Skip to main content

Stallone in Terminator 2? How one deepfake prankster is changing cinema history

In some parallel universe, there’s a version of Casino Royale with Hugh Jackman playing everyone’s favorite suave British agent, James Bond. And one in which Matthew McConaughey took the Leo role in Titanic. And DiCaprio and Brad Pitt co-starred in Brokeback Mountain. And Saved by the Bell’s Tiffani Thiessen played Rachel in Friends.

Recommended Videos

The entertainment industry isn’t exactly short on “what if?” scenarios in which actors came close to, but were ultimately passed over, playing iconic roles. For more than 99% of movie history, fans have been able to do little more than squirrel away this trivia for use in pop quizzes. That is until the arrival of deepfakes.

Springing to life in the past couple of years, deepfakes use artificial intelligence technology to combine and superimpose new images and videos onto existing source footage using machine learning. That could mean anything from face swaps to mapping one person’s body onto someone else’s movements. The results can be jaw-droppingly realistic, which is why many people rightfully worry about its potential to be used for malicious hoaxes.

Terminator learns how to smile [DeepFake]

One tech enthusiast and movie buff thinks different, though. Operating under the YouTube username “Ctrl Shift Face,” this high-tech Hollywood fan has used deepfake technology to create some astonishing remixes of iconic movie scenes — complete with all new actors. Ever wanted to see The Shining starring Jim Carrey instead of Jack Nicholson? Sly Stallone in Terminator 2: Judgement Day? Heck, he’s even broken with the movie theme by dropping David Bowie into Rick Astley’s infamous song-turned-meme Never Gonna Give You Up.

“The Bowie one is my favorite,” its creator told Digital Trends. “I wanted to Rickroll people and blow them away at the same time. Bowie fitted the role of Rick Astley, and had interesting facial features for a deepfake.”

“The more the network learns, the more detailed the result will be.”

So who exactly is this prankster mogul who can put some of the world’s biggest actors into movies they never actually appeared in with a few clicks of the mouse? He’s not telling. “I don’t want to share my real name really,” Ctrl Shift Face’s creator explained. “It’s not important, I think. I let my work speak for itself.” He did mention a few personal details, such as his age (31), his place of birth (Slovakia, although he no longer lives there), and the fact that his job involves computer graphics on some level.

Ultimately, however, the fact that we don’t know who is behind Ctrl Shift Face raises an important point about the world of deepfakes. No longer confined to a few top Hollywood special effects houses, this kind of smart CGI wizardry is now available to all comers. It’s code that’s freely available online, capable of placing any actor alive or dead into any movie you can think of. No multi-million dollar salary negotiation or air-conditioned trailer conversation necessary!

David Bowie - Training Time Lapse

“I’m not a coder, just a user,” said Ctrl Shift Face’s creator. “I don’t know the details about exactly how the software works. The workflow works like this: You add source and destination videos, then one neural network will detect and extract faces. Some data cleanup and manual extraction is needed. Next, the software analyzes and learns these faces. This step can sometimes take a few days. The more the network learns, the more detailed the result will be. In the final step, you combine these two and the result is your deepfake. There’s sometimes a bit of post-process needed as well.”

The future of fakes

While his favorite video is, as noted, the Bowie one, the one he feels is objectively the best is the Jim Carrey version of The Shining. Placing the face of the actor behind Ace Ventura: Pet Detective on the body of Jack Nicholson shouldn’t work, but it really, really does. “I had the idea to put a comedic actor into a serious dark scene,” he said. “Jim on Jack seemed like a good match.”

In the near future, it’ll be feasible to realistically recreate an actor’s speech using similar training data.

As for his least favorite? Terminator 2’s face swap with Stallone taking the role made famous by Arnold Schwarzenegger. “I guess my videos mirror my sense of humor,” he said. “For T2, there’s this joke from Last Action Hero, where it’s a sort of alternate universe where Sly played the Terminator.” But he doesn’t feel the results entirely worked, due to his choice to edit the audio to incorporate an impressionist doing a Stallone impersonation.

“I wasn’t able to edit it in seamlessly so the background music and ambient sounds have this noticeable jump,” he noted. “My version of the movie had had only 2.1 audio. Later, I realized if I had used 5.1 audio I could separate the audio channels and easily edit the new voice in. Another big regret was that the Bad to the Bone closing song really should have been Eye of the Tiger. It would have been a far better video than it is now.”

