AUTOMATIC1111 Stable Diffusion Web UI (SD WebUI, A1111, or Automatic1111) is an

open source Open source is source code that is made freely available for possible modification and redistribution. Products include permission to use the source code, design documents, or content of the product. The open-source model is a decentralized sof ...

generative artificial intelligence Generative artificial intelligence (generative AI, GenAI, or GAI) is a subset of artificial intelligence that uses generative models to produce text, images, videos, or other forms of data. These models machine learning, learn the underlying p ...

program that allows users to generate images from a text prompt. It uses

Stable Diffusion Stable Diffusion is a deep learning, text-to-image model released in 2022. It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and genera ...

as the base model for its image capabilities together with a large set of extensions and features to customize its output.

History

''SD WebUI'' was released on GitHub on August 22, 2022, by AUTOMATIC1111, 1 month after the initial release of Stable Diffusion. At the time, Stable Diffusion could only be run via the

command line A command-line interpreter or command-line processor uses a command-line interface (CLI) to receive commands from a user in the form of lines of text. This provides a means of setting parameters for the environment, invoking executables and pro ...

. ''SD WebUI'' quickly rose in popularity and has been described as "the most popular tool for running diffusion models locally." A user study of six StableDiffusion users showed that all participants had used SD WebUI at least once. The study showed that users ascribe SD WebUI's popularity to its ease of installation and support for open source tools. ''SD WebUI'' is one of the most popular user interfaces for Stable Diffusion, together with

ComfyUI ComfyUI is an open source, Node graph architecture#Use in Computer Graphics, node-based program that allows users to generate images from a series of Prompt (natural language), text prompts. It uses free diffusion models such as Stable Diffusion ...

. In February 2024, a book was published by ja:Gijutsu Hyoronsha on using Stable Diffusion with SD WebUI in Japanese. As of July 2024, the project had 136,000 stars on GitHub.

Features

''SD WebUI'' uses Gradio for its user interface. Each

parameter A parameter (), generally, is any characteristic that can help in defining or classifying a particular system (meaning an event, project, object, situation, etc.). That is, a parameter is an element of a system that is useful, or critical, when ...

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 ControlNet is an open industrial network protocol for industrial automation applications, also known as a fieldbus. ControlNet was earlier supported by ControlNet International, but in 2008 support and management of ControlNet was transferred to O ...

and custom

variational autoencoder In machine learning, a variational autoencoder (VAE), is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling, belonging to the families of probabilistic graphical models and variational Bayesian methods. ...

s. ''SD WebUI'' supports prompt weighting, image-to-image based generation,

inpainting Inpainting is a conservation process where damaged, deteriorated, or missing parts of an artwork are filled in to present a complete image. This process is commonly used in image restoration. It can be applied to both physical and digital art ...

, outpainting and

image scaling In computer graphics and digital imaging, image scaling refers to the resizing of a digital image. In video technology, the magnification of digital material is known as upscaling or resolution enhancement. When scaling a vector graphic image ...

. It supports over 20

samplers Sampler may refer to: * Sampler (signal), a digital signal processing device that converts a continuous signal to a discrete signal * Sampler (needlework), a handstitched piece of embroidery used to demonstrate skill in needlework * Sampler (surna ...

including DDIM, Euler, Euler a, DPM++ 2M Karras, and UniPC. It is also used for its various optimizations over the base Stable Diffusion.

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

and

Fooocus Fooocus is an open source generative artificial intelligence program that allows users to generate images from a text prompt. It uses Stable Diffusion XL as the base model for its image capabilities as well as a collection of default settings a ...

. 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. One of ''Forge'''s optimizations allowed users with low

VRAM Video random access memory (VRAM) is dedicated computer memory used to store the pixels and other graphics data as a framebuffer to be rendered on a computer monitor. This is often different technology than other computer memory, to facilitate ...

to generate images faster on some versions of Stable Diffusion. It improved generation speed for users with 8GB and 6GB VRAM by 30-45% and 60-75%, respectively. ''Forge'' also includes extra features such as support for more samplers than standard SD WebUI. Some of ''Forge'''s optimizations were borrowed from

, and others were developed by the Forge team. In August 2024, ''Forge'' added support for the

Flux Flux describes any effect that appears to pass or travel (whether it actually moves or not) through a surface or substance. Flux is a concept in applied mathematics and vector calculus which has many applications to physics. For transport ...

diffusion model developed by Black Forest Labs, which is not yet supported by SD WebUI.

