Saved in:
Bibliographic Details
Main Authors: Hu, Xirui, Wang, Jiahao, Chen, Hao, Zhang, Weizhan, Wang, Benqi, Li, Yikun, Nan, Haishun
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