Fooocus is an

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

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

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 based on Diffusion model, diffusion techniques. The generative artificial intelligence technology is the premier product of Stability AI and is considered to be a part of ...

XL as the base model for its image capabilities as well as a collection of default settings and prompts to make the image generation process more streamlined.

History

''Fooocus'' was created by Lvmin Zhang, a doctoral student at

Stanford University Leland Stanford Junior University, commonly referred to as Stanford University, is a Private university, private research university in Stanford, California, United States. It was founded in 1885 by railroad magnate Leland Stanford (the eighth ...

who previously studied at the

Chinese University of Hong Kong The Chinese University of Hong Kong (CUHK) is a public university, public research university in Sha Tin, New Territories, Hong Kong. Established in 1963 as a federation of three university college, collegesChung Chi College, New Asia Coll ...

and Soochow University. He is also the main author of

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 t ...

, which has been adopted by many other Stable Diffusion interfaces, such as

AUTOMATIC1111 AUTOMATIC1111 Stable Diffusion Web UI (SD WebUI, A1111, or Automatic1111) is an open source generative artificial intelligence program that allows users to generate images from a text prompt. It uses Stable Diffusion as the base model for its i ...

and

ComfyUI ComfyUI is an open source, node-based program that allows users to generate images from a series of text prompts. It uses free diffusion models such as Stable Diffusion as the base model for its image capabilities combined with other tools su ...

. As of 9 July 2024, the project had 38.1k stars on GitHub.

Features

''Fooocus''' main feature is that it is easy to set up and does not require users to manually configure model parameters to achieve desirable results. According to the project, it uses

GPT-2 Generative Pre-trained Transformer 2 (GPT-2) is a large language model by OpenAI and the second in their foundational series of Generative pre-trained transformer, GPT models. GPT-2 was pre-trained on a dataset of 8 million web pages. It was par ...

to automatically add more detail to the user's prompts. It includes common extensions such LCM low-rank adaptation by default which allows for faster generation speed. ''Fooocus'' prefers a photographic style by default, with a list of predefined styles to choose from. While ''Fooocus'' aims to provide good results out of the box, it also includes an "advanced" tab that allows for user customization. The

user interface In the industrial design field of human–computer interaction, a user interface (UI) is the space where interactions between humans and machines occur. The goal of this interaction is to allow effective operation and control of the machine fro ...

is based on Gradio.

References

{{Reflist, refs= {{cite web , author1 = 克雷西, author2= 萧箫 , title=Fooocus登顶GitHub热榜：4G显存低配畅玩AIGC , url=https://www.huxiu.com/article/1974982.html , script-website=zh: 虎嗅 , access-date=9 July 2024 , language=zh-Hans , date=26 August 2023 {{cite web , last1=Zhang , first1=Lvmin , title=Lvmin Zhang (Lyumin Zhang) , url=https://lllyasviel.github.io/Style2PaintsResearch/lvmin , website=lllyasviel.github.io , access-date=9 July 2024 {{cite web , last1=Hachman , first1=Mark , title=Fooocus is the easiest way to create AI art on your PC , url=https://www.pcworld.com/article/2253285/fooocus-is-the-easiest-way-to-run-ai-art-on-your-pc.html , website=

PC World ''PC World'' (stylized as PCWorld) is a global computer magazine published monthly by IDG. Since 2013, it has been an online-only publication. It offers advice on various aspects of PCs and related items, the Internet, and other personal tec ...

, access-date=9 July 2024 , language=en {{cite arXiv , last1=Zhang , first1=Lvmin , last2=Rao , first2=Anyi , last3=Agrawala , first3=Maneesh , title=Adding Conditional Control to Text-to-Image Diffusion Models , date=2023 , class=cs.CV , eprint=2302.05543 {{cite web , last1=Morton , first1=Brad , title=Want Powerful Local AI Image Generation on Windows? Use This Tool , url=https://www.howtogeek.com/want-powerful-local-ai-image-generation-on-windows-use-this-tool/ , website=How-To Geek , language=en , date=21 April 2024 {{cite web , last1=西川 , first1=和久 , title=【西川和久の不定期コラム】 Stable Diffusion高速化の決定版登場！？品質落とさず制限もほぼなしで2～3倍速に , url=https://pc.watch.impress.co.jp/docs/column/nishikawa/1547611.html , website= Impress Watch , access-date=9 July 2024 , language=ja , date=20 November 2023 {{cite arXiv , last1=Luo , first1=Simian , title=LCM-LoRA: A Universal Stable-Diffusion Acceleration Module , date=2023 , class=cs.CV , eprint=2311.05556 {{cite web , last1=Çıtak , first1=Emre , title=Fooocus: Features And How To Install - Dataconomy , url=https://dataconomy.com/2023/11/30/fooocus-features-and-how-to-install/ , website=dataconomy.com , access-date=9 July 2024 , date=30 November 2023 {{cite web , last1=Horsey , first1=Julian , title=Amazing Fooocus SDXL user interface for AI art generation , url=https://www.geeky-gadgets.com/fooocus-sdxl-user-interface/ , website=Geeky Gadgets , access-date=9 July 2024 , date=16 August 2023 {{cite web , last1=Zhang , first1=Lvmin , title=i , url=https://github.com/lllyasviel/Fooocus/commit/7386161937cccfe0f2172c2cf17a3986ea857941 , website=github.com , access-date=9 July 2024 {{cite web , last1=Zhang , first1=Lvmin , title=Create LICENSE , url=https://github.com/lllyasviel/Fooocus/commit/d33d8a47ae884e0836f15cae6d7113de253d98f4 , website=github.com , access-date=9 July 2024 {{cite web , last1=新 , first1=清士 , title=画像生成AIに2度目の革命を起こした「ControlNet」 (1/4) , url=https://ascii.jp/elem/000/004/137/4137393/ , website= ascii.jp , access-date=9 July 2024 , language=ja {{cite web , title=lllyasviel/Fooocus , url=https://github.com/lllyasviel/Fooocus , website=github.com , access-date=9 July 2024 , date=9 July 2024 {{cite web , last1=Zhang , first1=Lvmin , title=List of "Hidden" Tricks , url=https://github.com/lllyasviel/Fooocus?tab=readme-ov-file#list-of-hidden-tricks , website=GitHub.com , access-date=10 July 2024 , date=10 July 2024 {{cite web , last1=Pande , first1=Ayush , title=I turned my old PC into an AI image generation server - here's how I did it , url=https://www.xda-developers.com/turn-pc-into-ai-image-generator/ , website=XDA , language=en , date=17 September 2024, quote=Finally, I went with the Fooocus model (yup, that's the name) by developer lllyasviel, as it had the simplest installation procedure out of everything else I tried on my PC. {{cite web , last1=Esteban , first1=Félix , title=Las cinco mejores IA gratuitas para crear y editar imágenes , url=https://www.businessinsider.es/cinco-mejores-ia-gratuitas-crear-editar-imagenes-1363777 , website=Business Insider España , language=es , date=13 February 2024 Open-source artificial intelligence Free and open-source software