TensorX
返回文献探索

Paper · arXiv 2507.18634

Captain Cinema: Towards Short Movie Generation

Junfei Xiao, Ceyuan Yang, Lvmin Zhang, Shengqu Cai, Yang Zhao, Yuwei Guo, Gordon Wetzstein, Maneesh Agrawala, Alan Yuille, Lu Jiang

42 upvotesJuly 24, 2025arXiv 预印本
AI 摘要

Captain Cinema generates coherent short movies from textual descriptions using top-down keyframe planning and bottom-up video synthesis with Multimodal Diffusion Transformers.

top-down keyframe planningbottom-up video synthesisMultimodal Diffusion TransformersMM-DiTlong-context learningcinematic datasetinterleaved training strategy

Abstract

We present Captain Cinema, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context learning, to produce the spatio-temporal dynamics between them. This step is referred to as bottom-up video synthesis. To support stable and efficient generation of multi-scene long narrative cinematic works, we introduce an interleaved training strategy for Multimodal Diffusion Transformers (MM-DiT), specifically adapted for long-context video data. Our model is trained on a specially curated cinematic dataset consisting of interleaved data pairs. Our experiments demonstrate that Captain Cinema performs favorably in the automated creation of visually coherent and narrative consistent short movies in high quality and efficiency. Project page: https://thecinema.ai

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号