Automatic1111
Open source generative artificial intelligence UI From Wikipedia, the free encyclopedia
AUTOMATIC1111 Stable Diffusion Web UI (SD WebUI, A1111, or Automatic1111[3]) is an open source generative artificial intelligence program that allows users to generate images from a text prompt.[4] It uses Stable Diffusion as the base model for its image capabilities together with a large set of extensions and features to customize its output.[5]
| |
| Original author(s) | AUTOMATIC1111 |
|---|---|
| Developer(s) | AUTOMATIC1111 and community |
| Initial release | August 22, 2022[1] |
| Repository | github |
| Written in | Python |
| License | AGPL-3.0[2] |
History
SD WebUI was released on GitHub on August 22, 2022, by AUTOMATIC1111,[1] 1 month after the initial release of Stable Diffusion.[6] At the time, Stable Diffusion could only be run via the command line.[5] SD WebUI quickly rose in popularity and has been described as "the most popular tool for running diffusion models locally."[4][7] A user study of six StableDiffusion users showed that all participants had used SD WebUI at least once.[3] The study showed that users ascribe SD WebUI's popularity to its ease of installation and support for open source tools.[3] SD WebUI is one of the most popular user interfaces for Stable Diffusion, together with ComfyUI.[8] In February 2024, a book was published by ja:Gijutsu Hyoronsha on using Stable Diffusion with SD WebUI in Japanese.[9][10] As of July 2024, the project had 136,000 stars on GitHub.[11]
Features
SD WebUI uses Gradio for its user interface.[12][13][14] Each parameter in the Stable Diffusion program is exposed via a UI interface within SD WebUI. SD WebUI contains additional parameters not included in Stable Diffusion itself, such as support for Low-rank adaptations, ControlNet and custom variational autoencoders.[12][13][15] SD WebUI supports prompt weighting, image-to-image based generation, inpainting, outpainting and image scaling.[16] It supports over 20 samplers including DDIM, Euler, Euler a, DPM++ 2M Karras, and UniPC.[16][17] It is also used for its various optimizations over the base Stable Diffusion.[5]
Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge (Forge) is a notable fork of SD WebUI started by Lvmin Zhang, who is also the creator of ControlNet and Fooocus.[18][19] The initial goal of Forge was to improve the performance and features of SD WebUI with the intention to upstream changes back to SD WebUI.[18][19] One of Forge's optimizations allowed users with low VRAM to generate images faster on some versions of Stable Diffusion.[18] It improved generation speed for users with 8GB and 6GB VRAM by 30-45% and 60-75%, respectively.[18][19] Forge also includes extra features such as support for more samplers than standard SD WebUI.[20] Some of Forge's optimizations were borrowed from ComfyUI, and others were developed by the Forge team.[19] In August 2024, Forge added support for the Flux diffusion model developed by Black Forest Labs, which is not yet supported by SD WebUI.[21]
See also
References
Wikiwand - on
Seamless Wikipedia browsing. On steroids.