ComfyUI is a powerful and modular stable diffusion GUI with a
graph/nodes/flowchart based interface. It allows users to design and execute
advanced stable diffusion pipelines without needing to code.

Key features include:
- Node/graph/flowchart interface for complex workflows
- Support for multiple image models (SD1.x, SD2.x, SDXL, SD3, Flux, etc.)
- Video models support (Stable Video Diffusion, Mochi, LTX-Video, etc.)
- Audio models support (Stable Audio, ACE Step)
- Asynchronous queue system
- Smart memory management with automatic GPU offloading
- Works with as low as 1GB VRAM
- Support for LoRAs, hypernetworks, ControlNet, and upscaling models
- Fully offline operation