A Tool for Generating Monster Silhouettes with a Word-Conditioned Variational Autoencoder

Abstract

A character’s appearance is crucial to communicating game mechanics to the audience. Creating a game character’s design is a time-consuming task and requires design knowledge, skills, and experience. Research on how an AI system might be able to support this design process is an underexplored area. In this work we present a prototype of a variational autoencoder-based creativity support tool that modifies game character silhouettes by using words to describe the design’s desired properties.