One permission.
Years of outfits.
No manual
photo selection.
With full photo library permission, our SDK scans a user’s entire camera roll on-device, giving your app historical outfits, individual garments, and style context without manual photo uploads.
All of this happens on-device, even in airplane mode.
Optional cloud processing for brand / SKU resolution and AI-generated flatlays.
0:00 / 0:19
- Outfit history, backfilled
- Turn past OOTDs into a dated outfit archive, including looks from before the user joined.
- Style context on day one
- Use the pieces, colors, and aesthetics they already wear to personalize the first session.
- Lower cloud processing costs
- Run extraction on-device and reserve cloud processing for optional enrichment.
- Less manual closet setup
- Extract pieces and connect repeat appearances for easier cataloging, outfit suggestions, and rediscovery.
On-device performance
- Reference device
- iPhone 15 ProA17 Pro, 16-core Neural Engine, 8 GB RAM.
- Target runtime
- iOS 17+Apple Vision and Core ML with FP16 inference.
- Estimated processing
- 0.25–2 sec / outfit photo
- Peak memory
- 400–600 MiB
- Battery use
- 0.1–0.8% / 100 outfit photos