FaceSnap: Enhanced ID-fidelity Network for Tuning-free Portrait Customization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910007420780544 |
|---|---|
| author | Zhai, Benxiang Xu, Yifang Zhang, Guofeng Li, Yang Du, Sidan |
| author_facet | Zhai, Benxiang Xu, Yifang Zhang, Guofeng Li, Yang Du, Sidan |
| contents | Benefiting from the significant advancements in text-to-image diffusion models, research in personalized image generation, particularly customized portrait generation, has also made great strides recently. However, existing methods either require time-consuming fine-tuning and lack generalizability or fail to achieve high fidelity in facial details. To address these issues, we propose FaceSnap, a novel method based on Stable Diffusion (SD) that requires only a single reference image and produces extremely consistent results in a single inference stage. This method is plug-and-play and can be easily extended to different SD models. Specifically, we design a new Facial Attribute Mixer that can extract comprehensive fused information from both low-level specific features and high-level abstract features, providing better guidance for image generation. We also introduce a Landmark Predictor that maintains reference identity across landmarks with different poses, providing diverse yet detailed spatial control conditions for image generation. Then we use an ID-preserving module to inject these into the UNet. Experimental results demonstrate that our approach performs remarkably in personalized and customized portrait generation, surpassing other state-of-the-art methods in this domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00627 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FaceSnap: Enhanced ID-fidelity Network for Tuning-free Portrait Customization Zhai, Benxiang Xu, Yifang Zhang, Guofeng Li, Yang Du, Sidan Computer Vision and Pattern Recognition Benefiting from the significant advancements in text-to-image diffusion models, research in personalized image generation, particularly customized portrait generation, has also made great strides recently. However, existing methods either require time-consuming fine-tuning and lack generalizability or fail to achieve high fidelity in facial details. To address these issues, we propose FaceSnap, a novel method based on Stable Diffusion (SD) that requires only a single reference image and produces extremely consistent results in a single inference stage. This method is plug-and-play and can be easily extended to different SD models. Specifically, we design a new Facial Attribute Mixer that can extract comprehensive fused information from both low-level specific features and high-level abstract features, providing better guidance for image generation. We also introduce a Landmark Predictor that maintains reference identity across landmarks with different poses, providing diverse yet detailed spatial control conditions for image generation. Then we use an ID-preserving module to inject these into the UNet. Experimental results demonstrate that our approach performs remarkably in personalized and customized portrait generation, surpassing other state-of-the-art methods in this domain. |
| title | FaceSnap: Enhanced ID-fidelity Network for Tuning-free Portrait Customization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.00627 |