Live data from Hacker News

Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

github.com

41–50 of 129 posts

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#41

Earlier quoted context omitted.

I'm sure the point is already crossed. People on 4chan are making fake porn that is nearly indistinguishable - and they are complete amateurs.

Are you sure they're amateurs, not professionals don't it for fun (/pro boner/!?!).

I meant something a little different. Any random dude with a random mid-level PC can download the software and produce amazing results without any special hardware or knowledge. I recommend you to try it out for yourself.

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#42

I'm probably being captain obvious here, but if this is what's being released for free, I wonder how much better a polished commercial version does, and when we reach the point where we can't trust anything we see anymore. It doesn't even have to be super perfect, even reaching the point where it takes experts about two weeks to determine if something's real or not might already be long enough to do great damage. Fro…

If you compare OSS or free software to commercial software generally, I don’t think there are that many massive gaps. It’s mostly polish and small incremental improvements, but the underlying tech is mostly the same. Why would that be different in this case?

MS Office is still miles ahead of any OSS “alternative“, despite the many glaring bugs.

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#43
post #31

Earlier quoted context omitted.

Maybe but only after extensive proliferation. Initially, every Tom, Dick & Harry script kiddie will try to blackmail people whilst the public and justice system is not really aware of the technology possible. When eventually enough of the public is made aware to not trust photos and videos anymore then these types of blackmail attempts would be less effective. But there will still be less informed gullible targets.

Surely lawyers will know about the tech soon enough to simply show the same video evidence with the judge in place of the defendant -- reasonable doubt right there. The blackmail angle I expect will work for a while. People falsely accused of sexual crimes can have their lives ruined by the accusation.

The justice system will hopefully catch up quickly.

But as you say the media (real and social), political propaganda, etc will exploit the uninformed masses for all it is worth, so blackmail will still work. For a while.

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#45

I'm scared. I can't trust anything I haven't took myself. The problem is that other people not even know that this technology exists and if you tell them about it, you're a lier.

I don't think there's going to be a long period where this technology is being used and isn't widely known about. It'll be used extremely quickly to abuse people using their Facebook pictures, and once there's a Facebook angle the media will be able to run with it and everyone will get it.

It's already being used for quite a while and you talk as if you aren't aware of the fact. Quite Ironic.

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#46

Some applications for this kind of tech: - Porn, yeah, first application you can think of, there are already some startups doing it. - Doubling actors, and applied to sound, maybe you could translate from one language to another but kind of keeping the accent and tone. - Propaganda and misinformation. Now you can get your enemy to say and do whatever you want, on video. - Photo-realistic games. Create a rough 3D mode…

any ideas about porn startups that work on anything related to this? i know pornhub and their network banned deepfakes and there’s also some work being done on detecting deepfakes.

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#47

Earlier quoted context omitted.

Adobe have definitely bested most oss competitors in their space. Although with the amount of man power at their disposal it would be hard to beat.

The vast bulk of Adobe's advantage is in UX, not technical algorithms. Which makes perfect sense because that tends to be the case with most F/OSS software—technically brilliant but with an face only a programmer could love. Yes, Adobe do have some remarkable algorithms that would be difficult to replicate (e.g. heal brush and content aware fill) but these are a small minority of Adobe's software advantage. The one t…

Do you use the Astute plugins for AI, or the native pen tool? Affinity feels different, maybe less precise, but the functionality was way better compared with the native Adobe tool. You should try Figmas pen tool, I like it.

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#48
post #42

Earlier quoted context omitted.

If you compare OSS or free software to commercial software generally, I don’t think there are that many massive gaps. It’s mostly polish and small incremental improvements, but the underlying tech is mostly the same. Why would that be different in this case?

MS Office is still miles ahead of any OSS “alternative“, despite the many glaring bugs.

MS Office is still miles ahead in the benchmark of opening it's own proprietary files.

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#49
post #23

What media would someone collect now to be used in the future to reproduce the likeness of loved ones? Video clips of them moving? Talking? Different poses of pictures? Reading the dictionary out loud to get vocal patterns? Heck with impersonating the POTUS. What about a lost friend, sibling or parent?

Wouldn't that be some kind of horrific emotional uncanny valley?

Re: Nvidia Vid2vid: High-resolution photorealistic video-to-video translation

#50

I'm probably being captain obvious here, but if this is what's being released for free, I wonder how much better a polished commercial version does, and when we reach the point where we can't trust anything we see anymore. It doesn't even have to be super perfect, even reaching the point where it takes experts about two weeks to determine if something's real or not might already be long enough to do great damage. Fro…

It could also lead to crimes like Blackmail becoming extinct. It would be hard to hold incriminating recordings of anyone over them if near-perfect audio and video synthesis was common. Especially for public figures with lots training data available.

Yeah... The problem is try explaining deepfakes to your significant other when they are randomly sent what looks like a video of you cheating on them. Sure it’s possible but not likely.
Post reply on HN