Storytelling aims to generate reasonable and vivid narratives based on an
ordered image stream. The fidelity to the image story theme and the divergence
of story plots attract readers to keep reading. Previous works iteratively
improved the alignment of multiple modalities but ultimately resulted in the
generation of simplistic storylines for image streams. In this work, we propose
a new pipeline, termed LLaMS, to generate multimodal human-level stories that
are embodied in expressiveness and consistency. Specifically, by fully
exploiting the commonsense knowledge within the LLM, we first employ a sequence
data auto-enhancement strategy to enhance factual content expression and
leverage a textual reasoning architecture for expressive story generation and
prediction. Secondly, we propose SQ-Adatpter module for story illustration
generation which can maintain sequence consistency. Numerical results are
conducted through human evaluation to verify the superiority of proposed LLaMS.
Evaluations show that LLaMS achieves state-of-the-art storytelling performance
and 86% correlation and 100% consistency win rate as compared with previous
SOTA methods. Furthermore, ablation experiments are conducted to verify the
effectiveness of proposed sequence data enhancement and SQ-Adapter.

基于图像流生成合理和生动的故事情节的多模态的人类水平故事生成方法 LLaMS 通过充分利用 LLM 中的常识知识，首先采用序列数据自动增强策略来增强实际内容表达，并利用文本推理架构进行表达性故事生成和预测；其次，我们提出故事插图生成的 SQ-Adapter 模块来保持序列一致性。通过人工评估验证了 LLaMS 提出方法的优越性，与之前的 SOTA 方法相比具有最先进的故事性能，具有 86% 的相关性和 100% 的一致性胜率。此外，还进行了消融实验以验证所提出的序列数据增强和 SQ-Adapter 的有效性。