HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915679264833536 |
|---|---|
| author | Xu, Yifang Zhai, Benxiang Sun, Yunzhuo Li, Ming Li, Yang Du, Sidan |
| author_facet | Xu, Yifang Zhai, Benxiang Sun, Yunzhuo Li, Ming Li, Yang Du, Sidan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14542 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion Xu, Yifang Zhai, Benxiang Sun, Yunzhuo Li, Ming Li, Yang Du, Sidan Computer Vision and Pattern Recognition 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. |
| title | HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.14542 |