# TrInk: Ink Generation with Transformer Network

arXiv: https://arxiv.org/abs/2508.21098 · HTML: https://mlsanity.com/paper/2508.21098/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images](https://mlsanity.com/paper/2003.02567/) (2020)
- [DeepWriting: Making Digital Ink Editable via Deep Generative Modeling](https://mlsanity.com/paper/1801.08379/) (2018)
- [Adversarial Generation of Handwritten Text Images Conditioned on Sequences](https://mlsanity.com/paper/1903.00277/) (2019)
- [Generating Handwritten Chinese Characters using CycleGAN](https://mlsanity.com/paper/1801.08624/) (2018)
- [Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models](https://mlsanity.com/paper/2110.02891/) (2021)

## Built on by (most cited first, 2 of 2)

- [DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation](https://mlsanity.com/paper/2509.23624/) (2025)
- [BoundInk: Boundary-Aware Online Handwriting Generation](https://mlsanity.com/paper/2604.02103/) (2026)

## Abstract (arXiv)

In this paper, we propose TrInk, a Transformer-based model for ink generation, which effectively captures global dependencies. To better facilitate the alignment between the input text and generated stroke points, we introduce scaled positional embeddings and a Gaussian memory mask in the cross-attention module. Additionally, we design both subjective and objective evaluation pipelines to comprehensively assess the legibility and style consistency of the generated handwriting. Experiments demonstrate that our Transformer-based model achieves a 35.56% reduction in character error rate (CER) and an 29.66% reduction in word error rate (WER) on the IAM-OnDB dataset compared to previous methods. We provide an demo page with handwriting samples from TrInk and baseline models at: https://akahello-a11y.github.io/trink-demo/