Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911586455650304 |
|---|---|
| author | Wang, Zihao Wei, Yuxiang Zhou, Xinpeng Zhang, Tianyu Liang, Tao Bai, Yalong Zhang, Hongzhi Zuo, Wangmeng |
| author_facet | Wang, Zihao Wei, Yuxiang Zhou, Xinpeng Zhang, Tianyu Liang, Tao Bai, Yalong Zhang, Hongzhi Zuo, Wangmeng |
| contents | Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or latent codes rarely reflect them faithfully, leading to suboptimal personalization. We present Premier, a novel preference modulation framework for personalized image generation. Premier represents each user's preference as a learnable embedding and introduces a preference adapter that fuses the user embedding with the text prompt. To enable accurate and fine-grained preference control, the fused preference embedding is further used to modulate the generative process. To enhance the distinctness of individual preference and improve alignment between outputs and user-specific styles, we incorporate a dispersion loss that enforces separation among user embeddings. When user data are scarce, new users are represented as linear combinations of existing preference embeddings learned during training, enabling effective generalization. Experiments show that Premier outperforms prior methods under the same history length, achieving stronger preference alignment and superior performance on text consistency, ViPer proxy metrics, and expert evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20725 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation Wang, Zihao Wei, Yuxiang Zhou, Xinpeng Zhang, Tianyu Liang, Tao Bai, Yalong Zhang, Hongzhi Zuo, Wangmeng Computer Vision and Pattern Recognition Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or latent codes rarely reflect them faithfully, leading to suboptimal personalization. We present Premier, a novel preference modulation framework for personalized image generation. Premier represents each user's preference as a learnable embedding and introduces a preference adapter that fuses the user embedding with the text prompt. To enable accurate and fine-grained preference control, the fused preference embedding is further used to modulate the generative process. To enhance the distinctness of individual preference and improve alignment between outputs and user-specific styles, we incorporate a dispersion loss that enforces separation among user embeddings. When user data are scarce, new users are represented as linear combinations of existing preference embeddings learned during training, enabling effective generalization. Experiments show that Premier outperforms prior methods under the same history length, achieving stronger preference alignment and superior performance on text consistency, ViPer proxy metrics, and expert evaluations. |
| title | Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.20725 |