Apple and Cornell's FastFrames hits 36 ms per frame, making video generation interactive

NielsRogge · x · 2026-11-21

Apple and Cornell researchers (including Vladlen Koltun) released FastFrames, a family of autoregressive video diffusion models fast enough for real-time interaction.

Paper: arXiv:2611.23226; code and models (FastFrames-L/S) open-sourced on GitHub and Hugging Face.

Original post →

More from Multimodal

Multimodal channel →