ModelListedExternal

Toonout

our repository: our paper: ToonOut: Fine-tuned Background Removal for Anime Characters the dataset we collected to fine-tune this model Replicate endpoint to try out the model (courtesy of J. H. Cho @sprited)

Sourcehuggingface.co/joelseytre/toonout/tree/cbf720eca394edcde66b861a8a8c20fbabe9c748

KindOtherBase modelZhengPeng7/BiRefNetVersionRevision cbf720eBgrade

Model source

Kind: Other
File size: 844 MB
Base model: ZhengPeng7/BiRefNet
Version: vRevision cbf720e
Updated: Oct 9, 2026
Downloads: 508
Source: Hugging Face

Source description

ToonOut Model Weights

Please check out:

our repository: https://github.com/MatteoKartoon/BiRefNet
our paper: ToonOut: Fine-tuned Background Removal for Anime Characters
the dataset we collected to fine-tune this model
Replicate endpoint to try out the model (courtesy of J. H. Cho @sprited)

Model Comparison

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 (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 (CC-BY 4.0)

Example usage

Please refer to the demo notebook from our GitHub repo.

Citation

If you use ToonOut, please cite:

@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 & toongether.ai

Sources

1 source

Hugging FacePrimaryVersion cbf720eca394edcde66b861a8a8c20fbabe9c748

huggingface.co/joelseytre/toonout/tree/cbf720eca394edcde66b861a8a8c20fbabe9c748

Verified Oct 9

Model artifacts

1 artifact

birefnet_finetuned_toonout.pth

pth · 844 MB · SHA-256 8c7f8a0bc244…fbe5 · Hugging Face

Download

Source excerpts

3 excerpts

ReadmeJul 31huggingface.co/joelseytre/toonout

--- 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/) - [**Replicate endpoint**](https://replicate.com/sprited/birefnet-toonout) to try out the model (courtesy of J. H. Cho @[sprited](https://sprited.ai)) ![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)

NoteOct 9huggingface.co/joelseytre/toonout

Source context: 508 downloads · 24 likes · Pipeline image-segmentation · Repo joelseytre/toonout

NoteJul 31huggingface.co/joelseytre/toonout

Source context: 186 downloads · 21 likes · Pipeline image-segmentation · Repo joelseytre/toonout