Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.06505 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912492028952576 |
|---|---|
| author | Hu, Xirui Wang, Jiahao Chen, Hao Zhang, Weizhan Wang, Benqi Li, Yikun Nan, Haishun |
| author_facet | Hu, Xirui Wang, Jiahao Chen, Hao Zhang, Weizhan Wang, Benqi Li, Yikun Nan, Haishun |
| contents | Recent advances in text-to-image generation have driven interest in generating personalized human images that depict specific identities from reference images. Although existing methods achieve high-fidelity identity preservation, they are generally limited to single-ID scenarios and offer insufficient facial editability. We present DynamicID, a tuning-free framework that inherently facilitates both single-ID and multi-ID personalized generation with high fidelity and flexible facial editability. Our key innovations include: 1) Semantic-Activated Attention (SAA), which employs query-level activation gating to minimize disruption to the base model when injecting ID features and achieve multi-ID personalization without requiring multi-ID samples during training. 2) Identity-Motion Reconfigurator (IMR), which applies feature-space manipulation to effectively disentangle and reconfigure facial motion and identity features, supporting flexible facial editing. 3) a task-decoupled training paradigm that reduces data dependency, together with VariFace-10k, a curated dataset of 10k unique individuals, each represented by 35 distinct facial images. Experimental results demonstrate that DynamicID outperforms state-of-the-art methods in identity fidelity, facial editability, and multi-ID personalization capability. Our code will be released at https://github.com/ByteCat-bot/DynamicID. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06505 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability Hu, Xirui Wang, Jiahao Chen, Hao Zhang, Weizhan Wang, Benqi Li, Yikun Nan, Haishun Computer Vision and Pattern Recognition Artificial Intelligence Recent advances in text-to-image generation have driven interest in generating personalized human images that depict specific identities from reference images. Although existing methods achieve high-fidelity identity preservation, they are generally limited to single-ID scenarios and offer insufficient facial editability. We present DynamicID, a tuning-free framework that inherently facilitates both single-ID and multi-ID personalized generation with high fidelity and flexible facial editability. Our key innovations include: 1) Semantic-Activated Attention (SAA), which employs query-level activation gating to minimize disruption to the base model when injecting ID features and achieve multi-ID personalization without requiring multi-ID samples during training. 2) Identity-Motion Reconfigurator (IMR), which applies feature-space manipulation to effectively disentangle and reconfigure facial motion and identity features, supporting flexible facial editing. 3) a task-decoupled training paradigm that reduces data dependency, together with VariFace-10k, a curated dataset of 10k unique individuals, each represented by 35 distinct facial images. Experimental results demonstrate that DynamicID outperforms state-of-the-art methods in identity fidelity, facial editability, and multi-ID personalization capability. Our code will be released at https://github.com/ByteCat-bot/DynamicID. |
| title | DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.06505 |