CoolFace
Modelpublic

king1oo1/deepfake-model

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
4likes543downloads
Model Card

DeepGuard (Deepfake Model)

Model Overview

This is a fine-tuned version of `google/siglip2-base-patch16-224`, specifically trained for binary image classification to detect AI-generated and deepfake images. It is the core inference engine powering the DeepGuard AI Media Forensics App.

The model distinguishes between Real photographs and Fake (AI-generated or deepfake) images. By leveraging the powerful SigLIP2 vision-language encoder and training it on a diverse, multi-source dataset of over 330,000 images, this model demonstrates robust performance in identifying synthetic media, including outputs from modern generators like Midjourney, Stable Diffusion, and DALL·E.

MetricValue
ArchitectureSigLIP2 (Vision Transformer)
Base Modelgoogle/siglip2-base-patch16-224
Input Resolution224x224 pixels
Number of Classes2 (Real, Fake)
Model Size~372 MB
LicenseApache 2.0

Datasets

The model was trained on a carefully curated, balanced dataset of 40,000 images (20,000 real, 20,000 fake), sampled from five diverse, high-quality sources to ensure robustness and generalization across various forgery types.

Dataset NameSourceDescription
Deepfake and Real Imagesmanjilkarki/deepfake-and-real-imagesA foundational dataset of 190k human faces, split evenly between real and manipulated images created by various deepfake techniques. Images are 256x256 pixels[reference:0].
HardFake vs Real Faceshamzaboulahia/hardfakevsrealfacesA challenging test-oriented dataset of 1,288 high-quality images (700 fake, 589 real) designed to push the limits of detection models. Fake faces are generated using StyleGAN2, and real faces feature diverse attributes[reference:1].
GRAVEX-200Kmuhammadbilal6305/200k-real-vs-ai-visuals-by-mbilalA comprehensive multisource dataset of 200,000 face images, curated from six major sources including FaceForensics++, DFDC, Celeb-DF, and Stable Diffusion outputs (SD 1.5, 2.1, XL)[reference:2].
DeepDetect-2025ayushmandatta1/deepdetect-2025A large-scale dataset of over 112,000 images spanning diverse categories (people, animals, nature, urban, artworks), generated by cutting-edge models like DALL·E 3, Midjourney, and Stable Diffusion 3.
Super GenAI (SUT-Project)hiddenplant/sut-projectA dataset featuring high-fidelity images from the latest generative models, including Midjourney V6, Flux, and NanoBanana (SDXL), covering landscapes, portraits, and urban scenes.

Training Procedure

The model was fine-tuned using a progressive unfreezing strategy to adapt the pre-trained SigLIP2 encoder while preventing catastrophic forgetting. All training was performed on a Tesla T4 GPU in Google Colab.

Training Hyperparameters

StageEpochsLearning RateTrainable ParametersDescription
Stage 121e-3Classifier head onlyWarm-up phase to adapt the new binary classification head.
Stage 235e-5Classifier + Top 6 Transformer BlocksGradual unfreezing to allow the model to learn task-specific features.
Stage 321e-5All layersFull model fine-tuning with a very low learning rate for final convergence.
  • —Batch Size: 32
  • —Optimizer: AdamW
  • —Scheduler: Cosine Annealing
  • —Loss Function: Cross-Entropy Loss
  • —Data Augmentation: Random Horizontal Flip, Random Rotation (10°), Color Jitter

Performance Metrics

Evaluation on a held-out validation set results:

MetricScore
Accuracy78.5%
AUC> 0.86
F1 Score~0.78

Usage

You can load and use this model directly with the Hugging Face transformers library.

python
from transformers import AutoImageProcessor, AutoModelForImageClassification
from PIL import Image
import torch

# Load model and processor
model_name = "king1oo1/ai-vs-real-deepfake-model"  # Replace with your actual model ID
processor = AutoImageProcessor.from_pretrained(model_name)
model = AutoModelForImageClassification.from_pretrained(model_name)
model.eval()

# Load and preprocess an image
image = Image.open("path/to/your/image.jpg").convert("RGB")
inputs = processor(images=image, return_tensors="pt")

# Run inference
with torch.no_grad():
    outputs = model(**inputs)
    probs = torch.softmax(outputs.logits, dim=1)
    fake_prob = probs[0][1].item() * 100
    real_prob = probs[0][0].item() * 100

print(f"Fake probability: {fake_prob:.2f}%")
print(f"Real probability: {real_prob:.2f}%")
print(f"Verdict: {'FAKE' if fake_prob > 50 else 'REAL'}")