README.md

---
license: mit
base_model:
- ZhengPeng7/BiRefNet_HR
tags:
- background-removal
- mask-generation
- Dichotomous Image Segmentation
- Camouflaged Object Detection
- Salient Object Detection
- gguf
- vision.cpp
repo_url: https://github.com/ZhengPeng7/BiRefNet
pipeline_tag: image-segmentation
---
# GGUF models for BiRefNet

> This BiRefNet was trained with images in `2048x2048` for higher resolution inference.

BiRefNet is a model for dichotomous image segmentation (background removal). The
weights in this repository are converted for lightweight inference on consumer hardware
with [vision.cpp](https://github.com/Acly/vision.cpp).

* Original repository: [ZhengPeng7/BiRefNet (Github)](https://github.com/ZhengPeng7/BiRefNet)
* Original weights: [ZhengPeng7/BiRefNet_HR (HuggingFace)](https://huggingface.co/ZhengPeng7/BiRefNet_HR)


## Run

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

#### CLI
```sh
vision-cli birefnet -m BiRefNet_HR-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_HR-F16.gguf", device);
image_data mask       = birefnet_compute(model, image);
image_save(mask, "mask.png");
```