Image Segmentation
BiRefNet
swift-object-cutout
background-removal
image-matting
dichotomous-image-segmentation
core-ai
apple-silicon
macos
Instructions to use arraypress/cutout-birefnet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- BiRefNet
How to use arraypress/cutout-birefnet with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("arraypress/cutout-birefnet", trust_remote_code=True)# Option 2: use with BiRefNet # Install from https://github.com/ZhengPeng7/BiRefNet from models.birefnet import BiRefNet model = BiRefNet.from_pretrained("arraypress/cutout-birefnet") - Notebooks
- Google Colab
- Kaggle
Download cutout-birefnet-float16.aimodel/metadata.json from arraypress/cutout-birefnet: direct link, hf CLI and curl.
- Browser
- Download file 471 Bytes
-
https://huggingface.co/arraypress/cutout-birefnet/resolve/main/cutout-birefnet-float16.aimodel/metadata.json
- Command line
-
hf download hf://arraypress/cutout-birefnet/cutout-birefnet-float16.aimodel/metadata.json
-
curl -L -o metadata.json https://huggingface.co/arraypress/cutout-birefnet/resolve/main/cutout-birefnet-float16.aimodel/metadata.json
471 Bytes
| { | |
| "producer" : "coreai-core 1.0.0b3", | |
| "creationDate" : "20261016T175354Z", | |
| "description" : "BiRefNet general (ZhengPeng7\/BiRefNet@e2bf8e4), float16. Entry 'main': image [1,3,1024,1024] float32 RGB 0…1 → alpha [1,1,1024,1024] float32 0…1. Resize to 1024² and back in the host.", | |
| "assetVersion" : "2.0", | |
| "license" : "MIT", | |
| "author" : "Zheng, Gao, Fan, Liu, Laaksonen, Ouyang, Sebe — BiRefNet (CAAI AIR 2024), general; Core AI export by ObjectCutout" | |
| } |