paper-with-me

홈 › Papers

HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion

2025-12-16 · Yifang Xu, Benxiang Zhai, Yunzhuo Sun, Ming Li, Yang Li, Sidan Du arxiv

Recent advancements in diffusion-based technologies have made significant strides, particularly in identity-preserved portrait generation (IPG). However, when using multiple reference images from the same ID, existing methods typically produce lower-fidelity portraits and struggle to customize face attributes precisely. To address these issues, this paper presents HiFi-Portrait, a high-fidelity method for zero-shot portrait generation. Specifically, we first introduce the face refiner and landmark generator to obtain fine-grained multi-face features and 3D-aware face landmarks. The landmarks include the reference ID and the target attributes. Then, we design HiFi-Net to fuse multi-face features and align them with landmarks, which improves ID fidelity and face control. In addition, we devise an automated pipeline to construct an ID-based dataset for training HiFi-Portrait. Extensive experimental results demonstrate that our method surpasses the SOTA approaches in face similarity and controllability. Furthermore, our method is also compatible with previous SDXL-based works.

📄 PDF Abstract BibTeX arXiv:2512.14542

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion

2025-01-01 · CVPR 2025 1 · Yifang Xu, Benxiang Zhai, Yunzhuo Sun, Ming Li 외

Recent advancements in diffusion-based technologies have made significant strides, particularly in identity-preserved portrait generation (IPG). However, when using multiple reference images from the same ID, existin…

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation

2024-12-16 · CVPR 2025 1 · Yiren Song, Pei Yang, Hai Ci, Mike Zheng Shou

Recently, zero-shot methods like InstantID have revolutionized identity-preserving generation. Unlike multi-image finetuning approaches such as DreamBooth, these zero-shot methods leverage powerful facial encoders to ext…

Image Generation

One-Shot Identity-Preserving Portrait Reenactment

2020-04-26 · Sitao Xiang, Yuming Gu, Pengda Xiang, Mingming He 외

We present a deep learning-based framework for portrait reenactment from a single picture of a target (one-shot) and a video of a driving subject. Existing facial reenactment methods suffer from identity mismatch and pro…

DisentanglementGenerative Adversarial Network

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

2026-01-31 · Yifang Xu, Benxiang Zhai, Chenyu Zhang, Ming Li 외 arxiv

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, …

FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization

2024-10-16 · Cheng Yu, Haoyu Xie, Lei Shang, Yang Liu 외

In the field of human-centric personalized image generation, the adapter-based method obtains the ability to customize and generate portraits by text-to-image training on facial data. This allows for identity-preserved p…

DiversityImage GenerationPersonalized Image GenerationText to Image Generation+1