References

{{Reflist, refs= {{cite web , author1=AUTOMATIC1111 , title=Initial commit , url=https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/71cf18b012857b2cbbc52ff66f63db83689b6bfc , website=github , date=Aug 22, 2022 {{cite web , author1=AUTOMATIC1111 , title=add license file , url=https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/d97f467c0d27695d23edad5e4f8898a57e0ccb00 , website=github , access-date=11 July 2024 , date=Jan 15, 2023 {{cite web , author1=AUTOMATIC1111 , title=Stable Diffusion Web UI , url=https://github.com/AUTOMATIC1111/stable-diffusion-webui , website=github , date=August 2022 {{cite web , title=Announcing SDXL 1.0 , url=https://stability.ai/news/stable-diffusion-sdxl-1-announcement , website=Stability AI , date=July 26, 2023 {{cite web , last1=Mann , first1=Tobias , title=A friendly guide to local AI image gen with Stable Diffusion and Automatic1111 , url=https://www.theregister.com/2024/06/29/image_gen_guide/ , website=

The Register ''The Register'' is a British technology news website co-founded in 1994 by Mike Magee, John Lettice and Ross Alderson. The online newspaper's masthead sublogo is "''Biting the hand that feeds IT''." Their primary focus is information tech ...

, language=en , date=29 Jun 2024 {{cite web , last1=Lewis , first1=Nick , title=How to Run Stable Diffusion Locally With a GUI on Windows , url=https://www.howtogeek.com/832491/how-to-run-stable-diffusion-locally-with-a-gui-on-windows/ , website=How-To Geek , access-date=11 July 2024 , language=en , date=16 September 2022 {{cite book , last1=大崎 , first1=顕 , last2=水口 , first2=瑛介 , title=はじめてでもここまでできる Stable Diffusion画像生成［本格］活用ガイド , date=23 March 2024 , publisher= :ja:技術評論社 , isbn=978-4-297-14083-0 , language=ja {{cite web , author1=あわしろいくや , title=第817回参考書を片手にUbuntuでもStable Diffusion WebUIを動作させ、画像を生成する , url=https://gihyo.jp/admin/serial/01/ubuntu-recipe/0817 , website=gihyo.jp , publisher= :ja:技術評論社 , language=ja , date=12 June 2024 {{cite journal , last1=Wang , first1=Chenghao , last2=Chung , first2=Jeanhun , title=Research on AI Painting Generation Technology Based on the

table Diffusion Table may refer to: * Table (furniture), a piece of furniture with a flat surface and one or more legs * Table (landform), a flat area of land * Table (information), a data arrangement with rows and columns * Table (database), how the table data ...

