Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908767835127808 |
|---|---|
| author | Ge, Yanqi Liu, Jiaqi Fan, Qingnan Jiang, Xi Huang, Ye Qin, Shuai Gu, Hong Li, Wen Duan, Lixin |
| author_facet | Ge, Yanqi Liu, Jiaqi Fan, Qingnan Jiang, Xi Huang, Ye Qin, Shuai Gu, Hong Li, Wen Duan, Lixin |
| contents | In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while enabling effective style transfer effects. The past approaches in this field directly concatenate the content and style prompts for a prompt-level style injection, leading to unavoidable structure distortions. In this work, we propose a novel solution to the text-driven style transfer task, namely, Adaptive Style Incorporation~(ASI), to achieve fine-grained feature-level style incorporation. It consists of the Siamese Cross-Attention~(SiCA) to decouple the single-track cross-attention to a dual-track structure to obtain separate content and style features, and the Adaptive Content-Style Blending (AdaBlending) module to couple the content and style information from a structure-consistent manner. Experimentally, our method exhibits much better performance in both structure preservation and stylized effects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06835 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer Ge, Yanqi Liu, Jiaqi Fan, Qingnan Jiang, Xi Huang, Ye Qin, Shuai Gu, Hong Li, Wen Duan, Lixin Computer Vision and Pattern Recognition In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while enabling effective style transfer effects. The past approaches in this field directly concatenate the content and style prompts for a prompt-level style injection, leading to unavoidable structure distortions. In this work, we propose a novel solution to the text-driven style transfer task, namely, Adaptive Style Incorporation~(ASI), to achieve fine-grained feature-level style incorporation. It consists of the Siamese Cross-Attention~(SiCA) to decouple the single-track cross-attention to a dual-track structure to obtain separate content and style features, and the Adaptive Content-Style Blending (AdaBlending) module to couple the content and style information from a structure-consistent manner. Experimentally, our method exhibits much better performance in both structure preservation and stylized effects. |
| title | Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.06835 |