IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models
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_ | 1866909144439586816 |
|---|---|
| author | Cui, Siying Guo, Jia An, Xiang Deng, Jiankang Zhao, Yongle Wei, Xinyu Feng, Ziyong |
| author_facet | Cui, Siying Guo, Jia An, Xiang Deng, Jiankang Zhao, Yongle Wei, Xinyu Feng, Ziyong |
| contents | Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts. However, existing personalization methods face challenges, including test-time fine-tuning, the requirement of multiple input images, low preservation of identity, and limited diversity in generated outcomes. To overcome these challenges, we introduce IDAdapter, a tuning-free approach that enhances the diversity and identity preservation in personalized image generation from a single face image. IDAdapter integrates a personalized concept into the generation process through a combination of textual and visual injections and a face identity loss. During the training phase, we incorporate mixed features from multiple reference images of a specific identity to enrich identity-related content details, guiding the model to generate images with more diverse styles, expressions, and angles compared to previous works. Extensive evaluations demonstrate the effectiveness of our method, achieving both diversity and identity fidelity in generated images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13535 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models Cui, Siying Guo, Jia An, Xiang Deng, Jiankang Zhao, Yongle Wei, Xinyu Feng, Ziyong Computer Vision and Pattern Recognition Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts. However, existing personalization methods face challenges, including test-time fine-tuning, the requirement of multiple input images, low preservation of identity, and limited diversity in generated outcomes. To overcome these challenges, we introduce IDAdapter, a tuning-free approach that enhances the diversity and identity preservation in personalized image generation from a single face image. IDAdapter integrates a personalized concept into the generation process through a combination of textual and visual injections and a face identity loss. During the training phase, we incorporate mixed features from multiple reference images of a specific identity to enrich identity-related content details, guiding the model to generate images with more diverse styles, expressions, and angles compared to previous works. Extensive evaluations demonstrate the effectiveness of our method, achieving both diversity and identity fidelity in generated images. |
| title | IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.13535 |