Four key rooms, twelve vibes. Each variant is an AI restyle of the actual listing photo that keeps the architecture and only changes furniture, rugs, art, lighting, plants & decor β sized for a household with a 2- and 4-year-old. Pick a profile, go one image at a time: π / π / π«, tap why, jot a note. The page summarizes you as you go; export the JSON and hand it to Claude to learn your taste, generate a refined batch, and (once you've both rated) find your overlap.
Tip: use β β (or the big Next button) to move through images, and Y / M / N to rate the one you're on. Anything not generated yet shows its prompt β re-run GEMINI_API_KEY=β¦ python3 StyleStudy/generate.py to add more.
How this works β the feedback loop
Pick your profile (Earl / Natasha) β top-left. Ratings are kept separately for each of you, in this browser.
Go one at a time: the big reviewer shows a single room+vibe. Hit π Yes / π Meh / π« No (or Y/M/N), tap the chips for why, add a note. Then β or Next. (With "auto-advance" on, a verdict moves you along automatically β turn it off if you want to dwell.)
Compare: the β before button on the image swaps to the current staged listing photo, so you can sanity-check "is this actually better?". Click any image to see it full-screen.
β My summary ranks the 12 vibes by your votes, shows your recurring likes/dislikes, and gives a rough read of your taste.
Export ("β¬ Export JSON" / "π Copy for Claude") and send it to Claude β Claude reads the pattern, tells you what you seem to like, and generates a sharper next round.
Natasha does the same on her profile (same page, "Natasha" tab β or send her this folder and have her import yours).
Once you've both rated, open "β Both of us" β what you agree on, plus the short list where you'll need to negotiate. Claude can take both JSONs and propose the intersection set + next batch. Repeat β converge β expand the winner across every room.
Keys: ββ move Β· Y/M/N rate Β· B before Β· F full-screen Β· U next unrated