamless integration with existing ComfyUI projects.

The SuperPrompter node is a ComfyUI node that uses the SuperPrompt-v1 model from Hugging Face to generate text based on a given prompt. It provides various parameters to control the text generation process.

A comprehensive set of ComfyUI nodes for using Large Language Models (LLM) as text encoders for SDXL image generation through a trained adapter.

Prompt Stash is a simple plugin for ComfyUI that lets you save your prompts and organize them into multiple lists. It also features a pass-through functionality, so you can hook it up to an LLM node (or any text outputting node) and capture its outputs directly.

A small set of nodes I created for myself. Features multiple simultaneous prompts in batches, an image saver with ability to have JSON saved to separate folder, image analysis nodes, switches for text and numbers, and more.

A comprehensive collection of custom nodes for ComfyUI, focusing on image processing, text handling, and workflow optimization. Includes nodes for image blending, text overlay, batch processing, image resizing, and advanced save operations.

Transform AI image generation from random exploration into deliberate artistic navigation. This advanced KSampler replacement blends traditional noise with shader noise. Navigate latent space with intention using adjustable noise parameters, shape masks, and colors transformations.

An implementation of adaptive guidance for ComfyUI See [a/https://bcv-uniandes.github.io/adaptiveguidance-wp](https://bcv-uniandes.github.io/adaptiveguidance-wp)

Seed-VC: Very quickly convert `speech` or `singing` into another person's voice, without changing the content rhythm

Professional ComfyUI custom nodes for Tencent's HunyuanImage-3.0 80B multimodal model, with multiple loading modes, smart memory management, large image generation with CPU offload, and optional prompt enhancement via LLM APIs.

This is a universal custom node for ComfyUI that supports both Text-to-Image and Image-to-Image generation by calling various models via the official ModelScope API.

Nodes: KSampler With Refiner (Fooocus). The KSampler from [a/Fooocus](https://github.com/lllyasviel/Fooocus) as a ComfyUI node [w/NOTE: This patches basic ComfyUI behaviour - don't use together with other samplers. Or perhaps do? Other samplers might profit from those changes ... ymmv.]

A ComfyUI extension that helps users relink missing models in workflows

Instantly replace your image's background.

A LaMa preprocessor for ComfyUi

Image to 3D using Hunyuan-3D-2

ComfyUI custom nodes of clip-interrogator

View Image Metadata of ComfyUI as well as of ForgeUI or Automatic 1111 generated images in Easily Readable Format

FoleyCrafter is a video-to-audio generation framework which can produce realistic sound effects semantically relevant and synchronized with videos.

Fork of node to load models in INT8 for 1.5~2X Speed gains on 30 series cards. Contains additional fixes and performance improvements.

Quantization toolkit for ComfyUI with native W4A4, W4A8, and W8A8 conversion, mixed-precision loading, LoRA handling, and low-VRAM runtime controls.

Professional video object removal suite using MiniMax optimization. Includes BMO-enhanced nodes with VAE normalization, temporal preservation, and 6-step inference. Complete video inpainting solution for ComfyUI.

A set of nodes to prepare the noise predictions before the CFG function

Perform Bringing-Old-Photos-Back-to-Life

Multi-shot chaining for MiniMax-H3 audio+video: carry identity, voice and framing across shots so a sequence reads as one take.

A research Node based project on Artificial Intelligence using ComfyUI visual editor with Stable diffusion Local processing focus in mind. This custom node is intended to serve the purpose to offer a large palette of prompting scenrarios, based on Public Checkpoint Models OR/AND Private custom Models and LoRas. It includes an integrated learning machine process as well as a set of workflows.

Nodes for fine-tuning lora in ComfyUI, dependent on training tools such as kohya-ss/sd-scripts

Interactive sigma schedule editor for ComfyUI — NURBS spline curve widget

High-precision audio trimming custom node based on frame rates for ComfyUI - trim audio precisely by frame numbers instead of timestamps, perfectly matching video frame synchronization needs. (Description by CC)

This repository explains how to accelerate image generation in ComfyUI using Pruna, an inference optimization engine that makes AI models faster, smaller, cheaper, and greener. ComfyUI is a popular node-based GUI for image generation models, for which we provide a custom compilation node that accelerates Stable Diffusion (SD) and Flux inference, while preserving output quality.

'Eses Image Effect Bloom' image post processing effect for ComfyUI, it uses GPU and has optimized blur effect calculations. Minimal dependencies, simple and easy to use UI.

