Guide

How to spot an AI generated image

★ 4.1 / 5 from 700 ratings

To tell if a picture is AI generated, check it in this order: where it came from, whether the file carries a provenance label, and only then the visual tells — warped text, odd hands, objects that melt into each other, and light that disagrees with itself. No single tell proves anything. Three or four together usually do.

CAFFE BRAOD & COF
1 Sign with almost-letters 2 Two shadows, two suns 3 Cup handle fused to the hand 4 Window shows a different street 5 Fence rails stop and bend 6 Smudged background figure

The 30-second check

Looks come last. Most fakes are caught by where they came from, not by counting fingers.

  1. Find the first post

    Run a reverse image search (Google Lens or TinEye). If the earliest copy comes from an account that posts nothing but polished pictures, or the “news photo” appears on no news site, you have most of your answer.

  2. Read the file’s history

    Upload the original file to the Content Credentials verify site. Many AI tools and some cameras attach a signed record of how a picture was made. Google’s SynthID check in the Gemini app looks for the invisible signal Google’s AI tools hide in the pixels.

  3. Then zoom in

    Open the largest version you can find and look at the places on the list below. Screenshots and re-uploads blur exactly the details you need.

A missing label proves nothing. Most pictures online have none, and a screenshot strips it. A label that is present is strong evidence; an empty result is not evidence that a picture is real.

The 12 tells, and why they happen

Image models learn what pictures usually look like, not how the world is built. Wherever a detail follows strict rules, the rules are where they break.

01

Text that almost reads

Shop signs, labels, book spines and jersey numbers with letters that are nearly right, or the same word spelled two ways in one picture.

Why: the model draws the shape of writing, not the spelling.

02

Hands and small joints

Count the fingers, then check knuckles, nails and rings. Watch for fingers that merge, bend the wrong way, or vanish behind an object.

Why: hands look different in almost every photo, so the pattern is hard to learn.

03

Things that touch

Glasses arms that sink into hair, straps that end on a shoulder, a cup handle that grows out of a hand, earrings that join the jaw.

Why: where two objects meet, the model has to decide which one is in front.

04

Light that disagrees

Shadows that fall in two directions, a face lit from the left in a room lit from the right, or a person with no shadow on a sunny pavement.

Why: each part looks right on its own; the scene as a whole was never lit.

05

Wrong reflections

Mirrors, windows, sunglasses and puddles that show a different scene, the wrong pose, or nothing at all.

Why: a reflection has to agree with something outside the frame.

06

Skin like polished plastic

Even, poreless skin with a soft sheen, perfect teeth, and hair that shines the same way everywhere.

Why: models drift toward the most “average” flawless face.

07

A melting background

Faces in a crowd that turn into smudges, cars that blend into each other, trees that become texture.

Why: the model spends its detail where you are meant to look.

08

Patterns that break

Tiles, fences, brick, window rows and keyboard keys that skip, double up or bend halfway along.

Why: repeating a pattern exactly needs counting, which models do badly.

09

Pairs that don’t match

Two different earrings, collar points of different shapes, eyes with different reflections in them.

Why: each side is drawn as its own detail.

10

Objects that can’t work

Chairs with an extra leg, a bicycle with no chain, a guitar with the wrong number of strings, a door with no hinge side.

Why: the model knows how a thing looks, not how it is used.

11

The “too good” look

Glowing cinematic light, dead-centre framing, deep background blur on a phone snapshot, and every colour a little richer than life.

Why: models are tuned toward pictures people like, so everything looks like a poster.

12

No second angle

A big moment with one picture and no other photos, no video and no other witnesses. Real events leave a trail.

Why: a generator makes one image; the world makes many.

Run the checklist on your picture

Tick each tell you can actually see. The meter weighs them; it is a guide, not a verdict.

What I can see

Nothing ticked yet. Start with the source.

Free tools that help

ToolWhat it checksGood to know
Content Credentials verifyThe signed record (C2PA) that some AI tools, cameras and editors attach to a fileNeeds the original file; screenshots lose it
SynthID check in GeminiGoogle’s invisible signal in pictures made or edited with Google’s AIOnly finds pictures from tools that add that signal
Reverse image searchWhere else the picture appears, and when it first didThe fastest way to find the original
AI image detectorsA statistical guess from the pixelsWrong both ways often enough to treat as a hint only

The tells are fading. Here is what lasts.

In 2023 a six-fingered hand gave most fakes away. The best 2026 models write clean text on signs and draw hands correctly most of the time, and an edited real photo has real hands to begin with. The visual list above still catches a lot, but it catches less every year.

What does not fade is the trail. A real moment usually leaves several photos from several people. A file made by a mainstream AI tool more and more often carries a label. And an account that appeared last week with a hundred perfect pictures is a story in itself. Check the trail first, and use your eyes to confirm.

Wurt, the Wurt.app mascot

The fastest way to learn the tells: make a few

Wurt.app is a browser app for making pictures and videos with AI. Make a few pictures in Picwurt, then compare them at full size with the list above: you will quickly learn where to look. It is free to start, and after that you pay as you go, with no subscription.

Open Wurt.app

Questions people ask

How can I tell if an image is AI generated?

Work in three steps. Find where the picture first appeared, check the file for Content Credentials or another provenance label, then zoom in on the places AI still slips: text, hands, things that touch, shadows, reflections and background people. One tell is a hint; several together are strong evidence.

Is there a free way to check if a picture is AI?

Yes. The Content Credentials verify site reads the signed history some cameras and AI tools attach to a file, and Google’s SynthID check in the Gemini app looks for the invisible signal Google’s own AI tools add. A reverse image search shows where else the picture appears. All three are free.

If an image has no AI label, is it real?

No. Most pictures online carry no label at all, and a screenshot or a re-upload usually strips the file’s history. A missing label tells you nothing either way; a label that is present is much stronger evidence.

Do AI image detectors work?

They give a statistical guess, not a verdict. They can flag a real photo and miss a new AI picture, especially after it has been resized or compressed. Use a detector as one more signal next to the source, the provenance check and your own close look.

Why do AI images get hands and text wrong?

An image model learns what pictures usually look like, not how a hand is built or how a word is spelled. Small, rule-bound details are the hardest part to get right, so they are where errors show first. Newer models make far fewer of these mistakes, which is why the source and provenance checks matter more every year.

Keep reading