Let storytelling tell vivid stories: A multi-modal-agent-based unified storytelling framework

Open Webpage

Rongsheng Zhang, Jiji Tang, Chuanqi Zang, Mingtao Pei, Wei Liang, Zeng Zhao, Zhou Zhao

Published: 01 Jan 2025, Last Modified: 21 May 2025Neurocomputing 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Proposes the LLaMS framework for the storytelling task to generate human-preferred stories.•Introduces the Story-Adapter module designed for common image sequence styles.•Achieves the SOTA storytelling performance compared to prior methods.