{"ID":2851338,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20822","arxiv_id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","abstract":"State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this \"narrative gap\" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot to the last. Our architecture achieves precise directorial control through a Window Cross-Attention mechanism that localizes text prompts to specific shots, while a Sparse Inter-Shot Self-Attention pattern (dense within shots but sparse between them) ensures the efficiency required for minute-scale generation. Beyond setting a new state-of-the-art in narrative coherence, HoloCine develops remarkable emergent abilities: a persistent memory for characters and scenes, and an intuitive grasp of cinematic techniques. Our work marks a pivotal shift from clip synthesis towards automated filmmaking, making end-to-end cinematic creation a tangible future. Our code is available at: https://holo-cine.github.io/.","short_abstract":"State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this \"narrative gap\" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot...","url_abs":"https://arxiv.org/abs/2510.20822","url_pdf":"https://arxiv.org/pdf/2510.20822v1","authors":"[\"Yihao Meng\",\"Hao Ouyang\",\"Yue Yu\",\"Qiuyu Wang\",\"Wen Wang\",\"Ka Leong Cheng\",\"Hanlin Wang\",\"Yixuan Li\",\"Cheng Chen\",\"Yanhong Zeng\",\"Yujun Shen\",\"Huamin Qu\"]","published":"2025-10-23T17:59:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}
