Accelerating Diffusion Sampling via Exploiting Local Transition Coherence 事件

Accelerating Diffusion Sampling via Exploiting Local Transition Coherence arXiv:2503.09675v3 Announce Type: replace Abstract: Text-based diffusion models have made significant breakthroughs in generating high-quality images and videos from textual descriptions. However, the lengthy sampling time of the denoising process remains a significant bottleneck in practical applications. Previous methods either ignore the statistical relationships between adjacent steps or rely on attention or feature s