Jump to content

Automatic1111

From Wikipedia, the free encyclopedia
AUTOMATIC1111 Stable Diffusion Web UI
Original author(s)AUTOMATIC1111
Developer(s)AUTOMATIC1111 and community
Initial releaseAugust 22, 2022; 2 years ago (2022-08-22)[1]
Repositorygithub.com/AUTOMATIC1111/stable-diffusion-webui
Written inPython
LicenseAGPL-3.0[2]

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]

History

[edit]

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] In February 2024, a book was published by ja:Gijutsu Hyoronsha on using Stable Diffusion with SD WebUI in Japanese.[8][9] As of July 2024, the project had 136,000 stars on GitHub.[10]

Features

[edit]

SD WebUI uses Gradio for its user interface.[11][12][13] 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.[11][12][14] SD WebUI supports prompt weighting, image-to-image based generation, inpainting, outpainting and image scaling.[15] It supports over 20 samplers including DDIM, Euler, Euler a, DPM++ 2M Karras, and UniPC.[15][16] It is also used for its various optimizations over the base Stable Diffusion.[5]

Stable Diffusion WebUI Forge

[edit]

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.[17][18] 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.[17][18] One of Forge's optimizations allowed users with low VRAM to generate images faster on some versions of Stable Diffusion.[17] It improved generation speed for users with 8GB and 6GB VRAM by 30-45% and 60-75%, respectively.[17][18] Forge also includes extra features such as support for more samplers than standard SD WebUI.[19] Some of Forge's optimizations were borrowed from ComfyUI, and others were developed by the Forge team.[18] In August 2024, Forge added support for the Flux diffusion model developed by Black Forest Labs, which is not yet supported by SD WebUI.[20]

References

[edit]
  1. ^ a b AUTOMATIC1111 (Aug 22, 2022). "Initial commit". github.{{cite web}}: CS1 maint: numeric names: authors list (link)
  2. ^ AUTOMATIC1111 (Jan 15, 2023). "add license file". github. Retrieved 11 July 2024.{{cite web}}: CS1 maint: numeric names: authors list (link)
  3. ^ a b c Brade, Stephen; Wang, Bryan; Sousa, Mauricio; Oore, Sageev; Grossman, Tovi (29 October 2023). "Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models". Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. Association for Computing Machinery. pp. 1–14. arXiv:2304.09337. doi:10.1145/3586183.3606725. ISBN 979-8-4007-0132-0.
  4. ^ a b Mann, Tobias (29 Jun 2024). "A friendly guide to local AI image gen with Stable Diffusion and Automatic1111". The Register.
  5. ^ a b c Lewis, Nick (16 September 2022). "How to Run Stable Diffusion Locally With a GUI on Windows". How-To Geek. Retrieved 11 July 2024.
  6. ^ "Announcing SDXL 1.0". Stability AI. July 26, 2023.
  7. ^ Zhu, Andrew (2024). Using Stable Diffusion with Python: Leverage Python to control and automate high-quality AI image generation using Stable Diffusion. Packt Publishing. ISBN 978-1835084311. 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
  8. ^ 大崎, 顕; 水口, 瑛介 (23 March 2024). 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 (in Japanese). ja:技術評論社. ISBN 978-4-297-14083-0.
  9. ^ あわしろいくや (12 June 2024). "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". gihyo.jp (in Japanese). ja:技術評論社.
  10. ^ AUTOMATIC1111 (August 2022). "Stable Diffusion Web UI". github.{{cite web}}: CS1 maint: numeric names: authors list (link)
  11. ^ a b Wang, Chenghao; Chung, Jeanhun (30 June 2023). "Research on AI Painting Generation Technology Based on the [Stable Diffusion]". International Journal of Advanced Smart Convergence. 12 (2): 90–95. doi:10.7236/IJASC.2023.12.2.90. Stable Diffusion Web UI is a browser interface based on the Gradio library,
  12. ^ a b Kim, Seonuk; Ko, Taeyoung; Kwon, Yousang; Lee, Kyungho (9 October 2023). "Designing interfaces for text-to-image prompt engineering using stable diffusion models: a human-AI interaction approach". IASDR Conference Series. doi:10.21606/iasdr.2023.448. ISBN 978-1-912294-59-6.
  13. ^ Hook, Steve (10 January 2024). "Stable Diffusion WebUI - Run SDXL locally with the AUTOMATIC1111 GUI". PC Guide.
  14. ^ Pocock, Kevin (16 August 2023). "Stable Diffusion: How to Use VAE". PC Guide. Retrieved 11 July 2024.
  15. ^ a b Phoenix, James; Taylor, Mike (2024). "AUTOMATIC1111 Web User Interface". Prompt engineering for generative AI: future-proof inputs for reliable AI outputs at scale (First ed.). Beijing Boston: O'Reilly. ISBN 978-1098153434.
  16. ^ Zhang, Jing; Jiang, Yan (June 2023). "Style Transfer Technology of Batik Pattern Based on Deep Learning". Journal of Fiber Bioengineering and Informatics. 16 (1): 57–67. doi:10.3993/jfbim02171.
  17. ^ a b c d 西川 和久 (14 February 2024). "【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!". PC Watch (in Japanese).
  18. ^ a b c d 新清士 (February 26, 2024). "画像生成AI、安いPCでも高速に 衝撃の「Stable Diffusion WebUI Forge」 (1/4)". ASCII.jp (in Japanese).
  19. ^ Horsey, Julian (14 February 2024). "Stable Diffusion WebUI Forge up to 75% faster than Automatic 1111 and ComfyUI". Geeky Gadgets.
  20. ^ 田口和裕 (August 18, 2024). "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)". ASCII.jp (in Japanese).