The Observatory
Detect whether an image was generated via AI or Human.
Inference Backend:
Detecting...
All processing runs locally in your browser
image.png
AI Detection Engine
Loading...
Ateeqq AI vs Human Detector
SigLIP Vision Transformer · 99.23% Accuracy
Fine-tuned on the latest AI generators including Midjourney v6.1, Flux 1.1 Pro, Stable Diffusion 3.5, and GPT-4o image outputs.
WebGPU Accelerated
Detecting...
100% Private
No server upload
Model Size
56 MB ONNX
Analyzing image...
Running detection models
Analysis Complete
Results from browser-based detection
--
Verdict
Ensemble Prediction
Ateeqq AI Detector (99.23% accuracy)
Human
AI
Total Time
--
Avg/Model
--
Individual Model Analysis
Each model's prediction, weight, and training dataMethodology & Interpretation
Understanding ensemble weights and how to read resultsEnsemble Formula
Final = (P₁×W₁ + P₂×W₂ + P₃×W₃) / ΣW
P = AI probability
W = model weight
Model Info
- Ateeqq – 99.23% accuracy, trained on 2024 generators
- Coverage: MJ 6.1, Flux 1.1, SD 3.5, DALL-E 3, GPT-4o, Ideogram 2.0
- Architecture: SigLIP ViT-B/16 (86M params)
Interpretation Guide
- ≥70%: High confidence AI-generated
- 30-70%: Uncertain - may be edited or hybrid
- ≤30%: Likely human-created
- Low confidence: Image may be heavily post-processed
Known Limitations
- Generators released after model training may evade detection
- Heavy post-processing can fool detectors
- Hybrid content (real + AI elements) challenges classification