Exclusive: Here’s what AI thinks these iconic ‘gone too soon’ celebrities, including Tupac, would look like if they had lived to be 80 years old – do YOU recognize them?

>

Rap legend Tupac Shakur, soulful English singer-songwriter Amy Winehouse and many other beloved, “once in a lifetime” talents were tragically robbed of their full lives to share their talents with the world.

But DailyMail.com wondered what some of these icons would have looked like had they lived out their golden years.

So we turned on image-making artificial intelligence (AI) Midjourney to help imagine what these stars might look like at age 80.

The results were unusual and strange, as would be expected from a machine that shows snapshots from an alternate dimension of what might have been.

Scroll down to see if you recognize these famous characters in their AI-induced aging. The results may surprise you.

Midjourney’s answer to what 80-year-old Tupac might look like

American rapper and actor Tupac Shakur was killed in a shooting accident, a case that has remained unsolved for 27 years, although an arrest was made in the case on Friday.

Tupac Shakur

Tupac Shakur is remembered today for his poignant hits like “Changes” and “Dear Mama,” his social activism and the enduring mystery surrounding his motives for the 1996 murder.

Shakur was only 25 years old when he was shot four times in the chest on September 7, 1996 in Las Vegas. The rap icon died of complications from those wounds about a week later, on September 13.

Although decades have passed without any major developments regarding his death, Duane “Keefe D” Davis He was arrested Friday and charged with murder with a deadly weapon.

Would Amy Winehouse have kept her famous “Beehive” if she had lived to become the grand dame of pop music? Midjourney seemed to think so, even as the AI ​​dramatically revised the tattoo on the singer’s sleeve

Above, Amy Winehouse at the 2007 Elle Style Awards in London

Amy bar

Amy Winehouse was 27 when she was found dead in her home in Camden, north London, the victim of acute alcohol poisoning.

The Grammy Award-winning artist behind “Back to Black,” “Stronger Than Me,” and “Rehab” has faced her demons through her pop art as well as through her own attempts to regain her sobriety.

Some who knew her blame it not only on the pressures of fame, but also on pressure exacerbated by the demands of her record company’s upper management.

As her childhood friend Tyler James explained in his harrowing account of the singer’s final weeks, he believes Winehouse’s managers played a dangerous role in her death, pressuring her to continue working while she battled her demons.

Would Winehouse have kept her iconic beehive updo, had she lived to become a grand dame of pop?

Midjourney seemed to think so, even as the AI ​​dramatically revised the tattoo on the singer’s sleeve.

If he lived, Midjourney’s AI imagines comedian Chris Farley would retain his glam and hair color well into his 80s

Chris Farley (right) in 1993, with his friend and fellow SNL cast member Chris Rock during the 65th Annual Academy Awards – Elton John AIDS Foundation Gala in Los Angeles

Chris Farley

Sketch comedy legend Chris Farley was still in the process of transitioning from Saturday Night Live performer to comedy mainstay when a drug overdose took his life on December 18, 1997.

Farley was 33 years old.

DailyMail.com asked for a “realistic picture of what comedian Chris Farley would look like as an 80-year-old man”. Had he lived, Midjourney’s AI imagines the comedian would have retained his luster and hair color well into his 80s.

As a nod to NBC Studios, the request added “Radio City Music Hall” as “in the background behind him,” which apparently confused the AI ​​image maker into producing what looked like a generic New York background.

DailyMail.com requested a realistic, “artistic-looking” image of what “celebrity, actor and Knight’s Tale star Heath Ledger would look like as an 80-year-old man”.

This March 5, 2006 file photo shows Australian actor Heath Ledger arriving for the 78th Academy Awards at the Kodak Theater in Hollywood.

Heath Ledger

It’s been 15 years since Heath Ledger died at the age of 28 after an overdose.

While the actor who played the Joker in The Dark Knight and the cowboy in Brokeback Mountain was broadcasting his range as an actor, Ledger struggled with insomnia and anxiety in his final days, his friends and family said.

