Node-Based Editing for Multimodal Generation of Text, Audio, Image, and Video

TL;DR

This paper introduces a node-based storytelling system enabling multimodal content creation through graph-based story representation, supporting targeted editing, iterative refinement, and integration of text, images, audio, and video.

Contribution

The work presents a novel node-based interface for multimodal storytelling that allows flexible editing and generation of narratives across multiple media types.

Findings

Supports control over narrative structure.

Enables iterative generation of multimodal content.

Demonstrates effectiveness in story outline generation.

Abstract

We present a node-based storytelling system for multimodal content generation. The system represents stories as graphs of nodes that can be expanded, edited, and iteratively refined through direct user edits and natural-language prompts. Each node can integrate text, images, audio, and video, allowing creators to compose multimodal narratives. A task selection agent routes between specialized generative tasks that handle story generation, node structure reasoning, node diagram formatting, and context generation. The interface supports targeted editing of individual nodes, automatic branching for parallel storylines, and node-based iterative refinement. Our results demonstrate that node-based editing supports control over narrative structure and iterative generation of text, images, audio, and video. We report quantitative outcomes on automatic story outline generation and qualitative observations of editing workflows. Finally, we discuss current limitations such as scalability to longer narratives and consistency across multiple nodes, and outline future work toward human-in-the-loop and user-centered creative AI tools.