VideoDreamer: Customized Multi-Subject Text-to-Video Generation With Disen-Mix Finetuning on Language-Video Foundation Models

Hong Chen 0011, Xin Wang 0019, Guanning Zeng, Yipeng Zhang 0003, Yuwei Zhou, Feilin Han, Yaofei Wu, Wenwu Zhu 0001. VideoDreamer: Customized Multi-Subject Text-to-Video Generation With Disen-Mix Finetuning on Language-Video Foundation Models. IEEE Transactions on Multimedia, 27:2875-2885, 2025. [doi]

@article{ChenWZZZHWZ25,
  title = {VideoDreamer: Customized Multi-Subject Text-to-Video Generation With Disen-Mix Finetuning on Language-Video Foundation Models},
  author = {Hong Chen 0011 and Xin Wang 0019 and Guanning Zeng and Yipeng Zhang 0003 and Yuwei Zhou and Feilin Han and Yaofei Wu and Wenwu Zhu 0001},
  year = {2025},
  doi = {10.1109/TMM.2025.3557634},
  url = {https://doi.org/10.1109/TMM.2025.3557634},
  researchr = {https://researchr.org/publication/ChenWZZZHWZ25},
  cites = {0},
  citedby = {0},
  journal = {IEEE Transactions on Multimedia},
  volume = {27},
  pages = {2875-2885},
}