# Few-Shot Font Generation by Learning Fine-Grained Local Styles

arXiv: https://arxiv.org/abs/2205.09965 · HTML: https://mlsanity.com/paper/2205.09965/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [cGANs with Projection Discriminator](https://mlsanity.com/paper/1802.05637/) (2018)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [Multi-Content GAN for Few-Shot Font Style Transfer](https://mlsanity.com/paper/1712.00516/) (2017)
- [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021)
- [Separating Style and Content for Generalized Style Transfer](https://mlsanity.com/paper/1711.06454/) (2017)
- [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https://mlsanity.com/paper/1809.01361/) (2018)
- [Rethinking the Truly Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2006.06500/) (2020)
- [Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning](https://mlsanity.com/paper/1910.04987/) (2019)
- [Few-shot Font Generation with Localized Style Representations and Factorization](https://mlsanity.com/paper/2009.11042/) (2020)
- [Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts](https://mlsanity.com/paper/2104.00887/) (2021)
- [Few-shot Compositional Font Generation with Dual Memory](https://mlsanity.com/paper/2005.10510/) (2020)
- [Handwriting Transformers](https://mlsanity.com/paper/2104.03964/) (2021)
- [Multi-mapping Image-to-Image Translation via Learning Disentanglement](https://mlsanity.com/paper/1909.07877/) (2019)
- [Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis](https://mlsanity.com/paper/1706.08789/) (2017)
- [CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator](https://mlsanity.com/paper/2005.12500/) (2020)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [Pyramid Embedded Generative Adversarial Network for Automated Font Generation](https://mlsanity.com/paper/1811.08106/) (2018)
- [Handwritten Chinese Font Generation with Collaborative Stroke Refinement](https://mlsanity.com/paper/1904.13268/) (2019)

## Built on by (most cited first, 30 of 34)

- [FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning](https://mlsanity.com/paper/2312.12142/) (2023)
- [RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model](https://mlsanity.com/paper/2309.00810/) (2023)
- [Diff-Font: Diffusion Model for Robust One-Shot Font Generation](https://mlsanity.com/paper/2212.05895/) (2022)
- [FonTS: Text Rendering with Typography and Style Controls](https://mlsanity.com/paper/2412.00136/) (2024)
- [DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality](https://mlsanity.com/paper/2303.14585/) (2023)
- [CF-Font: Content Fusion for Few-shot Font Generation](https://mlsanity.com/paper/2303.14017/) (2023)
- [EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering](https://mlsanity.com/paper/2505.24417/) (2025)
- [VecFusion: Vector Font Generation with Diffusion](https://mlsanity.com/paper/2312.10540/) (2023)
- [TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster Design](https://mlsanity.com/paper/2308.04733/) (2023)
- [WordCon: Word-level Typography Control in Scene Text Rendering](https://mlsanity.com/paper/2506.21276/) (2025)
- [WeditGAN: Few-Shot Image Generation via Latent Space Relocation](https://mlsanity.com/paper/2305.06671/) (2023)
- [Few shot font generation via transferring similarity guided global style and quantization local style](https://mlsanity.com/paper/2309.00827/) (2023)
- [FontTransformer: Few-shot High-resolution Chinese Glyph Image Synthesis via Stacked Transformers](https://mlsanity.com/paper/2210.06301/) (2022)
- [VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization](https://mlsanity.com/paper/2308.14018/) (2023)
- [Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models](https://mlsanity.com/paper/2409.00786/) (2024)
- [HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolution](https://mlsanity.com/paper/2410.06488/) (2024)
- [Few-shot Font Generation by Learning Style Difference and Similarity](https://mlsanity.com/paper/2301.10008/) (2023)
- [DeepCalliFont: Few-shot Chinese Calligraphy Font Synthesis by Integrating Dual-modality Generative Models](https://mlsanity.com/paper/2312.10314/) (2023)
- [Diff-Oracle: Deciphering Oracle Bone Scripts with Controllable Diffusion Model](https://mlsanity.com/paper/2312.13631/) (2023)
- [MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation](https://mlsanity.com/paper/2503.02799/) (2025)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [FontAdapter: Instant Font Adaptation in Visual Text Generation](https://mlsanity.com/paper/2506.05843/) (2025)
- [Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation](https://mlsanity.com/paper/2601.01593/) (2026)
- [Local Style Awareness of Font Images](https://mlsanity.com/paper/2310.06337/) (2023)
- [Total Disentanglement of Font Images into Style and Character Class Features](https://mlsanity.com/paper/2403.12784/) (2024)
- [Text Image Generation for Low-Resource Languages with Dual Translation Learning](https://mlsanity.com/paper/2409.17747/) (2024)
- [One-Shot Multilingual Font Generation Via ViT](https://mlsanity.com/paper/2412.11342/) (2024)
- [AnyArtisticGlyph: Multilingual Controllable Artistic Glyph Generation](https://mlsanity.com/paper/2504.04743/) (2025)
- [Few-Part-Shot Font Generation](https://mlsanity.com/paper/2509.10006/) (2025)
- [DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation](https://mlsanity.com/paper/2511.22064/) (2025)

## Abstract (arXiv)

Few-shot font generation (FFG), which aims to generate a new font with a few examples, is gaining increasing attention due to the significant reduction in labor cost. A typical FFG pipeline considers characters in a standard font library as content glyphs and transfers them to a new target font by extracting style information from the reference glyphs. Most existing solutions explicitly disentangle content and style of reference glyphs globally or component-wisely. However, the style of glyphs mainly lies in the local details, i.e. the styles of radicals, components, and strokes together depict the style of a glyph. Therefore, even a single character can contain different styles distributed over spatial locations. In this paper, we propose a new font generation approach by learning 1) the fine-grained local styles from references, and 2) the spatial correspondence between the content and reference glyphs. Therefore, each spatial location in the content glyph can be assigned with the right fine-grained style. To this end, we adopt cross-attention over the representation of the content glyphs as the queries and the representations of the reference glyphs as the keys and values. Instead of explicitly disentangling global or component-wise modeling, the cross-attention mechanism can attend to the right local styles in the reference glyphs and aggregate the reference styles into a fine-grained style representation for the given content glyphs. The experiments show that the proposed method outperforms the state-of-the-art methods in FFG. In particular, the user studies also demonstrate the style consistency of our approach significantly outperforms previous methods.