Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910960964337664 |
|---|---|
| author | Liu, Zichuan Jiang, Liming Yan, Qing Jia, Yumin Kang, Hao Lu, Xin |
| author_facet | Liu, Zichuan Jiang, Liming Yan, Qing Jia, Yumin Kang, Hao Lu, Xin |
| contents | We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unified conditioning input. To achieve this, we introduce FaceCLIP, a multi-modal encoder that learns a joint embedding space for both identity and textual semantics. Given a reference face and a text prompt, FaceCLIP produces a unified representation that encodes both identity and text, which conditions a base diffusion model to generate images that are identity-consistent and text-aligned. We also present a multi-modal alignment algorithm to train FaceCLIP, using a loss that aligns its joint representation with face, text, and image embedding spaces. We then build FaceCLIP-SDXL, an ID-preserving image synthesis pipeline by integrating FaceCLIP with Stable Diffusion XL (SDXL). Compared to prior methods, FaceCLIP-SDXL enables photorealistic portrait generation with better identity preservation and textual relevance. Extensive experiments demonstrate its quantitative and qualitative superiority. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14202 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis Liu, Zichuan Jiang, Liming Yan, Qing Jia, Yumin Kang, Hao Lu, Xin Computer Vision and Pattern Recognition Artificial Intelligence We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unified conditioning input. To achieve this, we introduce FaceCLIP, a multi-modal encoder that learns a joint embedding space for both identity and textual semantics. Given a reference face and a text prompt, FaceCLIP produces a unified representation that encodes both identity and text, which conditions a base diffusion model to generate images that are identity-consistent and text-aligned. We also present a multi-modal alignment algorithm to train FaceCLIP, using a loss that aligns its joint representation with face, text, and image embedding spaces. We then build FaceCLIP-SDXL, an ID-preserving image synthesis pipeline by integrating FaceCLIP with Stable Diffusion XL (SDXL). Compared to prior methods, FaceCLIP-SDXL enables photorealistic portrait generation with better identity preservation and textual relevance. Extensive experiments demonstrate its quantitative and qualitative superiority. |
| title | Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.14202 |