We introduce Timestep Embedding Aware Cache (TeaCache), a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps, thereby ...
Abstract: As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by ...
Abstract: This paper considers video and audio transmission in ICN (Information-Centric Networking)/ CCN (ContentCentric Networking), where each intermediate node can cache content. We have proposed ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback