VibeStack

There’s a gap that every creative project runs into eventually. You know exactly what something should feel like. You have a reference in your head — maybe it’s a film still, a smell, a city at a specific hour. But the moment someone asks you to explain it, or the moment you try to hand it off to a designer or an AI tool, the feeling collapses into vague words that don’t carry the weight you intended.

VibeStack is my attempt to close that gap.

You type a description the way you’d say it out loud. Something like “brutalist Tokyo at 3am, neon on wet concrete, Blade Runner but make it fashion.” The engine takes that phrase and runs it through a multi-stage pipeline to extract, structure, and visualise the aesthetic intent hiding inside it.

The first stage parses the vibe. A language model reads the input and extracts semantic structure: keywords, emotional register, visual references, and color language. From there the engine reaches out to Unsplash and Pexels and pulls real photographs that match that aesthetic. Not AI-generated images, but actual moodboard material — the kind a creative director would gather manually.

Those images get embedded and clustered to find the dominant visual threads. A color palette is derived directly from that clustered imagery, so the hex codes reflect what’s actually in the reference material rather than what a model guesses should be there.

The final stage generates four production-ready prompts: one each for Midjourney, Stable Diffusion, Flux, and a web design brief for developers or AI coding tools. The web brief is the part I find most useful personally — it’s the kind of structured spec you can paste directly into Claude Code and immediately get something that feels right.

The whole process takes about twenty seconds.

Built with FastAPI, Next.js, and deployed on AWS App Runner with images on S3 and CloudFront.