Article: A simulation-based modelling framework for personalised design using an improved generative adversarial network Journal: International Journal of Simulation and Process Modelling (IJSPM) 2025 Vol.22 No.3/4 pp.160 - 170 Abstract: As a key component of the creative sector, art typeface design has progressively taken front stage given the growing demand for customised design. Manual design is common in traditional font design, which takes time and cannot rapidly adjust to individual needs. This paper presents StyleGANFont, a personalised art font design model based on improved generative adversarial network (GAN), which is capable of producing high-quality, diversified and personalised art fonts by means of multi-level style control, adaptive personalisation modelling and real-time user feedback to meet the demand for fast and tailored font design. To create typefaces, StyleGANFont has clear benefits according to the comparison and ablation experiments. At last, this work also addresses the direction of next research to support the continuous advancement of personalised art font generating technologies. Inderscience Publishers - linking academia, business and industry through research

Title: A simulation-based modelling framework for personalised design using an improved generative adversarial network

Authors: Mingyu Li

Addresses: Department of Public Basic Education, Henan Police College, Zhengzhou 450046, China

Abstract: As a key component of the creative sector, art typeface design has progressively taken front stage given the growing demand for customised design. Manual design is common in traditional font design, which takes time and cannot rapidly adjust to individual needs. This paper presents StyleGANFont, a personalised art font design model based on improved generative adversarial network (GAN), which is capable of producing high-quality, diversified and personalised art fonts by means of multi-level style control, adaptive personalisation modelling and real-time user feedback to meet the demand for fast and tailored font design. To create typefaces, StyleGANFont has clear benefits according to the comparison and ablation experiments. At last, this work also addresses the direction of next research to support the continuous advancement of personalised art font generating technologies.

Keywords: personalised art font generation; improved GAN; multi-level style control; user-preference modelling.

DOI: 10.1504/IJSPM.2025.150540

International Journal of Simulation and Process Modelling, 2025 Vol.22 No.3/4, pp.160 - 170

Received: 04 Jul 2025
Accepted: 15 Sep 2025
Published online: 16 Dec 2025 *

Title: A simulation-based modelling framework for personalised design using an improved generative adversarial network

Keep up-to-date