AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data
This addresses the challenge of high computational cost in video generation for users needing fast, personalized content, though it is incremental as it builds on existing video diffusion models.
The paper tackles the problem of generating personalized style videos efficiently without needing personalized video data, achieving a reduction in generation time from 25 seconds to about 1 second while maintaining performance.
This paper introduces an effective method for computation-efficient personalized style video generation without requiring access to any personalized video data. It reduces the necessary generation time of similarly sized video diffusion models from 25 seconds to around 1 second while maintaining the same level of performance. The method's effectiveness lies in its dual-level decoupling learning approach: 1) separating the learning of video style from video generation acceleration, which allows for personalized style video generation without any personalized style video data, and 2) separating the acceleration of image generation from the acceleration of video motion generation, enhancing training efficiency and mitigating the negative effects of low-quality video data.