Comment by jjcm
2 months ago
I'm working on a diffusion-powered UI design tool. My short term goal is to make AI-designed UI not look like Tailwind. My long-term goal is to be Figma, but powered by diffusion.
I quit Figma about 4mo ago to start working on this, and the gpt-image-2 drop really legitized the bet. I recently release Brands for diffui, which let you establish a design system and consistently generate with it. I made a Brand out of the recent UFO files release, which allow for some really fun designs:
https://diffui.ai/brand/2ff1b00a-d698-43ea-a42e-7c4a2e670c04 (no account required to generate with this if you want to try)
Neat! FYI when I tried it out, seems like there's a 60s timeout:
[Error] Failed to load resource: the server responded with a status of 504 (Gateway Time-out) (generate, line 0)
My "prompt" was, uh, simple: "Turns out, you don't need water to live."
TY for the error details! Helped me track down what was happening here - turns out nginx had a 60s timeout setup for calls, and promps average around 55-65s to return. Meant it was working 100% on dev, and apparently every attempt I had on prod was under that 60s count.
Just moved things to a websocket connection for the return. Should be working now - here's the image it generated for "Turns out, you don't need water to live": https://diffui.ai/files/brand-shares/2ff1b00a-d698-43ea-a42e...
[dead]