Metadata-Version: 2.4
Name: nobg
Version: 0.1.0rc0
Summary: Open source background removal models for image and video matting
Project-URL: Homepage, https://github.com/feyninc/nobg
Project-URL: Repository, https://github.com/feyninc/nobg
Project-URL: Issues, https://github.com/feyninc/nobg/issues
Author-email: Hafedh Hichri <lain@chonkie.ai>
License-Expression: MIT
License-File: LICENSE
Keywords: background-removal,deep-learning,huggingface,matting,pytorch
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Processing
Requires-Python: >=3.13
Requires-Dist: datasets>=5.0.0
Requires-Dist: huggingface-hub>=1.22.0
Requires-Dist: loadimg>=0.5.0
Requires-Dist: torch>=2.0
Requires-Dist: torchvision>=0.27.1
Requires-Dist: transformers[torch]>=5.0
Description-Content-Type: text/markdown

# nobg

A library for image and video matting with HuggingFace Hub integration.

## Installation

```bash
pip install nobg
```

## Usage

### AutoModel

Automatically detect and load the correct model architecture from a HuggingFace repo:

```python
from nobg import AutoModel

model = AutoModel.from_pretrained("nobg/BiRefNet")
```

### Load a specific model

```python
from nobg import ANN, GPT2, BiRefNet

model = ANN.from_pretrained("nobg/ann")
model = GPT2.from_pretrained("nobg/gpt2")
model = BiRefNet.from_pretrained("nobg/BiRefNet")
```

### Push to HuggingFace Hub

```python
model.push_to_hub("your-username/model-name")
```

## Citation

```bibtex
@software{nobg,
  title={nobg: Open Source Background Removal Models for Image and Video Matting},
  author={Hichri, Hafedh},
  year={2026},
  url={https://github.com/feyninc/nobg},
  license={MIT},
}
```
