图片视频画质优化
Go to file
2019-02-08 16:48:35 -05:00
bin adding amd support 2019-02-08 16:48:35 -05:00
_config.yml Set theme jekyll-theme-minimal 2018-11-29 13:34:05 -05:00
.gitignore added gitignore line for pycharm 2018-11-02 21:48:52 -04:00
LICENSE Initial commit 2018-02-24 11:34:41 -05:00
README.md added discussion group link 2019-02-08 14:28:01 -05:00
sample_input.mp4 replacing old sample clip with something new 2019-02-08 14:06:14 -05:00
sample_output.mp4 replacing old sample clip with something new 2019-02-08 14:06:14 -05:00

Video2X Lossless Video Enlarger

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

Prerequisites

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

  1. Operating System: Windows
  2. Nvidia GPU (AMD support is on the way)
  3. Nvidia GPU driver / Nvidia CUDNN
  4. FFMPEG
  5. Waifu2x Caffe

2.3.0 (February 8, 2019)

  • Added the ability to specify the cache directories as required by @AusNaminator
  • Fixed the problem where if there's insufficient RAM, the warning doesn't pause the script and prompt the user to reduce the amount of threads used.
  • Some other minor adjustments.

2.2.1 (February 1, 2019)

  • Fixed AAC codec error discovered by @meguerreroa

2.2.0 (December 21, 2018)

  • Rewritten main file to organize project structure. All executables have been moved into the bin folder.
  • Bulk enlarge videos in a folder function has been added.
  • Rewritten command line arguments parser to make arguments more clear.
  • Other minor improvements.

Setup Script (November 29, 2018)

  • Added setup script. Now you can install dependencies and generate video2x configuraiton automatically by running the video2x_setup.py script.

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

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 bin/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

To enlarge a video on a computer with NVIDIA GPU

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

To enlarge a video on a computer with CPU

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

Full Usage

usage: video2x.py [-h] -i INPUT -o OUTPUT -m {cpu,gpu,cudnn}
                  [-y {upconv_7_anime_style_art_rgb,upconv_7_photo,anime_style_art_rgb,photo,anime_style_art_y}]
                  [-t THREADS] [-c CONFIG] [--width WIDTH] [--height HEIGHT]
                  [-f FACTOR]

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

Basic Options:
  -i INPUT, --input INPUT
                        Specify source video file/directory
  -o OUTPUT, --output OUTPUT
                        Specify output video file/directory
  -m {cpu,gpu,cudnn}, --method {cpu,gpu,cudnn}
                        Specify upscaling method
  -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

Scaling Options:
  --width WIDTH         Output video width
  --height HEIGHT       Output video height
  -f FACTOR, --factor FACTOR
                        Factor to upscale the videos by

This project is based on the following softwares and projects.