PersonalVideo: High ID-Fidelity Video Customization With Static Images

Hengjia Li, Haonan Qiu, Shiwei Zhang, Xiang Wang, Yujie Wei, Yingya Zhang, Boxi Wu, Deng Cai

Keywords: Video identity customization; Text to video generation

Abstract: The current text-to-video (T2V) generation has made significant progress in synthesizing realistic general videos, but it is still unexplored in identity-specific human video generation with customized ID images. The key challenge lies in maintaining high ID fidelity consistently while preserving the original motion dynamic and prompt following after the identity injection. Current video identity customization methods mainly rely on reconstructing given identity images on text-to-image models, which have a divergent distribution with the T2V model. This process introduces a tuning-inference gap, leading to identity inaccuracy and dynamic degradation. To tackle this problem, we propose a novel framework, dubbed $\textbf{PersonalVideo}$, that applies direct supervision on videos synthesized by the T2V model to bridge the gap. Specifically, we introduce a learnable Spatial Identity Adapter under the supervision of pixel-space ID loss, which customizes the specific identity and preserves the original T2V model’s abilities (e.g., motion dynamic and prompt following). Furthermore, we employ simulated prompt augmentation to reduce overfitting by supervising generated results in more semantic scenarios, gaining good robustness even with only a single reference image available. Extensive experiments demonstrate our method’s superiority in delivering high identity faithfulness while preserving the inherent video generation qualities of the original T2V model, outshining prior approaches. Notably, our PersonalVideo seamlessly integrates with pre-trained SD components, such as ControlNet and style LoRA, requiring no extra tuning overhead.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2113