AI ToolsFeatured

ComfyUI

Name: ComfyUI
Author: Comfy-Org

by Comfy-Org

The most powerful and modular diffusion model GUI and backend with a graph/nodes interface.

View on GitHub

Stars

122,500

Forks

14,500

Language

Python

License

GPL-3.0

About

ComfyUI is the most powerful and modular AI engine for content creation — a node-graph interface for designing complex image, video, 3D, and audio generation workflows without code. Natively supports the latest open models (Flux, SD3.5, Qwen Image, Hunyuan, Wan) plus API nodes for closed models (Nano Banana, Seedance). Smart memory management runs large models on GPUs with as little as 1GB VRAM, and the async queue only re-executes the parts of a workflow that change. Desktop app, portable builds, or self-host.

Topics

stable-diffusionai-image-generationworkflowpytorchimage-generationnode-graph