README.md

metadata

license: apache-2.0
language:
  - en
base_model:
  - google/siglip2-base-patch16-224
pipeline_tag: image-classification
library_name: transformers
tags:
  - deepfake
  - Real

Fake-Real-Class-Siglip2

Fake-Real-Class-Siglip2 is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to classify images as either Fake or Real using the SiglipForImageClassification architecture.

The model categorizes images into two classes:

• Class 0: "Fake" – The image is detected as AI-generated, manipulated, or synthetic.
• Class 1: "Real" – The image is classified as authentic and unaltered.

!pip install -q transformers torch pillow gradio

import gradio as gr
from transformers import AutoImageProcessor
from transformers import SiglipForImageClassification
from transformers.image_utils import load_image
from PIL import Image
import torch

# Load model and processor
model_name = "prithivMLmods/Deepfake-Real-Class-Siglip2"
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)

def classify_image(image):
    """Classifies an image as Fake or Real."""
    image = Image.fromarray(image).convert("RGB")
    inputs = processor(images=image, return_tensors="pt")
    
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
    
    labels = model.config.id2label
    predictions = {labels[i]: round(probs[i], 3) for i in range(len(probs))}
    
    return predictions

# Create Gradio interface
iface = gr.Interface(
    fn=classify_image,
    inputs=gr.Image(type="numpy"),
    outputs=gr.Label(label="Classification Result"),
    title="Fake vs Real Image Classification",
    description="Upload an image to determine if it is Fake or Real."
)

# Launch the app
if __name__ == "__main__":
    iface.launch()

Intended Use:

The Fake-Real-Class-Siglip2 model is designed to classify images into two categories: Fake or Real. It helps in detecting AI-generated or manipulated images.

Potential Use Cases:

• Fake Image Detection: Identifying AI-generated or altered images.
• Content Verification: Assisting platforms in filtering misleading media.
• Forensic Analysis: Supporting research in detecting synthetic media.
• Authenticity Checks: Helping journalists and investigators verify image credibility.