Diff-PC: Identity-preserving and 3D-aware Controllable Diffusion for Zero-shot Portrait Customization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Yifang, Zhai, Benxiang, Zhang, Chenyu, Li, Ming, Li, Yang, Du, Sidan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912866363244544
author Xu, Yifang
Zhai, Benxiang
Zhang, Chenyu
Li, Ming
Li, Yang
Du, Sidan
author_facet Xu, Yifang
Zhai, Benxiang
Zhang, Chenyu
Li, Ming
Li, Yang
Du, Sidan
contents Portrait customization (PC) has recently garnered significant attention due to its potential applications. However, existing PC methods lack precise identity (ID) preservation and face control. To address these tissues, we propose Diff-PC, a diffusion-based framework for zero-shot PC, which generates realistic portraits with high ID fidelity, specified facial attributes, and diverse backgrounds. Specifically, our approach employs the 3D face predictor to reconstruct the 3D-aware facial priors encompassing the reference ID, target expressions, and poses. To capture fine-grained face details, we design ID-Encoder that fuses local and global facial features. Subsequently, we devise ID-Ctrl using the 3D face to guide the alignment of ID features. We further introduce ID-Injector to enhance ID fidelity and facial controllability. Finally, training on our collected ID-centric dataset improves face similarity and text-to-image (T2I) alignment. Extensive experiments demonstrate that Diff-PC surpasses state-of-the-art methods in ID preservation, facial control, and T2I consistency. Furthermore, our method is compatible with multi-style foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00639
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diff-PC: Identity-preserving and 3D-aware Controllable Diffusion for Zero-shot Portrait Customization
Xu, Yifang
Zhai, Benxiang
Zhang, Chenyu
Li, Ming
Li, Yang
Du, Sidan
Computer Vision and Pattern Recognition
Portrait customization (PC) has recently garnered significant attention due to its potential applications. However, existing PC methods lack precise identity (ID) preservation and face control. To address these tissues, we propose Diff-PC, a diffusion-based framework for zero-shot PC, which generates realistic portraits with high ID fidelity, specified facial attributes, and diverse backgrounds. Specifically, our approach employs the 3D face predictor to reconstruct the 3D-aware facial priors encompassing the reference ID, target expressions, and poses. To capture fine-grained face details, we design ID-Encoder that fuses local and global facial features. Subsequently, we devise ID-Ctrl using the 3D face to guide the alignment of ID features. We further introduce ID-Injector to enhance ID fidelity and facial controllability. Finally, training on our collected ID-centric dataset improves face similarity and text-to-image (T2I) alignment. Extensive experiments demonstrate that Diff-PC surpasses state-of-the-art methods in ID preservation, facial control, and T2I consistency. Furthermore, our method is compatible with multi-style foundation models.
title Diff-PC: Identity-preserving and 3D-aware Controllable Diffusion for Zero-shot Portrait Customization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.00639