Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications

Imke Grabe, Miguel Gonzalez Duque, Jichen Zhu

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


With the rise of Generative Adversarial Networks (GANs), AI has increasingly become a partner to human designers in
co-creating cultural artifacts. While generative models have been applied in various creative tasks across disciplines, a
theoretical foundation for understanding human-GAN collaboration is yet to be developed. Drawing from the mixed-initiative
co-creation community, we propose a preliminary framework to analyze co-creative GAN applications. We identify four
primary interaction patterns: Curating, Exploring, Evolving, and Conditioning. The suggested framework enables us to discuss
the affordances and limitations of the different kind of interactions underlying co-creative GAN applications
Original languageEnglish
Title of host publicationProceeding of the 3rd Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN ‘22)at ACM IUI Workshops
Publication date2022
Publication statusPublished - 2022


  • Generative Adversarial Networks
  • Co-creation
  • Human-AI Collaboration
  • Mixed-Initiative Interaction
  • Interaction Patterns


Dive into the research topics of 'Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications'. Together they form a unique fingerprint.

Cite this