photoshot VS CushyStudio

A little project I've been working on a project for the past month that offers low-cost AI avatar generation. And what distinguishes it from other AI avatar generators is, you can create as many AI avatars as you want, after training it once. Price for just generation is $0.01 per image(4k upscaled as well). Instead of using costly third-party APIs for training, inference, and upscaling, I'm using Runpod, which offers the lowest costs possible. The only way to get lower costs is getting so much volume that I can afford multiple GPU servers full time.

I somehow missed the boom in AI avatar generators over the last two months, and in this fast-moving field, it feels like you can become obsolete if someone else gets there even a week before you. I want to give credit to https://github.com/shinework/photoshot for the foundation and frontend styling. The MVP I had early this month had a working backend but frontend styling is just not something I'm good at

Yes I've released photoshot.app few days ago!

Finally ! Now that this is out, I can finally start adding proper video widgets to CushyStudio https://github.com/rvion/CushyStudio#readme . Really hope I can get in touch with StabilityAi people soon. Maybe Hacker News will help

I'm building CushyStudio https://github.com/rvion/cushystudio#readme to make Stable Diffusion practical and fun to play with.

It's still a bit rough around the corners, and I haven't properly launched it yet, but if you want to play with ControlNets, pre-processors, IP adapters, and all those various SD technologies, it's a pretty fun tool ! I personally use for real-time scribble to image, things like this :)

(will post that properly on HN in a few days / week I think, when early feedback will have been properly addressed)