Flux Detector
Flux has open weights, which means most of its output is produced on someone's own machine. No hosted service, no Content Credentials, often no metadata whatsoever. What is left is the pixels — and they still carry the signature.
Why open models are the harder case
Hosted generators can be made to sign their output. Open weights running locally cannot — nobody is in a position to enforce it.
No provenance to check
No Content Credentials, no service-side watermark, frequently no metadata at all. The shortcuts that work on DALL·E and Firefly are unavailable.
Local pipelines leave their own traces
Flux is usually run through ComfyUI, which often embeds the workflow in the PNG. When present, that settles it — check with our free EXIF viewer first.
Photorealism is the point
Flux is strong at photographic output, which is precisely the category our models handle best.
Sensor noise still missing
No camera means no sensor noise. What noise exists is statistically flat, and our noise analyzer measures that directly.
Frequency signature
Diffusion leaves a characteristic distribution in the frequency domain that survives compression better than most other evidence.
Fine detail without decay
Detail density stays constant across the frame instead of falling away from the focal point, as an optical system would produce.
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.
Not sure which model you are looking at? 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 runs into Flux output
- Stock buyers — Photorealistic images offered as photography.
- Platforms — Open models are what most volume generation uses.
- Clients — Commissioned work delivered as original photography.
- Moderators — Community rules on generated submissions.
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.
Photorealistic output is our strongest case, which happens to be where Flux is used most. The absence of metadata does not hurt us much — nine of the twelve methods never looked at metadata anyway.
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.