Dense Attention Latency: 1649s Radial Attention (Ours) Latency: 876s (1.9 Faster) PSNR: 27.3 (a) 117 Frames (Default Length)

Recent advances in diffusion models have enabled high-quality video generation, b making ut the additional training and temporal inference dimension on long significantly videos prohibiti increases vely computational expensive. In costs, this paper diffusion, we models: identify post-softmax a phenomenon attention we term scores Spatiotempor diminish al as Ener spatial gy Decay and temporal in video distance o scalable ver space sparse between and time attention tok in ens nature.