---
license: mit
base_model: joelseytre/toonout
tags:
  - background-removal
  - mask-generation
  - Dichotomous Image Segmentation
  - anime
  - vision.cpp
pipeline_tag: image-segmentation
---
# GGUF models for ToonOut

ToonOut is a fine-tuned variant of BiRefNet specialized for background removal
in anime-style images. The weights in this repository are converted for
lightweight inference on consumer hardware with
[vision.cpp](https://github.com/Acly/vision.cpp).

* Original repository: [MatteoKartoon/BiRefNet (Github)](https://github.com/MatteoKartoon/BiRefNet)
* Original weights: [joelseytre/toonout (HuggingFace)](https://huggingface.co/joelseytre/toonout)


## Run

Example inference with [vision.cpp](https://github.com/Acly/vision.cpp):

#### CLI
```sh
vision-cli birefnet -m BiRefNet-ToonOut-F16.gguf -i input.png -o mask.png --composite comp.png
```

#### C++
```c++
image_data image      = image_load("input.png");
backend_device device = backend_init();
birefnet_model model  = birefnet_load_model("BiRefNet-ToonOut-F16.gguf", device);
image_data mask       = birefnet_compute(model, image);
image_save(mask, "mask.png");
```