Fooocus

Fooocus
Original author(s)Lvmin Zhang
Initial releaseAugust 9, 2023; 16 months ago (2023-08-09)[1]
Repositorygithub.com/lllyasviel/Fooocus
Written inPython
LicenseGPLv3[2]

Fooocus is an open source generative artificial intelligence program that allows users to generate images from a text prompt.[3][4] It uses Stable Diffusion 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.[3][4][5]

History

Fooocus was created by Lvmin Zhang, a doctoral student at Stanford University who previously studied at the Chinese University of Hong Kong and Soochow University.[6][7] He is also the main author of ControlNet,[8][6][9] which has been adopted by many other Stable Diffusion interfaces such as AUTOMATIC1111 Stable Diffusion Web UI and ComfyUI. As of 9 July 2024, the project had 38.1k stars on GitHub.[10]

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.[6][3][11][12] According to the project, it uses GPT-2 to automatically add more detail to the user's prompts.[13] It includes common extensions such LCM Low-rank adaptation by default which allows for faster generation speed.[4][14] Fooocus prefers a photographic style by default, with a list of predefined styles to chose from.[3][15] While Fooocus aims to provide good results out of the box, it also includes an "advanced" tab that allows for user customization.[16] The user interface is based on Gradio.[17]

References

  1. ^ Zhang, Lvmin. "i". github.com. Retrieved 9 July 2024.
  2. ^ Zhang, Lvmin. "Create LICENSE". github.com. Retrieved 9 July 2024.
  3. ^ a b c d Hachman, Mark. "Fooocus is the easiest way to create AI art on your PC". PC World. Retrieved 9 July 2024.
  4. ^ a b c 西川, 和久 (20 November 2023). "【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". Impress Watch (in Japanese). Retrieved 9 July 2024.
  5. ^ Pande, Ayush (17 September 2024). "I turned my old PC into an AI image generation server - here's how I did it". XDA. 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.
  6. ^ a b c 克雷西; 萧箫 (26 August 2023). "Fooocus登顶GitHub热榜：4G显存低配畅玩AIGC". 虎嗅 (in Simplified Chinese). Retrieved 9 July 2024.
  7. ^ Zhang, Lvmin. "Lvmin Zhang (Lyumin Zhang)". lllyasviel.github.io. Retrieved 9 July 2024.
  8. ^ Zhang, Lvmin; Rao, Anyi; Agrawala, Maneesh (2023). "Adding Conditional Control to Text-to-Image Diffusion Models". arXiv:2302.05543 [cs.CV].
  9. ^ 新, 清士. "画像生成AIに2度目の革命を起こした「ControlNet」 (1/4)". ascii.jp (in Japanese). Retrieved 9 July 2024.
  10. ^ "lllyasviel/Fooocus". github.com. 9 July 2024. Retrieved 9 July 2024.
  11. ^ Morton, Brad (21 April 2024). "Want Powerful Local AI Image Generation on Windows? Use This Tool". How-To Geek.
  12. ^ Lanz, Jose Antonio (9 December 2023). "Conoce Las Mejores Herramientas de IA Para Generar Imágenes: Guía Detallada". Decrypt (in Spanish).
  13. ^ Zhang, Lvmin (10 July 2024). "List of "Hidden" Tricks". GitHub.com. Retrieved 10 July 2024.
  14. ^ Luo, Simian (2023). "LCM-LoRA: A Universal Stable-Diffusion Acceleration Module". arXiv:2311.05556 [cs.CV].
  15. ^ Esteban, Félix (13 February 2024). "Las cinco mejores IA gratuitas para crear y editar imágenes". Business Insider España (in Spanish).
  16. ^ Horsey, Julian (16 August 2023). "Amazing Fooocus SDXL user interface for AI art generation". Geeky Gadgets. Retrieved 9 July 2024.
  17. ^ Çıtak, Emre (30 November 2023). "Fooocus: Features And How To Install - Dataconomy". dataconomy.com. Retrieved 9 July 2024.