AI Product Photo Checker
Generated product shots are now cheaper than a photoshoot, which is a problem when the item in the picture does not exist. Check whether a listing image came from a camera before you pay for what it shows.
What fake listing photos have in common
Product imagery is unusually revealing: manufactured objects have rules, and generators break them in consistent ways.
Text that isn't text
Brand names, labels, spec panels and barcodes degrade into letter-shaped forms. On packaging this is immediate and obvious once you look.
Impossible construction
Seams that don't meet, hinges that cannot move, cables entering nowhere, screws in decorative positions.
Lighting without a source
Reflections and shadows that correspond to no lamp in the scene, or a shadow falling the wrong way relative to the highlight.
Materials that drift
A weave, grain or knurl that changes pattern across a single surface — physical materials do not do that.
Studio perfection, no studio
Catalogue-grade lighting on a supposedly casual seller photo, with none of the camera metadata a real shoot leaves behind.
Edited-out defects
Sometimes the photo is real but the damage was removed. That is a manipulation question, and it shows as a region with its own compression history.
How the analysis works
Upload the original file
Full resolution, straight from the source. Screenshots and re-saved copies destroy most of the evidence we measure.
12 independent methods run in parallel
Three neural networks look at the image as a whole. Nine forensic methods examine it as a signal: frequency (FFT) analysis, noise pattern, pixel-level statistics, EXIF metadata, Error Level Analysis, texture coherence, colour distribution, Benford's Law and edge detection.
You see the breakdown, not just a number
Every method reports separately, so you can tell whether the verdict rests on one weak signal or on nine that agree.
For images outside e-commerce, Start with our AI image detector — it covers any image type and runs the same twelve methods.
How much each method counts
Most detectors give you one number from one model. We run twelve independent analyzers and weight them — three neural networks carry the majority, but nine forensic methods examine the file as a signal and can overrule them. Here is the exact weighting we use in production:
| Method | Weight in final score |
|---|---|
| Neural network #2 | 25% |
| Neural network #1 | 15% |
| Neural network #3 | 15% |
| EXIF metadata | 10% |
| Frequency (FFT) | 6% |
| Benford's Law | 6% |
| Noise pattern | 5% |
| Error Level Analysis | 4% |
| Texture coherence | 4% |
| Edge detection | 4% |
| Pixel statistics | 3% |
| Colour distribution | 3% |
What people actually upload
These are our own numbers, not an industry estimate — every check run through FakeSec since launch. The split is closer than most people expect: roughly four in ten uploads really do turn out to be generated.
Who checks listing photos
- Buyers — Before paying for an item that may not exist.
- Marketplaces — Moderating listings at volume — see our API.
- Brands — Counterfeit listings using generated imagery.
- Honest sellers — Proving your own photos are real when disputed.
Accuracy — and where it breaks down
On our internal benchmark of 240,000 images (120,000 AI-generated, 120,000 real) the combined score reaches up to 98% on unedited, full-resolution files. That number drops, sometimes sharply, in four situations — and you should know them before trusting any result:
- Heavy compression. Social platforms re-encode everything. A photo pulled from Instagram has already lost much of its noise signature.
- Screenshots. A screenshot is a new image of an image. Original metadata and compression history are gone.
- Stylised content. Flat colour and clean lines remove the texture and noise evidence forensic methods depend on.
- Post-processing. Added grain, filters, upscaling and manual retouching all mask generation traces.
No detector on the market is 100% accurate — ours included. Treat a high score as strong evidence, not as proof. When a decision matters, look at which of the 12 methods agreed.
Marketplace images are heavily re-compressed by the platform, which weakens the forensic signal. Where possible, ask the seller to send the original file — a refusal is itself informative.
Frequently asked questions
Related tools
Check your first image now
Create a free account and get 3 checks. Full breakdown across all 12 methods, no card required.