 | |
| Original author(s) | Lvmin Zhang |
|---|---|
| Initial release | August 9, 2023 [1] |
| Repository | github |
| Written in | Python |
| License | GPLv3 [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]
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]
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] According to the project, it uses GPT-2 to automatically add more detail to the user's prompts. [12] It includes common extensions such LCM low-rank adaptation by default which allows for faster generation speed. [4] [13] Fooocus prefers a photographic style by default, with a list of predefined styles to choose from. [3] [14] While Fooocus aims to provide good results out of the box, it also includes an "advanced" tab that allows for user customization. [15] The user interface is based on Gradio. [16]
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.