Allegro
Rhymes AI class B live
Small open-source text-to-video DiT (2.8B) producing 6s clips at 15fps/720p; Apache-2.0, self-hostable, with a TI2V variant.
Layer 1 — factual axes
Layer 2 — output quality
No independent measure yet. We publish a quality figure only when a named external benchmark ranks this model — we don’t invent one.
Small open-source text-to-video DiT (2.8B) producing 6s clips at 15fps/720p; Apache-2.0, self-hostable, with a TI2V variant.