Video2X Lossless Video Enlarger

Official Discussion Group (Telegram): https://t.me/video2x

Prerequisites

Component names that are bolded are mandatory.

Component names that are italicized can be automatically downloaded and configured with the video2x_setup.py script.

1. Operating System: Windows
2. AMD GPU / Nvidia GPU
3. AMD GPU driver / Nvidia GPU driver / Nvidia CUDNN
4. FFMPEG
5. waifu2x-caffe / waifu2x-converter-cpp

2.4.3 (February 26, 2019)

• Fixed the bug where ffmpeg arguments (hwaccel) are not passed on to ffmpeg

2.4.2 (February 26, 2019)

• Added the function to detect insufficient GPU memory
• Added the function to create temporary folders automatically
• Fixed configuration file path error

2.4.1 (February 21, 2019)

• Video2X will now migrate all the audio tracks and subtitles to the output video.

2.4.0 (February 8, 2019)

• Added AMD Support. You can now use -d/--driver waifu2x_converter to specify the waifu2x driver to be waifu2x-converter-cpp. Note that you'll have to download and configure waifu2x-converter-cpp first.

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:

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

Clip is from trailer of animated movie "千と千尋の神隠し". Copyright belongs to "株式会社スタジオジブリ (STUDIO GHIBLI INC.)". Will delete immediately if use of clip is in violation of copyright.

Screenshot

Installation

Prerequisites

• Python 3
  Download: https://www.python.org/downloads/windows/
• FFMPEG Windows Build
  Download: https://ffmpeg.org/download.html
• waifu2x-caffe for Windows
  Download: https://github.com/lltcggie/waifu2x-caffe/releases
• waifu2x-converter-cpp
  Download: https://github.com/DeadSix27/waifu2x-converter-cpp/releases

Install Dependencies

First, clone the video2x repository.

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

Then you may run the video2x_setup.py script to install and configure the depencies automatically. This script is designed and tested on Windows 10.

This script will install ffmpeg, waifu2x-caffe to %LOCALAPPDATA%\\video2x and all python libraries.

$ python video2x_setup.py

Alternatively, you can also install the dependencies manually. Please refer to the prerequisites section to see what's needed.

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

Sample Videos

If you can't find a video clip to begin with, or if you want to see a before-after comparison, we have prepared some sample clips for you. The quick start guide down below will also be based on the name of the sample clips.

• Sample Video Original (240P) 1.7MB
• Sample Video Upscaled (1080P) 4.8MB

Clip is from anime "さくら荘のペットな彼女". Copyright belongs to "株式会社アニプレックス (Aniplex Inc.)". Will delete immediately if use of clip is in violation of copyright.

For Command Line Beginners

If you're unfamiliar of directories in command lines, then here's a short section that might help you to get started.

For example, if you downloaded the sample input video to C:\Users\[YourUsername]\Downloads, then the full path of your input video will be C:\Users\[YourUsername]\Downloads\sample_input.mp4, vice versa. The output path is also relative. If you want to export the output video to the current directory, just specify the output video name such as output.mp4. However, if you want to put the output video in a different directory, you should use relative or absolute path, such as C:\Users\[YourUsername]\Desktop\output.mp4.

If you're tired typing everything in, you can also drag the video file directly into the command line window, and Windows will fill in the full path of the video for you.

Nvidia CUDA (waifu2x-caffe)

Enlarge the video to 1920x1080 using CUDA. You may also use the -r/--ratio option.

$ python video2x.py -i sample_input.mp4 -o sample_output.mp4 -m gpu --width=1920 --height=1080

Nvidia CNDNN

Enlarge the video to 1920x1080 using CUDNN. You may also use the -r/--ratio option.

$ python video2x.py -i sample_input.mp4 -o sample_output.mp4 -m cudnn --width=1920 --height=1080

AMD or Nvidia (waifu2x-converter-cpp OpenCL)

Enlarge the video by 2 times using OpenCL. Note that waifu2x-converter-cpp doesn't support width and height.

$ python video2x.py -i sample_input.mp4 -o sample_output.mp4 -m gpu -r 2

CPU

Enlarge the video to 1920x1080 using the CPU. You may also use the -r/--ratio option. This is potentially much slower than using a GPU.

$ python video2x.py -i sample_input.mp4 -o sample_output.mp4 -m cpu --width=1920 --height=1080

Full Usage

General Options

-h, --help

show this help message and exit

File Input and Output

-i INPUT, --input INPUT

Specify source video file/directory

-o OUTPUT, --output OUTPUT

Specify output video file/directory

Upscaler Options

-m {cpu,gpu,cudnn}, --method {cpu,gpu,cudnn}

Specify upscaling method

-d {waifu2x_caffe,waifu2x_converter}, --driver {waifu2x_caffe,waifu2x_converter}

Waifu2x driver

-y {upconv_7_anime_style_art_rgb,upconv_7_photo,anime_style_art_rgb,photo,anime_style_art_y}, --model_type {upconv_7_anime_style_art_rgb,upconv_7_photo,anime_style_art_rgb,photo,anime_style_art_y}

Specify model to use

-t THREADS, --threads THREADS

Specify number of threads to use for upscaling

-c CONFIG, --config CONFIG

Manually specify config file

--width WIDTH

Output video width

--height HEIGHT

Output video height

-r RATIO, --ratio RATIO

Scaling ratio

License

Licensed under the GNU General Public License Version 3 (GNU GPL v3) https://www.gnu.org/licenses/gpl-3.0.txt

(C) 2018-2019 K4YT3X

Credits

This project relies on the following software and projects.

• FFMPEG
• waifu2x-caffe
• waifu2x-converter-cpp