Technology

59712 readers

5740 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

229

China’s AI overload: Baidu CEO warns of too many models, too few applications (www.scmp.com)

submitted 4 months ago by Alphane_Moon to c/technology

26 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] Alphane_Moon 22 points 4 months ago* (last edited 4 months ago)

Image/video upscaling via neural net is something I would pay for.

I currently use freeware/open source alternatives, but I am planning to get a copy of Topaz Video AI in the future.

Even the freeware/open source algorithms are incredible in terms of quality. You do get artifacts and it doesn't handle certain things very well (I get problems with watermarks); but that might be my lack of knowledge.

When I first did a successful SD upscale (x2 resolution), it almost felt like magic.

I had seen some pretty impressive neural net upscaling before (Arrival of a Train at La Ciotat, Lumière Brothers, 1896), but it's a whole different feeling when you can do it yourself with pretty solid results.