# GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1905.12502 · HTML: https://mlsanity.com/paper/1905.12502/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 16 of 16)

- [DualVector: Unsupervised Vector Font Synthesis with Dual-Part Representation](https://mlsanity.com/paper/2305.10462/) (2023)
- [Impressions2Font: Generating Fonts by Specifying Impressions](https://mlsanity.com/paper/2103.10036/) (2021)
- [Learning Implicit Glyph Shape Representation](https://mlsanity.com/paper/2106.08573/) (2021)
- [Font Generation with Missing Impression Labels](https://mlsanity.com/paper/2203.10348/) (2022)
- [Ambigram Generation by A Diffusion Model](https://mlsanity.com/paper/2306.12049/) (2023)
- [GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models](https://mlsanity.com/paper/2408.07259/) (2024)
- [Towards Book Cover Design via Layout Graphs](https://mlsanity.com/paper/2105.11088/) (2021)
- [Calligrapher: Freestyle Text Image Customization](https://mlsanity.com/paper/2506.24123/) (2025)
- [VecGlypher: Unified Vector Glyph Generation with Language Models](https://mlsanity.com/paper/2602.21461/) (2026)
- [Conjugate Gradient Method for Generative Adversarial Networks](https://mlsanity.com/paper/2203.14495/) (2022)
- [TaCo: Textual Attribute Recognition via Contrastive Learning](https://mlsanity.com/paper/2208.10180/) (2022)
- [Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks](https://mlsanity.com/paper/2109.12628/) (2021)
- [Font Representation Learning via Paired-glyph Matching](https://mlsanity.com/paper/2211.10967/) (2022)
- [GAS-NeXt: Few-Shot Cross-Lingual Font Generator](https://mlsanity.com/paper/2212.02886/) (2022)
- [Total Disentanglement of Font Images into Style and Character Class Features](https://mlsanity.com/paper/2403.12784/) (2024)
- [SplatFont3D: Structure-Aware Text-to-3D Artistic Font Generation with Part-Level Style Control](https://mlsanity.com/paper/2512.00413/) (2025)

## Abstract (arXiv)

In this paper, we propose GlyphGAN: style-consistent font generation based on generative adversarial networks (GANs). GANs are a framework for learning a generative model using a system of two neural networks competing with each other. One network generates synthetic images from random input vectors, and the other discriminates between synthetic and real images. The motivation of this study is to create new fonts using the GAN framework while maintaining style consistency over all characters. In GlyphGAN, the input vector for the generator network consists of two vectors: character class vector and style vector. The former is a one-hot vector and is associated with the character class of each sample image during training. The latter is a uniform random vector without supervised information. In this way, GlyphGAN can generate an infinite variety of fonts with the character and style independently controlled. Experimental results showed that fonts generated by GlyphGAN have style consistency and diversity different from the training images without losing their legibility.