video2x/README.md
2018-11-29 12:40:38 -05:00

2.9 KiB

Video2X Video Enlarger

This software is currently designed for Windows.

2.1.6 (November 26, 2018)

  • Restored the option to define a factor which the will be upscaled by, which is suggested by @wuast94 .

2.1.4 (November 2, 2018)

  • Added hardware acceleration option for ffmpeg. Ffmpeg will use hardware acceleration (GPU, usually) if --gpu or --cudnn is given. You can customize the method to use in video2x.json.

Description

Video2X is an automation software based on waifu2x image enlarging engine. It extracts frames from a video, enlarge it by a number of times without losing any details or quality, keeping lines smooth and edges sharp.

For short: Video2X enlarges your video without losing details

Watch for the sharper edges in this screenshot around the shadows:

preview

Or you can watch the YouTube video Demo: https://www.youtube.com/watch?v=PG94iPoeoZk

Screenshot

screenshot


Installation

Prerequisites

After downloading the dependencies, clone the video2x package.

$ git clone https://github.com/K4YT3X/video2x.git
$ cd video2x

Then you'll need to install python dependencies before start using video2x. Install simply by executing the following command.

$ pip install -r requirements.txt

Quick Start

To enlarge a video on a computer with NVIDIA GPU

$ python video2x.py -v VIDEO_FILE -o OUTPUT_FILENAME --width OUTPUT_WIDTH --height OUTPUT_HEIGHT --gpu

To enlarge a video on a computer without NVIDIA GPU

$ python video2x.py -v VIDEO_FILE -o OUTPUT_FILENAME --width OUTPUT_WIDTH --height OUTPUT_HEIGHT --cpu

Full Usage

usage: video2x.py [-h] [--width WIDTH] [--height HEIGHT] [-v VIDEO]
                  [-o OUTPUT] [-y MODEL_TYPE] [--cpu] [--gpu] [--cudnn]

optional arguments:
  -h, --help            show this help message and exit

Controls:
  --width WIDTH         Output video width
  --height HEIGHT       Output video height
  -v VIDEO, --video VIDEO
                        Specify source video file
  -o OUTPUT, --output OUTPUT
                        Specify output file
  -y MODEL_TYPE, --model_type MODEL_TYPE
                        Specify model to use
  --cpu                 Use CPU for enlarging
  --gpu                 Use GPU for enlarging
  --cudnn               Use CUDNN for enlarging

This project is based on the following softwares and projects.