this post was submitted on 31 Jul 2024
102 points (91.1% liked)

PC Gaming

8205 readers
539 users here now

For PC gaming news and discussion. PCGamingWiki

Rules:

  1. Be Respectful.
  2. No Spam or Porn.
  3. No Advertising.
  4. No Memes.
  5. No Tech Support.
  6. No questions about buying/building computers.
  7. No game suggestions, friend requests, surveys, or begging.
  8. No Let's Plays, streams, highlight reels/montages, random videos or shorts.
  9. No off-topic posts/comments.
  10. Use the original source, no clickbait titles, no duplicates. (Submissions should be from the original source if possible, unless from paywalled or non-english sources. If the title is clickbait or lacks context you may lightly edit the title.)

founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] Shawdow194@kbin.run 54 points 1 month ago (6 children)

To be fair, stop motion animating is fucking time consuming and such an art. Let alone for first person camera views AND third person

Having an AI quickly generate a hand wave motion etc and convert to first person and vice versa would save hours and hours of capping one frame at a time

[–] rhombus@sh.itjust.works 35 points 1 month ago (2 children)

Most digital animation done by hand isn’t done in the stop motion/frame-by-frame way, It’s done with key frames that are interpolated between. That’s not to say it isn’t still super time consuming (especially when done well).

[–] Shawdow194@kbin.run 13 points 1 month ago (1 children)

Yes! You nailed it

A lot of motions still need to be scrubbed frame by frame and adjusted if any of the key frames dont interpolate cleanly

It's one of those menial tasks that AI could actually specialize and hugely assist in for simple repetitive animations. Or imagine have a custom animation that the AI/ML uniquely generates the key frames on the fly. Talking distant future but every animation could be potentially be entirely unique everytime you see it

[–] rhombus@sh.itjust.works 4 points 1 month ago

I could see a system where you very loosely define a handful of keyframes, give it some kind of description for what your looking for, and then the model fills in the rest for you. It almost certainly would still require some tweaking on the artists part, but I think a huge benefit is that AI can be non-deterministic. If you don’t like what you got you can just run it again without changing inputs. Maybe save multiple runs and manually combine all the best elements. Lots of opportunity.

load more comments (3 replies)