图片视频画质优化
Go to file
2018-05-19 18:24:31 -04:00
_config.yml Set theme jekyll-theme-architect 2018-03-01 12:20:49 -05:00
.gitignore help keeping the trash out of the repo 2018-05-19 00:49:35 -04:00
ffmpeg.py v2.0.1: fixed audio insertion issues 2018-05-19 18:24:31 -04:00
LICENSE Initial commit 2018-02-24 11:34:41 -05:00
README.md added missing details 2018-05-19 01:10:06 -04:00
testvid.mp4 initial 2018-02-24 13:36:14 -05:00
video2x.py v2.0 beta: better CUI + enhancements + bug fixes 2018-05-19 00:54:06 -04:00
waifu2x.py v2.0 enhanced structure 2018-05-19 00:54:16 -04:00

Video2X Video Enlarger

Current Version: 2.0 beta

2.0 Beta Changes

  1. Fixed contents meant for demonstration
  2. Fixed audio issues
  3. Better CUI
  4. Now using absolute path for every file
  5. Added progress bar for showing waifu2x enlarging progress

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: snapshot

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

Quick Start

To enlarge a video on a computer with NVIDIA GPU

$ python video2x.py -v VIDEO_FILE -o OUTPUT_FILENAME -f TIMES_TO_ENLARGE --gpu

To enlarge a video on a computer without NVIDIA GPU

$ python video2x.py -v VIDEO_FILE -o OUTPUT_FILENAME -f TIMES_TO_ENLARGE --cpu

Full Usage

usage: video2x.py [-h] [-f FACTOR] [-v VIDEO] [-o OUTPUT] [-y MODEL_TYPE]
                  [--cpu] [--gpu] [--cudnn]

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

Controls:
  -f FACTOR, --factor FACTOR
                        Factor to enlarge video by
  -v VIDEO, --video VIDEO
                        Specify 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