Ask Lemmy
A Fediverse community for open-ended, thought provoking questions
Rules: (interactive)
1) Be nice and; have fun
Doxxing, trolling, sealioning, racism, and toxicity are not welcomed in AskLemmy. Remember what your mother said: if you can't say something nice, don't say anything at all. In addition, the site-wide Lemmy.world terms of service also apply here. Please familiarize yourself with them
2) All posts must end with a '?'
This is sort of like Jeopardy. Please phrase all post titles in the form of a proper question ending with ?
3) No spam
Please do not flood the community with nonsense. Actual suspected spammers will be banned on site. No astroturfing.
4) NSFW is okay, within reason
Just remember to tag posts with either a content warning or a [NSFW] tag. Overtly sexual posts are not allowed, please direct them to either !asklemmyafterdark@lemmy.world or !asklemmynsfw@lemmynsfw.com.
NSFW comments should be restricted to posts tagged [NSFW].
5) This is not a support community.
It is not a place for 'how do I?', type questions.
If you have any questions regarding the site itself or would like to report a community, please direct them to Lemmy.world Support or email info@lemmy.world. For other questions check our partnered communities list, or use the search function.
6) No US Politics.
Please don't post about current US Politics. If you need to do this, try !politicaldiscussion@lemmy.world or !askusa@discuss.online
Reminder: The terms of service apply here too.
Partnered Communities:
Logo design credit goes to: tubbadu
view the rest of the comments
Interestingly enough, even the simpler things like removing the censoring of certain countries' videos still look super wonky. I mean removing that mosaic is something I figure quite some people would be interested in. Yet technology doesn't seem advanced enough to do it properly. And I've had a look at what people do with the video generators, and they've made quite some advancements. Pulling off clothes kinda works now. But it's still fairly limited in all other aspects. They do a short clip of one specific thing. And seems they're limited to one movement type and you'd need the next customized model for the next thing that happens. And then also make sure the people in the video look alike... Do 20 tries until those 5sec look somewhat realistic... And those clips don't line up well. Fluids don't seem to work, I have no clue whether they have some control over facial expressions or whatever is important when "acting" like realistic humans... I bet we're still a bit away from it generating a video of "the act" from start to finish... I'd also predict this is a good use-case for generative AI, though. I mean why not? And it'll lead to all kinds of issues, like the ability to generate videos of celebrities, other not-okay things... But all the human-made 30s clips aren't really high quality to begin with either. So it shouldn't be too hard for AI to get a foot in the door of the porn market.
But if there's really 2-3 min videos out there like you said, I'd like to see them. Just for research purposes... Because all I've seen is longer videos with one thing repeating but nothing really happens. Or people stitching together clips, but they'll be doing a million cuts to entirely different camera angles or narration to hide how all the clips aren't really consistent.