Downloads · 30 days
0
verifai-models
canemirbora/verifai-models
verifai-models is a image classification model from canemirbora. Use it when you need a label for an image. The card lists the license as mit.
Pre-trained model weights for VerifAI - AI-Generated Media Detector.
Access
Public
Updated Jan 28, 2026
Repo size
2.9 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt2.1 MB · 73%
At a glance
- Task
- Image Classification
- License
- mit
- Access
- Public
- Created
- Jan 28, 2026
- Updated
- Jan 28, 2026
- SHA
- 0d3f500c
Model card
From the Hugging Face model README
VerifAI Model Weights
Pre-trained model weights for VerifAI - AI-Generated Media Detector.
AI-Generated Media Detector — Detect AI-generated images and videos with calibrated confidence scores, localized evidence, and robustness evaluation.
Files
| File | Size | Description |
|---|---|---|
modern_ai_detector.pt | 2.0 MB | CLIP ViT-L/14 classification head |
frequency_classifier.joblib | 774 KB | Gradient Boosting frequency classifier |
Performance
| Dataset | Real Acc | Fake Acc | Overall |
|---|---|---|---|
| Defactify (SD3, SDXL, DALL-E 3, MidJourney) | 97.0% | 100.0% | 98.5% |
| COCO_AI (SD, FLUX, Ideogram) | 92.5% | 98.5% | 95.5% |
| Average | 94.8% | 99.2% | 97.0% |
Usage
from verifai import VerifAI
# Weights are downloaded automatically
detector = VerifAI()
result = detector.detect("image.jpg")
print(f"Label: {result.label}")
print(f"Confidence: {result.confidence:.1%}")
Architecture
Fusion Detector = CLIP (80%) + Frequency (20%)
- CLIP Head: 768 → 512 → 256 → 2 with LayerNorm, GELU, Dropout
- Frequency Classifier: GradientBoostingClassifier on FFT/DCT features
Training
Trained on:
- Defactify Dataset - Modern AI generators
- VCT² COCO_AI - COCO + AI variants
License
MIT License
- Task
- Image Classification
- License
- mit
- Created
- Jan 28, 2026
- Updated
- Jan 28, 2026