Metadata-Version: 2.1
Name: vsdpir
Version: 2.2.0
Summary: DPIR function for VapourSynth
Home-page: https://github.com/HolyWu/vs-dpir
Author: HolyWu
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Multimedia :: Video
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: requests
Requires-Dist: tqdm
Requires-Dist: VapourSynth (>=55)
Requires-Dist: vsutil

# DPIR
Plug-and-Play Image Restoration with Deep Denoiser Prior, based on https://github.com/cszn/DPIR.


## Dependencies
- [NumPy](https://numpy.org/install)
- [ONNX Runtime](https://onnxruntime.ai/). CUDA and TensorRT require `onnxruntime-gpu`, while DirectML requires `onnxruntime-directml`. Note that only one of `onnxruntime`, `onnxruntime-gpu` and `onnxruntime-directml` should be installed at a time in any one environment.
- [VapourSynth](http://www.vapoursynth.com/) R55 or newer.
- (Optional) [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit)
- (Optional) [cuDNN](https://developer.nvidia.com/cudnn)
- (Optional) [TensorRT](https://developer.nvidia.com/tensorrt)


## Installation
```
pip install --upgrade vsdpir
python -m vsdpir
```


## Usage
```python
from vsdpir import DPIR

ret = DPIR(clip)
```

See `__init__.py` for the description of the parameters.
