add [ 🦾 Auto detect prompt ] to #photoai which figures out the prompt for the copycat input image for better results

make API endpoint for interrogating photo #photoai

save training time (for API cost) and output ZIP when training complete webhook is sent but query server for it because it doesn’t include it in the webhook data #photoai

keep CLIP interrogator model warm too in model heater #photoai

make script to add Docker training output ZIP to models.db because before today we didn’t save it yet on training completion #photoai

make light mode #photoai

finish copycat gallery that searches Unsplash #photoai

add API endpoint for Unsplash search #photoai

import training ID and training Docker output ZIP for models already trained so we can modify existing trained models to add ControlNet etc. #photoai

pics to IG #photoai

push my own ML model to Replicate #photoai

fix undo with shadow canvas #photoai

get help from random Swedish guy to build my own ML models #photoai

take bath to think how to do Unsplash search #photoai

add search bar and close X to expanded copycat gallery #photoai

add ?ref= tracking besides affiliate tracking #photoai

make copycat gallery expandable so we can add Unsplash search soon #photoai

if FB or Google ad don’t track affiliate to avoid ppl abusing #photoai

if clicking Remix/Copycat on photo taken switch mode and scroll down to copycat image #photoai

add FAQ text that nothing should cover eyes #photoai