Journal of Digital Landscape Architecture

Seite drucken

Comparative Analysis of Landscape Element Images Created by Text-to-Image Artificial Intelligence Tools in the Design Process

The rapid development of generative artificial intelligence (AI) technology is changing many fields. Accordingly, this study focused on ways to utilize basic generative text-to-image AI tools in the landscape design process with the aim to save time in the existing design study process. We compared three AI tools, Midjourney, Synthesys X, and Playground AI, using three prompts and determined that they have different advantages regarding the individual landscape elements. We identified which AI tool showed the highest score for each landscape element and the highest overall score. Synthesys X was found to perform well in paving and Midjourney in tree shape. In creating the desired space shape, Synthesys X and Playground AI showed strength. Thus, our study provides guidelines for the use of the various AI tools in the design study process.

Autor / Author: Kim, Sungmin; Lee, Yumi
Institution / Institution: Seoul National University, Seoul/Republic of Korea; Seoul National University, Seoul/Republic of Korea
Seitenzahl / Pages: 8
Sprache / Language: Englisch
Veröffentlichung / Publication: JoDLA – Journal of Digital Landscape Architecture, 9-2024
Tagung / Conference: Digital Landscape Architecture 2024 – New Trajectories in Computational Urban Landscapes and Ecology
Veranstaltungsort, -datum / Venue, Date: Vienna University of Technology, Austria 05-06-24 - 07-06-24
Schlüsselwörter (de):
Keywords (en): Generative AI image, prompt engineering, design tool, text-to-image
Paper review type: Full Paper Review
DOI: doi:10.14627/537752097
8042 -