I did a hackathon this weekend for leapml.dev and built out a site that lets you generate images with stable diffusion in the browser:
Each image gets tagged and stored in a database so you can go back and look at what prompts, seeds, step, models people have used to make nice images. There is also a rudeimntary voting system and the homepage is sorted by highest rated.
But the most exciting bit is I added my own custom fine tuned model to it last night that I'm calling "Psychedelia". All of the top images one the homepage are using this model.
It seems to work best with basic prompts and I often still get artifacts like double heads, but I'm quite happy with the initial results and will continue to fine tune.
The site is built with NextJS, TailwindCSS and Supabase and you can login and generate images for free.
Hope you enjoy!
Thanks, Alex
Show HN: Psychedelia fine tuned Stable Diffusion model
aiart.fm