2023, Vol. 8, No. 4. - go to content...

Permanent address of this page - https://kostumologiya.ru/en/12ivkl423.html

Метаданные этой статьи так же доступны на русском языке

Full article in PDF format (file size: Файл не найден)

For citation:

[Generation of patterns for textile products using the Recraft neural network] Journal of Clothing Science, 2023, Vol. 8, No. 4. Available at: https://kostumologiya.ru/PDF/.pdf (in Russian).

Generation of patterns for textile products using the Recraft neural network

Ryzhkova Anastasia Dmitrievna
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: legkaya.design@yandex.ru
ORCID: https://orcid.org/0009-0003-3386-6820

Kazakova Natalia Yurʹevna
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: Kazakova-nu@rguk.ru
ORCID: https://orcid.org/0000-0003-0006-1412

Abstract. Neural networks represent one of the most advanced and dynamically developing areas of artificial intelligence. One aspect of the use of neural networks in textile design is their ability to generate patterns. Tasks that previously required the creative intervention of artists can now be partially delegated to neural networks trained on vast amounts of data and capable of creating unique images in a matter of seconds. In addition, neural networks are capable of synthesizing new ideas, combining different styles and providing unique solutions, making them a valuable tool in the creative process of creating textile patterns.

The article tested the effectiveness of the Recraft neural network in the context of creating seamless patterns for textile products. The main goal of the study was to reduce the time and labor costs of designers in creating seamless patterns.

To achieve this goal, methods for applying patterns to textile products were analyzed, and technical requirements for images applied to fabric in one way or another were described. Next, the features of the «Recraft» neural network were described and tested using various text queries. As a result of testing, we proposed optimal visual styles for creating images that can serve as the basis for future unique patterns. The process of working with the Recraft neural network was described in detail, and an optimal algorithm for interacting with this technology was proposed.

This research and practical recommendations are aimed at improving the efficiency of the design process, reducing time and labor costs, which in turn contributes to the development of the textile design industry through the introduction of innovative technologies.

Keywords: neural network; generative adversarial neural network; neural network in design; artificial intelligence; recraft; seamless patterns; pattern creation; design; innovative technologies; algorithm

Download article in PDF format