An extension that's adds advanced audio processing capabilities to ComfyUI with professional-grade audio effects and AI-powered audio enhancement.

A voice conversion extension node for ComfyUI based on [a/FreeVC](https://github.com/OlaWod/FreeVC), enabling high-quality voice conversion capabilities within the ComfyUI framework.

Custom ComfyUI Nodes for TTS with Kokoro, genenrate and merge speakers for new style generations.

This extension provides various SDXL Prompt Stylers. See: [a/youtube](https://youtu.be/WBHI-2uww7o?si=dijvDaUI4nmx4VkF)

Node2.0-based professional alignment & real-time node color picker - innovative first support: A must-have plugin for managing node layout and color schemes in ComfyUI. Features a real-time color picker, alignment, 7 preset colors, grayscale/custom modes, and one-click reverse alignment.

Symbolic Music Generation, NotaGen node for ComfyUI.

A visual prompt builder ComfyUI custom node for structured JSON prompt generation. Build photography-style prompts with camera settings, lighting, composition, and color palettes. Compatible with FLUX (Black Forest Labs), z-image, and other JSON-prompt models.

Comfyui-rodin is a 3D generation extension based on Rodin-API. It provides many of the functionality nodes currently available in RodinAPI and It provides a 3D preview node for ComfyUI.

Custom set of nodes used by glif.app. With glif you can build mini apps that are powered by custom comfy workflows.

ComfyUI custom nodes for Z-Image Image-to-LoRA generation. Generate personalized LoRA weights from reference images using DiffSynth-Studio's Z-Image pipeline.

Integrates Polotno Canvas Editor into ComfyUI for advanced image editing and design

ComfyUI implementation of video color grading using 3D LUT generation from reference images via two-stage diffusion process.

The ComfyUI Text Overlay Plugin provides functionalities for superimposing text on images. Users can select different font types, set text size, choose color, and adjust the text's position on the image.

Comfyui-rodin is a 3D generation extension based on Rodin-API. It provides many of the functionality nodes currently available in RodinAPI and It provides a 3D preview node for ComfyUI.

ComfyUI node for Maya1 TTS - Expressive voice generation with 20+ emotions, voice design, and SNAC neural codec

ComfyUI implementation of the [a/InstantX IP-Adapter for SD3.5 Large](https://huggingface.co/InstantX/SD3.5-Large-IP-Adapter).

a comfyui cuatom node for audio subtitling based on [a/whisperX](https://github.com/m-bain/whisperX.git) and [a/translators](https://github.com/UlionTse/translators)

Bridge between ComfyUI and blender's ComfyUI-BlenderAI-node addon.

Generate Audio from any video and or text

ComfyUI nodes to use Sapiens2

ComfyUI OmniConsistency Nodes is a collection of nodes for ComfyUI that allows you to load and use OmniConsistency models.

This extension provides a node that allows you to overlay text on an image or a batch of images with support for custom fonts and styles.

Image to caption with CLIP ViT-L/14. Small and fast addition to the CLIP-L model you already have loaded to generate captions for images within your workflow.

Nodes:Stability SD3, Stability Outpainting, Stability Search and Replace, Stability Image Core, Stability Inpainting, Stability Remove Background, Stability Creative Upscale. Add API key to environment variable 'SAI_API_KEY' Alternatively you can write your API key to file 'sai_platform_key.txt' You can also use and/or override the above by entering your API key in the 'api_key_override' field of each node.

This is a custom node for ComfyUI that allows you to use the WaveSpeed AI API directly in ComfyUI. WaveSpeed AI is a high-performance AI image and video generation service platform offering industry-leading generation speeds. For more information, see [a/WaveSpeed AI Documentation](https://wavespeed.ai/docs).

Batched Runge-Kutta Samplers for ComfyUI

Anima Detail Enhancer Node for ComfyUI

Complete workflow suite for ComfyUI that transforms images into PBR material sets ready for game engines and 3D software.

ComfyUI extension for FLUX FaceIR aligned-face and whole-image restoration.

UI-only extension for model library management and workflow authoring. Features visual model/LoRA insertion, prompt notebooks, gallery, and safe file management. Includes 'Model Doctor' to auto-restore broken model paths using metadata previously injected by this plugin.

This suite of nodes unlocks high-performance parallel processing in ComfyUI by utilizing **Model Replication**. Unlike standard offloading which moves a single model instance between devices, these nodes create independent replicas of the model on each selected GPU/CPU, allowing for true simultaneous batch processing.

