video2x

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

https://github.com/k4yt3x/video2x

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
    1 of 24 committers (4.2%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (15.8%) to scientific vocabulary

Keywords

anime4k frame-interpolation machine-learning neural-networks realcugan realesrgan rife super-resoluion upscale-video vulkan
Last synced: 6 months ago · JSON representation

Repository

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

Basic Info
  • Host: GitHub
  • Owner: k4yt3x
  • License: agpl-3.0
  • Language: C++
  • Default Branch: master
  • Homepage: https://docs.video2x.org
  • Size: 548 MB
Statistics
  • Stars: 13,394
  • Watchers: 145
  • Forks: 1,199
  • Open Issues: 48
  • Releases: 37
Topics
anime4k frame-interpolation machine-learning neural-networks realcugan realesrgan rife super-resoluion upscale-video vulkan
Created almost 8 years ago · Last pushed 11 months ago
Metadata Files
Readme Changelog Contributing Funding License Code of conduct Citation Security

README.md

Video2X: A machine learning-based video super resolution and frame interpolation framework.

Version 6.0.0

Video2X 6.0.0 highlights:

  • Complete rewrite of the Video2X project in C/C++.
  • Faster and more efficient architecture.
  • Cross-platform support for Windows and Linux.
  • Vastly improved output quality.
  • New GUI and installer for easy setup on Windows.
Click to see more details Version 6.0.0 is a complete rewrite of this project in C/C++. It: - genuinely works this time, with much less hassle compared to the 5.0.0 beta; - is blazing fast, thanks to the new optimized pipeline and the efficiency of C/C++; - is cross-platform, available now for both Windows and Linux; - offers significantly better output quality with Anime4K v4, Real-ESRGAN, Real-CUGAN, and RIFE; - supports two modes: filtering (upscaling) and frame interpolation; - supports Anime4K v4 and all custom MPV-compatible GLSL shaders; - supports Real-ESRGAN, Real-CUGAN, and RIFE (all models) via ncnn and Vulkan; - requires zero additional disk space during processing, just space for the final output.

6.4.0-screenshot

Hardware Requirements

Your system must meet the minimum hardware requirements below to run Video2X.

  • CPU
    • The precompiled binaries require CPUs with AVX2 support.
    • Intel: Haswell (Q2 2013) or newer
    • AMD: Excavator (Q2 2015) or newer
  • GPU
    • The GPU must support Vulkan.
    • NVIDIA: Kepler (GTX 600 series, Q2 2012) or newer
    • AMD: GCN 1.0 (Radeon HD 7000 series, Q1 2012) or newer
    • Intel: HD Graphics 4000 (Q2 2012) or newer

Install on Windows

Download the Latest Windows Installer Executable (6.4.0)

You can download the latest Windows release on the releases page. For basic GUI usage, refer to the documentation. If you're unable to download directly from GitHub, try the mirror site. The GUI currently supports the following languages:

- English (United States)

  • Portugus (Portugal)
  • Franais (France)
  • Deutsch (Deutschland)

Install on Linux

Video2X packages are available for the Linux distros listed below. A universal AppImage is also available for other distros. If you'd like to build it from source code, refer to the PKGBUILD file for a general overview of the required dependencies and commands.

Container Image

Video2X container images are available on the GitHub Container Registry for easy deployment on Linux and macOS. If you already have Docker/Podman installed, only one command is needed to start upscaling a video. For more information on how to use Video2X's Docker image, please refer to the documentation.

Google Colab

You can use Video2X on Google Colab for free if you don't have a powerful GPU of your own. You can borrow a powerful GPU (NVIDIA T4, L4, or A100) on Google's server for free for a maximum of 12 hours per session. Please use the free resource fairly and do not create sessions back-to-back and run upscaling 24/7. This might result in you getting banned. You can get Colab Pro/Pro+ if you'd like to use better GPUs and get longer runtimes. Usage instructions are embedded in the Colab Notebook.

Telegram Discussion Group

Join our Telegram discussion group to ask any questions you have about Video2X, chat directly with the developers, or discuss super resolution, frame interpolation technologies, or the future of Video2X in general.

Documentation

Comprehensive documentation for Video2X is available at https://docs.video2x.org/. It offers detailed instructions on how to build, install, use, and develop with this program.

Video Demos (Outdated)

Spirited Away Demo\ Upscale demo: Spirited Away's movie trailer

  • Spirited Away: YouTube | Bilibili
  • Bad Apple!!: YouTube | Bilibili
    • 384P 30 FPS to 4K 120 FPS with waifu2x and DAIN
    • The original video's copyright belongs to
  • The Pet Girl of Sakurasou: YouTube | Bilibili
    • 240P 29.97 to 1080P 60 FPS with waifu2x and DAIN
    • The original video's copyright belongs to ASCII Media Works

Standard Test Clip

The following clip can be used to test if your setup works properly. This is also the standard clip used for running performance benchmarks.

