SwarmUI

SwarmUI is a self-hosted AI image generation interface for people who want both straightforward generation controls and access to detailed ComfyUI workflows. You can use it with models running on your own hardware.

• Generation and editing: Create images through the Generate tab, edit images and let the interface build workflows automatically.
• ComfyUI workflows: Work directly with the node graph when you need control over individual processing steps.
• Output comparisons: Use the Grid Generator to compare results, with support for multiple GPUs generating images for the same user at once.
• Image, video and audio models: Generate images with Stable Diffusion, Flux and Krea 2, video with MiniMax H3, Wan and LTX-2, and audio with ACE-Step.

SwarmUI runs on Windows and Linux, or through Docker, with a browser interface. On macOS, it requires an M-series Apple Silicon processor. It supports ComfyUI and optionally AUTOMATIC1111/stable-diffusion-webui as a backend.

You can also deploy it on rented GPUs through Runpod or Vast.ai. Those deployments run on remote hardware rather than your own machine. SwarmUI is free and open source under the MIT license; connected backends and bundled components have separate license terms.