Image Segmentation
MLX
Safetensors
BiRefNet
moonbox
background-removal
dichotomous-image-segmentation
Instructions to use moonbox-dev/BiRefNet_lite-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use moonbox-dev/BiRefNet_lite-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download moonbox-dev/BiRefNet_lite-MLX --local-dir BiRefNet_lite-MLX
- BiRefNet
How to use moonbox-dev/BiRefNet_lite-MLX with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("moonbox-dev/BiRefNet_lite-MLX", 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("moonbox-dev/BiRefNet_lite-MLX") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download fp16/config.json from moonbox-dev/BiRefNet_lite-MLX: direct link, hf CLI and curl.
- Browser
- Download file 99 Bytes
-
https://huggingface.co/moonbox-dev/BiRefNet_lite-MLX/resolve/main/fp16/config.json
- Command line
-
hf download hf://moonbox-dev/BiRefNet_lite-MLX/fp16/config.json
-
curl -L -o config.json https://huggingface.co/moonbox-dev/BiRefNet_lite-MLX/resolve/main/fp16/config.json
99 Bytes
| { | |
| "model_type": "birefnet", | |
| "backbone": "swin_v1_t", | |
| "input_size": 1024, | |
| "precision": "fp16" | |
| } | |