[ LAB NOTES ]
What we're learning about identity.
MAY 14 · 8 MIN · IDENTITY
Why your AI character looks different every shot.
The identity drift problem in generative video, and our N-1 reference approach for keeping a single character locked across an entire session.
Read post →
APR 28 · 6 MIN · METHOD
The 24-frame test: how we measure consistency.
Our AuraFace benchmark methodology. How we score identity similarity across 50+ scenes, and why 0.91 is the number we care about.
Read post →
APR 02 · 7 MIN · STACK
We tried every video model. Here's what we shipped on.
An honest look at the model landscape in spring 2026, and what we learned from a year of pairing rendering with cognition in production.
Read post →