lumos-1-autoregressive-video

【数据与研究】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.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准