Finally a solution for daily standups.
I can pay someone to attend meetings all over the world, by just impersonating me.
Avatarify lets users run realtime deepfakes on live video calls
31–40 of 127 posts
Re: Avatarify lets users run realtime deepfakes on live video calls
#32Theoretically you can deepfake yourself but then be not at the place, just pipe in your voice. Prob be accomplished by linking it to some Twilo API
Re: Avatarify lets users run realtime deepfakes on live video calls
#33Earlier quoted context omitted.
As someone whose tried this repo extensively with politican sound clips (I wanted to troll buddies on discord) - it kinds blows. Don't get me wrong - it's really neat but the results are far less good than one may expect. Sometimes it almost works, and then it's just totally absurd. Long pauses, voices that don't sound compelling, total failures on female voices. It's great in theory but it showed me that there's a t…
Real Time Voice Cloning certainly has iffy output, but it's probably the most popular because it provides the easiest plug-and-play experience with even a simple UI to get started. The author says he's working on a more polished toolkit called Resemble.AI, but I've never tried it. https://www.resemble.ai/ There's certainly a market out there for just beautifying existing repos to making it easier for non-scholars to…
And sometimes it's not even non-scholars, just people from a different, and not even very-different field.
Re: Avatarify lets users run realtime deepfakes on live video calls
#34Hey guys! I'm one of the founders of Impressions, the first mobile deepfake app on a phone. Try it out and give us your thoughts. Right now it's out for IOS but Android is on route. Here's our website https://impressions.app
Re: Avatarify lets users run realtime deepfakes on live video calls
#35Earlier quoted context omitted.
If I understood it correctly, deepfakes are relatively easy to detect by software if you know what you’re looking for. I can imagine video conferencing software can implement this, and display a warning in similar ways that phishing emails are currently handled.
Deepfakes are implemented with Generative Adverserial Networks (GANs), where one component is a discriminative network that is already trying to distinguish real from fake, to provide feedback to the generation. So I think any detection algorithms would get into a never-ending arms race.
The discriminative networks aren't very good at discriminating. I remember hearing people in the field saying they deliberately used under-powered discriminators because they got better generators that way. Was a year or two ago though so who knows if that's still true.
Re: Avatarify lets users run realtime deepfakes on live video calls
#36Earlier quoted context omitted.
If I understood it correctly, deepfakes are relatively easy to detect by software if you know what you’re looking for. I can imagine video conferencing software can implement this, and display a warning in similar ways that phishing emails are currently handled.
Deepfakes are implemented with Generative Adverserial Networks (GANs), where one component is a discriminative network that is already trying to distinguish real from fake, to provide feedback to the generation. So I think any detection algorithms would get into a never-ending arms race.
None of the popular distributions use GANs, except that GANs have been used in experimental (later abandoned) modules. Unfortunately the Deepfake/GAN fallacy has been stuck in the Wikipedia entry for years.
Re: Avatarify lets users run realtime deepfakes on live video calls
#37It would be interesting to see how far you could get using deepfakes as a method for video call compression.
Train a model locally ahead of time and upload it to a server, then whenever you have a call scheduled the model is downloaded in advance by the other participants.
Now, instead of having to send video data, you only have to send a representation of the facial movements so that the recipients can render it on their end. When the tech is a little further along, it should be possible to get good quality video using only a fraction of the bandwidth.
Re: Avatarify lets users run realtime deepfakes on live video calls
#38Earlier quoted context omitted.
As someone whose tried this repo extensively with politican sound clips (I wanted to troll buddies on discord) - it kinds blows. Don't get me wrong - it's really neat but the results are far less good than one may expect. Sometimes it almost works, and then it's just totally absurd. Long pauses, voices that don't sound compelling, total failures on female voices. It's great in theory but it showed me that there's a t…
Real Time Voice Cloning certainly has iffy output, but it's probably the most popular because it provides the easiest plug-and-play experience with even a simple UI to get started. The author says he's working on a more polished toolkit called Resemble.AI, but I've never tried it. https://www.resemble.ai/ There's certainly a market out there for just beautifying existing repos to making it easier for non-scholars to…
See https://www.descript.com/lyrebird-ai for another one with an on-site demo.
Re: Avatarify lets users run realtime deepfakes on live video calls
#39It would be interesting to see how far you could get using deepfakes as a method for video call compression. Train a model locally ahead of time and upload it to a server, then whenever you have a call scheduled the model is downloaded in advance by the other participants. Now, instead of having to send video data, you only have to send a representation of the facial movements so that the recipients can render it on…
Excellent idea and we'll surely be seeing something like this, there are AR apps that already map facial expressions to avatars.
Downside could be some uncanny valley if the models are not very high quality.
But if I had to make a prediction, I'd expect we'll get much more value from higher bandwidth, ultra high definition streaming and features like 3d cameras / virtual reality. I think we have a tendency to really underestimate how important high definition is for human communication.
Re: Avatarify lets users run realtime deepfakes on live video calls
#40It would be interesting to see how far you could get using deepfakes as a method for video call compression. Train a model locally ahead of time and upload it to a server, then whenever you have a call scheduled the model is downloaded in advance by the other participants. Now, instead of having to send video data, you only have to send a representation of the facial movements so that the recipients can render it on…
Very cool idea. The coding used in H264 is a variant of the DCT, so moving one layer of abstraction up from there basically moves from semi-analog to fully digital. I agree that it should only require a fraction of the bandwidth because you'd only be sending parametric data rather than full video.