{"ID":2824386,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.23519","arxiv_id":"2512.23519","title":"IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.23519","url_pdf":"https://arxiv.org/pdf/2512.23519v1","authors":"[\"Donghao Zhou\",\"Jingyu Lin\",\"Guibao Shen\",\"Quande Liu\",\"Jialin Gao\",\"Lihao Liu\",\"Lan Du\",\"Cunjian Chen\",\"Chi-Wing Fu\",\"Xiaowei Hu\",\"Pheng-Ann Heng\"]","published":"2025-12-29T14:54:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}