Skip to Content

Become Horrifying With Baidu’s Creepy, Cool Face-Morphing AI App

Baidu Research’s FaceYou app uses facial tracking to blend your face with a zombie’s, and the results are surprisingly good.
October 29, 2015

I don’t have a costume picked out for Halloween yet, but a free iPhone app rolled out on Wednesday by Chinese Internet giant Baidu’s research division makes that unnecessary, at least for sharing creepy photos and videos of myself online. 

A new iPhone app from Baidu Research lets you morph your face with that of a zombie, several presidents, animals, and more.

Called FaceYou, the app takes advantage of face-tracking technology and techniques like image blending to overlay one of several faces–that of a zombie, president, skeleton, pig, or others–on top of your own. When you move your face a bit, change facial expressions, or speak, your digital mask moves in sync with the real you, in real time on your smartphone’s display. You can make photos or videos of yourself looking like, say, a zombie whose face is covered in staple-pinched gashes, and share the results with friends.

A video Baidu made shows off a few of these effects, and they’re pretty impressive. The woman in the clip starts out with a zombie face, then switches to a skeleton, some sort of weird mask, and so on.  

In a quick test, I was surprised by how well a couple of the faces seemed to morph and work with my own. In one case, when I applied a garishly made-up female face, the eye makeup almost looked real, even as I moved my face around and opened and closed my eyes. I found the human faces looked the most believable on me, and the female ones in particular, which isn’t that surprising (I don’t make a very convincing Bill Clinton or pomeranian, apparently). 

If you don’t like any of the included faces, you can take a photo of a face or use one from the snaps in your camera roll. This, I found, makes the whole experience even weirder. Try replacing your face with that of a co-worker or family member and you’ll see what I mean.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.