This post is my submission for DEV Education Track: Build Apps with Google AI Studio.
What I Built
I built an On-Demand Coloring Book Studio, a web application that generates printable, custom black-and-white coloring pages from user descriptions using Google AI Studio and the Imagen API. Using systematic prompt engineering for high-contrast vector outlines and negative prompt modifiers, the app allows users to select age groups, adjust line complexity, fill colors online, and export complete multi-page PDF coloring books.
Demo
My Experience
Working through this track showed me how effective system instructions are at turning raw diffusion models into specialized design utilities. Structuring automated prompt modifiers (forcing clean line art while strictly penalizing shading, gradients, and dark backgrounds) made the Imagen API consistently output clear, print-ready vector pages. It was surprising how seamlessly Google AI Studio helped prototype both the UI layout logic and the underlying API calls in one cohesive workflow.
Top comments (1)
Nice use case because coloring pages have a very concrete output constraint. The model can make something pretty, but the product wins or loses on line clarity, printable contrast, and whether the generated page has enough open areas for the person actually coloring it.