Skip to content
This repository has been archived by the owner on May 11, 2023. It is now read-only.

AI Video Processing/Upscaling With VapourSynth in Google Colab

License

Notifications You must be signed in to change notification settings

AlphaAtlas/VapourSynthColab

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 

Repository files navigation

VapourSynthColab

A Google Colab notebook set up for both conventional and machine learning-based video processing. Run ESRGAN or MXNet models, OpenCL and CUDA filters, and CPU filters on video frames simultaneously in VapourSynth scripts, or use VapourSynth filters to pre/post process videos for other ML Colab projects, and do it all in the cloud for free.

Colab1.png Colab2.png

Basic usage:

For basics on VapourSynth and super resolution filters, see the wiki (and links to other guides) here:

Browse through VS plugins and scripts here, search for "vapoursynth" on github, or look through the "VapourSynthImports" folder and VapourSynth's imported plugins:

I highly recommend stabilizing ESRGAN output with a temporal filter, or using a dedicated video model from another repo. Also, keep in mind that Colab's CPU is very slow, and that sessions are limited to 12 hours, so use GPU accelerated filters wherever possible in scripts with heavy CPU filters, and write your processesed videos to Google Drive or Nextcloud.

Grab models for specific kinds of content here, or train your own:

For help, just post an issue, or ask in the Game Upscale or Animation Upscale Discords.

Releases

No releases published

Packages

No packages published