From Words to Worlds: Transforming One-line Prompt into Immersive Multi-modal Digital Stories with Communicative LLM Agent

TL;DR

This paper introduces the StoryAgent framework that leverages Large Language Models and generative tools to automate and enhance the creation of immersive, multi-modal digital stories from simple prompts, improving scalability and engagement.

Contribution

The paper presents a novel framework combining top-down story drafting with bottom-up asset generation, enabling automated, consistent, and interactive digital storytelling across multiple modalities.

Findings

Able to produce coherent digital stories without reference videos

Automates story creation, reducing manual intervention

Enhances engagement through multi-modal content

Abstract

Digital storytelling, essential in entertainment, education, and marketing, faces challenges in production scalability and flexibility. The StoryAgent framework, introduced in this paper, utilizes Large Language Models and generative tools to automate and refine digital storytelling. Employing a top-down story drafting and bottom-up asset generation approach, StoryAgent tackles key issues such as manual intervention, interactive scene orchestration, and narrative consistency. This framework enables efficient production of interactive and consistent narratives across multiple modalities, democratizing content creation and enhancing engagement. Our results demonstrate the framework's capability to produce coherent digital stories without reference videos, marking a significant advancement in automated digital storytelling.