Serving up this steaming pile of
Celebrity Gossip
Gay Politics
Gay News
and Pointless Bitchery
Since 1995

Hello and thank you for being a DL contributor. We are changing the login scheme for contributors for simpler login and to better support using multiple devices. Please click here to update your account with a username and password.

Hello. Some features on this site require registration. Please click here to register for free.

Hello and thank you for registering. Please complete the process by verifying your email address. If you can't find the email you can resend it here.

Hello. Some features on this site require a subscription. Please click here to get full access and no ads for $1.99 or less per month.

This Person Does Not Exist.

The link below uses AI to generate human faces that don't exist. Follow the link and just refresh the page to generate a new face!

The next 10 years are going to destroy models, actors, and criminal forensics as AI and Machine Learning have been getting exponentially better at creating human faces. Artificially created, photo-realistic pictures and videos are going to fuck with what people perceive as real or fake.

Offsite Link
by Anonymousreply 2207/31/2020

Malformed faces sometimes show up in the periphery of the images. It’s fucking creepy.

by Anonymousreply 107/31/2020

Yea, the algorithms are not perfect.... yet, but they are constantly improving. The usual tell tale signs at this point that it is fake are the periphery of the image that you mention, eyes, hairlines, and teeth.

Again, if this is what they can do now, imagine it in 10 years.

by Anonymousreply 207/31/2020

Wow, just wow.

by Anonymousreply 307/31/2020

This is cool, OP. thanks!

by Anonymousreply 407/31/2020

They look more real than some famous like certain CEOs or presidents

by Anonymousreply 507/31/2020

How do they know those faces don't exist? Have they seen all the billions of faces that exist?

by Anonymousreply 607/31/2020

Well, R6 even though the 7.8 billion people on the planet SEEMS like a large number, the mathematical permutations and combinations that can be done with a person's face based on human facial features is a trillion trillion trillion times more.

When you get into large numbers like that, coming across an identical face, even with 7.8 billion real people, is statistically unlikely.

Offsite Link
by Anonymousreply 707/31/2020

The image is not real. Period, if someone looks like it, that's another thing.

by Anonymousreply 807/31/2020

Whoa. Some of them look very real. I’m scared.

by Anonymousreply 907/31/2020

R1, like this one!

I think it does a better job with female faces.

Offsite Link
by Anonymousreply 1007/31/2020

Yes, it seems biased to generate a lot of female and children's faces not sure why tho....

R9 you should be scared!

by Anonymousreply 1107/31/2020

Here’s another mutant.

Offsite Link
by Anonymousreply 1207/31/2020

And some dissolving eyeglasses.

Offsite Link
by Anonymousreply 1307/31/2020

Oh my god, I could do this all night.

Offsite Link
by Anonymousreply 1407/31/2020

Just one more. This one is freaking me out, man.

Offsite Link
by Anonymousreply 1507/31/2020

LOL! R12 - R15

Behold our future!

by Anonymousreply 1607/31/2020

So what I’m gathering is that the faces are pretty well symmetrical and regular. There don’t seem to be any real irregularities that I see in people I know. Like a long philtrum or a scar on the eyebrow (it’s very common!) or a hooked nose.

But the faces are mostly believable. The hair and some of the coloring. I’m trying to poke holes in this thing, because I’m actually alarmed at how real some of them look.

by Anonymousreply 1707/31/2020

it only generates ugly people? If it can't make hot ones what's the point?

by Anonymousreply 1807/31/2020

THE CAT ONES!

Offsite Link
by Anonymousreply 1907/31/2020

As the kids say “this thing is cursed!”

by Anonymousreply 2007/31/2020

Scruffy!

Offsite Link
by Anonymousreply 2107/31/2020

Haha I didn't even see the cat ones! But this is a common problem for machine learning algorithms. Shape and colors that look very similar confuse the algorithm.

A common example used to test the robustness of the algorithms is whether they can tell the difference between a dog or bagel.

Offsite Link
by Anonymousreply 2207/31/2020
Loading
Need more help? Click Here.

Yes indeed, we too use "cookies." Don't you just LOVE clicking on these things on every single site you visit? I know we do! You can thank the EU parliament for making everyone in the world click on these pointless things while changing absolutely nothing. If you are interested you can take a look at our privacy/terms or if you just want to see the damn site without all this bureaucratic nonsense, click ACCEPT and we'll set a dreaded cookie to make it go away. Otherwise, you'll just have to find some other site for your pointless bitchery needs.

×

Become a contributor - post when you want with no ads!