Stable Diffusion web UI (AUTOMATIC1111)
A local AI image generator and editor for Windows, Linux and Apple Silicon, with Stable Diffusion model support and an AGPL-3.0 license.
Stable Diffusion web UI (AUTOMATIC1111) is a browser interface for generating and editing images with models running on your own hardware. It's for artists and anyone who wants control over prompts, models and image variations. The software is open source under AGPL-3.0.
You can create images from text, rework an existing picture, replace selected areas with inpainting or extend its edges with outpainting. Face restoration uses GFPGAN or CodeFormer, while upscalers such as RealESRGAN increase image resolution. It also supports tileable textures and batch image processing.
Its detailed controls suit people who want to compare results and repeat a particular look. Prompt weighting and negative prompts influence image content, while comparison grids show how different settings affect the output. The app saves generation settings inside images and can restore them later. Live previews show generation progress.
Model support includes Stable Diffusion, Alt-Diffusion and Segmind Stable Diffusion, plus checkpoints in safetensors format. You can use LoRAs and textual inversion embeddings, train embeddings or hypernetworks, and merge checkpoints. Community extensions and an API let you add capabilities or connect generation to other software.
It runs locally on Windows, Linux and Apple Silicon Macs. Supported hardware includes NVIDIA and AMD GPUs, Intel CPUs and GPUs, and Ascend NPUs, with support for graphics cards with 4GB of VRAM. You can also run it through online services such as Google Colab, where computation takes place remotely.
