koz"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"Bulletin of Manash Kozybayev North Kazakhstan University2958-003X2958-0048М. Қозыбаев атындағы СҚУ10.54596/2958-0048-2026-1-240-250koz-2539Research ArticleТЕХНИЧЕСКИЕ НАУКИTECHNICAL SCIENCESСРАВНИТЕЛЬНЫЙ АНАЛИЗ МУЛЬТИГЕНЕРАТИВНЫХ НЕЙРОСЕТЕВЫХ МОДЕЛЕЙ ПРИ РЕШЕНИИ ПРИКЛАДНЫХ ЗАДАЧ ДИЗАЙНАCOMPARATIVE ANALYSIS OF MULTIGENERATIVE NEURAL NETWORK MODELS IN SOLVING APPLIED DESIGN PROBLEMShttps://orcid.org/0000-0002-6211-5634ШапореваА. В.ShaporevaA. V.

Петропавловск

Associate Professor of the Department of Building and design, PhD

Petropavlovsk

annvolkova@mail.ruhttps://orcid.org/0000-0002-3077-3499КазанбаеваА. С.KazanbayevaA. S.

Петропавловск

Associate Professor of the Department of Building and design, PhD

Petropavlovsk

akazanbaeva83@mail.ruhttps://orcid.org/0009-0009-3108-5338ШашкинаИ. С.ShashkinaI. S.

Петропавловск

Senior lecturer of the Department of Building and design, PhD

Petropavlovsk

irashashkina@mail.ruhttps://orcid.org/0009-0006-1406-2837РаковецН. С.RakovetsN. S.

Петропавловск

Senior lecturer of the Department of Building and design, PhD

Petropavlovsk

neli.69@mail.ruhttps://orcid.org/0009-0005-4761-5824ПоповаЮ. А.PopovaYu. A.

Петропавловск

Senior lecturer of the Department of Building and design, PhD

Petropavlovsk

y_popova_29@mail.ruhttps://orcid.org/0009-0003-1536-4587МицихД. Т.MitsihD. T.

Петропавловск

Senior lecturer of the Department of Building and design, PhD

Petropavlovsk

dtzaripova@ku.edu.kzНАО «Северо-Казахстанский университет имени Манаша Козыбаева»КазахстанManash Kozybayev North Kazakhstan University NPLCKazakhstan20260804202601 (69)240250Copyright © Шапорева А.В., Казанбаева А.С., Шашкина И.С., Раковец Н.С., Попова Ю.А., Мицих Д.Т., 20262026Шапорева А.В., Казанбаева А.С., Шашкина И.С., Раковец Н.С., Попова Ю.А., Мицих Д.Т.Shaporeva A.V., Kazanbayeva A.S., Shashkina I.S., Rakovets N.S., Popova Y.A., Mitsih D.T.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.ku.edu.kz/jour/article/view/2539

В статье рассматриваются возможности применения мультигенеративных нейросетевых моделей для решения прикладных задач в дизайне. Целью исследования являлась сравнительная оценка результатов генерации дизайн-проектов, выполненных нейросетями ChatGPT, Gemini и Copilot, на основе заданных текстовых промтов и исходных визуальных данных. В рамках эксперимента были сформированы два типа задач: создание новой малой архитектурной формы и доработка существующего проекта дизайна компьютерной аудитории. Оценка результатов осуществлялась экспертной группой дизайнеров по системе критериев, включающей художественные, функциональные, эргономические и экономические параметры. Полученные данные показали, что мультигенеративные нейросети способны генерировать конкурентоспособные концептуальные решения, различающиеся по степени технологической сложности, дизайнерской выразительности и реализуемости. Наиболее сбалансированные результаты продемонстрировали решения, ориентированные на сочетание визуальной выразительности и практической применимости. Сделан вывод о перспективности использования мультигенеративных подходов как инструмента поддержки проектной деятельности в дизайне.

The article discusses the possibilities of using multigenerative neural network models to solve applied problems in design. The aim of the study was to compare the results of design project generation performed by ChatGPT, Gemini, and Copilot neural networks based on specified text scripts and initial visual data. As part of the experiment, two types of tasks were formed: the creation of a new small architectural form and the refinement of an existing design project for a computer audience. The evaluation of the results was carried out by an expert group of designers according to a system of criteria, including artistic, functional, ergonomic and economic parameters. The data obtained showed that multigenerative neural networks are capable of generating competitive conceptual solutions that vary in the degree of technological complexity, design expressiveness, and feasibility. The most balanced results were demonstrated by solutions focused on a combination of visual expressiveness and practical applicability. The conclusion is made about the prospects of using multigenerative approaches as a tool to support project activities in design.

