ComfyUI

Comfy-Org/ComfyUI

A local GUI and backend for combining image, video and audio generation models as node graphs, supporting the latest models like Flux, Wan and Qwen-Image.

Why pick itNew open models usually land in ComfyUI first; workflows can be saved as files and shared. A no-setup desktop version is available.

Install

InstallDownload ComfyUI Desktop from comfy.org, or pip install comfy-cli && comfy install

GitHub: Comfy-Org/ComfyUI
Website: comfy.org
Stars: ★ 143k
License: GPL-3.0
Language: Python
Last push: Oct 25, 2026
Category: Creative

Good for

Build image, video, audio and 3D generation pipelines as a node graph without code
Run open models such as Flux, Qwen Image and Wan locally
Reuse workflows as templates or subgraphs, or expose them through a simple App Mode UI
Integrate workflows into other applications through the local API

Getting started

Download ComfyUI Desktop from comfy.org (Windows, macOS), or run pip install comfy-cli && comfy install
Open a workflow from the template library
Download the models it needs and run it

Before you install

The project says it can run large open models on as little as 4GB VRAM plus 8GB RAM; manual install supports NVIDIA, AMD, Intel, Apple Silicon and Ascend. Comfy Cloud is a paid option if you lack hardware.

Summarized by AI from the project docs; check the official docs before relying on it.

In the news

10/25, 14:15Open source
BFL Open-Sources FLUX 3 Image Klein
Black Forest Labs released the open-weights model FLUX 3 Image Klein, featuring a 5.6B parameter architecture. The model supports native 4K and text rendering, with its distilled version generating images in about 8.9 seconds on an RTX 4070 GPU and integrating with ComfyUI.
T客邦

Similar tools

MoneyPrinterTurboCreative · ★ 135k
Automatically generate HD short videos from topics or keywords, including scripts, subtitles, background music, and editing.
UpscaylCreative · ★ 51k
A desktop AI image upscaler that enlarges low-res photos or illustrations 2–16× and restores detail, with batch processing.
IndexTTSCreative · ★ 24.7k
Zero-shot speech synthesis open-sourced by bilibili: clone a voice from a few seconds of reference audio, with control over emotion and exact duration. Strong in Chinese and English.
pyVideoTransCreative · ★ 19.5k
Translates videos from one language to another: speech recognition, subtitle translation and dubbing, merged back into the video. Can also do transcription or TTS alone.
VideoLingoCreative · ★ 18.9k
One click for speech recognition, sentence segmentation, translation, subtitle alignment and AI dubbing, outputting Netflix-standard single-line subtitles.