---
license: mit
tags:
- image-segmentation
- background-removal
- anime
pretty_name: ToonOut
datasets:
- joelseytre/toonout
base_model:
- ZhengPeng7/BiRefNet
pipeline_tag: image-segmentation
---

# ToonOut Model Weights

Please check out:

 - **our repository:** https://github.com/MatteoKartoon/BiRefNet
 - **our paper:** [*ToonOut: Fine-tuned Background Removal for Anime Characters*](https://arxiv.org/abs/2509.06839)
 - [**the dataset we collected to fine-tune this model**](https://huggingface.co/datasets/joelseytre/toonout/)

![Model Comparison](models_comparison.png)

## Model Summary

**ToonOut** is a fine-tuned variant of **BiRefNet** specialized for **background removal in anime-style images**.  
BiRefNet performs strongly on realistic imagery but struggles with stylized content (e.g., hair wisps, line art, transparency).  
Fine-tuned on the [ToonOut Dataset](https://huggingface.co/datasets/joelseytre/ToonOut) (1,228 images), ToonOut delivers a notable boost for anime segmentation:

- **Pixel Accuracy:** 95.3% → **99.5%** (on our test set)

---

## Model Details

- **Architecture:** BiRefNet (fine-tuned)
- **License:** MIT
- **Training data:** [ToonOut Dataset](https://huggingface.co/datasets/joelseytre/ToonOut) (CC-BY 4.0)

---

## Example usage

Please refer to [the demo notebook](https://github.com/MatteoKartoon/BiRefNet/blob/main/toonout_demo.ipynb) from our GitHub repo.

---

## Citation

If you use ToonOut, please cite:

~~~bibtex
@misc{muratori2025toonout,
  title={ToonOut: Fine-tuned Background Removal for Anime Characters},
  author={Muratori, Matteo and Seytre, Joël},
  year={2025},
  eprint={2509.06839},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2509.06839},
  doi={10.48550/arXiv.2509.06839}
}
~~~

---

## Authors & Contact

- **Authors:** Matteo Muratori (University of Bologna, Kartoon AI), Joël Seytre (Kartoon AI)  
- **Contact:** joel@kartoon.ai, matteo.muratori9@studio.unibo.it

⸻

Project by *Kartoon AI*, powering **toongether**, check us out at [kartoon.ai](kartoon.ai) & [toongether.ai](toongether.ai)