
Gemini + FLUX · AI menu visualizer
Turn any menu photo into a visual menu.
Upload a menu photo. Gemini extracts every dish, FLUX generates photorealistic food images, and your guests get a visual menu they can browse and talk to.
01 Scan
Gemini 2.5 Flash reads the menu photo and extracts every dish with structured data.
02 Visualize
FLUX Pro generates photorealistic dish images. Top dishes get premium quality.
03 Serve
A live visual menu page with voice AI so guests can ask what to order.
AI menu visualizer
Gemini → FLUX pipeline

Drop a menu photo here
JPG, PNG, or WebP. Use a clear, full-page shot.
A static menu becomes a visual one.
Gemini reads the menu, FLUX generates dish images, and each card shows the dish with a photorealistic photo.
Pipeline
Gemini extracts dishes → FLUX generates photorealistic images → sit.fyi builds a live visual menu with voice AI.
Upload a menu to see the full pipeline in action.
Gemini 2.5 Flash for extraction · FLUX Pro + Schnell for dish images · Dish canonicalization for prompt grounding Open live guest demo
Get early access
Be the first to know when we launch new features for your restaurant.