Inconclusive
Signals are mixed or weak. We can't tell with confidence — context, source, and your own judgement matter here.
Analysed Specimen
Heads up — 4 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.
ML detectors disagree with each other
Note2 models confidently say "AI" (Ml Python Siglip, Ml Commfor) while 2 confidently say "real" (Itsnotai V2, Xrayon Convnext). This image sits at the edge of what ML can decide — manual review is recommended.
Just above the real threshold
NoteThe score (42/100) is between real (40) and inconclusive. There is not enough confidence to call this a clean "real" verdict.
Upsampling artifacts in the frequency domain
AI evidenceFFT analysis found strong upsampling patterns — a fingerprint of diffusion-model VAE decoders (latent → pixel-space upscale).
ML detectors see this image differently
NoteML scores span a wide range (2–94). Different architectures read different feature spaces; the majority vote strengthens the consensus, but no single model is fully reliable here.
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
- INA v2 (FLUX/MJ)read real · 2/100
BEiT-Large dual-head classifier trained on FLUX, Midjourney, and real photo corpora.
- SigLIP AI Detectorflagged AI · 94/100
SigLIP visual-language model probing semantic vs perceptual coherence.
Model Agreement
Variance across 6 ML detectors. Higher agreement means the models converged on the same reading; lower agreement means treat the verdict with care.
Evidence — 16 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 Models6 detectors · mean 45▸ expand▾ collapse
Pixel & Frequency Forensics7 detectors · mean 41▸ expand▾ collapse
Provenance & Metadata3 detectors · mean 54▸ expand▾ collapse
Image Quality
- Dimensions
- 800 × 600 px
- Aspect
- 1.333
- File size
- 44.4 KB
- Bytes / pixel
- 0.095
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: 1.0616 – 20.0530
Noise Fingerprint
- Variance
- 37.50
- Std deviation
- 6.12
- Mean
- -0.0
- Spatial corr.
- 1.538
- Mean Δ
- 1.88
- σ
- 2.66
- CV
- 1.416
- Uniformity
- -0.416