Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.23519 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917174040330240 |
|---|---|
| author | Zhou, Donghao Lin, Jingyu Shen, Guibao Liu, Quande Gao, Jialin Liu, Lihao Du, Lan Chen, Cunjian Fu, Chi-Wing Hu, Xiaowei Heng, Pheng-Ann |
| author_facet | Zhou, Donghao Lin, Jingyu Shen, Guibao Liu, Quande Gao, Jialin Liu, Lihao Du, Lan Chen, Cunjian Fu, Chi-Wing Hu, Xiaowei Heng, Pheng-Ann |
| contents | Recent visual generative models enable story generation with consistent characters from text, but human-centric story generation faces additional challenges, such as maintaining detailed and diverse human face consistency and coordinating multiple characters across different images. This paper presents IdentityStory, a framework for human-centric story generation that ensures consistent character identity across multiple sequential images. By taming identity-preserving generators, the framework features two key components: Iterative Identity Discovery, which extracts cohesive character identities, and Re-denoising Identity Injection, which re-denoises images to inject identities while preserving desired context. Experiments on the ConsiStory-Human benchmark demonstrate that IdentityStory outperforms existing methods, particularly in face consistency, and supports multi-character combinations. The framework also shows strong potential for applications such as infinite-length story generation and dynamic character composition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23519 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation Zhou, Donghao Lin, Jingyu Shen, Guibao Liu, Quande Gao, Jialin Liu, Lihao Du, Lan Chen, Cunjian Fu, Chi-Wing Hu, Xiaowei Heng, Pheng-Ann Computer Vision and Pattern Recognition Recent visual generative models enable story generation with consistent characters from text, but human-centric story generation faces additional challenges, such as maintaining detailed and diverse human face consistency and coordinating multiple characters across different images. This paper presents IdentityStory, a framework for human-centric story generation that ensures consistent character identity across multiple sequential images. By taming identity-preserving generators, the framework features two key components: Iterative Identity Discovery, which extracts cohesive character identities, and Re-denoising Identity Injection, which re-denoises images to inject identities while preserving desired context. Experiments on the ConsiStory-Human benchmark demonstrate that IdentityStory outperforms existing methods, particularly in face consistency, and supports multi-character combinations. The framework also shows strong potential for applications such as infinite-length story generation and dynamic character composition. |
| title | IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.23519 |