Accelerating Diffusion Sampling via Exploiting Local Transition Coherence

ArXi:2503.09675v3 Announce Type: replace 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 similarity between them, which often only works with specific network structures.