Instructions to use nobg/BiRefNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- nobg
How to use nobg/BiRefNet with nobg:
pip install nobg
# Option 1: use via the predict method from nobg import AutoModel, AutoProcessor model = AutoModel.from_pretrained("nobg/BiRefNet").eval() processor = AutoProcessor.from_pretrained("nobg/BiRefNet") cutout = model.predict(processor, "image.jpg")# Option 2: use the model and processor directly import torch from loadimg import load_img from nobg import AutoModel, AutoProcessor model = AutoModel.from_pretrained("nobg/BiRefNet").eval() processor = AutoProcessor.from_pretrained("nobg/BiRefNet") image = load_img("image.jpg").convert("RGB") inputs = processor(image, return_tensors="pt") with torch.no_grad(): outputs = model(pixel_values=inputs["pixel_values"]) alpha = processor.post_process_alpha_matting(outputs, target_sizes=[(image.height, image.width)])[0] processor.cutout(image, alpha).save("output.png") - BiRefNet
How to use nobg/BiRefNet with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("nobg/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("nobg/BiRefNet") - Notebooks
- Google Colab
- Kaggle
Download model.safetensors from nobg/BiRefNet: direct link, hf CLI and curl.
- Browser
- Download file 881 MB
-
https://huggingface.co/nobg/BiRefNet/resolve/main/model.safetensors
- Command line
-
hf download hf://nobg/BiRefNet/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/nobg/BiRefNet/resolve/main/model.safetensors
881 MB
- Xet hash:
- 90213911b7bee8f115b88a11eda61c4346cf1457f1ef71f665c5c3f9c58205f2
- Size of remote file:
- 881 MB
- SHA256:
- 8d5af44e605ec7bab2e532957db88b89126c25e887f700515756348e3bf647cb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.