Image Classification
Transformers
Safetensors
swin-frequency-hybrid
deepfake-detection
synthetic-image-detection
swin-transformer
frequency-analysis
Instructions to use SadraCoding/SDXL-Deepfake-Detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SadraCoding/SDXL-Deepfake-Detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="SadraCoding/SDXL-Deepfake-Detector") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import SwinFrequencyHybridDetector model = SwinFrequencyHybridDetector.from_pretrained("SadraCoding/SDXL-Deepfake-Detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
270c326
1
Parent(s): b1250d2
Frequency Analysis Added
Browse files- README.md +36 -146
- config.json +9 -51
- model.safetensors +2 -2
- preprocessor_config.json +1 -2
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -3,173 +3,63 @@ license: mit
|
|
| 3 |
tags:
|
| 4 |
- image-classification
|
| 5 |
- deepfake-detection
|
| 6 |
-
-
|
| 7 |
-
-
|
| 8 |
-
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
- xhlulu/140k-real-and-fake-faces
|
| 12 |
-
metrics:
|
| 13 |
-
- accuracy
|
| 14 |
-
- f1
|
| 15 |
-
- precision
|
| 16 |
-
- recall
|
| 17 |
-
model-index:
|
| 18 |
-
- name: SDXL-Deepfake-Detector
|
| 19 |
-
results:
|
| 20 |
-
- task:
|
| 21 |
-
type: image-classification
|
| 22 |
-
name: Image Classification
|
| 23 |
-
dataset:
|
| 24 |
-
name: 140k Real and Fake Faces
|
| 25 |
-
type: xhlulu/140k-real-and-fake-faces
|
| 26 |
-
metrics:
|
| 27 |
-
- type: accuracy
|
| 28 |
-
value: 0.97
|
| 29 |
-
name: Accuracy
|
| 30 |
---
|
| 31 |
|
| 32 |
-
#
|
| 33 |
-
### Detecting AI-Generated Faces with Precision and Purpose
|
| 34 |
|
| 35 |
-
|
| 36 |
-
>
|
| 37 |
-
Developed by **[SadraCoding](https://github.com/SadraCoding)**
|
| 38 |
|
| 39 |
-
-
|
| 40 |
-
|
| 41 |
-
## Why This Matters
|
| 42 |
-
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**.
|
| 43 |
-
|
| 44 |
-
---
|
| 45 |
-
|
| 46 |
-
## Model Overview
|
| 47 |
-
|
| 48 |
-
**SDXL-Deepfake-Detector** is a fine-tuned vision transformer that classifies human faces as **artificial (0)** or **human (1)**, achieving an accuracy of **97%**.
|
| 49 |
|
| 50 |
-
##
|
| 51 |
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
-
|
| 56 |
-
- Broader generalization from a large-scale real/fake face dataset
|
| 57 |
-
- Efficient training on limited hardware (single RTX 3060)
|
| 58 |
-
|
| 59 |
-
The result is a lightweight, high-accuracy detector optimized for **both SDXL and general diffusion-based deepfakes**.
|
| 60 |
-
|
| 61 |
-
### Key Highlights
|
| 62 |
-
- **Architecture**: Fine-tuned Vision Transformer (ViT) via Hugging Face `transformers`
|
| 63 |
-
- **Dataset**: 140k balanced real/fake face images
|
| 64 |
-
- **License**: [MIT](https://opensource.org/licenses/MIT) — free for research and commercial use
|
| 65 |
-
- **Hardware**: Trained on a single NVIDIA RTX 3060 (12GB VRAM) — proving high impact doesn’t require massive resources
|
| 66 |
-
|
| 67 |
-
---
|
| 68 |
|
| 69 |
-
##
|
| 70 |
|
| 71 |
-
|
| 72 |
-
```bash
|
| 73 |
-
pip install transformers torch pillow
|
| 74 |
-
```
|
| 75 |
-
### Python Script (If you face any issues, try using Transformers 4.36.2)
|
| 76 |
-
```python
|
| 77 |
-
#predict.py
|
| 78 |
-
import argparse
|
| 79 |
-
from transformers import AutoModelForImageClassification, AutoFeatureExtractor
|
| 80 |
-
from PIL import Image
|
| 81 |
-
import torch
|
| 82 |
-
import os
|
| 83 |
-
|
| 84 |
-
def main():
|
| 85 |
-
parser = argparse.ArgumentParser(
|
| 86 |
-
description="Classify an image as 'artificial' or 'human' using the SDXL-Deepfake-Detector."
