Aller au contenu
ModelPrésentéExterne
Télécharger

BiRefNet GGUF

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.

Sourcehuggingface.co/Acly/BiRefNet-GGUF/tree/4f6018e2f35cedf26c8ddf0fec1475252f8ba280
TypeOtherModèle de baseZhengPeng7/BiRefNetVersionRevision 4f6018eBClasse

Source du modèle

Type
Other
Taille du fichier
84,5–420 MB
Modèle de base
ZhengPeng7/BiRefNet
Version
vRevision 4f6018e
Mis à jour
20 oct. 2026
Téléchargements
1,5 k
Source
Hugging Face

Description de la source

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.

Run

Example inference with vision.cpp:

CLI

vision-cli birefnet -m BiRefNet-F16.gguf -i input.png -o mask.png --composite comp.png

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");

Sources

1 source
Hugging FacePrincipalVersion 4f6018e2f35cedf26c8ddf0fec1475252f8ba280
huggingface.co/Acly/BiRefNet-GGUF/tree/4f6018e2f35cedf26c8ddf0fec1475252f8ba280

Vérifié 20 oct.

Artefacts du modèle

3 artefacts

BiRefNet-dynamic-F16.gguf

gguf · 420 MB · SHA-256 c7add90033d5…dcf3 · Hugging Face

Télécharger

BiRefNet-F16.gguf

gguf · 420 MB · SHA-256 5d5fd824c8fb…4d77 · Hugging Face

Télécharger

BiRefNet-lite-F16.gguf

gguf · 84,5 MB · SHA-256 7b5397a2c98d…4fa5 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme3 aoûthuggingface.co/Acly/BiRefNet-GGUF

--- license: mit base_model: ZhengPeng7/BiRefNet tags: - background-removal - mask-generation - Dichotomous Image Segmentation - vision.cpp pipeline_tag: image-segmentation --- # 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"); ```

Note20 oct.huggingface.co/Acly/BiRefNet-GGUF

Source context: 1455 downloads · 17 likes · Pipeline image-segmentation · Repo Acly/BiRefNet-GGUF

Note3 aoûthuggingface.co/Acly/BiRefNet-GGUF

Source context: 1028 downloads · 15 likes · Pipeline image-segmentation · Repo Acly/BiRefNet-GGUF