Bring Your Dreams to Life: Continual Text-to-Video Customization

Customized text-to-video generation (CTVG) has recently witnessed great progress in generating tailored videos from user-specific text. However, most CTVG methods assume that personalized concepts remain static and do not expand incrementally over time. Additionally, they struggle with forgetting and concept neglect when continuously learning new concepts, including subjects and motions. To resolve the above challenges, we develop a novel Continual Customized Video Diffusion (CCVD) model, which can continuously learn new concepts to generate videos across various text-to-video generation tasks by tackling forgetting and concept neglect. To address catastrophic forgetting, we introduce a concept-specific attribute retention module and a task-aware concept aggregation strategy. They can capture the unique characteristics and identities of old concepts during training, while combining all subject and motion adapters of old concepts based on their relevance during testing. Besides, to tackle concept neglect, we develop a controllable conditional synthesis to enhance regional features and align video contexts with user conditions, by incorporating layer-specific region attention-guided noise estimation. Extensive experimental comparisons demonstrate that our CCVD outperforms existing CTVG models.

Authors

• Jiahua Dong
• Xudong Wang Ant Group
• Wenqi Liang State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences. Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences. University of Chinese Academy of Sciences.
• Zongyan Han
• Meng Cao International Digital Economy Academy (IDEA)
• Duzhen Zhang Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences
• Hanbin Zhao Zhejiang University
• Zhi Han State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences
• Salman Khan Mohamed bin Zayed University of Artificial Intelligence, (MBZUAI), UAE Australian National University, Canberra ACT, Australia
• Fahad Shahbaz Khan Mohamed Bin Zayed University of Artificial Intelligence Linkoping University

Keywords

No keywords are indexed for this paper.