The ‘creepy’ deepfakes anyone can create: How Deep Nostalgia animates your family photos

Genealogy site MyHeritage uses deep learning technique to bring images to life

MyHeritage: ‘Some people love the Deep Nostalgia feature and consider it magical, while others find it creepy and dislike it.’ Photograph: MyHeritage.com

MyHeritage: ‘Some people love the Deep Nostalgia feature and consider it magical, while others find it creepy and dislike it.’ Photograph: MyHeritage.com

 

Deep Nostalgia, a new service from the genealogy site MyHeritage that animates old family photos, has gone viral on social media, in another example of the way artificial-intelligence-based image manipulation is becoming increasingly mainstream.

Launched in late February, the service uses an AI technique called deep learning to automatically animate faces in photographs uploaded to the system. Because of its ease of use, and free trial, it soon took off on Twitter, where users uploaded animated versions of old family photos, celebrity pictures and even drawings and illustrations.

Like most “deepfakes” – the name for the popular use of this technology to map one person’s face on to footage of another – the service is exceptionally good at smoothly animating features and expressions. But it can struggle to generate data to fill in the “gaps” in what it can see from the source images, causing a sense of the uncanny.

“Some people love the Deep Nostalgia feature and consider it magical, while others find it creepy and dislike it,” MyHeritage says about its technology. “Indeed, the results can be controversial, and it’s hard to stay indifferent to this technology. This feature is intended for nostalgic use, that is, to bring beloved ancestors back to life. Our driver videos don’t include speech in order to prevent abuse of this, such as the creation of deepfake videos of living people.”

Not every video created with the service is elegantly animated, or even good enough to be unsettling, of course. An animated version of the infamous bust of Cristiano Ronaldo, for instance, is exactly as distressing as the static version.

While the automatically produced videos of Deep Nostalgia are not likely to fool anyone into thinking they are real footage, more careful application of the same technology can be difficult to distinguish from reality.

Tom Cruise seems to be a particular subject of choice. In 2019 a video clip went viral of the comedian Bill Hader being morphed into the Hollywood star as he performed an impression on David Letterman’s show.

Last month, a new TikTok account named deeptomcruise racked up millions of views with a series of videos that are, it claims, deepfake versions of the actor talking to camera. The Cruise fakes are so accurate that many programmes designed to recognise manipulated media are unable to spot them. – Guardian

The Irish Times Logo
Commenting on The Irish Times has changed. To comment you must now be an Irish Times subscriber.
SUBSCRIBE
GO BACK
Error Image
The account details entered are not currently associated with an Irish Times subscription. Please subscribe to sign in to comment.
Comment Sign In

Forgot password?
The Irish Times Logo
Thank you
You should receive instructions for resetting your password. When you have reset your password, you can Sign In.
The Irish Times Logo
Please choose a screen name. This name will appear beside any comments you post. Your screen name should follow the standards set out in our community standards.
Screen Name Selection

Hello

Please choose a screen name. This name will appear beside any comments you post. Your screen name should follow the standards set out in our community standards.

The Irish Times Logo
Commenting on The Irish Times has changed. To comment you must now be an Irish Times subscriber.
SUBSCRIBE
Forgot Password
Please enter your email address so we can send you a link to reset your password.

Sign In

Your Comments
We reserve the right to remove any content at any time from this Community, including without limitation if it violates the Community Standards. We ask that you report content that you in good faith believe violates the above rules by clicking the Flag link next to the offending comment or by filling out this form. New comments are only accepted for 3 days from the date of publication.