Stable Diffusion web UI is an open-source web interface for Stable Diffusion, a diffusion model that generates images from text prompts. Its repository is hosted on GitHub by the developer AUTOMATIC1111, whose name is often used for the program. It is built with Gradio, a Python library for browser interfaces, and runs on the user's own computer.
The user installs Python and git, downloads the repository and runs a start script; the program loads a model file, called a checkpoint, and opens a page in the browser. It offers txt2img (an image from a text prompt) and img2img (a new image from an input image), inpainting and outpainting (redrawing part of an image or extending it past its borders), negative prompts, and Textual Inversion, Hypernetworks and LoRA add-ons that adapt a model to a style or subject. An Extras tab restores faces with GFPGAN or CodeFormer and enlarges images with neural-network upscalers such as RealESRGAN and SwinIR. An API and community extensions are supported. NVIDIA GPUs are recommended; AMD, Intel and Apple Silicon also work.
It is free software under the AGPL-3.0 license.