AI-Generated or Real? 8 Ways to Spot the Difference

AI-generated images are becoming increasingly realistic, making it harder to distinguish them from real photos. However, even the most advanced neural networks still struggle with certain details. By knowing what to look for, you can spot AI-generated images with ease. Here are some key tricks to help you identify them.

Why telling AI-generated images from real ones at all?

Photo hoaxes appeared long before the advent of artificial intelligence. But if earlier only a professional could change a photo or add non-existent details with the help of photo editing and retouching, now anyone can get the desired photo by simply setting certain parameters to the program. At first glance, there is nothing wrong with this: many people are just having fun.

But some unscrupulous people use artificial intelligence to create fake profiles in social networks or publish fake photos and videos of celebrities. This is how they try to influence public opinion or swindle users out of money. Therefore, it is especially important today to be able to distinguish real pictures from fake ones.

This is not an easy task, as artificial intelligence is constantly evolving and the quality of the images it creates is steadily increasing. A recent study showed that only 61% of people are able to distinguish an image created by AI from a real photo.

Errors in the fingers and the eyes.

AI generates images by using all available photos on the web and their text descriptions. Although neural networks are constantly improving, a real photo can still be distinguished from a generated image by small details.

For example, it is still difficult for AI to draw pupils and earlobes. These elements are usually difficult to see in most real photos, so they are often deformed or blurred in the generated images.

Besides, AI is not too good at drawing hands yet. Often a generated image can be easily identified by simply counting the fingers. But even if the neural network doesn’t make a mistake in the number, the nails in the image often look unnatural, and the fingers themselves seem too long, short or just look strange.

This is due to the fact that in real photos, the hands are not always in the focus of the camera. Although the latest versions of some software have already learnt to correct these errors, so you should not rely only on this parameter.

Texture and pattern repetition.

AI sometimes struggles with complex textures or patterns, leading to noticeable repetition or awkward transitions. Unnatural patterns in textures like hair, skin, clothing, or background elements can be a giveaway.

A real painting can be easily distinguished from an image created by an AI if you look closely at the surface of the canvas. Although AI does a good job at imitating strokes and copying the author’s artistic style, it can’t draw cracks in the paint and other traces of time.

Background anomalies.

Backgrounds in AI images can be a giveaway. Many are overly simplistic, overly complex, or contain elements that don’t belong. Pay attention to the background as much as the main subject

Little details.

Artificial intelligence can be used to create images of historical documents and artifacts. But even though these pictures look quite authentic at first glance, they are betrayed by small details. For example, AI doesn’t always “age” exhibits and doesn’t draw creases and folds on them. In addition, some historical outfits, as well as inscriptions and hieroglyphs, may look too imaginative.

Inconsistent lighting and shadows.

Neural networks sometimes incorrectly place the light source or make mistakes when drawing shadows. If, after careful examination of the image, you notice that the objects in the picture cast shadows in different directions or reflections look unnatural, you are most likely looking at an AI-generated image.

AI has already learnt to draw food so deliciously that most consumers prefer generated images to real photos. And given that neural networks tend to portray food as more calorific, researchers have already started to sound the alarm.

Often, the footage created by AI looks too perfect. The surface of the water seems unrealistically smooth, and the leaves on the trees are strikingly bright. However, if you take a closer look, you will notice that reflections in the water follow the contours of buildings incorrectly, and the light falls on tree branches at a strange angle.

The more people in the image, the more errors there are.

If AI copes well with the image of one character, the need to place 2 characters in the picture may confuse the program. As a result, the limbs in the created picture start to grow into each other, while accessories look strange. While generating people in the background, AI can use the same figure several times. These signs can also help to distinguish a generated picture from a real one.

AI often makes mistakes when placing objects.

Since artificial intelligence is not familiar with the laws of physics, it can make mistakes in some details. As a result, in generated images, soft objects will look hard, hands will grow into food and cups, and bags will exist separately from the hands that carry them.

Use of reverse image search tools.

Utilize reverse image search engines like TinEye to trace the origin of a suspicious image. These tools can help determine if an image has been artificially generated or altered.

AI-generated images are becoming more convincing, but they still have flaws that can reveal their true nature. By using these tips, you can improve your skills.