2024, Vol. 9, No. 2. - go to content...

Permanent address of this page - https://kostumologiya.ru/en/01tlkl224.html

Метаданные этой статьи так же доступны на русском языке

Full article in PDF format (file size: 1.2 MB)

For citation:

Mochalina D.R., Sineva O.V. Neural networks in the development of light industry collections. Journal of Clothing Science. 2024; 9(2). Available at: https://kostumologiya.ru/PDF/01TLKL224.pdf (in Russian).

Neural networks in the development of light industry collections

Mochalina Darya Ruslanovna
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: daryartm@bk.ru
RSCI: https://elibrary.ru/author_profile.asp?id=1204457

Sineva Olga Vladimirovna
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: olga-mgudt@mail.ru
RSCI: https://elibrary.ru/author_profile.asp?id=435847

Abstract. Traditionally, designers rely on their experience and imagination to create collections. However, with the advancement of technology, new horizons have opened up, using innovative tools to expand and improve the creative process. Artificial intelligence (AI) has made significant strides in various industries, and the fashion industry is no exception. The merging of artificial intelligence with the world of fashion is the dawn of a new era where algorithms collaborate with designers to breathe life into materials and silhouettes. One of these tools is neural networks — advanced platforms that use the power of artificial intelligence. In the fashion industry, neural networks are used to predict trends, analyze consumer preferences, and even create new design concepts. Neural networks use deep analysis algorithms trained on large sets of design data, allowing them to create realistic and varied designs based on input parameters provided by the user.

The article analyzes neural networks in the modern fashion industry, testing the effectiveness of the «Midjourney» neural network for textile and footwear products. The main goal of the study: reducing the time and labor costs of designers at the collection development stage. To achieve this goal, methods for developing images based on text queries, creating images using the /blend and /describe commands, developing seamless prints in the «Midjourney» neural network, comparing the programs «Midjourney» and «Adobe Illustrator» in creating sketches with prints were analyzed. The result of the research was the development of an algorithm for creating a sketch using a seamless print developed in the Midjourney neural network and an example of a sketch design based on a seamless print developed in the Midjourney neural network.

Keywords: digital technologies; design; 3D modeling; light industry; computer-aided design; sustainable development; graphic editors; neural networks

Download article in PDF format