P—001Prototype Development2026

Vibe-Based Art Discovery

A mood-driven discovery interface for navigating a huge portfolio of limited-edition art prints.

Vibe-Based Art Discovery project

Instead of searching by keyword or category, users express what they are looking for through five aesthetic sliders: Subtle vs. Intense, Nature vs. Urban, Abstract vs. Figurative, Minimalist vs. Detailed, and Geometric vs. Organic.

I developed the scoring pipeline behind it. A multimodal vision model analyses each artwork and assigns it a position along every slider axis. This happens once, at indexing time.

The filtering itself is intentionally classical and deterministic: no neural inference at query time, just fast lookups against precomputed scores. The result feels expressive and intuitive while remaining predictable and auditable.

Next projectRoom Match