|
| 87 |
-
)
|
| 88 |
-
parser.add_argument("--image", type=str, required=True, help="Path to the input image file")
|
| 89 |
-
args = parser.parse_args()
|
| 90 |
-
|
| 91 |
-
# Validate image path
|
| 92 |
-
if not os.path.isfile(args.image):
|
| 93 |
-
raise FileNotFoundError(f"Image file not found: {args.image}")
|
| 94 |
-
|
| 95 |
-
# Load model and feature extractor from Hugging Face Hub
|
| 96 |
-
model_name = "SADRACODING/SDXL-Deepfake-Detector"
|
| 97 |
-
print(f"Loading model '{model_name}'...")
|
| 98 |
-
model = AutoModelForImageClassification.from_pretrained(model_name)
|
| 99 |
-
feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
|
| 100 |
-
|
| 101 |
-
# Set device (GPU if available)
|
| 102 |
-
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 103 |
-
model.to(device)
|
| 104 |
-
model.eval()
|
| 105 |
-
print(f"Running on device: {device}")
|
| 106 |
-
|
| 107 |
-
# Load and preprocess image
|
| 108 |
-
image = Image.open(args.image).convert("RGB")
|
| 109 |
-
inputs = feature_extractor(images=image, return_tensors="pt").to(device)
|
| 110 |
-
|
| 111 |
-
# Inference
|
| 112 |
-
with torch.no_grad():
|
| 113 |
-
outputs = model(**inputs)
|
| 114 |
-
|
| 115 |
-
logits = outputs.logits
|
| 116 |
-
predicted_class_idx = logits.argmax(-1).item()
|
| 117 |
-
predicted_label = model.config.id2label[predicted_class_idx]
|
| 118 |
-
|
| 119 |
-
# Output
|
| 120 |
-
print(f"Prediction Result")
|
| 121 |
-
print(f"Class Index: {predicted_class_idx}")
|
| 122 |
-
print(f"Label : {predicted_label}")
|
| 123 |
-
|
| 124 |
-
if __name__ == "__main__":
|
| 125 |
-
main()
|
| 126 |
-
```
|
| 127 |
-
### How to use
|
| 128 |
-
```bash
|
| 129 |
-
python predict.py --image path/to/image
|
| 130 |
-
```
|
| 131 |
|
| 132 |
-
|
| 133 |
|
| 134 |
-
|
|
|
|
|
|
|
|
|
|
| 135 |
|
| 136 |
-
|
| 137 |
-
- Trained primarily on **frontal, well-lit, aligned face crops** — may underperform on:
|
| 138 |
-
- Low-resolution or blurry images
|
| 139 |
-
- Heavily occluded or non-frontal faces
|
| 140 |
-
- GAN-generated faces (e.g., StyleGAN2/3)
|
| 141 |
-
- Label mapping:
|
| 142 |
-
- `0` → `"artificial"` (AI-generated / Deepfake)
|
| 143 |
-
- `1` → `"human"` (authentic human face)
|
| 144 |
|
| 145 |
-
|
| 146 |
|
| 147 |
-
---
|
| 148 |
|
| 149 |
-
|
| 150 |
|
| 151 |
-
|
| 152 |
-
- **Transparency** is essential in the fight against synthetic media.
|
| 153 |
-
- **Accessibility** ensures researchers, journalists, and civil society can audit and use detection tools without gatekeeping.
|
| 154 |
-
- **Privacy matters**: The model runs **entirely offline** — your images never leave your device.
|
| 155 |
|
| 156 |
-
|
| 157 |
|
| 158 |
-
---
|
| 159 |
|
| 160 |
-
|
|
|
|
|
|
|
| 161 |
|
| 162 |
-
|
| 163 |
-
- **Framework**: [Hugging Face Transformers](https://huggingface.co/docs/transformers)
|
| 164 |
-
- **Model & Code**: [GitHub Repository](https://github.com/SadraCoding/SDXL-Deepfake-Detector) | [Hugging Face Hub](https://huggingface.co/SADRACODING/SDXL-Deepfake-Detector)
|
| 165 |
|
| 166 |
-
|
| 167 |
|
| 168 |
-
|
| 169 |
|
| 170 |
-
|
| 171 |
|
| 172 |
-
---
|
| 173 |
|
| 174 |
-
|
| 175 |
-
> — SadraCoding
|
|
|
|
| 3 |
tags:
|
| 4 |
- image-classification
|
| 5 |
- deepfake-detection
|
| 6 |
+
- synthetic-image-detection
|
| 7 |
+
- swin-transformer
|
| 8 |
+
- frequency-analysis
|
| 9 |
+
library_name: transformers
|
| 10 |
+
base_model: Organika/sdxl-detector
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Spatial–Frequency Hybrid Detector for Synthetic Face Images
|
|
|
|
| 14 |
|
| 15 |
+
This repository contains a fine-tuned checkpoint for binary image classification. Given an input image, the model predicts one of two labels: `artificial` or `human`.
