Probably real
More signals lean toward real than AI, but some give weaker readings. Worth a second look on close inspection.
Analysed Specimen
Heads up — 3 things to know
Why this analysis might be off
We highlight every disagreement and unusual signal we found so you can judge for yourself. Stronger warnings come first; informational notes are at the bottom.
Multiple detectors unreachable
Note2 ML detectors did not respond (Ml Python Siglip, Ml Commfor). The verdict was computed with reduced evidence; reliability is lower than usual.
Upsampling artifacts in the frequency domain
AI evidenceFFT analysis found strong upsampling patterns — a fingerprint of diffusion-model VAE decoders (latent → pixel-space upscale).
Weak overall confidence
NoteAggregate verdict confidence is 30/100. Several detectors returned uncertain answers or were offline. Read the verdict as a guideline, not as a final answer.
Origin Check
Trace this image elsewhere
Cross-reference the source against major reverse-image services. Each link opens in a new tab with the image URL preloaded — ZONN.ai does not re-upload the image.
Google Lens
Yandex
TinEye
Bing VisualWhy this verdict
- Noise Patternflagged AI · 94/100
Sensor-noise (PRNU) fingerprint check. Real cameras leave camera-unique noise.
- Frequency Analysisflagged AI · 73/100
Fast-Fourier inspection. Diffusion outputs leave periodic spectral peaks.
Model Agreement
Variance across 2 ML detectors. Higher agreement means the models converged on the same reading; lower agreement means treat the verdict with care.
Evidence — 12 detectors reviewed
What each detector saw
Each detector independently gave this imagea score from 0 (definitely real) to 100 (definitely AI). The score above is their weighted consensus — detectors with higher confidence count more. No single detector decides; you read the spread.
ML Models2 detectors · mean 50▸ expand▾ collapse
Pixel & Frequency Forensics7 detectors · mean 55▸ expand▾ collapse
Provenance & Metadata3 detectors · mean 54▸ expand▾ collapse
Image Quality
- Dimensions
- 800 × 800 px
- Aspect
- 1.000
- File size
- 69.4 KB
- Bytes / pixel
- 0.111
Frequency Analysis
Edge Consistency
Per-region edge density (4 × 4 grid). Uneven distribution may indicate localized editing or splicing; uniform fields are typical of fully synthetic outputs.
Range: 1.5897 – 6.5502
Noise Fingerprint
- Variance
- 10.20
- Std deviation
- 3.19
- Mean
- 0.0
- Spatial corr.
- 0.855
- Mean Δ
- 0.99
- σ
- 0.98
- CV
- 0.992
- Uniformity
- 0.008