MagicID：面向身份一致性与动态保持的视频定制混合偏好优化

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

March 16, 2025

作者: Hengjia Li, Lifan Jiang, Xi Xiao, Tianyang Wang, Hongwei Yi, Boxi Wu, Deng Cai

cs.AI

摘要

视频身份定制旨在基于用户的参考图像，生成高保真视频，这些视频需保持身份一致性并展现显著的动态特性。然而，现有方法面临两大挑战：视频时长增加导致的身份退化，以及训练过程中动态性减弱，这主要归因于它们依赖传统的静态图像自重建训练。为解决这些问题，我们提出了MagicID，一个旨在直接促进生成符合用户偏好、身份一致且动态丰富的视频的新框架。具体而言，我们建议构建带有明确身份和动态奖励的成对偏好视频数据，以替代传统的自重建方法，进行偏好学习。针对定制偏好数据的限制，我们引入了一种混合采样策略。该方法首先通过利用源自参考图像的静态视频优先保障身份一致性，随后采用基于前沿的采样方法提升生成视频的动态运动质量。通过利用这些混合偏好对，我们优化模型，使其与定制偏好对之间的奖励差异相匹配。大量实验表明，MagicID成功实现了身份一致性和自然动态性，在多项指标上超越了现有方法。

English

Video identity customization seeks to produce high-fidelity videos that maintain consistent identity and exhibit significant dynamics based on users' reference images. However, existing approaches face two key challenges: identity degradation over extended video length and reduced dynamics during training, primarily due to their reliance on traditional self-reconstruction training with static images. To address these issues, we introduce MagicID, a novel framework designed to directly promote the generation of identity-consistent and dynamically rich videos tailored to user preferences. Specifically, we propose constructing pairwise preference video data with explicit identity and dynamic rewards for preference learning, instead of sticking to the traditional self-reconstruction. To address the constraints of customized preference data, we introduce a hybrid sampling strategy. This approach first prioritizes identity preservation by leveraging static videos derived from reference images, then enhances dynamic motion quality in the generated videos using a Frontier-based sampling method. By utilizing these hybrid preference pairs, we optimize the model to align with the reward differences between pairs of customized preferences. Extensive experiments show that MagicID successfully achieves consistent identity and natural dynamics, surpassing existing methods across various metrics.