Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
ComfyUI helps artists, designers, and content creators generate images, videos, audio, and even 3D models using AI without writing any code. You input descriptions or existing media, and the system processes them through a visual flowchart of AI models to produce highly customized creative outputs. This is ideal for visual artists, marketers, or anyone experimenting with generative AI for media creation.
106,230 stars. Actively maintained with 118 commits in the last 30 days.
Use this if you want to create highly customized AI-generated images, videos, or audio using a visual, drag-and-drop interface, leveraging advanced features like ControlNet, inpainting, and model merging.
Not ideal if you're looking for a simple, one-click AI generation tool without needing to understand or configure complex workflows.
Stars
106,230
Forks
12,230
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
118
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Comfy-Org/ComfyUI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Compare
Related models
Comfy-Org/comfy-cli
Command Line Interface for Managing ComfyUI
YanWenKun/ComfyUI-Docker
🐳Dockerfile for 🎨ComfyUI. | 容器镜像与启动脚本
runpod-workers/worker-comfyui
ComfyUI as a serverless API on RunPod
Acly/comfyui-tooling-nodes
Nodes for using ComfyUI as a backend for external tools. Send and receive images directly...
pollockjj/ComfyUI-MultiGPU
This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well...