A modular web interface for generating images, video and some audio with Stable Diffusion, Flux and other models.
Script installers for Windows, Linux and Apple-silicon Macs, with Docker, Colab and cloud GPU options.
SwarmUI is an MIT-licensed web interface for local AI image generation, formerly named StableSwarmUI. It suits beginners and experts who want a script-installed UI covering Stable Diffusion, Flux and video models.
You run install-windows.bat or install-linux.sh, or the macOS launch script on M-series Macs, and open the web interface. The README says it supports image and video models, some audio models, and can run in Docker, on Google Colab or on rented GPUs such as Runpod and Vast.ai.
It suits people who want a friendlier front end than raw node graphs and are comfortable with a beta-stage tool. It does not suit anyone who needs a stable 1.0 release or hosted support.
install-windows.bat and install-linux.sh set it up for you.
Stable Diffusion, Flux, video models and some audio models.
Docs cover Docker, Google Colab, Runpod and Vast.ai.
macOS runs only on M-series Macs via a launch script.
SwarmUI itself is MIT, though connected projects may carry GPL variants.
Described as a modular, extensible web interface.
Free under the MIT licence. The only cost is your own hardware or any cloud GPU you rent to run it; the project shows no paid plan.
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
No. The README says you can only run it on Mac computers with M-series Apple silicon processors.
SwarmUI is MIT-licensed. The README notes that connected projects may use GPL-variant licences and that each model has its own licence.
The README documents Google Colab and cloud GPU providers such as Runpod and Vast.ai as alternatives to a local card.
See Zekai first in Google