https://github.com/holywu/vs-rife

RIFE function for VapourSynth
https://github.com/holywu/vs-rife

pytorch rife tensorrt vapoursynth

Last synced: 6 days ago
JSON representation

RIFE function for VapourSynth

• Host: GitHub
• URL: https://github.com/holywu/vs-rife
• Owner: HolyWu
• License: mit
• Created: 2021-07-28T03:10:15.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2025-02-06T14:00:44.000Z (15 days ago)
• Last Synced: 2025-02-15T07:52:17.798Z (6 days ago)
• Topics: pytorch, rife, tensorrt, vapoursynth
• Language: Python
• Homepage:
• Size: 111 MB
• Stars: 113
• Watchers: 3
• Forks: 9
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# RIFE

Real-Time Intermediate Flow Estimation for Video Frame Interpolation, based on https://github.com/hzwer/Practical-RIFE.

## Dependencies

- [PyTorch](https://pytorch.org/get-started/) 2.6.0 or later

- [VapourSynth](http://www.vapoursynth.com/) R66 or later

- [vs-miscfilters-obsolete](https://github.com/vapoursynth/vs-miscfilters-obsolete) (only needed for scene change detection)

`trt` requires additional packages:

- [TensorRT](https://developer.nvidia.com/tensorrt) 10.7.0.post1 or later

- [Torch-TensorRT](https://pytorch.org/TensorRT/) 2.6.0 or later

To install the latest stable version of PyTorch and Torch-TensorRT, run:

```

pip install -U packaging setuptools wheel

pip install -U torch torchvision --index-url https://download.pytorch.org/whl/cu126

pip install --no-deps -U torch_tensorrt --index-url https://download.pytorch.org/whl/cu126

pip install -U tensorrt --extra-index-url https://pypi.nvidia.com

```

## Installation

```

pip install -U vsrife

```

If you want to download all models at once, run `python -m vsrife`. If you prefer to only download the model you

specified at first run, set `auto_download=True` in `rife()`.

## Usage

```python

from vsrife import rife

ret = rife(clip)

```

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