Skip to main content

The Ask AI pipeline

Staff only

Internal design notes — stripped from the public build. The public pages describe Ask AI only as observable behaviour ("suggests a designed avatar from your photo"); the mechanism below stays here.

Ask AI turns a photo into a designed avatar:

  1. An on-infrastructure vision model reads coarse descriptors from the photo — skin tone, hair, glasses, facial hair, and so on. The photo is discarded, never stored.
  2. Portrait's own deterministic map turns those descriptors into avataaars options.
  3. Those options seed the Design editor. The user tweaks and saves through the normal designed path.

It's assisted, not an exact likeness. The value — and the thing worth not publishing — is the descriptor set and the deterministic descriptor → avataaars option map, which together are what make the suggestion reproducible without a per-request model call at read time.

Endpoint: POST /me/avatar/from-photo.