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

Pheng-Ann Heng (The Chinese University of Hong Kong) · Quanjian Song · Donghao Zhou (The Chinese University of Hong Kong) · Jingyu Lin (Monash University) · Fei Shen (Nanjing University of Science and Technology) · Jiaze Wang (The Chinese University of Hong Kong) · Xiaowei Hu (South China University of Technology) · Cunjian Chen (Monash University)

artsconcept consistencycreativityfilmsgameslong-term scene-sharing attentionnarrative coherencescene consistencyscene planningscene-oriented story generationstorytellingsubject diversitytext-to-image models training-free frameworkvlm-guided scene planning

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.