---
license: apache-2.0
metrics:
- accuracy
- f1
base_model:
- google/vit-base-patch16-224-in21k
pipeline_tag: image-classification
library_name: transformers
---
Predicts with about 97% accuracy whether an attached image is AI-generated.

See https://www.kaggle.com/code/dima806/ai-vs-human-generated-images-prediction-vit for details.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6449300e3adf50d864095b90/RBfE9AIiEMlriYujz2FJQ.png)

```
Classification report:

              precision    recall  f1-score   support

       human     0.9606    0.9849    0.9726     15990
AI-generated     0.9845    0.9596    0.9719     15990

    accuracy                         0.9723     31980
   macro avg     0.9726    0.9723    0.9723     31980
weighted avg     0.9726    0.9723    0.9723     31980
```