Desert Ant Labs

Eye: On-device Image Understanding

Image understandingClosed beta

On-device image understanding that scores any image in one call: best-frame pick, per-axis quality, scene, tags, and a perceptual embedding for burst dedupe.

Eye scores any image in a single call. It returns a best-frame pick score, per-axis quality (interestingness, composition, thumbnail quality, subject clarity, aesthetic), a scene class, tags and concepts, an optional identity-blind face analysis, and a perceptual embedding used for near-duplicate burst dedupe. Use it to pick the best photo from a burst, the best frame from a video, or the best thumbnail from a clip.

Eye is in closed beta. In development. Early access on request.

Use cases

Best-of selection

Pick the best photo from a burst, the best frame from a video, or the best thumbnail from a clip.

Identity-blind face scoring

Score faces as visual content (geometry, expression, attention) for a best headshot, no blinks, eyes on camera. It does not perform face recognition.

What it does

  • One call: pick score, quality axes, scene class, tags and concepts
  • Perceptual embedding for near-duplicate burst dedupe
  • Optional EyeFaces module (+22 MB), identity-blind by design

Specs

Size
~27 MB core, +22 MB optional face module
Backbone
TinyCLIP-40M (distilled from a LAION-400M teacher)
Platform
Apple (Swift); Android and web planned

Early access

Tell us what you are building and we will get you set up.