Home/AI/ComfyUI
C
Website Repository
Capabilities:image
License:GPL-3.0
Open sourceLocal runtime

ComfyUI

About

A node-based interface for Stable Diffusion and other diffusion models. Powerful graph workflows give you fine-grained control over generation pipelines — from simple prompts to complex multi-stage compositions.

Pricing

Free

ComfyUI is a node-based workflow tool for generative image AI. You wire together nodes — samplers, models, latents, ControlNet — to build precise and reproducible pipelines.

Key Features

  • Node graph editor with drag-and-drop workflows.
  • Runs locally with GPU or CPU.
  • Workflow sharing via JSON files.
  • Support for SDXL, SD3, Flux and video models.
  • Custom nodes and extensions.
  • API server mode for automation.

Pricing

ComfyUI is free and open source under GPL-3.0.

Getting Started

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI && pip install -r requirements.txt
python main.py

Open http://127.0.0.1:8188 and load an example workflow.