SnackSnap
AI menu photography for independent restaurants: a camera-roll snap becomes a menu-ready image, no photographer required.
The question I was chasing
Could the same engine behind RoomSnap (multi-provider AI imaging wrapped in a real, paid product) be pointed at a completely different trade?
RoomSnap proved a solo build could carry commercial image-editing for estate agents. SnackSnap was the test of whether that playbook travels: the same problem shape, a phone photo that needs to look professional, but a different industry and a different idea of what 'good' looks like.
Why it exists
Independent restaurants can't afford menu photography, so their dishes turn up on delivery apps as dim phone snaps that sell nothing. The fix has to be effortless: upload a camera-roll photo, get a clean, appetising, menu-ready image, and get straight back to running the kitchen.
The constraints
Food is its own problem. A property photo run through the wrong model looks fake; a dish run through the wrong model looks inedible, which is worse. So quality control couldn't be an afterthought, and the output had to be export-ready for the exact places it's used: social, and the major delivery apps. And like any product with money moving through it, the accounts, payments and limits had to genuinely work, not demo-work.
The decisions that mattered
Reuse the hard-won commercial scaffolding from RoomSnap rather than rebuild it (Supabase for accounts, Stripe for payments) so the new bet was about the imaging, not the plumbing.
Route across several imaging providers instead of betting on one, because the best model for appetising food isn't the best for anything else, and food is unforgiving.
Offer a few clean style options rather than infinite knobs: a restaurant owner wants 'make this look good', not a parameter panel.
What it is
An AI imaging platform for hospitality. Upload a camera-roll photo of a dish and get professional, menu-ready images instantly, with multiple style options and quick exports for popular social and delivery apps.
Built with: Codex, Claude, Gemini, multiple AI imaging APIs, Cursor, Supabase, Stripe
Where it landed
Live, and proof that the RoomSnap approach generalises: the same core of multi-provider imaging plus real commercial scaffolding, aimed at a new vertical. What I'd revisit is the same thing I'd revisit on RoomSnap: the provider-routing logic, which deserves to become one shared layer both products draw on rather than two parallel implementations.
Part of the Rolling Waves work archive.