Web App · Education

Raimi's AI Art Lab

Visitors compose a prompt step by step with the museum character Raimi, choosing what they want to draw, and an AI generates the artwork. Designed so young visitors learn the principles of prompt engineering through play, with a 10-step (+5 advanced) choice-based prompt builder that shows how a prompt is put together. The off-the-shelf GPT service used before suffered repeated connection conflicts on the exhibition floor. Moving to a custom web app and serverless backend eliminated 100% of those conflicts; the backend calls the OpenAI image-generation API, auto-watermarks every image with the museum logo, and dual-stores results on Cloudflare R2 and Supabase. Visitors take their creations home instantly via QR code, and shipping it as a web app locked the exhibition kiosk down from other apps. It now runs live at the museum, generating an average of 142 images on weekdays and 557 on weekends. It is the first service at the museum whose generation volume could be quantified, through its own backend.