Can you still distinguish between real photo and AI image? Prove yourself in the test

Fake photos of Trump or the Pope are going viral on the internet. “Blame” are always better AI image generators, which can be easily used by everyone. Do you recognize the AI ​​photos in this test?

Oliver Wietlisbach

With artificial intelligence (AI) like Midjourney or Microsoft’s Bing Image Creator, even laymen can create any image in no time. A short text description such as “draw a picture of rabbits taking selfies together” yields these four AI-generated images after a few seconds.

Image

Three of the following photos are real and one is made by artificial intelligence. Do you recognize the AI ​​image?

What image has been created by an artificial intelligence?

Image
Image
Image
Image
Surprise

Which dog is fake?

Image
Image
Image
Image
Surprise

Which child doesn’t even exist?

Image
Image
Image
Image
Surprise

Which piece of meat is generated by AI?

Raw tenderloin steaks with herbs and spices on wooden background
Image
Image
Image
Surprise

Which woman only exists virtually?

Image
Image
Image
Image
Surprise

Which tiger should no one be afraid of?

Image
Image
Image
Image
Surprise

In which apartment can’t anyone put their feet up on the sofa?

Image
Image
Image
Image
Surprise

Which chalet will you never find in the Swiss Alps?

Image
Image
Image
Image
Surprise

Which Matterhorn Did Artificial Intelligence Create?

Image
Two dead: a mountain guide and his guest died in an accident on Wednesday.  (archive image)
Image
Image
Surprise

All real photos in the article are courtesy of Shutterstock photography agency. The AI-generated photos were created using the current version 5 of the text-to-image generator Midjourney.

Version 5 is only available in an early alpha version, but some results are already so good they’re barely distinguishable from photos. This is especially true for landscape, food and nature shots. Problems are reported by AI image generators with eyes and hands and objects held by the hands. These are sometimes strangely distorted. With Midjourney in the latest version, this is not perfect either, but it has improved enormously.

AI graphics generated by Midjourney V5.

Professional photographers and artists can use AI tools to create photos and paintings that are much more realistic or creative than our first attempts at Midjourney. A selection of impressive examples can be found here.

Painting generated by Midjourney V5.

If you want to become an AI artist yourself, you can get started with the following text-to-image generators:

  • Bing Image Creator: Free, easy to use, currently supports English input only, based on DALL-E.
  • DALL-E: Offers more options than Bing Image Creator, free version often overloaded, like OpenAI’s ChatGPT.
  • Midjourney: A bit more complicated for beginners, the latest version 5 delivers excellent results, but is currently only available to subscribers, administered via Discord chat.
  • Stable Distribution: Free open source alternative to DALL-E and Midjourney that can be tried here or here without an account. Versions with an account and additional paid features are available here or here.

Oliver Wietlisbach

Source: Watson

follow:
Ella

Ella

I'm Ella Sammie, author specializing in the Technology sector. I have been writing for 24 Instatnt News since 2020, and am passionate about staying up to date with the latest developments in this ever-changing industry.

Related Posts