@article{article_1588484, title={Text to Image in Landscape Architecture: Artificial Intelligence Approaches}, journal={Kent Akademisi}, volume={18}, pages={1824–1844}, year={2025}, DOI={10.35674/kent.1588484}, author={Kahvecioğlu, Ceren and Ast, Mahmut Can and Sağlık, Alper}, keywords={Yapay Zeka, Metinden Görsele, Peyzaj Mimarlığı, Peyzaj Tasarımı, Konsept}, abstract={Generating ideas for designing spaces with creative and diverse concepts in landscape architecture design is a time-consuming process. With technological advancements, effective use of time has become increasingly significant, and applications that produce creative, realistic, and elaborate visuals from text in the field of artificial intelligence (AI) have attracted attention. However, the use of AI applications in landscape architecture raises many questions regarding the rapid and accurate development of design ideas through the Text-to-Image (T2I) method: how satisfying are AI-generated visuals in terms of professional accuracy and aesthetics? Can AI accurately perceive professional terms? What is the general relationship between AI and landscape architecture? Apart from coming up with an answer to these questions, this study aims to investigate the potential of text-to-image (T2I) models in generating design concepts for landscape architecture. Fifty professional terms were selected and used to create 70-word prompts across six distinct design concepts. Four popular T2I models (Dall-E, MidJourney, LookX, and mnml) were employed to generate visuals based on these prompts. The images generated were evaluated based on their adherence to professional standards, aesthetic appeal, creativity, and technical accuracy. Results indicated that while AI models could effectively interpret a wide range of professional terms, including abstract and highly technical concepts, there were limitations in capturing the nuanced details of landscape design. This study highlights the potential of AI to assist landscape architects in the early stages of the design process, but also underscores the need for human expertise to refine and optimize AI-generated designs. Future research should explore ways to improve the accuracy and specificity of AI-generated landscape designs, as well as investigate the potential of integrating AI with other design tools and techniques.}, number={4}, publisher={Ahmet FİDAN}