I built an API for Text to Image generation
Hey Indiehackers :)
I've been working on a figma plugin for the past few weeks using stable diffusion, in doing so, of course I needed to setup stable diffusion on a GPU powered instance.
This was a pain, as with both AWS and GCP you have to request a quota increase before you can get an instance, and that process took several days.
In addition, setting up stable diffusion and fixing CUDA and driver errors on the instance for hours was not fun.
That's why I decided to publicize my API that I'm using for stable diffusion, and help other indie hackers fast-track.
It features both text2Img and img2img generation, with img2img generation behind a custom plan. I plan to add more features like textual inversion soon.
If you're interested in building the next viral stable diffusion application, please reach out and I'd love to help you get setup with the API!
This looks excellent! Congratulations on launching.