генеративный дизайнискусственный интеллектAI - проектированиеAI - дизайноценка AI - проектовgenerative designartificial intelligenceAI designAI designevaluation of AI projectsReferencesChoo S. Generative artificial intelligence and building design: early photorealistic render visualization of facades using local identity-trained models // Journal of Computational Design and Engineering. - 2024. - URL: https://doi.org/10.1093/icde/qwae017 (data obrashcheniya: 15.02.2026).Choo S. Generative artificial intelligence and building design: early photorealistic render visualization of facades using local identity-trained models // Journal of Computational Design and Engineering. - 2024. - URL: https://doi.org/10.1093/icde/qwae017 (data obrashcheniya: 15.02.2026).Yuan P.F. Toward a generative Al-augmented design era // Architectural Intelligence. - 2023. - URL: https://doi.org/10.1007/s44223-023-00038-9 (data obrashcheniya: 10.02.2026).Yuan P.F. Toward a generative Al-augmented design era // Architectural Intelligence. - 2023. - URL: https://doi.org/10.1007/s44223-023-00038-9 (data obrashcheniya: 10.02.2026).Odiah A., Gosling S. Laying the foundations for using generative AI images in architectural research // Architectural Intelligence. - 2024. - URL: https://doi.org/10.1007/s44223-024-00076-x (data obrashcheniya: 01.02.2026).Odiah A., Gosling S. Laying the foundations for using generative AI images in architectural research // Architectural Intelligence. - 2024. - URL: https://doi.org/10.1007/s44223-024-00076-x (data obrashcheniya: 01.02.2026).Wang X., He Z., Peng X. Artificial-Intelligence-Generated Content with Diffusion Models: A Literature Review // Mathematics. - 2024. - URL: https://doi.org/10.3390/math12070977 (data obrashcheniya: 14.02.2026) .Wang X., He Z., Peng X. Artificial-Intelligence-Generated Content with Diffusion Models: A Literature Review // Mathematics. - 2024. - URL: https://doi.org/10.3390/math12070977 (data obrashcheniya: 14.02.2026) .Cao Y., Aziz A.A., Arshard W.N.R. Stable diffusion in architectural design: Closing doors or opening new horizons? // International Journal of Architectural Computing. - 2024. - URL: https://doi.org/10.1177/14780771241270257 (data obrashcheniya: 11.02.2026).Cao Y., Aziz A.A., Arshard W.N.R. Stable diffusion in architectural design: Closing doors or opening new horizons? // International Journal of Architectural Computing. - 2024. - URL: https://doi.org/10.1177/14780771241270257 (data obrashcheniya: 11.02.2026).Li C., Zhang T., Du X., et al. Generative AI Models for Different Steps in Architectural Design: A Literature Review - 2024. - URL: https://doi.org/10.48550/arXiv.2404.01335 (data obrashcheniya: 11.02.2026) .Li C., Zhang T., Du X., et al. Generative AI Models for Different Steps in Architectural Design: A Literature Review - 2024. - URL: https://doi.org/10.48550/arXiv.2404.01335 (data obrashcheniya: 11.02.2026) .He Z., Wang Y.-H., Zhang J. Generative AIBIM: An automatic and intelligent structural design pipeline integrating BIM and generative AI - 2023. - URL: https://doi.org/10.1016/i.inffus.2024.102654 (data obrashcheniya: 19.02.2026).He Z., Wang Y.-H., Zhang J. Generative AIBIM: An automatic and intelligent structural design pipeline integrating BIM and generative AI - 2023. - URL: https://doi.org/10.1016/i.inffus.2024.102654 (data obrashcheniya: 19.02.2026).Kapsalis T. UrbanGenAI: Reconstructing Urban Landscapes using Panoptic Segmentation and Diffusion Models // arXiv. - 2024. - URL: https://arxiv.org/abs/2401.14379 (data obrashcheniya: 12.02.2026).Kapsalis T. UrbanGenAI: Reconstructing Urban Landscapes using Panoptic Segmentation and Diffusion Models // arXiv. - 2024. - URL: https://arxiv.org/abs/2401.14379 (data obrashcheniya: 12.02.2026).Li P., Li B. Generating Daylight-driven Architectural Design via Diffusion Models // arXiv. - 2024. - URL: https://doi.org/10.48550/arXiv.2404.13353 (data obrashcheniya: 15.02.2026).Li P., Li B. Generating Daylight-driven Architectural Design via Diffusion Models // arXiv. - 2024. - URL: https://doi.org/10.48550/arXiv.2404.13353 (data obrashcheniya: 15.02.2026).Blinova M., Molodcha M. Use of Artificial Intelligence in Educational Design for Architecture Students // Municipal Economy of Cities. - 2024. - URL: https://doi.org/10.33042/2522-1809-2024-3-184-53-58 (data obrashcheniya: 10.02.2026).Blinova M., Molodcha M. Use of Artificial Intelligence in Educational Design for Architecture Students // Municipal Economy of Cities. - 2024. - URL: https://doi.org/10.33042/2522-1809-2024-3-184-53-58 (data obrashcheniya: 10.02.2026).Generative AI models for different steps in architectural design: A literature review // Frontiers of Architectural Research. - 2024. - URL: https://doi.org/10.1016/i.foar.2024.10.001 (data obrashcheniya: 10.02.2026)Generative AI models for different steps in architectural design: A literature review // Frontiers of Architectural Research. - 2024. - URL: https://doi.org/10.1016/i.foar.2024.10.001 (data obrashcheniya: 10.02.2026)

The authors declare that there are no conflicts of interest present.