Metadata-Version: 2.3
Name: vsdpir
Version: 4.0.0
Summary: DPIR function for VapourSynth
Project-URL: Homepage, https://github.com/HolyWu/vs-dpir
Project-URL: Issues, https://github.com/HolyWu/vs-dpir/issues
Author-email: HolyWu <holywu@gmail.com>
License-File: LICENSE
Keywords: DPIR,PyTorch,TensorRT,VapourSynth
Classifier: Environment :: GPU :: NVIDIA CUDA
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Multimedia :: Video
Requires-Python: >=3.10
Requires-Dist: numpy
Requires-Dist: requests
Requires-Dist: torch>=2.3.0
Requires-Dist: tqdm
Requires-Dist: vapoursynth>=66
Requires-Dist: vstools
Description-Content-Type: text/markdown

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


## Dependencies
- [PyTorch](https://pytorch.org/get-started/) 2.3 or later
- [VapourSynth](http://www.vapoursynth.com/) R66 or later

`trt` requires additional Python packages:
- [TensorRT](https://developer.nvidia.com/tensorrt/) 10.0.1
- [Torch-TensorRT](https://pytorch.org/TensorRT/)

To install TensorRT, simply run `pip install tensorrt==10.0.1`

To install Torch-TensorRT, Windows users can pip install the whl file on [Releases](https://github.com/HolyWu/vs-dpir/releases). Linux users can run `pip install --pre torch-tensorrt --index-url https://download.pytorch.org/whl/nightly/cu121` (requires PyTorch nightly build).


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


## Usage
```python
from vsdpir import dpir

ret = dpir(clip)
```

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