LLM-Enabled Style and Content Regularization for Personalized Text-to-Image Generation
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_ | 1866908331276238848 |
|---|---|
| author | Yu, Anran Feng, Wei Zhang, Yaochen Li, Xiang Meng, Lei Wu, Lei Meng, Xiangxu |
| author_facet | Yu, Anran Feng, Wei Zhang, Yaochen Li, Xiang Meng, Lei Wu, Lei Meng, Xiangxu |
| contents | The personalized text-to-image generation has rapidly advanced with the emergence of Stable Diffusion. Existing methods, which typically fine-tune models using embedded identifiers, often struggle with insufficient stylization and inaccurate image content due to reduced textual controllability. In this paper, we propose style refinement and content preservation strategies. The style refinement strategy leverages the semantic information of visual reasoning prompts and reference images to optimize style embeddings, allowing a more precise and consistent representation of style information. The content preservation strategy addresses the content bias problem by preserving the model's generalization capabilities, ensuring enhanced textual controllability without compromising stylization. Experimental results verify that our approach achieves superior performance in generating consistent and personalized text-to-image outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15309 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Enabled Style and Content Regularization for Personalized Text-to-Image Generation Yu, Anran Feng, Wei Zhang, Yaochen Li, Xiang Meng, Lei Wu, Lei Meng, Xiangxu Computer Vision and Pattern Recognition The personalized text-to-image generation has rapidly advanced with the emergence of Stable Diffusion. Existing methods, which typically fine-tune models using embedded identifiers, often struggle with insufficient stylization and inaccurate image content due to reduced textual controllability. In this paper, we propose style refinement and content preservation strategies. The style refinement strategy leverages the semantic information of visual reasoning prompts and reference images to optimize style embeddings, allowing a more precise and consistent representation of style information. The content preservation strategy addresses the content bias problem by preserving the model's generalization capabilities, ensuring enhanced textual controllability without compromising stylization. Experimental results verify that our approach achieves superior performance in generating consistent and personalized text-to-image outputs. |
| title | LLM-Enabled Style and Content Regularization for Personalized Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15309 |