Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
arstechnica.com
Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
You're viewing a single thread.
71 comments
-
Can we maybe stop making these? XD
-
-
This coming from the guy who turned himself into a fly for fun
-
It’s not his fault earth girls are easy.
-
ask dna doo doo doo doo
-
-
-
-
Like what even is a legitimate use case for these? It just seems tailor made for either misinformation or pointless memes, neither of which seem like a good sales pitch
-
I could see a few uses, but the biggest would probably be advertising. Tailored ads that look like they’re coming from a real person.
Imagine Jake from State Farm addressing you personally about your insurance in an ad.
Not that I endorse advertising, I’d like to see it all banned.
I think it could be useful to humanise some things though and talking to a “person” AI in a video call might be more comfortable for some people wanting to do tasks such as say navigate my mobile phone carriers shitty AI help system.
Really any sort of AI assistant device could benefit from a human imprint.
-
Imagine your dead relative selling you extended warranty for your vehicle.
-
Deepfakes are being used to personalize political messages in India, here's a fun article on it which also points out an instance all the way back from 2020: https://www.aljazeera.com/news/2024/2/20/deepfake-democracy-behind-the-ai-trickery-shaping-indias-2024-elections
It also mentions using deepfakes to target constituencies speaking different languages, to defame opposing parties, and even creating deepfakes to cast doubt on legitimate videos:
Ahead of the state election in November, the caller requested that Jadoun alter a problematic but authentic video of their candidate – whose party he did not disclose – to make a realistic deepfake. The aim: to claim that the original was a deepfake, and the deepfake the original.
-
In Australia they handed out fliers designed to look like an official government department, and targeted Chinese speaking communities who might not notice the difference.
Dodgy politicians will use anything, the solution is to go after them for doing it rather than focusing on the method because they’ll just find another method if they don’t get stopped.
-
-
-
Say you’re a movie studio director making the next big movie with some big name celebs. Filming is in progress, and one of the actor dies in the most on brand way possible. Everyone decides that the film must be finished to honor the actor’s legacy, but how can you film someone who is dead? This technology would enable you to create footage the VFX team can use to lay over top of stand-in actor’s face and provide a better experience for your audience.
I’m sure there are other uses, but this one pops to mind as a very legitimate use case that could’ve benefited from the technology.
-
how can you film someone who is dead?
Hot take: don't? They're dead, leave them dead. Rewrite and reshoot if you really have to.
-
Sure that’s an entirely valid option; but not the one the producing team and the deceased’s family opted for… and they had a much larger say in it than you and I combined.
-
-
We've already recreated dead actors or older actors whole cloth with VFX. Plus it still seems like a niche use case for something that can be done by VFX artists that can also do way more
-
Having done something before doesn’t mean they shouldn’t find ways to make it better though. The “deepfake”-esque techniques can provide much better quality replicas. Not to mention, as resolution demand increases, it would be harder to leverage older assets and techniques to meet the new demands.
Another similar area is what LLM is doing to/for developers. We already have developers, why do we need AI to code? Well, they can help with synthesizing simpler code and freeing up devs to focus on more complicated problems. They can also democratize the ability to develop solutions to non-developers, just like how the deepfake solutions could democratize content creation for non/less-skilled VFX specialists, helping the industry create better content for everyone.
-
They can also democratize the ability to develop solutions to non-developers,
This is insane. If you don't understand everything a piece of code is doing, publishing it is insanely reckless. You absolutely must know how to code to publish acceptable software.
-
Try telling that to businesses. Sadly, you’d more likely to be laughed all the way to the door as opposed to being taken seriously. For the non technical people leading businesses, they’d rather something working 90% of the time today than 100% of the time next week.
-
-
-
-
this is so dystopian. Imagine spending your career honing your skill as an actor, dying and then having a computer replace you with just a photograph as a source. How is that honoring an actor??
An actual, practical example is generating video for VR chats like Apple has somewhat tried to do with their headset. Rather than using the cameras/sensors to generate and animate a 3d model based on you, it could do something more like this, albeit 2d.
-
Gotta crank up that dystopia meter.
This is slowly moving toward having Content On Demand. Imagine being able to prompt your content app for a movie/series you want to watch, and it just makes it and streams it to you.
-
-
Maybe a historical biopic in the style of photos of the time. Like take pictures of Lincoln, Grant, Lee, etc., use voice actors plus modern reenactors for background characters, and build it into a whole movie.
I dunno, I'm probably reaching.
-
-
If they use the speech tech on top of it, you wouldn't even know if you were talking to the person you think you are.
-
-
I think you're falling for the overblown fearmongering headline, and pointless memes is a great reason to make things.
-
Avatars for ugly people who are good at games and want to get into streaming
-
-
71 comments