Reproduce “StoryEngine: A State-Grounded Agentic Framework for Video Storytelling” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yingrui Wang, Zeqing Wang, Yeying Jin
StoryEngine separates planned story states from generated images to maintain cross-shot continuity. Events update entity locations and attributes; grounded references, a continuity gate, and bounded evaluator-guided repair help render shots without letting frames redefine the plan. On the 60-story, 10-shot benchmark with Veo 3.1, it scores 0.7690 average, above ViMax’s 0.6274, but these scores are on a narrow visual benchmark.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.