---
title: BiRefNet-GGUF
canonical_url: "https://www.modelscope.cn/models/xiaowu89/BiRefNet-GGUF"
md_url: "https://www.modelscope.cn/models/xiaowu89/BiRefNet-GGUF.md"
repository: xiaowu89/BiRefNet-GGUF
chinese_name: BiRefNet-GGUF
last_updated: 2026-07-29
license: mit
pipeline_tag: image-segmentation
tasks:
  - image-segmentation
base_model:
  - ZhengPeng7/BiRefNet
base_model_relation: quantized
library_name:
  - gguf
  - other
frameworks:
  - other
downloads: 587
stars: 1
tags:
  - background-removal
  - mask-generation
  - "Dichotomous Image Segmentation"
  - vision.cpp
---

# BiRefNet-GGUF

> BiRefNet-GGUF - xiaowu89 在 ModelScope 开源的模型。GGUF models for BiRefNet

xiaowu89/BiRefNet-GGUF 是 ModelScope 魔搭社区上的image-segmentation模型，采用 mit 许可，基于 ZhengPeng7/BiRefNet 构建。

- **Repository**: xiaowu89/BiRefNet-GGUF
- **License**: mit
- **Tasks**: image-segmentation
- **Base model**: ZhengPeng7/BiRefNet
- **Tags**: background-removal, mask-generation, Dichotomous Image Segmentation, vision.cpp
- **Downloads**: 587
- **Stars**: 1
- **Last updated**: 2026-07-29

Source: https://www.modelscope.cn/models/xiaowu89/BiRefNet-GGUF

---

# GGUF models for BiRefNet

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 (HuggingFace)](https://huggingface.co/ZhengPeng7/BiRefNet)


## Run

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

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