Just some AI news (Getting better) :D

[Nimos]

Some might remember the video I posted in another thread. Now someone has improved the ability to add voice to them as well, based on a single image.

We proposed EMO, an expressive audio-driven portrait-video generation framework. Input a single reference image and the vocal audio, e.g. talking and singing, our method can generate vocal avatar videos with expressive facial expressions, and various head poses, meanwhile, we can generate videos with any duration depending on the length of input video.

It's difficult not to be impressed by it and wonder what this will be like in 5 years given the speed this is going.

 

[Twilight Hue]

I like historical imagery. Brought to life ....

Spooky stuff.

 

[Nimos]

I like historical imagery. Brought to life ....

Spooky stuff.

There are a lot of interesting things you could do, Im surprised that no one has made Abraham Lincoln or someone speak some of these speeches from back then etc. I would think that would be one of the first things people would do

No matter how you twist and turn it, there are a lot of opportunities with this technology for sure.

 

[Nimos]

Spooky stuff.

Imagine you hook up a dead relative, get a picture and then train an AI on their life, then you could essentially speak to a "fake" version of them in real-time, as if you were on a video call or something.

It would be pretty creepy, but it is very close to where you could actually do it, if not already.

 

[Twilight Hue]

Imagine you hook up a dead relative, get a picture and then train an AI on their life, then you could essentially speak to a "fake" version of them in real-time, as if you were on a video call or something.

It would be pretty creepy, but it is very close to where you could actually do it, if not already.

It's certainly in the realm of possibility.

 

[Twilight Hue]

There are a lot of interesting things you could do, Im surprised that no one has made Abraham Lincoln or someone speak some of these speeches from back then etc. I would think that would be one of the first things people would do

No matter how you twist and turn it, there are a lot of opportunities with this technology for sure.

Looks like someone did that already. An interview!

Although granted, the voice , mindset, and context of the speech would require some creative licensing.

 

[Nimos]

Looks like someone did that already. An interview!

Although granted, the voice , mindset, and context of the speech would require some creative licensing.

Cool, he is a bit stiff in his movement but will get cool once improved