DailyMail.com requested a realistic, “artistic-looking” image of what “celebrity, actor and Knight’s Tale star Heath Ledger would look like as an 80-year-old man”.

Mr. Ledger, according to the prompt, should be “sitting in a convertible parked in Los Angeles at dusk.”

Artificial intelligence (AI) software Midjourney creates images from simple text prompts

Midjourney’s AI-based technology allows images to be generated from simple text prompts.

Over the past year, there has been an increase in text-to-image generators amid the broader rise of generative AI, which supports software that creates text, sounds, or images based on the data it is fed.

Using technology, users enter prompts, ranging from simple tasks, such as drawing a dog, to silly tasks, such as presenting an object in an environment or shape in which it would not normally appear.

The program then creates the image in the form of a photorealistic photo or a professional painting.

This technology takes billions of images from all over the Internet, and identifies patterns between the image and the text words that accompany it.

How to spot deep fakes

1. Abnormal eye movement. Eye movements that don’t appear normal — or lack of eye movement, such as the absence of blinking — are big red flags. It is difficult to replicate the eyelash process in a way that looks natural. It is also difficult to replicate a real person’s eye movements. This is because someone’s eyes usually follow the person they are talking to.

2. Unnatural facial expressions. When something doesn’t look right in the face, it may indicate facial change. This happens when one image is superimposed on top of another.

3. Awkwardly positioned facial features. If someone’s face is pointing one way and their nose is pointing another, you should be skeptical about the authenticity of the video.

4. Lack of emotion. You can also detect what’s known as “facial morphing” or image merging if someone’s face isn’t showing the emotions it should be in line with what they’re supposed to be saying.

5. Inappropriate body appearance or posture. Another sign is that the person’s body shape does not appear normal, or there is a strange or asymmetrical position of the head and body. This may be one of the easiest inconsistencies to spot, because deepfakes typically focus on facial features rather than the entire body.

6. Abnormal body movement or body shape. If someone looks distorted or skewed when they turn to the side or move their head, or their movements are jerky and disjointed from frame to frame, you should suspect the video is fake.

7. Abnormal coloring. Unnatural skin tone, discoloration, strange lighting, and misplaced shadows are all signs that what you’re seeing is likely fake.

8. Hair that doesn’t look real. You will not see frizzy or frizzy hair. Why? Fake images will not be able to generate these individual characteristics.

9. Teeth that don’t look real. Algorithms may not be able to generate individual teeth, so the absence of outlines of individual teeth could be a clue.

10. The image is unclear or distorted. If the edges of photos are blurry or visual elements are out of alignment — for example, where someone’s face and neck meet their body — you’ll know something’s not right.

11. Noise or inconsistent sound. Deepfake creators usually spend more time on video images rather than audio. The result can be poor lip syncing, robotic voices, strange word pronunciations, digital background noise, or even the absence of sound.

12. Images that look unnatural when slowed down. If you’re watching a video on a screen larger than your smartphone or have video editing software that can slow down video playback, you can zoom in on the images and examine them more closely. For example, zooming in on the lips will help you tell if they’re really talking or if their lip sync is bad.

13. Hashtag contradictions. There is an encryption algorithm that helps video creators show that their videos are authentic. The algorithm is used to insert hashtags at specific places throughout the video. If the hashtags change, you should suspect video tampering.

14. Digital fingerprints. Blockchain technology can also create a digital fingerprint for videos. Although this blockchain-based verification is not foolproof, it can help prove the authenticity of the video. Here’s how it works. When you create a video, the content is recorded in a ledger that cannot be changed. This technique can help prove the authenticity of a video.

15. Reverse image searches. An original image search, or a computer-assisted reverse image search, can discover similar videos online to help determine if the image, audio or video has been altered in any way. Although reverse video search technology is not yet available to the general public, investing in a tool like this could be worthwhile.

(tags for translation) Daily Mail

Related Post