Skip to content
SPECIFICTION
Get listed

AUTOMATIC1111 Stable Diffusion WebUI

github.com

WebWindowsmacOSLinuxAPISelf-hosted
Visit github.com
Spec score 8.1 #47 of 124 in AI image generators

What it is

AUTOMATIC1111 Stable Diffusion WebUI is a Gradio-based interface for generating and editing images with Stable Diffusion. It provides text-to-image and image-to-image modes, plus inpainting, outpainting, color sketch, and prompt matrix tools. The Extras tab offers face restoration and upscaling tools including GFPGAN, CodeFormer, RealESRGAN, ESRGAN, SwinIR, Swin2SR, and LDSR. Users can train embeddings and hypernetworks, use LoRAs, and add custom scripts or community extensions. The project lists support for Stable Diffusion 2.0, Alt-Diffusion, and Segmind Stable Diffusion, and includes an API. It provides installation instructions for Windows, Linux, and Apple Silicon Macs, and lists PNG and JPEG output. The README recommends NVIDIA GPUs and links setup guidance for AMD GPUs, Intel CPUs and GPUs, and Ascend NPUs. Its one-click installation still needs Python and Git installed. The project lists support for 4 GB video cards, with reports of 2 GB working. It is free and self-hosted.

Spec sheet

Purpose
Stable Diffusion web UI is a browser interface for Stable Diffusion built with the Gradio library.Read 12 Oct 2026 · github.com
Intended users
The repository provides installation instructions and developer documentation for users running the interface and contributors building scripts or extensions.Read 12 Oct 2026 · github.com
Free plan
YesRead 20 Sep 2026 · github.com
API
The README lists an API, and the wiki says to enable it with the --api command-line argument.Read 12 Oct 2026 · github.com
Integrations
The README lists integrations or support for xformers, DeepDanbooru, and Composable-Diffusion.Read 12 Oct 2026 · github.com
Security
The repository's Security page opened, but the page content did not provide a security or compliance statement.Read 12 Oct 2026 · github.com
Support
The wiki includes setup, usage, troubleshooting, and developer documentation pages.Read 12 Oct 2026 · github.com
License
The repository identifies its license as AGPL-3.0.Read 12 Oct 2026 · github.com
API access
YesRead 20 Sep 2026 · github.com
Customization
Users can train embeddings and hypernetworks, use LoRAs, and add community custom scripts and extensions.Read 11 Oct 2026 · github.com
Editing tools
Listed tools include outpainting, inpainting, color sketch, and prompt matrix.Read 12 Oct 2026 · github.com
Extensions
The project supports custom scripts and community extensions, including optional History and Aesthetic Gradients extensions.Read 12 Oct 2026 · github.com
Hardware
The README recommends NVIDIA GPUs and also links setup instructions for AMD GPUs, Intel CPUs and GPUs, and Ascend NPUs.Read 11 Oct 2026 · github.com
Image editing
Features include color sketch, prompt matrix, tiling, and batch processing.Read 11 Oct 2026 · github.com
Image enhancement
The Extras tab includes face restoration and image upscalers such as GFPGAN, CodeFormer, RealESRGAN, ESRGAN, SwinIR, Swin2SR, and LDSR.Read 11 Oct 2026 · github.com
Image generation
The interface provides text-to-image and image-to-image modes.Read 12 Oct 2026 · github.com
Installation
The README links installation instructions for NVIDIA and AMD GPUs, Intel CPUs and GPUs, Ascend NPUs, and Apple Silicon.Read 12 Oct 2026 · github.com
Local installation
The project provides installation instructions for Windows, Linux, and Apple Silicon Macs.Read 11 Oct 2026 · github.com
Local setup
The NVIDIA setup guide describes launching the interface at a local URL and says low-VRAM options can reduce memory use at the cost of performance.Read 12 Oct 2026 · github.com
Low-memory support
The feature list says 4 GB video cards are supported, with reports of 2 GB working.Read 11 Oct 2026 · github.com
Model support
The project lists support for Stable Diffusion 2.0, Alt-Diffusion, and Segmind Stable Diffusion.Read 11 Oct 2026 · github.com
Model training
The README lists a Training tab with hypernetwork and embedding options, plus image preprocessing features.Read 12 Oct 2026 · github.com
Output formats
PNG,JPEGRead 20 Sep 2026 · github.com
Reference images
YesRead 20 Sep 2026 · github.com
Requirements
The README says the one-click install and run script still requires Python and Git.Read 12 Oct 2026 · github.com
Text-to-image
YesRead 20 Sep 2026 · github.com
Upscaling and restoration
The Extras tab lists GFPGAN, CodeFormer, RealESRGAN, ESRGAN, SwinIR, Swin2SR, and LDSR tools.Read 12 Oct 2026 · github.com
Warranty
The license states the program is provided without warranty to the extent permitted by law.Read 11 Oct 2026 · github.com

Strong points and limits

Strong points

  • Text-to-image and image-to-image modes
  • Includes inpainting and outpainting tools
  • Supports custom scripts and community extensions
  • PNG and JPEG output
  • Free to use

Limits

  • One-click setup still requires Python and Git
  • Low-VRAM options can reduce performance
  • Program is provided without warranty

Who it suits

The interface suits people who want to run Stable Diffusion locally and use image generation, editing, or extension tools. Its setup guidance also covers contributors building scripts or extensions.

Verdict

AUTOMATIC1111 offers a broad set of generation, editing, and enhancement tools for a locally run interface. Setup requires Python and Git, and low-VRAM settings trade performance for reduced memory use.

Where Specifiction places it

Alternatives to AUTOMATIC1111 Stable Diffusion WebUIAll alternatives →