---
license: apache-2.0
pipeline_tag: image-classification
tags:
- art
- legal
---

# Nonescape AI-generated image classifier

This model predicts whether an input image was created by an artificial‑image generator (e.g. Stable Diffusion, Midjourney, GAN, deepfake pipeline) or captured with a conventional camera.
It ships with Python and JavaScript/TypeScript SDKs and open‑weights in both Safetensors and ONNX formats.

## Model Details

### Model Description

Nonescape is a binary image‑classification model trained to distinguish synthetic (AI‑generated) from authentic (photographic/hand‑crafted) imagery.

- **Developed by:** Aedilic Inc.
- **Model type:** Image Classifier
- **License:** Apache 2.0

### Model Sources

- **Repository:** https://github.com/aediliclabs/nonescape
- **Demo:** https://www.nonescape.com

## Uses

| Use‑case                  | Description                                                         | End Users                              |
| ------------------------- | ------------------------------------------------------------------- | -------------------------------------- |
| **Content moderation**    | Flag AI artwork uploads on social platforms or stock‑media sites    | Trust & Safety teams                   |
| **Media forensics**       | Assist journalists and OSINT researchers verifying image provenance | Investigative reporters, fact‑checkers |
| **Legal evidence triage** | Early filtering of manipulated exhibits                             | Attorneys, e‑discovery vendors         |

## How to Get Started with the Model

[Python library](https://github.com/aediliclabs/nonescape/tree/master/python)

```python
from nonescape import NonescapeClassifier

# Load model
classifier = NonescapeClassifier("nonescape-v0.safetensors")

# Single image
result = classifier.predict("image.jpg")
print(f"AI Generated: {result.is_synthetic}, Confidence: {result.confidence}")

# Multiple images
results = classifier.predict(["img1.jpg", "img2.jpg"])
```

[Javascript/NodeJS library](https://github.com/aediliclabs/nonescape/tree/master/javascript)

```javascript
import { LocalClassifier } from '@aedilic/nonescape';

const classifier = new LocalClassifier({
  onProgress: (progress) => console.log(`Loading: ${Math.round(progress.current / progress.total * 100)}%`)
});

await classifier.initialize();

// Single image
const result = await classifier.predict(imageFile);
console.log(`AI Generated: ${result.isSynthetic}, Confidence: ${result.confidence}`);

// Multiple images
const results = await classifier.predict([image1, image2, image3]);

classifier.dispose();
```

### Recommendations

- Use a high threshold (e.g. `0.9`) for tasks like filtering images, that require a low false-positive rate
- Use the default threshold of `0.5` for tasks like content moderation, that require a low false-negative rate but can live with some false positives

## Training Details

The model was trained on 1M+ images scraped from across the internet.

## Evaluation

The model was evaluated on the [Adversarial AI-Art dataset](https://arxiv.org/pdf/2404.14581) to make it comparable with other SOTA models.
It achieves the best overall accuracy, outperforming open-source and commercial models.

![accuracy benchmark](https://www.nonescape.com/nonescape-accuracy.jpg)

The GitHub repository contains all code to replicate the model evaluation.