comfyui

The self-hosted AI workstation. Autonomous screen agents, 3-tier neural routing, parallel agent swarms, video generation, 4K/8K upscaling, RAG, voice interface, 60+ tool execution engine — all running locally on your hardware.

Convert your workflows into nodes and chain them together

Calculate the execution time of all nodes.

A ComfyUI node pack that implements FreeLong (NeurIPS 2024) spectral blending for Wan 2.2 video generation

ComfyUI to TouchDesigner custom node for real-time streaming of images, video, 3D models, audio, and text.

Upscaling stable diffusion latents using a small neural network.

a simple lama remover

A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captioning and visual analysis.

A slightly opinionated Nix flake for ComfyUI with curated custom nodes. Supports macOS (Apple Silicon) and Linux with CUDA.

Common workflows and resources for generating AI images with ComfyUI.

all ComfyUI http/ws APIs. support NodeJS / Browser environments. and advanced programmable workflow.

TBG Enhanced Tiled Upscaler and Refiner upscales up to 200MP with precise control. It features dual-model processing (structure + detail), per-pixel denoising to control where creativity is applied, and per-tile and per-object prompts, denoise, and seeds. Advanced fast previews. New generative tile fusion seamless joining, even on high-denoise.

GPTs for ComfyUI | Explanation Creation Resolution | ComfyUI 助手

ComfyUI TCD implementation

MCWW: Additional non-node based UI for ComfyUI focused on inference. Stable UI states; presets; and advanced queue. Based on Gradio

Custom tools to enhance your Open-Webui Experience! 🚀

ComfyUI Depth Anything (v1/v2/v3/distill-any-depth) Tensorrt Custom Node (up to 14x faster) ⚡

3D x AI hybrid editor, built with three.js

Janky implementation of HiDiffusion for ComfyUI

Extended Save node for ComfyUI