Video & image tools · Free online tool

AI Image Detector

Check an image for AI-generation signals, compare detector results, and inspect its recorded metadata.

Check an image

Drop an image here

or choose one from your device

JPG, PNG or WebP · Up to 12 MB

How to use the AI Image Detector

  1. 01

    Choose, drop, or paste a JPG, PNG, or WebP image.

  2. 02

    Select Check image and review the detector results.

  3. 03

    Explore the findings and available generator matches, then compare them with the original source.

01

Three kinds of evidence, kept separate

A model response, a generator comparison, and recorded metadata answer different questions.

AI-generation signals

Compare three model outputs and the overall result. A nonzero output on a real photo is possible; the number is not a probability that the photo is fake.

Conditional generator matches

For supported high-signal results, compare trained generator classes and families. A top match is relative to known options, not proof of which service created the image.

Recorded file evidence

Inspect selected camera fields, timestamps, software markers, generation settings, and Content Credentials presence. These are observed file data, with their verification limits stated.

02

Read the result without turning a score into a verdict

  • An output of 30/100 is a model response. It does not mean 30% of the picture is artificial or a measured 30% chance that it is generated.
  • Generator comparisons apply to the classes represented in the attribution model. An unfamiliar generator may resemble one of those classes.
  • Model outputs cannot verify the caption, photographer, publication date, or event depicted in an image.
  • The separate face check uses historical face-swap and face-reenactment models. No detected face and a face that could not be assessed are different outcomes; neither receives an invented zero score.

Swipe or scroll sideways to see every column →

ResultMeaningUseful next step
No clear AI-generation signalThe checks did not establish a strong overall AI-generation signal.Review the source. This does not certify a photograph as authentic or unedited.
InconclusiveThe signals are intermediate, disagree, or do not support a clear classification.Keep the distinction unresolved; do not choose whichever output confirms an assumption.
AI-generation signals foundThe model comparison or recorded evidence supports further scrutiny.Inspect the findings and conditional generator comparison, then seek independent evidence.
03

What the file itself can tell you

Camera fields, software names, and credentials can add context to the detector results.

  • Recorded orientation can change an image's displayed dimensions. File details show the orientation and displayed width and height.
  • Image patches used for generator classification are samples, not an edit-location heatmap.

Swipe or scroll sideways to see every column →

Observed dataWhat it supportsWhat it does not prove
Camera fields or capture timestampThe file records those values.That the values are genuine or that the pixels came directly from that camera.
Recognized AI software or workflow metadataThe metadata names a tool or contains a recognized generation-settings structure.That the metadata is original or that every pixel was generated by that tool.
Content Credentials containerA recognized container is embedded in the file.A valid signature or verified provenance chain; those are not validated here.
No recognized AI metadataThe inspected fields contain no recognized markers.That AI was not used. Exports and social platforms can remove metadata.
04

Choose a useful file to analyze

Use the closest available copy of the original. Screenshots add interface elements, while repeated exports can alter signals and remove metadata.

  • One megapixel is one million pixels. Multiply width by height to compare with the 24-megapixel limit.
  • The file limit is 12 MiB, or 12,582,912 bytes. File size and pixel dimensions must both fit.
  • Changing a filename extension does not convert an image. Use an image editor's export or save-as function.

Swipe or scroll sideways to see every column →

FileFits the limits?What to consider
JPG, 4,000 × 3,000 pixels, 4 MiBYes: 12 megapixelsNo resizing is needed to meet these limits.
WebP, 8,000 × 4,000 pixels, 2 MiBNo: 32 megapixelsThe pixel limit applies even when compression makes the file small.
PNG, 3,000 × 2,000 pixels, 14 MiBNo: over 12 MiBExport a smaller copy if necessary; the new file may produce different outputs.
HEIC image from a phoneNo: unsupported formatExport a JPG, PNG, or WebP copy. Keep the original for reference.
05

Before you share an image or its result

Find the original

Look for the original post or image file. Screenshots and repeated exports can remove useful context.

Compare the evidence

Read the overall signal alongside individual detector outputs and recorded metadata. Keep disagreements unresolved.

Check the context

Verify the caption, date, and source separately. An image detector cannot confirm that an event happened as described.

Frequently asked questions

How do I check whether an image is AI-generated?

Choose a supported image and select Check image. The tool compares three model outputs and inspects selected metadata. It reports no clear AI-generation signal, an inconclusive result, or AI-generation signals found. None of these is proof of how the image was made.

Does 30/100 mean a 30% chance that my photo is AI-generated?

No. Model outputs are not calibrated probabilities, accuracy ratings, or percentages of edited pixels. A genuine camera photo can produce a nonzero output. The overall signal and individual outputs are shown separately so a single number is not treated as a verdict.

What does an inconclusive result mean?

The available model signals do not support a clear conclusion under this tool's decision rules. Models may disagree or return intermediate outputs. Keep the result unresolved and review the original file and independent evidence.

Can it identify which AI generator was used?

When the overall AI-generation signal is high and attribution is available, the tool shows relative matches to the generator families and 27 generator classes represented in its attribution model. This is a conditional comparison, not verified identification. It cannot reliably name a generator outside its trained set. Other results show no reliable generator attribution.

What reasons does the result provide?

The findings compare model outputs and report evidence recorded in the file, such as camera fields, software markers, or a Content Credentials container. They do not identify which pixels were edited or prove how the image was made.

Do camera metadata or Content Credentials prove that an image is real?

No. EXIF camera fields, timestamps, and software names can be edited or removed. This tool detects recognized Content Credentials containers but does not verify their signatures or claims. Missing credentials or AI metadata do not establish authenticity either.

Which formats and sizes are supported?

Use a still JPG/JPEG, PNG, or WebP up to 12 MiB and 24 megapixels. Images must be at least 64 × 64 pixels and no more than 16,384 pixels on either side. HEIC, GIF, SVG, animated PNG/WebP, and video files are not supported.

Can I check screenshots, edited photos, or face swaps?

Supported screenshots and edited photos can be checked, but cropping, compression, overlays, and editing can affect the outputs. A separate face check uses models trained on historical face-swap and face-reenactment data when a face can be assessed. It is not a universal detector of modern face manipulation and does not affect the overall AI-generation result. Use the closest available copy of the original.

← Explore all free tools