The original clip came from the anime "."\ Copyright of this clip belongs to .

License

This project is licensed under GNU AGPL version 3.\ Copyright (C) 2018-2025 K4YT3X and contributors.

AGPLv3

This project includes or depends on these following projects:

| Project | License | | ------------------------------------------------------------------------------------- | --------------- | | FFmpeg/FFmpeg | LGPLv2.1, GPLv2 | | Tencent/ncnn | BSD 3-Clause | | bloc97/Anime4K | MIT License | | nihui/realcugan-ncnn-vulkan | MIT License | | nihui/rife-ncnn-vulkan | MIT License | | xinntao/Real-ESRGAN-ncnn-vulkan | MIT License |

More licensing information can be found in the NOTICE file.

Special Thanks

Special thanks to the following individuals for their significant contributions to the project, listed in alphabetical order.

Owner

  • Name: K4YT3X
  • Login: k4yt3x
  • Kind: user

所謂的正確之物會隨人們各自的意志而遷移無常

Committers

Last synced: 11 months ago

All Time
  • Total Commits: 970
  • Total Committers: 24
  • Avg Commits per committer: 40.417
  • Development Distribution Score (DDS): 0.044
Past Year
  • Commits: 186
  • Committers: 7
  • Avg Commits per committer: 26.571
  • Development Distribution Score (DDS): 0.043
Top Committers
Name Email Commits
k4yt3x k****x@k****m 927
BrianPetkovsek 1****k 10
sat3ll 3****l 7
Integral i****l@m****g 3
Felixkruemel f****l@g****e 2
Peter Dave Hello h****u@p****g 2
Steve Nixon s****n@g****m 2
jitsuCM j****M@a****m 1
Dawei Feng d****g@o****m 1
Fireshadow f****w 1
Frosty! 7****m 1
Henje j****m@y****e 1
ImportTaste 5****e 1
Neo_Chen (BU4AK) c****i@g****m 1
Owen Quinlan h****t@b****t 1
Prescot o****t@g****m 1
YOUSIKI Y****i@o****m 1
donicrosby d****5@g****m 1
konqi i****4@g****m 1
lbrunkho l****b@m****k 1
mayiflex 9****x 1
medram m****y@g****m 1
plambeto p****o@g****m 1
劃破黑夜 1****b@g****m 1
Committer Domains (Top 20 + Academic)

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 446
  • Total pull requests: 44
  • Average time to close issues: 5 months
  • Average time to close pull requests: 10 days
  • Total issue authors: 359
  • Total pull request authors: 20
  • Average comments per issue: 3.46
  • Average comments per pull request: 2.32
  • Merged pull requests: 28
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 187
  • Pull requests: 37
  • Average time to close issues: 8 days
  • Average time to close pull requests: 4 days
  • Issue authors: 148
  • Pull request authors: 13
  • Average comments per issue: 3.37
  • Average comments per pull request: 1.05
  • Merged pull requests: 27
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • Pete4K (14)
  • wuast94 (9)
  • k4yt3x (8)
  • cr08 (8)
  • BuyMyMojo (6)
  • LukeShortCloud (5)
  • ArmandBernard (4)
  • arximboldi (4)
  • metzo007 (4)
  • Xyz00777 (3)
  • MatteCrystal (3)
  • HauptlingHD (3)
  • FelixRobotics (3)
  • reindex-ot (3)
  • Mirrorman95 (3)
Pull Request Authors
  • k4yt3x (28)
  • Integral-Tech (6)
  • Henje (2)
  • lbrunkho (2)
  • alper-han (2)
  • angelobdev (2)
  • arximboldi (2)
  • avan06 (2)
  • ShortyCM (2)
  • aa-ko (2)
  • B1ACK917 (2)
  • BonsenW (2)
  • LukeShortCloud (2)
  • aa-sikkkk (2)
  • NeoChen1024 (2)
Top Labels
Issue Labels
type:Enhancement (107) type:Bug (90) state:Backlog (69) state:InProgress (23) type:Question (22) false positive (17) state:timedOut (15) help wanted (12) component:GUI (10) state:Queued (9) component:FFmpeg (5) state:WaitingForCreator (4) state:Done (4) state:Testing (4) cannot reproduce (4) platform:Linux (4) component:Container (3) state:waitingForCreator (3) state:Planned (3) decision:wontfix (3) component:Algorithms (2) component:Containers (2) state:inProgress (2) component:Colab (2) decision:WontFix (1) platform:macOS (1) state:TimedOut (1) component:Algorithm (1) component:CLI (1) component:Packaging (1)
Pull Request Labels
type:Enhancement (3) decision:wontMerge (2)