Prompting for products: Investigating design space exploration strategies for text-to-image generative models

TL;DR

This study addresses how text-to-image diffusion tools can be used for design-space exploration in product design, focusing on aligning prompts with outputs to achieve feasible, novel, and aesthetically pleasing designs. It analyzes global versus local editing modes on Leonardo.AI and examines time spent, prompt length, mono versus multi-criteria prompts, and goal orientation as key factors shaping design outcomes. The findings show that prompt strategy and editing mode have a stronger relationship with design quality than time or prompt length, with early-stage multi-criteria prompts (feasibility and novelty) aiding exploration and later-stage mono-criteria, aesthetics-focused prompts enhancing refinement and feasibility. The work provides practical guidelines for designers using GenAI in product design and highlights limitations of current tools, calling for broader tool comparisons and larger, more diverse studies to generalize findings across platforms and design domains.

Abstract

Text-to-image models are enabling efficient design space exploration, rapidly generating images from text prompts. However, many generative AI tools are imperfect for product design applications as they are not built for the goals and requirements of product design. The unclear link between text input and image output further complicates their application. This work empirically investigates design space exploration strategies that can successfully yield product images that are feasible, novel, and aesthetic, which are three common goals in product design. Specifically, user actions within the global and local editing modes, including their time spent, prompt length, mono vs. multi-criteria prompts, and goal orientation of prompts, are analyzed. Key findings reveal the pivotal role of mono vs. multi-criteria and goal orientation of prompts in achieving specific design goals over time and prompt length. The study recommends prioritizing the use of multi-criteria prompts for feasibility and novelty during global editing, while favoring mono-criteria prompts for aesthetics during local editing. Overall, this paper underscores the nuanced relationship between the AI-driven text-to-image models and their effectiveness in product design, urging designers to carefully structure prompts during different editing modes to better meet the unique demands of product design.

Figures (7)

• Figure 1: Global and Local Editing Modes in Leonardo.AI and Their Example Input and Output. The global editing mode is primarily for generating entire images by entering text prompts, while the local editing mode is for more detailed refinement of selected images using features like prompting, masking, and erasing.
• Figure 2: Example Problem in the Crowd-Sourced Image Evaluations
• Figure 3: The Distribution of Time Spent in Global and Local Editing Modes. On average, the participants spent about 38.5% of their time in the global editing mode, and the other 61.5% in the local editing mode.
• Figure 4: Average Prompt Length. The participants use significantly longer prompts in the global editing mode compared to the local editing mode.
• Figure 5: Percentage of Mono-Criteria (Feasibility, Novelty, and Aesthetics-Oriented), Multi-Criteria, and No-Criteria Prompts. The participants use much more multi-criteria prompts in the global editing mode than in the local editing mode. Most of the mono-criteria prompts in the global editing mode are feasibility or novelty-oriented, while those in the local editing mode are mostly feasibility-oriented with some being novelty and aesthetics-oriented.