---
language: en
license: apache-2.0
datasets:
- cyberagent/crello
pipeline_tag: text-generation
library_name: transformers
tags:
- graphic design
- design completion
- multimodal
- markup document
base_model:
- bigcode/starcoderbase-7b
---

# Multimodal Markup Document Models (MarkupDM)

<div align="left">

[![arxiv paper](https://img.shields.io/badge/arxiv-paper-orange)](https://arxiv.org/abs/2409.19051)
<a href='https://cyberagentailab.github.io/MarkupDM/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>

</div>

![teaser](./teaser.png)

This repository provides the pre-trained MarkupDM model for graphic design completion. The model can automatically complete partially designed graphics by generating appropriate text/visual content, positioning, and styling, as demonstrated in our paper [Multimodal Markup Document Models for Graphic Design Completion](https://arxiv.org/abs/2409.19051).

## Usage

For detailed usage instructions, please refer to the [MarkupDM GitHub repository](https://github.com/CyberAgentAILab/MarkupDM).

## License

This repository is released under the Apache-2.0 license.

## Citation

```bibtex
@inproceedings{Kikuchi2025,
  title     = {Multimodal Markup Document Models for Graphic Design Completion},
  author    = {Kotaro Kikuchi and Ukyo Honda and Naoto Inoue and Mayu Otani and Edgar Simo-Serra and Kota Yamaguchi},
  booktitle = {ACM International Conference on Multimedia},
  year      = {2025},
  doi       = {10.1145/3746027.3755420}
}
```