![Robot on the couch](https://splendidpage.com/media/posts/44/2024-07-12_16-10-03_3317.png)
My list of all useful AI models that can run selfhosted
Automatic1111
https://github.com/AUTOMATIC1111/stable-diffusion-webui
Stable Diffusion web UI. Already become a classic over the last couple of years.
Fooocus
https://fooocus.one
https://github.com/lllyasviel/Fooocus
A minimalistic image generator that has few tools but works best by default. If you need precision and refinement, then it is better to use Automatic. The creator of Fooocus is the creator of ControlNet, a very important subsystem for Stable Diffusion that revolutionized the world of image creation by giving artists and designers complete control over the artwork they create. The creator compares his project to Midjourney in terms of artistic quality and usability. Indeed, the barrieStable Diffusionr to entry into this neural network is very low, and the results are excellent from the first generation.
InvokeAI
https://www.invoke.com
https://github.com/invoke-ai/InvokeAI
"InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies..." bla-bla-bla...
It appeared later than the automatic 1111, it develops quickly, has a beautiful interface, but in my hands it works worse. Perhaps the problem is my hands.