Stable Diffusion web UI

What is Stable Diffusion web UI?

Stable Diffusion web UI, commonly called AUTOMATIC1111, is an open-source browser interface for running Stable Diffusion models locally. Built on the Gradio library, it offers txt2img and img2img modes, inpainting, outpainting, color sketch, prompt matrix and an X/Y/Z plot for comparing parameters across a grid of images. Prompt tools include attention weighting, negative prompts, saved styles, prompt editing mid-generation and composable prompts. An Extras tab bundles GFPGAN and CodeFormer face restoration plus several upscalers, and a training tab handles textual inversion embeddings and hypernetworks. LoRAs, checkpoint merging and community extensions are supported, and generation settings are stored in each image so it can be reproduced. It runs on NVIDIA, AMD, Intel and Apple Silicon setups, and the readme says it supports 4GB video cards. There is no price: it is free software, and you supply the hardware and model files.

Use cases

• Generate images from text locally
• Transform images with img2img
• Inpaint and outpaint pictures
• Upscale images and restore faces
• Train textual inversion embeddings
• Compare settings with X/Y/Z plots
• Merge Stable Diffusion checkpoints

Who it's for

• AI artists
• Hobbyists
• Developers
• Designers

Why use Stable Diffusion web UI

• There are no per-image fees, and prompts and images stay on your own computer.
• A large set of controls, such as inpainting and X/Y/Z plots, makes it a workshop for experimenting with models and settings.
• Generation parameters are stored with each image, so you can restore and reproduce a result later.
• It runs on modest hardware, with the readme noting support for 4GB cards.
• Community extensions and custom scripts let you add features beyond the core set.

Stable Diffusion web UI features

• Text-to-image and image-to-image modes
• Inpainting, outpainting and color sketch
• Attention syntax for emphasizing prompt words
• Prompt matrix and X/Y/Z plot
• Negative prompts and saved styles
• Textual inversion, hypernetworks and LoRA support
• Extras tab with GFPGAN, CodeFormer and upscalers
• Highres Fix and checkpoint merger
• Generation parameters saved in PNG and JPEG metadata
• Built-in API and community extensions
• Support for 4GB video cards

Stable Diffusion web UI integrations

• Google Colab
• xformers
• Stable Diffusion 2.0
• RunwayML inpainting model

How to get started with Stable Diffusion web UI

1. Install the required dependencies, including Python and Git, for your platform.
2. On Windows with an NVIDIA card, download the release package and run update.bat then run.bat; otherwise clone the repository and run webui-user.bat or webui.sh.
3. Open the local address the script prints in your browser and load a Stable Diffusion checkpoint.
4. Enter a prompt, adjust sampling and size settings, and generate in txt2img mode.
5. Refine results with img2img, inpainting, Highres Fix or the Extras upscalers.

Stable Diffusion web UI limitations

• Self-hosted: you install it and supply your own GPU and model files
• Python and Git must be installed first; the readme calls for Python 3.10.6 on Windows
• NVIDIA GPUs are the recommended path; AMD, Intel and Apple Silicon use separate instructions
• Documentation lives in the project wiki rather than the readme

Stable Diffusion web UI pricing

Stable Diffusion web UI is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Stable Diffusion web UI alternatives

The main Stable Diffusion web UI alternatives listed on Debuly are ComfyUI, Midjourney, DiffusionBee, Deep Dream Generator, FLUX and Playform. The table compares pricing and platforms; order is A–Z.

1. 

   ComfyUI

   Node-based interface and backend for building diffusion workflows for images, video and 3D, run locally or on Comfy Cloud.

   Image generationDeveloper platformsDesign
   Open sourceVisit ComfyUI (official site)
2. 

   Deep Dream Generator

   Online AI art platform with 30+ image, video and editing models, an energy-based usage system and a public community gallery.

   Image generationVideoDesign
   FreemiumVisit Deep Dream Generator (official site)
3. 

   DiffusionBee

   Free desktop app that runs Stable Diffusion on your own Mac or Windows PC for offline text-to-image and image editing.

   Image generationDesignVideo
   FreeVisit DiffusionBee (official site)
4. 

   FLUX

   Black Forest Labs' official repository for running FLUX.1 open-weight models locally for text-to-image generation and image editing.

   Image generationDeveloper platforms
   Open sourceVisit FLUX (official site)
5. 

   Midjourney

   AI image and video generator that turns text prompts into artwork, sold as monthly or annual subscriptions with no free plan.

   Image generationVideoDesign
   PaidVisit Midjourney (official site)
6. 

   Playform

   Browser-based AI art studio for artists with text-to-image, sketch-to-image, face mixing, upscaling and custom model training; free to generate.

   Image generationDesign
   FreemiumVisit Playform (official site)

Stable Diffusion web UI FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: none collected yet, so a monogram is shown.
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.