RTFM

World Labs' real-time frame model: a learned renderer that turns a single image into an explorable 3D scene and generates new viewpoints on the fly, with reflections, glossy surfaces, shadows and lens flare, on a single H100.

Исследовательское превью, объявлено 16.10.2025; демо в браузере на rtfm.worldlabs.ai.

Understands

images

Produces

video

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.