Our own product2025Wardrova
An AI stylist that knows your wardrobe.
- Project
- Our own product
- Our role
- Product · iOS development · AI integration
- Duration
- 4 months
01 / Behind the product
A real need. A considered solution.
Challenge
Outfit apps usually recommend from a store catalogue. Building outfits from what the user already owns is much harder, because the wardrobe has to be digitised first and nobody tags dozens of garments by hand.
Approach
We automated wardrobe entry: the user uploads a photo, the background is removed with RMBG 2.0 on fal.ai, then a vision model extracts category, subcategory, colour (hex), pattern, season and occasion; on failure the original image and sensible defaults remain. Records live in per-user Firestore collections with images in Firebase Storage, and older on-device data migrates automatically. Suggestions are computed from tomorrow’s weather, the calendar and a style quiz. A social feed (posts, hashtags, comments, follows), virtual try-on and an A/B testing service share the same app.
Result
Live on the App Store. Once the wardrobe is scanned, the morning outfit decision collapses into one screen; the outfit calendar, style statistics and colour analytics run on top of that data. Turkish and English.
02 / Inside the product
The experience, on screen.
Open a screen to explore the details.06 images
03 / Scope & details
The details make the experience.
- 01
Clothing recognition and automatic tagging from photos
- 02
Weather-aware outfit suggestions
- 03
Outfit calendar, style statistics and colour analytics
- 04
Background removal (RMBG 2.0) with automatic category, colour and pattern tagging
- 05
Social feed, virtual try-on, per-user data on Firestore + Storage
Technology
INSIDE THE PRODUCT
The engineering behind the interface.
Systems we built and concrete problems we addressed in this project.
Upload → remove background → tag → save
On upload RMBG 2.0 removes the background, a vision model extracts category, subcategory, primary and secondary colour (hex), pattern, season and occasion, and the record lands under /users/{uid}/closet-items. If the model fails the original image and smart default tags remain.
A silent migration from device to cloud
The previous version kept the wardrobe in AsyncStorage. On first launch the data migrates to Firestore, the user is told, and security rules ensure only the owner can read or write.
Suggestion inputs
Outfit suggestions are computed from a tomorrow-weather service, calendar entries, style analysis and the wardrobe; the daily suggestion is cached. Try-on results and collages live in separate services, social posts and profile stats in Firestore.
- 4,2 / 5
- App Store rating
- 10
- ratings
Your idea could be next.
What could we build for you?
From a first release to a growing platform. Let’s plan the design, development and launch together.
From Türkiye to the US, UK, Australia and everywhere in between.