Browsing by Author "Gokmen, Sabri"

Now showing 1 - 4 of 4

Integrating Stable Diffusion via Remote Server APIs for Enhanced Parametric Design Workflows
(Sage Publications Ltd, 2026) Gokmen, Sabri; Alsan, Huseyin Fuat; Arsan, Taner; Ozen, Figen; Keskin, Ebru Ece
The current advancements of deep learning models offer potential applications for computational design through sets of generated images controlled by parametric inputs, yet they remain disconnected from geometry-driven parametric tools. For this reason, we study the implications of text and image-based generation methods to be used in traditional parametric design procedures. We implement this study by integrating Stable Diffusion and ControlNet to Rhino Grasshopper through a Python-based remote-API plug-in. This API allows a direct connection to the diffusion-based image generation methods without any middleware. Our main contribution is to enable architects and designers to interactively generate and investigate new design ideas in their native parametric design environment. We evaluate potential impact on parametric design education with 15 architecture students using a single GPU server running Stable Diffusion v1.5 across three exercises: Text-to-Image, Image-to-Image using Rhinoceros view captures, and Parametric-Model-to-Image with ControlNet. Quantitative results showed that the API-enabled image generation averaged 4-15 seconds per image, allowing seamless integration with parametric workflows for all 15 students in a classroom setting. Performance evaluations show that our approach offers significantly improved efficiency and responsiveness compared to existing diffusion-based tools, highlighting its suitability for seamless integration within parametric design environments. Qualitative feedback indicated improved design ideation, greater fluency in prompt engineering, and enhanced understanding of parametric logic through iterative visual experimentation. These findings demonstrate the potential of real-time AI integration to augment both conceptual design and parametric design education.
Prompt2Product: Integrating Stable Diffusion for Parametric Modeling and Manufacturing of Ceramic Products
(Education and Research in Computer Aided Architectural Design in Europe, 2025) Gokmen, Sabri; Alsan, H. Fuat; Gokmen, Pelin Alkan; Arsan, Taner
Citation - WoS: 4
Citation - Scopus: 4
A Recursive Algorithm for the Generative Study of Seljuk Muqarnas in Kayseri and Sivas
(Kim Williams Books, 2023) Gokmen, Sabri; Aykin, Yusuf; Basik, Altan; Alacam, Sema
Recent developments in archeological research extend diverse technological methods for the geometric deciphering and cultural understanding of various historical building components. One of the emerging methods in this field is the development of generative algorithms to develop computational models for the comparative study of variation among different structures belonging to a common era, style, or region. In this study, we present a novel approach for the computational analysis and parametric modeling of muqarnas found among Anatolian Seljuk architecture in Kayseri and Sivas built in the 13th century. Using four different octagonal muqarnas structures, we outline common generative rules showing recursive stacking of geometric layers, fractal patterns and hierarchical branching of the axis of symmetry. A recursive algorithm is developed that can offer a generative study of muqarnas structures using proportions based on the 'silver ratio.' The development of the algorithm is presented through rules and variations that can offer a novel perspective for the geometric understanding and categorization of muqarnas in the region.
Citation - WoS: 2
Citation - Scopus: 3
Stripped and Layered Fabrication of Minimal Surface Tectonics Using Parametric Algorithms
(de Gruyter Poland Sp Z O O, 2023) Gokmen, Sabri
This article describes a parametric design and fabrication workflow influenced by Frei Otto's form-finding experiments on soap films. The research investigates minimal surface geometry by combining physical and digital experiments in a computational framework. Operating on mesh topology, various parametric design tools and plug-ins in Rhinoceros/Grasshopper are presented to discuss the translation of minimal surfaces to flat strips suitable for planar fabrication using flexible materials. These tools are tested on a case study to show the automated design and manufacture of double-curved surfaces as double-layered strips running in perpendicular directions that can be affixed at point connections for structural stability. The development of the parametric workflow, material constraints, and stripped fabrication of layers are discussed.