Stability-AI/StableSwarmUI

StableSwarmUI, A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.

StableSwarmUI – A modular web UI for Stable Diffusion

What it is

  • A browser‑based interface that lets you run Stable Diffusion (and related models) locally. It focuses on high performance, easy access to power‑tools, and extensibility via plugins.

Key features

  • Generate tab – simple UI for quick image creation with options like grid generation, image editor, and auto‑workflow creation.
  • Comfy Workflow tab – raw graph editor for advanced users, exposing the full ComfyUI node‑based workflow.
  • Multi‑GPU “swarm” – can distribute generation across many GPUs to speed up large batches.
  • Backend flexibility – can use ComfyUI, AUTOMATIC1111, or the Stability AI API; optional YOLOv8 face detection, aesthetic scoring, PickScore, etc.
  • Extension system – users can add custom nodes or plugins, each with its own licensing.
  • Cross‑platform installers – one‑click scripts for Windows, Linux, macOS (Apple‑silicon only) and a Docker launch script.

How to get started

  1. Windows – download install‑windows.bat from the releases page; it installs Git, .NET 8, downloads models, and launches the server.
  2. Linux/macOS – run the provided install‑linux.sh or launch‑macos.sh after installing Git, Python 3, and .NET 8.
  3. Docker – clone the repo, run launch‑docker.sh (requires Nvidia Container Toolkit for GPU support).
  4. Open a browser to http://localhost:7801 and follow the on‑screen install wizard.

Current status

  • Marked Beta (v0.6.4.1). Core generation and workflow tools are stable, but features like mobile browser support, full model display, LLM‑assisted prompting, and a packaged Electron app are still planned.
  • Development moved from Stability AI to an independent maintainer (mcmonkeyprojects/SwarmUI). Migration instructions are provided.

Legal / licensing

  • The core code is MIT‑licensed. It bundles or can auto‑install a variety of third‑party components (e.g., 7‑zip, ComfyUI, AUTOMATIC1111, YOLOv8) each under their own licenses (LGPL, GPL, AGPL, Apache 2, MIT, etc.). Users should be aware of those licenses, especially when distributing generated content or extensions.

Who it’s for

  • Beginners who want a straightforward “click‑to‑generate” UI.
  • Power users who need multi‑GPU batch generation, custom node graphs, or want to plug in extra tools like aesthetic scoring.
  • Developers interested in extending the UI with new nodes or integrations.

All information is taken directly from the repository’s README.

Related

  • Project
    Bing-su/adetailer

    An extension for the Stable Diffusion web UI that automates masking and inpainting to refine details in generated images.

  • Project
    mcmonkeyprojects/SwarmUI

    SwarmUI is an open‑source, web‑based UI for running AI image, video, and audio generation models (Stable Diffusion, Flux, etc.). It offers a beginner‑friendly Generate tab, an advanced Comfy‑style workflow editor, multi‑GPU “swarm” support, and extensible plugins. Installers exist for Windows, Linux, macOS (Apple‑silicon), and Docker, with cloud‑GPU templates for Runpod and Vast.ai. The project is in an “Almost‑Release” beta (v0.9.8) and is MIT‑licensed, though it can auto‑install GPL/AGPL components.

  • Project
    palxiao/poster-design

    An open-source AI poster design tool and online image editor featuring a DOM canvas, AI background removal, and a full management backend.

  • Project
    aloshdenny/reverse-SynthID

    A reverse-engineering project that detects and removes Google's invisible SynthID watermarks from Gemini-generated images using spectral analysis and a multi-stage adversarial pipeline.