The Shining starring Jim Carrey : Episode 1 - Concentration [DeepFake]

He said that he has heard from studios but “I can’t talk details.” That means we don’t know whether the remixes have been held in high regard or the total opposite. Given Hollywood’s enthusiasm about digitally de-aging actors, or even reincarnating deceased ones by putting their heads onto other actors’ bodies, it seems this technology will increasingly find its way into big-budget blockbusters. But it’s less clear if Tinseltown is happy that such tools are available for everyone.

How Deep Fakes Will Make Fake News Worse - The Deets

Things could be about to get even more convincing, too. While the attempt to replace Arnie’s audio on Terminator 2 didn’t work as planned, there are efforts afoot in research labs to pioneer the audio equivalent of deepfakes. That means that, in the near future, it’ll be feasible to realistically recreate an actor’s speech using similar training data.

“That’s out of my expertise,” Ctrl Shift Face’s creator said. “But I may collaborate with people that can do these types of AI voices in the future.”

Luke Dormehl
Former Digital Trends Contributor
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
BYD’s cheap EVs might remain out of Canada too
BYD Han

With Chinese-made electric vehicles facing stiff tariffs in both Europe and America, a stirring question for EV drivers has started to arise: Can the race to make EVs more affordable continue if the world leader is kept out of the race?

China’s BYD, recognized as a global leader in terms of affordability, had to backtrack on plans to reach the U.S. market after the Biden administration in May imposed 100% tariffs on EVs made in China.

Read more
Tesla posts exaggerate self-driving capacity, safety regulators say
Beta of Tesla's FSD in a car.

The National Highway Traffic Safety Administration (NHTSA) is concerned that Tesla’s use of social media and its website makes false promises about the automaker’s full-self driving (FSD) software.
The warning dates back from May, but was made public in an email to Tesla released on November 8.
The NHTSA opened an investigation in October into 2.4 million Tesla vehicles equipped with the FSD software, following three reported collisions and a fatal crash. The investigation centers on FSD’s ability to perform in “relatively common” reduced visibility conditions, such as sun glare, fog, and airborne dust.
In these instances, it appears that “the driver may not be aware that he or she is responsible” to make appropriate operational selections, or “fully understand” the nuances of the system, NHTSA said.
Meanwhile, “Tesla’s X (Twitter) account has reposted or endorsed postings that exhibit disengaged driver behavior,” Gregory Magno, the NHTSA’s vehicle defects chief investigator, wrote to Tesla in an email.
The postings, which included reposted YouTube videos, may encourage viewers to see FSD-supervised as a “Robotaxi” instead of a partially automated, driver-assist system that requires “persistent attention and intermittent intervention by the driver,” Magno said.
In one of a number of Tesla posts on X, the social media platform owned by Tesla CEO Elon Musk, a driver was seen using FSD to reach a hospital while undergoing a heart attack. In another post, a driver said he had used FSD for a 50-minute ride home. Meanwhile, third-party comments on the posts promoted the advantages of using FSD while under the influence of alcohol or when tired, NHTSA said.
Tesla’s official website also promotes conflicting messaging on the capabilities of the FSD software, the regulator said.
NHTSA has requested that Tesla revisit its communications to ensure its messaging remains consistent with FSD’s approved instructions, namely that the software provides only a driver assist/support system requiring drivers to remain vigilant and maintain constant readiness to intervene in driving.
Tesla last month unveiled the Cybercab, an autonomous-driving EV with no steering wheel or pedals. The vehicle has been promoted as a robotaxi, a self-driving vehicle operated as part of a ride-paying service, such as the one already offered by Alphabet-owned Waymo.
But Tesla’s self-driving technology has remained under the scrutiny of regulators. FSD relies on multiple onboard cameras to feed machine-learning models that, in turn, help the car make decisions based on what it sees.
Meanwhile, Waymo’s technology relies on premapped roads, sensors, cameras, radar, and lidar (a laser-light radar), which might be very costly, but has met the approval of safety regulators.

Read more
Waymo, Nexar present AI-based study to protect ‘vulnerable’ road users
waymo data vulnerable road users ml still  1 ea18c3

Robotaxi operator Waymo says its partnership with Nexar, a machine-learning tech firm dedicated to improving road safety, has yielded the largest dataset of its kind in the U.S., which will help inform the driving of its own automated vehicles.

As part of its latest research with Nexar, Waymo has reconstructed hundreds of crashes involving what it calls ‘vulnerable road users’ (VRUs), such as pedestrians walking through crosswalks, biyclists in city streets, or high-speed motorcycle riders on highways.

Read more