SadraCoding
/

SDXL-Deepfake-Detector

@@ -1,4 +1,4 @@
-# 🎭 SDXL-Deepfake-Detector
 ### Detecting AI-Generated Faces with Precision and Purpose
 >*Not just another classifier — a tool for digital truth.*
@@ -7,16 +7,16 @@ Developed by **[Sadra Milani Moghaddam](https://sadramilani.ir/)**
 ---
-## 🌍 Why This Matters
 As generative AI (like SDXL, DALL·E, and Midjourney) becomes more accessible, the line between real and synthetic media blurs — especially for vulnerable communities. This project started as a technical experiment but evolved into a **privacy-aware, open-source defense** against visual misinformation, with a focus on **ethical AI deployment**.
 ---
-## 🚀 Model Overview
-**SDXL-Deepfake-Detector** is a fine-tuned vision transformer that classifies human faces as **AI-Generated (0)** or **Real (1)**.
-## 🧠 Training Approach
 This model was obtained by **fine-tuning** the [`Organika/sdxl-detector`](https://huggingface.co/Organika/sdxl-detector) — a vision transformer pre-trained specifically to detect SDXL-generated faces — on the [140k Real and Fake Faces](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) dataset.
@@ -27,7 +27,7 @@ This approach leverages:
 The result is a lightweight, high-accuracy detector optimized for **both SDXL and general diffusion-based deepfakes**.
-### ✅ Key Highlights
 - **Architecture**: Fine-tuned Vision Transformer (ViT) via Hugging Face `transformers`
 - **Dataset**: 140k balanced real/fake face images
 - **License**: [MIT](https://opensource.org/licenses/MIT) — free for research and commercial use
@@ -35,7 +35,7 @@ The result is a lightweight, high-accuracy detector optimized for **both SDXL an
 ---
-## 💻 Quick Start
 ### Dependencies
 ```bash
@@ -98,7 +98,7 @@ if __name__ == "__main__":
 python predict.py --image path/to/image
 ```
-## 📊 Performance & Limitations
 > **Note**: Final test accuracy will be reported after full evaluation. Preliminary results show strong generalization on SDXL- and diffusion-based face forgeries.
@@ -109,13 +109,13 @@ python predict.py --image path/to/image
   - GAN-generated faces (e.g., StyleGAN2/3)
 - Label mapping:
   - `0` → `"artificial"` (AI-generated / Deepfake)
-  - `1` → `"real"` (authentic human face)
 > ⚠️ This tool is **not a forensic proof**, but a probabilistic detector. Use responsibly.
 ---
-## 🌱 Philosophy & Ethics
 This model is open-source because:
 - **Transparency** is essential in the fight against synthetic media.
@@ -126,7 +126,7 @@ As a developer from a vulnerable community, I believe AI safety tools must be **
 ---
-## 🙌 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)
@@ -134,7 +134,7 @@ As a developer from a vulnerable community, I believe AI safety tools must be **
 ---
-## 📬 How to Contribute
 Fine-tune this model on your domain-specific data using Hugging Face `Trainer`.

+# SDXL-Deepfake-Detector
 ### Detecting AI-Generated Faces with Precision and Purpose
 >*Not just another classifier — a tool for digital truth.*
 ---
+## Why This Matters
 As generative AI (like SDXL, DALL·E, and Midjourney) becomes more accessible, the line between real and synthetic media blurs — especially for vulnerable communities. This project started as a technical experiment but evolved into a **privacy-aware, open-source defense** against visual misinformation, with a focus on **ethical AI deployment**.
 ---
+## Model Overview
+**SDXL-Deepfake-Detector** is a fine-tuned vision transformer that classifies human faces as **artificial (0)** or **human (1)**.
+## Training Approach
 This model was obtained by **fine-tuning** the [`Organika/sdxl-detector`](https://huggingface.co/Organika/sdxl-detector) — a vision transformer pre-trained specifically to detect SDXL-generated faces — on the [140k Real and Fake Faces](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) dataset.
 The result is a lightweight, high-accuracy detector optimized for **both SDXL and general diffusion-based deepfakes**.
+### Key Highlights
 - **Architecture**: Fine-tuned Vision Transformer (ViT) via Hugging Face `transformers`
 - **Dataset**: 140k balanced real/fake face images
 - **License**: [MIT](https://opensource.org/licenses/MIT) — free for research and commercial use
 ---
+## Quick Start
 ### Dependencies
 ```bash
 python predict.py --image path/to/image
 ```
+## Performance & Limitations
 > **Note**: Final test accuracy will be reported after full evaluation. Preliminary results show strong generalization on SDXL- and diffusion-based face forgeries.
   - GAN-generated faces (e.g., StyleGAN2/3)
 - Label mapping:
   - `0` → `"artificial"` (AI-generated / Deepfake)
+  - `1` → `"human"` (authentic human face)
 > ⚠️ This tool is **not a forensic proof**, but a probabilistic detector. Use responsibly.
 ---
+## Philosophy & Ethics
 This model is open-source because:
 - **Transparency** is essential in the fight against synthetic media.
 ---
+## 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)
 ---
+## How to Contribute
 Fine-tune this model on your domain-specific data using Hugging Face `Trainer`.