Lumos 1 Autoregressive Video

Generate videos autoregressively by extending LLM architectures to spatiotemporal data. MM-RoPE balances frequency spectra across temporal and spatial dimensions, while Autoregressive Diffusion Forcing enables efficient parallel decoding. Lumos-1 (0.5B-3B variants) matches or exceeds Show-o2 and COSMOS on text-to-video with training on 48 GPUs.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 34c1ba57cd

Frequently asked questions

npx get-skill add adu2021/lumos-1-autoregressive-video