How it works

Three screens for the shopper. Fourteen subsystems behind them. Here is what actually happens in those nine seconds.

  1. 01
    Validate

    Format, size, and whether the photo is actually usable — one person, front-facing, sharp enough. Rejected in under half a second, at no cost.

  2. 02
    Moderate

    Input gates run before any AI spend: NSFW, apparent minors, policy. Output is checked again before the shopper sees anything.

  3. 03
    Prepare

    Normalise orientation and colour, person-aware crop, and resolve the garment to a phrase like "a red plaid flannel shirt" — cached per product.

  4. 04
    Route

    Pick a model that has cleared the quality benchmark, then optimise for cost and latency within that pool. Never the other way round.

  5. 05
    Compose

    The person photo, the garment, and a versioned prompt that names three constraints: preserve identity, realistic fit, keep background.

  6. 06
    Validate again

    Identity drift, garment presence, artefacts, NSFW. A failure fails over to another provider rather than shipping a bad image.

  7. 07
    Label & store

    Watermark, EU AI-disclosure badge, and machine-readable provenance metadata. Stored on a TTL-bucketed path behind signed URLs.

See it for yourself

The playground runs this exact pipeline — the same one API consumers hit.

Open the playground