Contact person: Steeven Villa (steeven.villa@um.ifi.lmu.de

Internal Partners:

  1. Ludwig-Maximilians-Universität München (LMU), Steeven Ville and Sebastian Feger  

External Partners:

  1. Sheffield Hallam University Enterprises Limited, Daniela Petrelli  

 

Novel AI systems enable individuals to maximize their creative potential by rapidly prototyping ideas based on initial sketches or idea descriptions. A generative AI system is the bridge between an individual’s thought and its physical manifestation. Traditional approaches, on the other hand, require a greater investment of effort, involvement, and time, which was historically associated with a sense of ownership over the creation and agency (or control) over the creation process. As the paradigm shift caused by AI significantly reduces the amount of work required to achieve a desired result, individuals consistently report low agency and ownership over their creations, and such boundaries are unclear even in the legal sphere. Therefore, it is essential to understand how these variables can be balanced to foster a strong sense of ownership while allowing users to fully exploit the potential of AI systems. In this project, we seeked to achieve this understanding by creating an interactive exhibition where visitors to a science museum will interact with a generative AI system to create illustrations for a children’s book based on rough sketches and prompts. The participants will be instructed to collaborate with an image-generating AI system to illustrate a children’s storybook with a simple plot. Participants will start with their own sketch or by selecting one from a set. When an illustration is finished, participants will be asked if they want to sign the illustration with their name, the name of the AI model, or both. Participants will have the option to display their illustrations on the exhibition’s billboard. We will conclude by asking them three brief questions about self-efficacy. The interaction will be logged to record the degree of intervention (iterating over the illustrations, using a starting sketch instead of drawing their own sketch, signature ownership). We plan to carry out a limited quantitative study with observations of visitors’ behavior paired with interviews. With the collected data, we will be able to analyze the correlations between time, effort, ownership, and self-efficacy in the AI-assisted creative process, and ultimately gain insights into how to design such systems to promote a sense of ownership in the user. This project falls under WP3. It examines the Pragmatic aspects of communication and collaboration between humans and AI by exploring how participants collaborate with an AI system to translate their initial sketches or prompts into meaningful illustrations for visual narratives for Storytelling. Everything from the lens of influence of the participants’ sense of ownership and agency and how it impacts the outcome and design process.

Results Summary

This project led to the development of three unique museum exhibitions featured at the Deutsches Museum, Bonn Museum, and Alte Pinakothek. At the core of each exhibition is a generative AI system that enables visitors to co-create children’s book stories, giving them the freedom to shape the narrative using drawing inputs. This AI system is specifically tailored for a museum installation environment, ensuring it remains offline and highly reliable.

A notable feature of the Alte Pinakothek installation (developed in collaboration with Sheffield University) is the physical prototype’s symmetrical design, which embodies the collaborative dynamic between human creativity and AI assistance. The visitor is seated on one side, interacting directly with the system. Opposite them, a glowing cube represents the AI presence, actively responding to the user’s inputs. This cube subtly illuminates and adapts based on the AI’s activity, providing visual cues that guide and inspire users through the story-making process.

Additionally, two master’s theses were developed within this project’s framework, and initial data from over 300 user interactions at the Deutsches Museum has already been gathered. These interactions will form the basis for future research publications, offering valuable insights into the role of AI in creative storytelling and user engagement within museum settings. There is a planned paper submission of the project.

Tangible Outcomes

  1. Backend: https://github.com/dorj222/storybookcreator 
  2. Video presentation summarizing the project