this post was submitted on 18 Sep 2023
25 points (100.0% liked)
Linux
48143 readers
788 users here now
From Wikipedia, the free encyclopedia
Linux is a family of open source Unix-like operating systems based on the Linux kernel, an operating system kernel first released on September 17, 1991 by Linus Torvalds. Linux is typically packaged in a Linux distribution (or distro for short).
Distributions include the Linux kernel and supporting system software and libraries, many of which are provided by the GNU Project. Many Linux distributions use the word "Linux" in their name, but the Free Software Foundation uses the name GNU/Linux to emphasize the importance of GNU software, causing some controversy.
Rules
- Posts must be relevant to operating systems running the Linux kernel. GNU/Linux or otherwise.
- No misinformation
- No NSFW content
- No hate speech, bigotry, etc
Related Communities
Community icon by Alpár-Etele Méder, licensed under CC BY 3.0
founded 5 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
You could use
ffmpeg
or python to split the video into a sequence of images and an audio file, then AI upscale the images using Upscayl, and finally combine the upscaled images and audio back into a video, usingffmpeg
.I've seen issues in the past where the audio would be out-of-sync when recombining the frames because ffmpeg wouldn't output the right number of frames, so someone wrote a python script to split the video into frames and apparently it works correctly.
Also see: https://superuser.com/questions/1758192/how-can-i-split-a-video-into-frames-and-then-reassemble-it-with-the-audio-too
This probably won't work well because you will want stability between images. An upscaler that isn't video-aware will result in lots of distracting flickering.
Wow, I didn’t think of that. Thank you!
Off topic but that one answer on superuser looks a lot like it was AI generated.
Wouldn't you lose a lot of quality during decode/encode?
Not really, because you can output to png so decoding is lossless, and since your AI upscaled images are of a much higher quality, the resultant video would be a higher quality video as well.