How Creatives Approach GenAI Image Generation: Tensions Between Structured Guidance, Self-Experimentation, and Creative Autonomy

TL;DR

This study explores how artists and hobbyists learn and navigate GenAI image tools, revealing a tension between structured guidance and creative autonomy in AI literacy support.

Contribution

It provides empirical insights into creatives' learning preferences and introduces a research probe to understand perceptions of guidance in AI tool usage.

Findings

Creatives use self-experimentation and tutorials to learn GenAI tools.

Many find AI terminology confusing, impacting their learning.

Guidance helps understanding but may limit creativity.

Abstract

As generative AI tools increasingly influence creative practice, they raise longstanding HCI questions about how creatives learn complex software and how they can be better supported. We conducted an interview study with artists and hobbyists (n=8) and a follow-up survey (n=159) to understand how this population approaches and seeks guidance for GenAI image tools. We found that creatives commonly use either self-experimentation or tutorials to explore GenAI tools, yet many struggle with confusing AI terminology. To gain further insight into creatives' learning experiences, we developed a research probe to elicit creatives' perceptions of structured guidance. Our user study with 17 creatives revealed that, even when creatives described the guidance as helpful for understanding AI, many still preferred self-experimentation, feeling that guidance could limit their creativity. Our findings highlight a central tension in supporting AI literacy for creatives: balancing guidance and promoting literacy while preserving creative freedom.