# Structure-Level Disentangled Diffusion for Few-Shot Chinese Font Generation

arXiv: https://arxiv.org/abs/2602.18874 · HTML: https://mlsanity.com/paper/2602.18874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 21 Feb 2026.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer](https://mlsanity.com/paper/2312.09008/) (2023)
- [On the Effectiveness of Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2211.15583/) (2022)
- [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://mlsanity.com/paper/2211.01335/) (2022)
- [Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning](https://mlsanity.com/paper/1910.04987/) (2019)
- [FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning](https://mlsanity.com/paper/2312.12142/) (2023)
- [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)
- [Diff-Font: Diffusion Model for Robust One-Shot Font Generation](https://mlsanity.com/paper/2212.05895/) (2022)
- [Few-Shot Font Generation by Learning Fine-Grained Local Styles](https://mlsanity.com/paper/2205.09965/) (2022)
- [Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator](https://mlsanity.com/paper/2205.00146/) (2022)
- [Learning to Write Stylized Chinese Characters by Reading a Handful of Examples](https://mlsanity.com/paper/1712.06424/) (2017)
- [A Unified Framework for Generalizable Style Transfer: Style and Content Separation](https://mlsanity.com/paper/1806.05173/) (2018)
- [HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolution](https://mlsanity.com/paper/2410.06488/) (2024)

## Abstract (arXiv)

Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images. Achieving accurate content rendering and faithful style transfer requires effective disentanglement between content and style. However, existing approaches achieve only feature-level disentanglement, allowing the generator to re-entangle these features, leading to content distortion and degraded style fidelity. We propose the Structure-Level Disentangled Diffusion Model (SLD-Font), which receives content and style information from two separate channels. SimSun-style images are used as content templates and concatenated with noisy latent features as the input. Style features extracted by a CLIP model from target-style images are integrated via cross-attention. Additionally, we train a Background Noise Removal module in the pixel space to remove background noise in complex stroke regions. Based on theoretical validation of disentanglement effectiveness, we introduce a parameter-efficient fine-tuning strategy that updates only the style-related modules. This allows the model to better adapt to new styles while avoiding overfitting to the reference images' content. We further introduce the Grey and OCR metrics to evaluate the content quality of generated characters. Experimental results show that SLD-Font achieves significantly higher style fidelity while maintaining comparable content accuracy to existing state-of-the-art methods.