ACM SIGCHI Conference on Human Factors in Computing Systems 2025

Paratrouper

Exploratory Creation of Character Cast Visuals Using Generative AI

Paratrouper is a multi-modal tool for visual character cast design. One can use text, sketches, and image references to generate images of original characters within cards. Characters can be sorted and styled in groups, visualized from multiple angles in character sheets, and staged together in different settings. Note: Character images are AI-generated.

Abstract

Great characters are critical to the success of many forms of media, such as comics, games, and films. Designing visually compelling casts of characters requires significant skill and consideration, and there is a lack of specialized tools to support this endeavor. We investigate how AI-driven image-generation techniques can empower creatives to explore a variety of visual design possibilities for individual and groups of characters. Informed by interviews with character designers, Paratrouper is a multi-modal system that enables creating and experimenting with multiple permutations for character casts and visualizing them in various contexts as part of a holistic approach to design. We demonstrate how Paratrouper supports different aspects of the character design process, and share insights from its use by eight creators. Our work highlights the interplay between creative agency and serendipity, as well as the visual interrelationships among character aesthetics.

Download publication

Associated Researchers

Joanne Leong

University of Toronto & MIT Media Lab

Thomas Driscoll

University of Toronto

Tovi Grossman

University of Toronto

Related Publications

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us