11–20 of 127 posts
I’m sure we will see more and more of this. One question is when they get so good, how can people figure out that it’s a deep fake or a real human? Will we have captchas for videos soon ? sigh
Good question, maybe sign your videos with a key? Or perhaps another neural network to distinguish the real from the fake?
It betrays that it's a fake, which I think makes it easier to be a fun joke.
Once the pandemic is over, I'm never using Zoom again anyway.
Voice fake has been done already as well. https://github.com/CorentinJ/Real-Time-Voice-Cloning
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 ton of work to be done with voice cloning.
Props to the author for using UMAP to seperates voices though
Also lol at the demand being so high that there are open issues of people offering to pay others to install this on their machine. Freelancing opportunities show up in the strangest of places...
I’m sure we will see more and more of this. One question is when they get so good, how can people figure out that it’s a deep fake or a real human? Will we have captchas for videos soon ? sigh
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.
So I think any detection algorithms would get into a never-ending arms race.
I’m sure we will see more and more of this. One question is when they get so good, how can people figure out that it’s a deep fake or a real human? Will we have captchas for videos soon ? sigh
Good question, maybe sign your videos with a key? Or perhaps another neural network to distinguish the real from the fake?
Couldn't I just wear an N-95 mask? Once the pandemic is over, I'm never using Zoom again anyway.
The way that the mouth and eyes move, but that the rest of the face is pretty static, is actually really charming to me. It betrays that it's a fake, which I think makes it easier to be a fun joke.
Original repo code that Avatarify is based on called First Order Model: https://github.com/AliaksandrSiarohin/first-order-model
Short video demonstrating First Order Model: https://www.youtube.com/watch?v=mUfJOQKdtAk
The way that the mouth and eyes move, but that the rest of the face is pretty static, is actually really charming to me. It betrays that it's a fake, which I think makes it easier to be a fun joke.
“My internet speed is very low. I know the video is choppy”.