Bring Your Dreams to Life: Continual Text-to-Video Customization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912756698972160 |
|---|---|
| author | Dong, Jiahua Wang, Xudong Liang, Wenqi Han, Zongyan Cao, Meng Zhang, Duzhen Zhao, Hanbin Han, Zhi Khan, Salman Khan, Fahad Shahbaz |
| author_facet | Dong, Jiahua Wang, Xudong Liang, Wenqi Han, Zongyan Cao, Meng Zhang, Duzhen Zhao, Hanbin Han, Zhi Khan, Salman Khan, Fahad Shahbaz |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05802 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bring Your Dreams to Life: Continual Text-to-Video Customization Dong, Jiahua Wang, Xudong Liang, Wenqi Han, Zongyan Cao, Meng Zhang, Duzhen Zhao, Hanbin Han, Zhi Khan, Salman Khan, Fahad Shahbaz Computer Vision and Pattern Recognition 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. |
| title | Bring Your Dreams to Life: Continual Text-to-Video Customization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.05802 |