Table of Contents
Fetching ...

StoryComposerAI: Supporting Human-AI Story Co-Creation Through Decomposition and Linking

Shuo Niu, Dylan Clements, Marina Margalit Nemanov, Hyungsin Kim

TL;DR

This work implements and evaluates StoryComposerAI, a system that exemplifies a paradigm of creative decomposition and linking that allows creators to clearly communicate creative intent by prompting GenAI to tailor specific story elements, such as storylines, personas, locations, and scenes, while maintaining coherence among them.

Abstract

GenAI's ability to produce text and images is increasingly incorporated into human-AI co-creation tasks such as storytelling and video editing. However, integrating GenAI into these tasks requires enabling users to retain control over editing individual story elements while ensuring that generated visuals remain coherent with the storyline and consistent across multiple AI-generated outputs. This work examines a paradigm of creative decomposition and linking, which allows creators to clearly communicate creative intent by prompting GenAI to tailor specific story elements, such as storylines, personas, locations, and scenes, while maintaining coherence among them. We implement and evaluate StoryComposerAI, a system that exemplifies this paradigm for enhancing users' sense of control and content consistency in human-AI co-creation of digital stories.

StoryComposerAI: Supporting Human-AI Story Co-Creation Through Decomposition and Linking

TL;DR

This work implements and evaluates StoryComposerAI, a system that exemplifies a paradigm of creative decomposition and linking that allows creators to clearly communicate creative intent by prompting GenAI to tailor specific story elements, such as storylines, personas, locations, and scenes, while maintaining coherence among them.

Abstract

GenAI's ability to produce text and images is increasingly incorporated into human-AI co-creation tasks such as storytelling and video editing. However, integrating GenAI into these tasks requires enabling users to retain control over editing individual story elements while ensuring that generated visuals remain coherent with the storyline and consistent across multiple AI-generated outputs. This work examines a paradigm of creative decomposition and linking, which allows creators to clearly communicate creative intent by prompting GenAI to tailor specific story elements, such as storylines, personas, locations, and scenes, while maintaining coherence among them. We implement and evaluate StoryComposerAI, a system that exemplifies this paradigm for enhancing users' sense of control and content consistency in human-AI co-creation of digital stories.
Paper Structure (10 sections, 2 figures, 1 table)

This paper contains 10 sections, 2 figures, 1 table.

Figures (2)

  • Figure 1: Decomposition and Linking (DLCI) Workflow.
  • Figure 2: StoryComposerAI Interface. (1) Story creation begins with the user either selecting an AI-suggested idea or typing their own and (6) viewing the produced storyboard. From the storyboard, (b) the navigation bar allows the user to access the component edit pages, the storyboard, or start over, which is available on all edit pages as well. Interacting with an image brings the user (5) to the scene edit screen, where the user can edit either the image prompt or narration using the (a) chat box where they can instruct Gemini to modify the corresponding component. The user can use the (d) carousel to navigate to different scenes or press on a (c) highlighted persona or location name in the image prompt to navigate to either the (3) Persona Edit or (4) Location Edit Screens. By using the navigation bar on any of the edit screens the user can reach the (2) Storyline Edit Screen.