Bring Your Dreams to Life: Continual Text-to-Video Customization
This work addresses incremental learning challenges in customized video generation for users needing dynamic concept expansion, though it is incremental as it builds on existing CTVG methods.
The paper tackles the problem of catastrophic forgetting and concept neglect in continual text-to-video customization, where existing methods fail as personalized concepts expand over time. The proposed CCVD model outperforms baselines on DreamVideo and Wan 2.1 backbones, demonstrating improved performance in generating videos across various tasks.
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 baselines on both the DreamVideo and Wan 2.1 backbones. The code is available at https://github.com/JiahuaDong/CCVD.