---
title: Eruku - Styled Text Generation
emoji: 🖋️
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 4.44.1
app_file: app.py
pinned: true
license: apache-2.0
models:
  - blowing-up-groundhogs/eruku
tags:
  - handwriting-generation
  - styled-text
  - text-to-image
  - autoregressive
  - WACV2026
short_description: Generate handwritten text in any style
---

# 🖋️ Eruku - Autoregressive Styled Text Image Generation

**Autoregressive Styled Text Image Generation, but Make it Reliable**

WACV 2026 | [Paper](https://arxiv.org/abs/2510.23240) | [Project Page](https://eruku.carminezacc.com) | [Model](https://huggingface.co/blowing-up-groundhogs/eruku)

## Key Features

- **🎯 Optional Style Text**: Unlike previous methods, Eruku works without requiring transcription of the style image
- **🛑 Explicit Stopping**: Dedicated end-of-generation token prevents repetition artifacts
- **✨ CFG-Guided**: Classifier-Free Guidance for better text adherence

## How to Use

1. Upload a handwriting sample as the style image
2. Optionally enter the text from the style image (helps but not required!)
3. Enter the text you want to generate
4. Click Generate!

## Citation

```bibtex
@inproceedings{zaccagnino2026eruku,
    title={{Autoregressive Styled Text Image Generation, but Make it Reliable}},
    author={Zaccagnino, Carmine and Quattrini, Fabio and Pippi, Vittorio 
            and Cascianelli, Silvia and Tonioni, Alessio and Cucchiara, Rita},
    booktitle={Proceedings of the IEEE/CVF Winter Conference on 
               Applications of Computer Vision (WACV)},
    year={2026}
}
```

## Authors

Carmine Zaccagnino, Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Alessio Tonioni, Rita Cucchiara

University of Modena and Reggio Emilia | Google