README.md

---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: '-'
  output:
    url: images/wallpaper-supernova.jpg
base_model: dima806/deepfake_vs_real_image_detection
instance_prompt: null
license: apache-2.0
---
# DeepFakeDetection

<Gallery />

## Model description 

---
license: apache-2.0
metrics:
- accuracy
- f1
---
Checks whether an image is real or fake (AI-generated).

See https:&#x2F;&#x2F;www.kaggle.com&#x2F;code&#x2F;dima806&#x2F;deepfake-vs-real-faces-detection-vit for more details.

&#x60;&#x60;&#x60;
Classification report:

              precision    recall  f1-score   support

        Real     0.9921    0.9933    0.9927     38080
        Fake     0.9933    0.9921    0.9927     38081

    accuracy                         0.9927     76161
   macro avg     0.9927    0.9927    0.9927     76161
weighted avg     0.9927    0.9927    0.9927     76161
&#x60;&#x60;&#x60;


## Download model

Weights for this model are available in PyTorch,Safetensors format.

[Download](/ompathak/DeepFakeDetection/tree/main) them in the Files & versions tab.