You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

license: mit base_model: google/vit-base-patch16-224 pipeline_tag: image-classification tags: - deepfake - deepfake-detection - image-classification - computer-vision - vision-transformer datasets: - ControlNet/AV-Deepfake1M-PlusPlus

Real vs Fake Image Detection

Overview

Real vs Fake Image Detection is a deep learning model designed to classify images as either REAL (authentic images) or FAKE (AI-generated or deepfake images).

The model is built using the Vision Transformer (ViT) architecture and fine-tuned for binary image classification tasks.

This model can help identify synthetic media created by modern AI image generation systems.

Model Details

Feature	Value
Model Type	Image Classification
Architecture	Vision Transformer (ViT Base)
Base Model	google/vit-base-patch16-224
Task	Deepfake Detection
Labels	REAL, FAKE
Framework	PyTorch + Transformers

Dataset

The model was trained using the dataset:

AV-Deepfake1M-PlusPlus

This dataset contains a large number of real and manipulated images designed for deepfake detection research.

Dataset link: https://huggingface.co/datasets/ControlNet/AV-Deepfake1M-PlusPlus

Installation

Install required libraries:

pip install transformers torch pillow
---

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support