Update README.md

README.md

@@ -1,47 +1,47 @@
 ---
 tags:
-- image-classification
-- computer-vision
-- deepfake-detection
-- fine-tuned
+  - image-classification
+  - computer-vision
+  - deepfake-detection
+  - fine-tuned
 license: mit
 datasets:
-- 140k-real-and-fake-faces
+  - 140k-real-and-fake-faces
 metrics:
-- accuracy
+  - accuracy
 ---
 
 # 🎭 SDXL-Deepfake-Detector
 
-**A high-performance deep learning model fine-tuned for the binary classification of real vs. fake faces, designed for images potentially generated by advanced synthesis models.**
+**A high-performance deep learning model for binary classification of real versus synthetically generated (deepfake) human faces.**
 
-This project was developed by **[Sadra Milani Moghaddam](https://sadramilani.ir/)**.
+Developed by **[Sadra Milani Moghaddam](https://sadramilani.ir/)**, this model is designed to detect faces generated by state-of-the-art synthesis models—including those based on SDXL and similar architectures—while maintaining strong generalization across diverse image sources.
 
-## 🚀 Model Description
+## 🚀 Model Overview
 
-The **SDXL-Deepfake-Detector** is a specialized image classification model engineered to distinguish between authentic human faces and synthetically generated (deepfake) faces. The model was trained using **transfer learning** principles to provide robust and reliable detection.
+**SDXL-Deepfake-Detector** is a fine-tuned image classification model built using transfer learning. It leverages a pre-trained vision backbone and is optimized specifically for distinguishing authentic human faces from AI-generated forgeries.
 
-### Key Features & Performance
+### Key Features
 
-| Metric | Value | Notes |
-| :--- | :--- | :--- |
-| **Task** | Binary Image Classification | Real Face (0) vs. Deepfake Face (1) |
-| **Dataset** | [140K Real and Fake Faces (Kaggle)](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) | A large dataset containing 140,000 high-quality images. |
-| **Test Accuracy** | **0.91** (91%) | Achieved on the independent test set. |
-| **Hardware** | NVIDIA RTX 3060 (12GB VRAM) | Training performed on suitable hardware for efficiency. |
+- **Task**: Binary image classification (Real = 0, Deepfake = 1)  
+- **Training Dataset**: [140k Real and Fake Faces (Kaggle)](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces)  
+- **Test Accuracy**: **91%** on an independent hold-out test set  
+- **Hardware Used for Training**: NVIDIA RTX 3060 (12GB VRAM)  
+- **License**: [MIT](https://opensource.org/licenses/MIT)  
+
+This model is suitable for integration into media forensics pipelines, content moderation systems, or any application requiring reliable deepfake detection at the image level.
 
 ---
 
-## 💻 Usage with Hugging Face Transformers
+## 💻 Usage
 
-To load and use the model in your Python environment, use the standard `transformers` and `PIL` libraries.
+You can easily load and run inference with this model using the Hugging Face `transformers` library.
 
 ### Installation
 
 ```bash
 pip install transformers torch pillow
 ```
-
 ```python
 import argparse
 from transformers import AutoModelForImageClassification, AutoFeatureExtractor
@@ -49,11 +49,12 @@ from PIL import Image
 import torch
 
 def main():
-    parser = argparse.ArgumentParser(description="Predict image class using fine-tuned model from Hugging Face Hub")
-    parser.add_argument("--image", type=str, required=True, help="Path to the input image")
+    parser = argparse.ArgumentParser(
+        description="Classify an image as 'Real' or 'Deepfake' using the SDXL-Deepfake-Detector."
+    )
+    parser.add_argument("--image", type=str, required=True, help="Path to the input image file")
     args = parser.parse_args()
 
-    # Load model and feature extractor directly from Hugging Face Hub
     model_name = "SADRACODING/SDXL-Deepfake-Detector"
     model = AutoModelForImageClassification.from_pretrained(model_name)
     feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
@@ -78,6 +79,17 @@ def main():
 if __name__ == "__main__":
     main()
 ```
----
-license: mit
----
+
+```bash
+python predict.py --image path/to/face_image.jpg
+```
+## 📄 License
+
+This model is released under the [MIT License](https://opensource.org/licenses/MIT), allowing for both commercial and non-commercial use with proper attribution.
+
+## 🙌 Acknowledgements
+
+- **Dataset**: [140k Real and Fake Faces](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) by xhlulu  
+- **Framework**: [Hugging Face Transformers](https://huggingface.co/docs/transformers)
+- **Github**: 
+- **Developer**: [Sadra Milani Moghaddam](https://sadramilani.ir/)