AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References
Jiahao Wang, Hualian Sheng, Sijia Cai, Yuxiao Yang, Weizhan Zhang, Caixia Yan, Bing Deng, Jieping Ye

TL;DR
AnyID introduces a scalable, multi-reference video generation framework that preserves identity with high fidelity and allows precise attribute control, overcoming limitations of single-reference methods.
Contribution
It presents a novel omni-referenced architecture and differential prompt paradigm for flexible, high-fidelity identity-preserving video synthesis from diverse inputs.
Findings
Achieves ultra-high identity fidelity in generated videos.
Provides superior attribute-level controllability.
Demonstrates robustness across various input formats.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Multimodal Machine Learning Applications · Face recognition and analysis
