AnyID：从任意视觉参考生成超高保真通用身份保持视频
AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References
提出统一异构身份输入（人脸、肖像、视频）的全参考架构与主参考生成范式，结合差分提示词实现属性级可控性，并用人类偏好数据做强化学习微调，为身份保持视频生成提供了可复用的多参考融合与可控生成思路。
原文依据 we present AnyID, an ultra-fidelity identity-preservation video generation framework that features two core contributions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论身份保持视频生成提供了强大的创意表达工具，使用户能够定制以自己喜爱的角色为主角的视频。然而，现有方法通常针对单一身份参考进行设计和优化。这一基本假设限制了创作灵活性，无法充分适应多样化的真实世界输入格式。依赖单一来源也构成了一种不适定场景，导致本质上的模糊设定，使模型难以在新颖上下文中忠实复现身份。为解决这些问题，我们提出 AnyID，一个超高保真身份保持视频生成框架，具有两项核心贡献。首先，我们引入可扩展的全参考架构，有效将异构身份输入（例如人脸、肖像和视频）统一为连贯表示。其次，我们提出主参考生成范式，指定一个参考作为规范锚点，并使用新颖的差分提示词实现精确的属性级可控性。我们在大规模、精心整理的数据集上进行训练以确保鲁棒性和高保真度，然后使用强化学习进行最终微调阶段。该过程利用由人类评估构建的偏好数据集，其中标注者基于两个关键标准对视频进行成对比较：身份保真度和提示词可控性。大量评估验证了 AnyID 在不同任务设定下实现了超高身份保真度以及优越的属性级可控性。项目页面：https://johnneywang.github.io/AnyID-webpage。
英文原文摘要 1727 字符
Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing methods are typically designed and optimized for a single identity reference. This underlying assumption restricts creative flexibility by inadequately accommodating diverse real-world input formats. Relying on a single source also constitutes an ill-posed scenario, causing an inherently ambiguous setting that makes it difficult for the model to faithfully reproduce an identity across novel contexts. To address these issues, we present AnyID, an ultra-fidelity identity-preservation video generation framework that features two core contributions. First, we introduce a scalable omni-referenced architecture that effectively unifies heterogeneous identity inputs (e.g., faces, portraits, and videos) into a cohesive representation. Second, we propose a primary-referenced generation paradigm, which designates one reference as a canonical anchor and uses a novel differential prompt to enable precise, attribute-level controllability. We conduct training on a large-scale, meticulously curated dataset to ensure robustness and high fidelity, and then perform a final fine-tuning stage using reinforcement learning. This process leverages a preference dataset constructed from human evaluations, where annotators performed pairwise comparisons of videos based on two key criteria: identity fidelity and prompt controllability. Extensive evaluations validate that AnyID achieves ultra-high identity fidelity as well as superior attribute-level controllability across different task settings. Project page: https://johnneywang.github.io/AnyID-webpage.