Tuning-Free Image Customization with Image and Text Guidance
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_ | 1866913416978890752 |
|---|---|
| author | Li, Pengzhi Nie, Qiang Chen, Ying Jiang, Xi Wu, Kai Lin, Yuhuan Liu, Yong Peng, Jinlong Wang, Chengjie Zheng, Feng |
| author_facet | Li, Pengzhi Nie, Qiang Chen, Ying Jiang, Xi Wu, Kai Lin, Yuhuan Liu, Yong Peng, Jinlong Wang, Chengjie Zheng, Feng |
| contents | Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference image or text descriptions; and 3) time-consuming fine-tuning, which limits their practical application. In response, we introduce a tuning-free framework for simultaneous text-image-guided image customization, enabling precise editing of specific image regions within seconds. Our approach preserves the semantic features of the reference image subject while allowing modification of detailed attributes based on text descriptions. To achieve this, we propose an innovative attention blending strategy that blends self-attention features in the UNet decoder during the denoising process. To our knowledge, this is the first tuning-free method that concurrently utilizes text and image guidance for image customization in specific regions. Our approach outperforms previous methods in both human and quantitative evaluations, providing an efficient solution for various practical applications, such as image synthesis, design, and creative photography. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12658 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tuning-Free Image Customization with Image and Text Guidance Li, Pengzhi Nie, Qiang Chen, Ying Jiang, Xi Wu, Kai Lin, Yuhuan Liu, Yong Peng, Jinlong Wang, Chengjie Zheng, Feng Computer Vision and Pattern Recognition Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference image or text descriptions; and 3) time-consuming fine-tuning, which limits their practical application. In response, we introduce a tuning-free framework for simultaneous text-image-guided image customization, enabling precise editing of specific image regions within seconds. Our approach preserves the semantic features of the reference image subject while allowing modification of detailed attributes based on text descriptions. To achieve this, we propose an innovative attention blending strategy that blends self-attention features in the UNet decoder during the denoising process. To our knowledge, this is the first tuning-free method that concurrently utilizes text and image guidance for image customization in specific regions. Our approach outperforms previous methods in both human and quantitative evaluations, providing an efficient solution for various practical applications, such as image synthesis, design, and creative photography. |
| title | Tuning-Free Image Customization with Image and Text Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12658 |