DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation

ICLR 2026 Conference Submission5976 Authors

Keywords: Text-Line Generation, Online Handwriting, Latent Diffusion Transformer

TL;DR: We propose DiffInk, the the first latent diffusion Transformer framework for text to online handwriting generation (TOHG).

Abstract: Deep generative models have advanced text-to-online handwriting generation (TOHG), which aims to synthesize realistic pen trajectories conditioned on textual input and style references. However, most existing methods still primarily focus on character- or word-level generation, resulting in inefficiency and a lack of holistic structural modeling when applied to full text lines. To address these issues, we propose DiffInk, the first latent diffusion Transformer framework for full-line handwriting generation. We first introduce InkVAE, a novel sequential variational autoencoder enhanced with two complementary latent-space regularization losses: (1) an OCR-based loss enforcing glyph-level accuracy, and (2) a style-classification loss preserving writing style. This dual regularization yields a semantically structured latent space where character content and writer styles are effectively disentangled. We then introduce InkDiT, a novel latent diffusion Transformer that integrates target text and reference styles to generate coherent pen trajectories. Experimental results demonstrate that DiffInk outperforms existing state-of-the-art methods in both glyph accuracy and style fidelity, while significantly improving generation efficiency. Code will be made publicly available.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 5976