Drippler
An AI wardrobe concept: branding plus product UI across web and mobile.
The problem
AI styling and digital wardrobe concepts fail because they require too much manual input. Users do not want to upload and manually tag the color, cut, and fabric of every item in their closet. Furthermore, typical recommendations are presented as flat image grids that lack visual layering, making it hard to see how clothes combine.
Process
I designed a computer-vision intake flow for turning uploaded wardrobe photos into structured closet items. The core product surface was a drag-and-drop outfit canvas where users could stack, scale, and layer clothing items, with recommendations framed around style metadata and closet gaps.
Outcome
As a concept case study, the useful proof is the product thinking: reduce manual wardrobe setup, make outfit composition visual, and connect styling recommendations back to the user’s actual closet. I do not present conversion or engagement metrics for this project.
Solution highlights
AI-vision closet intake
Extracts clothing attributes (category, color, pattern, material) from a photo with no manual inputs.
Drag-and-drop layering canvas
Lets users stack, scale, and combine closet items to test outfit combinations.
Cohesive recommendations
Suggests trending or matching wardrobe additions based on closet color and style gaps.
One-tap outfit purchase
Calculates sizing and combines multiple selected clothing items into a single checkout flow.
