Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929519100690432 |
|---|---|
| author | Ma, Yuhang Xu, Wenting Tang, Jiji Jin, Qinfeng Zhang, Rongsheng Zhao, Zeng Fan, Changjie Hu, Zhipeng |
| author_facet | Ma, Yuhang Xu, Wenting Tang, Jiji Jin, Qinfeng Zhang, Rongsheng Zhao, Zeng Fan, Changjie Hu, Zhipeng |
| contents | Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have encountered challenges in preserving characters with high-fidelity consistency due to inadequate feature extraction and concept confusion of reference characters. Therefore, we propose Character-Adapter, a plug-and-play framework designed to generate images that preserve the details of reference characters, ensuring high-fidelity consistency. Character-Adapter employs prompt-guided segmentation to ensure fine-grained regional features of reference characters and dynamic region-level adapters to mitigate concept confusion. Extensive experiments are conducted to validate the effectiveness of Character-Adapter. Both quantitative and qualitative results demonstrate that Character-Adapter achieves the state-of-the-art performance of consistent character generation, with an improvement of 24.8% compared with other methods. Our code will be released at https://github.com/Character-Adapter/Character-Adapter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16537 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization Ma, Yuhang Xu, Wenting Tang, Jiji Jin, Qinfeng Zhang, Rongsheng Zhao, Zeng Fan, Changjie Hu, Zhipeng Computer Vision and Pattern Recognition Artificial Intelligence Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have encountered challenges in preserving characters with high-fidelity consistency due to inadequate feature extraction and concept confusion of reference characters. Therefore, we propose Character-Adapter, a plug-and-play framework designed to generate images that preserve the details of reference characters, ensuring high-fidelity consistency. Character-Adapter employs prompt-guided segmentation to ensure fine-grained regional features of reference characters and dynamic region-level adapters to mitigate concept confusion. Extensive experiments are conducted to validate the effectiveness of Character-Adapter. Both quantitative and qualitative results demonstrate that Character-Adapter achieves the state-of-the-art performance of consistent character generation, with an improvement of 24.8% compared with other methods. Our code will be released at https://github.com/Character-Adapter/Character-Adapter. |
| title | Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2406.16537 |