this post was submitted on 29 Jul 2023
152 points (90.9% liked)
Technology
59298 readers
4551 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I just tried. It's basically https://github.com/xinntao/Real-ESRGAN expect OP's program upscales video, frame by frame, and combines those frames into a new video.
Video looks like it's made by AI. Tried on old video - not sure if old or new video looking better. Contours in new video are difderent with each frame lol.
OP did a great job, but overall technology is not there yet. Videos aren't looking good tbh.
Does it configure it's own venv or do I need to to that?
Edit: doesn't look like it. That should be just common practice, Like how oobabooga/SD work. Makes life easier.
What python version?
Edit:
I just downloaded from the releases, giving it a test now
Here we are in 2023 and people still have to ask for venv and which Python versions. I don't understand why these AI devs on these smaller scales seem to be container adverse.
Did the same. :)
It's very ai-upscaley. I think if there is some extra processing steps, then this could be really good.
Quality was bad because ScaleUp had bitrate problem. Now i fixed that. Results now much better.