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

Authors

  • Adrian Gonzalez Cinvestav IPN Unidad Guadalajara
  • Matthew Guzdial University of Alberta
  • Felix Ramos Cinvestav IPN Unidad Guadalajara

DOI:

https://doi.org/10.1609/aiide.v17i1.18915

Keywords:

Creativity Support Tool, Design Support Tool, Conditional Variational Autoencoder, Image Generation For Games, Natural Language Interface, Content Generation

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.

Downloads

Published

2021-10-04

How to Cite

Gonzalez, A., Guzdial, M., & Ramos, F. (2021). A Tool for Generating Monster Silhouettes with a Word-Conditioned Variational Autoencoder. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 17(1), 237-239. https://doi.org/10.1609/aiide.v17i1.18915