πŸ”₯ Deepfake Image Detection Model (Ensemble)

πŸ“Œ Overview

This model detects whether an image is REAL or FAKE (AI-generated).

It uses an ensemble of 2 Vision Transformer (ViT & EfficientNet-B4) models:

  • model.safetensors

🧠 Model Details

model safetensor

🎯 Task

Binary Classification:

  • 0 β†’ REAL
  • 1 β†’ FAKE

πŸ“₯ Input

  • Image (RGB)
  • Size: 224 Γ— 224

πŸ“€ Output

  • Fake probability (0 to 1)

βš™οΈ Installation

pip install torch torchvision timm safetensors pillow
Downloads last month
8
Safetensors
Model size
92.9M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Space using Simma7/image_model 1