Towards Sustainable Creativity Support: An Exploratory Study on Prompt Based Image Generation

2025-04-10

AI Summary

This study addresses the challenge of reducing the energy consumption of AI image generation without compromising its supportive role in human creativity. Through a controlled user study with 24 participants, we integrated prompt behavior coding, a multidimensional creativity support scale, fine-grained energy consumption logging, and statistical modeling (ANOVA and correlation analysis). Our work provides the first empirical evidence of the energy-efficiency–creativity-support relationship at the *per-prompt* level. We identify the number of generated images per prompt as a critical mediating variable: decreasing this quantity significantly reduces energy consumption while preserving users’ perceived creativity support. Based on these findings, we propose a novel evaluation paradigm for sustainable AI-powered creative tools centered on prompt optimization. This paradigm offers both theoretical foundations and practical guidelines for green human-AI co-creation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Intelligent User Interfaces
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Creativity is a valuable human skill that has long been augmented through both analog and digital tools. Recent progress in generative AI, such as image generation, provides a disruptive technological solution to supporting human creativity further and helping humans generate solutions faster. While AI image generators can help to rapidly visualize ideas based on user prompts, the use of such AI systems has also been critiqued due to their considerable energy usage. In this paper, we report on a user study (N = 24) to understand whether energy consumption can be reduced without impeding on the tool's perceived creativity support. Our results highlight that, for example, a main effect of (image generation) condition on energy consumption, and index of creativity support per prompt but not per task, which seem mainly attributed to image quantity per prompt. We provide details of our analysis on the relation between energy usage, creativity support, and prompting behavior, including attitudes towards designing with AI and its environmental impact.

Problem

• Reducing energy consumption in AI image generation
• Balancing creativity support and energy efficiency
• Analyzing prompting behavior's impact on sustainability

Innovation

• Prompt-based image generation for creativity
• Reducing energy use in AI image generation
• Analyzing creativity support per prompt