Leonardo AI Detector
Leonardo is aimed at game assets and concept art, which puts it in a specific commercial situation: studios, asset marketplaces and clients increasingly require disclosure of generated material, and contracts increasingly say so explicitly.
Checking game art and concept work
Asset and concept art sits between photography and illustration, and that position affects what evidence exists.
Stylised means less signal
Painterly and rendered art carries less of the noise and texture evidence that photographs provide. Confidence is lower here and we say so on the result rather than hiding it.
Detail that does not prioritise
Concept artists direct attention deliberately. Generated pieces distribute rendering effort evenly across the frame.
Design logic that does not hold
Weapons, armour, machinery and architecture in generated art often look right and could not function — straps attaching to nothing, mechanisms that cannot move.
Asset-set inconsistency
A real asset pack shares a coherent style, palette and scale. Generated sets drift between items in ways that show when you view them together.
No layered source
Professional pipelines produce layered files and iterations. Generated work arrives flat, with no working history behind it.
Upscaler traces
Most generation workflows end in an upscaler, leaving a frequency signature detectable even after metadata is gone.
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.
If you do not know which tool produced the image, start with our general 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 this
- Game studios — Assets delivered under contracts requiring original work.
- Asset marketplaces — Store policies on generated content.
- Clients — Concept art commissioned as original.
- Artists — Defending your own portfolio against accusation.
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.
Same honest limitation as all stylised art: confidence is lower than on photographs. For a contractual dispute, layered source files and iteration history settle authorship far better than any detector score, ours included.
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.