ComfyUI custom node for Attention Couple

ComfyUI-CrewAI aims to integrate Crew AI's multi-agent collaboration framework into the ComfyUI environment. By combining the strengths of Crew AI's role-based, collaborative AI agent system with ComfyUI's intuitive interface, we will create a robust platform for managing and executing complex AI tasks seamlessly

A [a/Matchering](https://github.com/sergree/matchering)-node for ComfyUI. NOTE: You take TWO audio files and feed them into Matchering

ComfyUI custom node implementation of VideoMaMa for video matting with mask conditioning.

ComfyUI nodes for YuE2-3B: a style description and lyrics become a readable score and then a complete 48 kHz stereo song, generated locally.

Spectrum sampling acceleration technique for SDXL models using Chebyshev polynomials to forecast spectral features and skip redundant UNet computations.

Professional voice cloning and audio editing node for ComfyUI using Step Audio EditX

Create immersive 3D stereoscopic images and videos! Transform your ComfyUI generations into stunning side-by-side 3D visuals for videos and image sequences. Powered by Depth-Anything-V2, no external depth maps needed. Perfect for VR, 3D displays, and cross-eyed viewing - no special glasses required!

Modularized version of Disco Diffusion for use with ComfyUI.

A single-node ComfyUI custom package that turns up to 4 reference images into a 2×2 stitched grid and injects it into Flux Klein 9B conditioning.

Comfyui-deepseek-r1 Node Plugin

a custom node for [a/MaskGCT](https://github.com/open-mmlab/Amphion/blob/main/models/tts/maskgct/README.md) to Zero-Shot Text-to-Speech

A custom node for ComfyUI that provides a visual gallery for managing and applying multiple LoRA models.

This is a Seed-X-PPO-7B ComfyUI plugin. Easy to use

A facefusion custom node for ComfyUI. Swap or restore faces for image or video

An extension supporting more streamlined prompt queue management.

ComfyUI_LucidFlux:Caption-Free Universal Image Restoration with a Large-Scale Diffusion Transformer，you can use it in ComfyUI

NODES: ComfyUI-YuE2-Trainer - Experimental trainer nodes for YuE2

ComfyS3 seamlessly integrates with [a/Amazon S3](https://aws.amazon.com/en/s3/) in ComfyUI. This open-source project provides custom nodes for effortless loading and saving of images, videos, and checkpoint models directly from S3 buckets within the ComfyUI graph interface.

Progressive upscaling node for flow-matching models that incrementally doubles resolution with flow-consistent re-noising, denoising, and skip residual blending to preserve composition.

a custom nodde for [a/IMAGDressing](https://github.com/muzishen/IMAGDressing)

Sigma-locked two-stage sampler and dual resolution selector for Krea 2 (and possibly other) workflows in ComfyUI.

Qwen Image Edit uses a Vision Language Model to analyze input images and automatically enhance prompts with detailed descriptions.

Qwen Image Edit uses a Vision Language Model to analyze input images and automatically enhance prompts with detailed descriptions.

Provides nodes to utilise NVIDIA NIM, a set of accelerated inference microservices that allow you to run AI models on NVIDIA GPUs anywhere.

Two simple nodes for stereoscopic image generation. Nodes: Stereo Image Node - a basic port from the Automatic1111 stereo script in thygate/stable-diffusion-webui-depthmap-script, LazyStereo - a naïve stereo image generator

FL Song Gen - AI-powered song generation nodes for ComfyUI. Generate complete songs with vocals and instrumentals from lyrics using Tencent's SongGeneration (LeVo) model. Features style transfer, auto style presets, dual-track output, and up to 4m30s song generation.

Musubi Tuner by kohya_ss

This project provides a node for ComfyUI to use the JoyCaption-Beta model in GGUF format for image captioning.

High‑quality music audio enhancement for ComfyUI: FlashSR super‑resolution + Fat Llama spectral enhancement (GPU & CPU).

A custom node for ComfyUI that integrates LM Studio's vision models to generate text descriptions of images. It provides a flexible and customizable way to add image-to-text capabilities to your ComfyUI workflows, working with LM Studio's local API.

The custom Snap processing node has been converted for ComfyUI production. It currently includes a simple PyQt5 interactive interface as well as practical nodes for basic operations like area calculation..

This custom node for ComfyUI allows you to create layers of an image based on input masks and save them into a PSD file.

A Chinese and English text translation plugin for ComfyUI.