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

TL;DR

This paper introduces CCVD, a continual learning model for text-to-video generation that effectively learns new concepts over time without forgetting previous ones, improving customization and regional feature control.

Contribution

The paper presents a novel CCVD model with concept-specific retention and task-aware aggregation to mitigate forgetting and neglect in continual text-to-video synthesis.

Findings

CCVD outperforms existing baselines on DreamVideo and Wan 2.1 datasets.

The model effectively preserves old concepts during incremental learning.

Enhanced regional feature control improves video quality and relevance.

Abstract

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.