Stable Diffusion WebUI

Stable Diffusion WebUI (commonly called A1111 WebUI) is a Gradio-based local interface for Stable Diffusion, open-sourced by AUTOMATIC1111 in August 2022. It is the earliest, most extensively extended, and best-documented local WebUI in the SD ecosystem. The repository has long held the top star count among peer projects (160k+) and serves as the baseline that later forks (Fooocus, WebUI Forge, and others) build upon.

Core capabilities cover the full SD image generation workflow. First, txt2img and img2img generation modes support a wide range of samplers (Euler, DPM++ family, UniPC, and more) with tunable parameters. Second, Inpainting and Outpainting handle localized repainting and canvas extension. Third, the built-in Extras tab integrates GFPGAN and CodeFormer for face restoration, plus ESRGAN, RealESRGAN, SwinIR, and LDSR for upscaling. Fourth, training and fine-tuning support Textual Inversion, Hypernetwork, and LoRA workflows. Fifth, an extension mechanism lets the community ship thousands of scripts and add-ons (ControlNet, ADetailer, Aesthetic Gradients, and many more), installable directly from a URL.

Use cases include local SD experiments, LoRA training, prompt-engineering research, concept art and rough sketches for professional illustrators, and any reproducible parameter-driven workflow. The onboarding bar is moderate: Windows users install Python 3.10.6 and Git, then double-click webui-user.bat; Linux users run webui.sh. Installation guides cover NVIDIA, AMD, Apple Silicon, Intel, and Ascend NPUs. 4GB of VRAM handles base models; 6GB+ runs SDXL. Beyond the hardware baseline, a tolerance for the command line helps.

Licensed under AGPL-3.0: the project is free and open-source, but anyone who modifies it and offers it as a service must publish the derivative source — this is the biggest license difference between A1111 and its contemporaries (Fooocus, WebUI Forge, ComfyUI).