ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning

arXiv:2406.14130v1 Announce Type: new
Abstract: Recently, advancements in video synthesis have attracted significant attention. Video synthesis models such as AnimateDiff and Stable Video Diffusion have demonstrated the practical applicability of diffusion models in creating dynamic visual content. The emergence of SORA has further spotlighted the potential of video generation technologies. Nonetheless, the extension of video lengths has been constrained by the limitations in computational resources. Most existing video synthesis models can only generate short video clips. In this paper, we …

abstract arxiv attention cs.cv diffusion diffusion models dynamic emergence potential practical sora stable video diffusion synthesis technologies tuning type via video video diffusion video generation visual