, journal=International Journal of Advanced Smart Convergence , date=30 June 2023 , volume=12 , issue=2 , pages=90–95 , doi=10.7236/IJASC.2023.12.2.90 , url=https://koreascience.kr/article/JAKO202318743365053.page , quote=Stable Diffusion Web UI is a browser interface based on the Gradio library, {{cite journal , last1=Kim , first1=Seonuk , last2=Ko , first2=Taeyoung , last3=Kwon , first3=Yousang , last4=Lee , first4=Kyungho , title=Designing interfaces for text-to-image prompt engineering using stable diffusion models: a human-AI interaction approach , journal=IASDR Conference Series , date=9 October 2023 , doi=10.21606/iasdr.2023.448 , url=https://dl.designresearchsociety.org/iasdr/iasdr2023/fullpapers/155/, doi-access=free , isbn=978-1-912294-59-6 {{cite web , last1=Pocock , first1=Kevin , title=Stable Diffusion: How to Use VAE , url=https://www.pcguide.com/apps/how-to/stable-diffusion-how-to-use-vae/ , website=PC Guide , access-date=11 July 2024 , date=16 August 2023 {{cite web , last1=Hook , first1=Steve , title=Stable Diffusion WebUI - Run SDXL locally with the AUTOMATIC1111 GUI , url=https://www.pcguide.com/ai/stable-diffusion-webui-sdxl/ , website=PC Guide , date=10 January 2024 {{cite book , last1=Brade , first1=Stephen , last2=Wang , first2=Bryan , last3=Sousa , first3=Mauricio , last4=Oore , first4=Sageev , last5=Grossman , first5=Tovi , chapter=Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models , title=Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology , date=29 October 2023 , pages=1–14 , doi=10.1145/3586183.3606725 , chapter-url=https://dl.acm.org/doi/abs/10.1145/3586183.3606725 , publisher=Association for Computing Machinery, arxiv=2304.09337 , isbn=979-8-4007-0132-0 {{cite book , last1=Phoenix , first1=James , last2=Taylor , first2=Mike , title=Prompt engineering for generative AI: future-proof inputs for reliable AI outputs at scale , date=2024 , publisher=O'Reilly , location=Beijing Boston , isbn=978-1098153434 , edition=First , section=AUTOMATIC1111 Web User Interface {{cite web , author1=西川和久 , title=【西川和久の不定期コラム】 VRAMが少ないGPUで画像生成AIを諦めていた人に。「Stable Diffusion WebUI Forge」登場！ , url=https://pc.watch.impress.co.jp/docs/column/nishikawa/1568551.html , website=PC Watch , language=ja , date=14 February 2024 {{cite web , author1=新清士 , title=画像生成AI、安いPCでも高速に衝撃の「Stable Diffusion WebUI Forge」 (1/4) , url=https://ascii.jp/elem/000/004/185/4185940/ , website=ASCII.jp , language=ja , date=February 26, 2024 {{cite web , author1=田口和裕 , title=話題の画像生成AI「FLUX.1」をStable Diffusion用の「WebUI Forge」で動かす（高速化も試してみました） (1/6) , url=https://ascii.jp/elem/000/004/215/4215695/ , website=ASCII.jp , language=ja , date=August 18, 2024 {{cite web , last1=Horsey , first1=Julian , title=Stable Diffusion WebUI Forge up to 75% faster than Automatic 1111 and ComfyUI , url=https://www.geeky-gadgets.com/stable-diffusion-webui-forge/ , website=Geeky Gadgets , date=14 February 2024 {{cite book , last1=Zhu , first1=Andrew , title=Using Stable Diffusion with Python: Leverage Python to control and automate high-quality AI image generation using Stable Diffusion , date=2024 , publisher=Packt Publishing , isbn=978-1835084311 , quote=Stable Diffusion WebUI from AUTO MATIC1111: This might be the most popular web-based application currently that allows users to generate images and text using Stable Diffusion. It provides a GUI interface that makes it easy to experiment with different settings and parameters {{cite journal , last1=Zhang , first1=Jing , last2=Jiang , first2=Yan , title=Style Transfer Technology of Batik Pattern Based on Deep Learning , journal=Journal of Fiber Bioengineering and Informatics , date=June 2023 , volume=16 , issue=1 , pages=57–67 , doi=10.3993/jfbim02171 {{cite journal , last1=Hu , first1=Qihan , last2=Xu , first2=Zhenghui , last3=Du , first3=Peng , last4=Zeng , first4=Hao , last5=Ma , first5=Tongqing , last6=Zhao , first6=Youbing , last7=Xie , first7=Hao , last8=Zhang , first8=Peng , last9=Liu , first9=Shuting , last10=Zang , first10=Tongnian , last11=Wang , first11=Xuemei , title=CanFuUI: A Canvas-Centric Web User Interface for Iterative Image Generation with Diffusion Models and ControlNet , journal=AI-generated Content , date=2024 , volume=1946 , pages=128–138 , doi=10.1007/978-981-99-7587-7_11 , url=https://doi.org/10.1007/978-981-99-7587-7_11 , publisher=Springer Nature Singapore , language=en , quote=Currently, the most popular user interfaces for Stable Diffusion are Stable Diffusion WebUI and ComfyUI. Open-source artificial intelligence Free and open-source software

History

Features

Stable Diffusion WebUI Forge

See also

References