SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Song, Quanjian, Zhou, Donghao, Lin, Jingyu, Shen, Fei, Wang, Jiaze, Hu, Xiaowei, Chen, Cunjian, Heng, Pheng-Ann
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912671900631040
author Song, Quanjian
Zhou, Donghao
Lin, Jingyu
Shen, Fei
Wang, Jiaze
Hu, Xiaowei
Chen, Cunjian
Heng, Pheng-Ann
author_facet Song, Quanjian
Zhou, Donghao
Lin, Jingyu
Shen, Fei
Wang, Jiaze
Hu, Xiaowei
Chen, Cunjian
Heng, Pheng-Ann
contents Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial role of scenes in storytelling, which restricts their creativity in practice. This paper introduces scene-oriented story generation, addressing two key challenges: (i) scene planning, where current methods fail to ensure scene-level narrative coherence by relying solely on text descriptions, and (ii) scene consistency, which remains largely unexplored in terms of maintaining scene consistency across multiple stories. We propose SceneDecorator, a training-free framework that employs VLM-Guided Scene Planning to ensure narrative coherence across different scenes in a ``global-to-local'' manner, and Long-Term Scene-Sharing Attention to maintain long-term scene consistency and subject diversity across generated stories. Extensive experiments demonstrate the superior performance of SceneDecorator, highlighting its potential to unleash creativity in the fields of arts, films, and games.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22994
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
Song, Quanjian
Zhou, Donghao
Lin, Jingyu
Shen, Fei
Wang, Jiaze
Hu, Xiaowei
Chen, Cunjian
Heng, Pheng-Ann
Computer Vision and Pattern Recognition
Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial role of scenes in storytelling, which restricts their creativity in practice. This paper introduces scene-oriented story generation, addressing two key challenges: (i) scene planning, where current methods fail to ensure scene-level narrative coherence by relying solely on text descriptions, and (ii) scene consistency, which remains largely unexplored in terms of maintaining scene consistency across multiple stories. We propose SceneDecorator, a training-free framework that employs VLM-Guided Scene Planning to ensure narrative coherence across different scenes in a ``global-to-local'' manner, and Long-Term Scene-Sharing Attention to maintain long-term scene consistency and subject diversity across generated stories. Extensive experiments demonstrate the superior performance of SceneDecorator, highlighting its potential to unleash creativity in the fields of arts, films, and games.
title SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.22994