AI RESEARCH
Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache
arXiv CS.CV
•
ArXi:2602.22654v2 Announce Type: replace Diffusion models have nstrated remarkable success in image and video generation, yet their practical deployment remains hindered by the substantial computational overhead of multi-step iterative sampling. Among acceleration strategies, caching-based methods offer a