Building Consistent Characters through Open-Source Generative AI

Luca Martini; Lara La Tessa; Daniele Zolezzi

doi:10.3991/ijet.v19i08.50223

Building Consistent Characters through Open-Source Generative AI

Authors

Luca Martini University of Genoa, Genoa, Italy https://orcid.org/0009-0006-8453-8407
Lara La Tessa University of Genoa, Genoa, Italy https://orcid.org/0009-0008-1024-4275
Daniele Zolezzi University of Genoa, Genoa, Italy https://orcid.org/0000-0002-5355-1426

DOI:

https://doi.org/10.3991/ijet.v19i08.50223

Keywords:

Generative AI, Consistent Characters, Open Source

Abstract

This paper presents a pipeline for creating consistent characters using open-source generative AI tools, aimed at enhancing educational content. Through the use of XTTS, Fooocus, and FaceFusion, a talking avatar of the marine biologist Raffaele Issel was developed, accurately replicating his facial and vocal features. This study demonstrates how these tools can generate high-quality, engaging educational materials with minimal technical expertise and resources. The methodology facilitates the creation of interactive avatars for use in graphic novels and comic books, enriching museum and educational experiences.

Downloads

Published

2024-11-26

How to Cite

Martini, L., La Tessa, L., & Zolezzi, D. (2024). Building Consistent Characters through Open-Source Generative AI. International Journal of Emerging Technologies in Learning (iJET), 19(08), pp. 82–89. https://doi.org/10.3991/ijet.v19i08.50223