This study evaluates the performance of three widely-used text-to-image AI models—DALL-E, MidJourney, and Stable Diffusion—in generating interior design visuals. Five standardized prompts, covering essential design elements such as architectural features, style, furniture, lighting, textiles, accessories, and layout, were provided to each AI model. The resulting visuals were then assessed by 15 experienced professionals and academics with over 10 years of expertise in interior design. Using a detailed rating system, the study found that MidJourney consistently outperformed the others, excelling in categories like design style, textiles, and lighting. DALL-E proved effective in generating architectural features but struggled with finer details, particularly in textiles and lighting. Stable Diffusion lagged behind in overall performance, especially in categories like layout and furniture. The study highlights the importance of prompt specificity in shaping AI-generated visuals and suggests areas for future improvement in AI models, particularly in complex design tasks.
31 August 2026 in Interaction Design and Architecture(s)
Spatial representation is a cornerstone of the creative interior design industry, yet traditional static mediums often result in material waste and significant miscommunication between designers and occupants. This paper proposes an empirical evaluation framework that utilizes a user-centered mobile application prototype as a proof-of-concept to foster methodological dialogue through participatory design. Grounded in the emerging framework of Human-Building Interaction (HBI), the study evaluates how interactive digital tools can reduce cognitive load and enhance decision-making accuracy. Following an expert heuristic evaluation (N=3) that demonstrated substantial agreement (K=0.578), usability testing (N=10) based on ISO 9241-11 standards showed high effectiveness (90.2%) and efficiency (89.85%). A comparative pilot study indicated that mobile interactivity can enhance spatial comprehension and user agency within exploratory consultation settings compared to traditional static methods. By providing rigorous metrics for engagement, this research presents a scalable prototype that highlights both the potentials and accessibility barriers of digital-first workflows as digital catalysts in design practice.
31 December 2021 in Ordu Üniversitesi Bilim ve Teknoloji Dergisi
Due to the COVID-19 outbreak, which was declared as a pandemic in 2020 by the World Health Organization, many educational institutions around the world started distance education. However, since distance education is an unusual field for the stakeholders of education, this sudden change created chaos both for institutions in terms of providing the necessary infrastructure and for educators in terms of redesigning instruction techniques and tools. This article, it is aimed to discuss a distance education course design proposal for a basic design course, which is taught generally in the first two semesters within a studio environment at the department of architecture, through a) student opinions that were obtained through an online questionnaire that was conducted at the end of the semester, evaluations made by the authors about b) the process outputs and achievements and c) the tools. The results show that, the distance education course design proposal for the basic design course of the department of architecture, which requires collaboration and interaction between students and instructors, evaluated as being efficient both in terms of the tools and methods used and in terms of creating an online collaborative workspace.