A Gradio-based web interface for running and managing Stable Diffusion image generation on local hardware. It provides text-to-image, image-to-image, inpainting, upscaling, face restoration, and model training capabilities.
Project overview
Supports local execution on GPUs with as little as 4GB VRAM and includes a one-click install and run script for Windows.
Project type
Model Runtime · Image & Vision
Use cases
Image Processing
Deployment
Python environment
License
AGPL-3.0
Best for
Creators and developers who need a graphical web interface to manage and run Stable Diffusion image generation tasks on local hardware.
Users operating on systems with limited GPU memory, specifically those with 4GB of VRAM, with reports of functionality on 2GB cards.
Key capabilities
Generate images from text prompts using Stable Diffusion.
Generate images from existing images and text prompts.
Modify specific parts of an image or extend its borders.
Increase image resolution using various neural network upscalers.
Fix and restore faces in generated images using GFPGAN or CodeFormer.
Train embeddings, hypernetworks, and LoRAs.
Interact with the application programmatically via an API.
Merge up to 3 checkpoints into one.
Limitations and risks
Newer versions of Python may not support torch, which can affect installation or execution.
Running arbitrary Python code from the UI is possible if the --allow-code flag is enabled.
Getting started
Windows users must first install Python and Git. Afterward, they can download the sd.webui.zip from the v1.0.0-pre release, extract its contents, and run update.bat followed by run.bat to streamline setup.
Evidence and sources
README: A web interface for Stable Diffusion, implemented using Gradio library.
README: 4GB video card support (also reports of 2GB working)
Release: 1.10.1
README: 1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract its contents. 2. Run `update.bat`. 3. Run…
README: Install [Python 3.10.6](https://www.python.org/downloads/release/python-3106/) (Newer version of Python does not support torch)