|
|
|
|
|
|
|
| 16 |
|
| 17 |
+
> **Experimental research model.** This classifier is not an authenticity or provenance verifier. Its predictions reflect its training data and preprocessing; they do not establish who created an image, whether a face is real, or whether an image was manipulated. Do not use it as the sole basis for high-impact decisions.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
+
## Links
|
| 20 |
|
| 21 |
+
- **GitHub source, scripts, report, and protocol:** [SadraCoding/SDXL-Deepfake-Detector](https://github.com/SadraCoding/SDXL-Deepfake-Detector)
|
| 22 |
+
- **Live demo:** [sdxldd.ir](https://sdxldd.ir)
|
| 23 |
+
- **Base checkpoint:** [Organika/sdxl-detector](https://huggingface.co/Organika/sdxl-detector)
|
| 24 |
+
- **Dataset referenced by the project:** [140k Real and Fake Faces](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
+
## Model details
|
| 27 |
|
| 28 |
+
The model starts from the Swin image-classification checkpoint `Organika/sdxl-detector`. It combines pooled spatial features from Swin with a learned encoding of the input's centered 2D Fourier log-magnitude. A fusion classifier predicts the final label, and an auxiliary classifier is trained on the Swin features.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
+
The image processor resizes inputs to 224 × 224, rescales pixel values, and applies ImageNet channel normalization. The class mapping stored with this checkpoint is:
|
| 31 |
|
| 32 |
+
| ID | Label |
|
| 33 |
+
| --- | --- |
|
| 34 |
+
| 0 | `artificial` |
|
| 35 |
+
| 1 | `human` |
|
| 36 |
|
| 37 |
+
An optional adaptive inference path predicts first from the Swin features and runs the frequency branch for samples below a confidence threshold. The checkpoint's default threshold is 0.90. Softmax confidence should not be interpreted as calibrated probability unless calibration has been evaluated separately.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
+
## Intended use and limitations
|
| 40 |
|
| 41 |
+
The project references the Kaggle 140k Real and Fake Faces collection, a face-image dataset commonly described as containing real and StyleGAN-generated images. This is a narrow benchmark domain. It does not establish performance on unseen generators, face swaps, video, current text-to-image systems, or arbitrary images in the wild. Dataset version, split construction, and complete run provenance are not included with the checkpoint.
|
| 42 |
|
| 43 |
+
The project's checked-in metrics artifact reports 93.27% clean accuracy on one run of 10,905 images. Split provenance and other details needed to reproduce or independently interpret this result are incomplete; treat it as a historical result, not a generalization claim. The Hugging Face model page's previously reported 97% accuracy has different or undocumented evaluation details and should not be compared directly with that artifact.
|
| 44 |
|
| 45 |
+
Potential dataset shortcuts, distribution shift, image compression, preprocessing, identity overlap, and generator-specific artifacts can affect predictions. The project has not established that the frequency branch improves performance over a matched Swin-only baseline. See the GitHub [research report](https://github.com/SadraCoding/SDXL-Deepfake-Detector/blob/main/REVISED_PROJECT_REPORT.md) and [research protocol](https://github.com/SadraCoding/SDXL-Deepfake-Detector/blob/main/docs/research_protocol.md) for details.
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
+
## Using the checkpoint
|
| 48 |
|
| 49 |
+
This checkpoint uses a custom architecture (`SwinFrequencyHybridDetector`), so the model implementation and inference scripts are provided in the GitHub repository. Follow its [installation and quick-start instructions](https://github.com/SadraCoding/SDXL-Deepfake-Detector#installation). In brief, clone the source, install the requirements and a compatible PyTorch build, then run the prediction script from `model/`:
|
| 50 |
|
| 51 |
+
```bash
|
| 52 |
+
python scripts/predict.py --image /path/to/image.jpg
|
| 53 |
+
```
|
| 54 |
|
| 55 |
+
The script selects CUDA when available and otherwise uses CPU. It reports the predicted class, confidence, adaptive-path status, measured model-call latency, and descriptive image diagnostics. Only process images you have permission to use.
|
|
|
|
|
|
|
| 56 |
|
| 57 |
+
## Training data
|
| 58 |
|
| 59 |
+
The dataset is not included in this repository. The source project describes downloading it separately from [Kaggle](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) and arranging it into `train/{fake,real}`, `val/{fake,real}`, and `test/{fake,real}` directories. Review the dataset's current access terms and image rights before use. Dataset terms are separate from the code license.
|
| 60 |
|
| 61 |
+
## License and attribution
|
| 62 |
|
| 63 |
+
The project declares MIT for its original code. The initialized upstream model, derived checkpoint, and dataset may have separate terms. The upstream `Organika/sdxl-detector` card identifies a CC BY-NC 3.0 license and non-commercial restrictions; review its current terms before using or redistributing this checkpoint. The MIT license does not grant rights to third-party weights or dataset images.
|
| 64 |
|
| 65 |
+
Please cite the [source project](https://github.com/SadraCoding/SDXL-Deepfake-Detector), the [base model](https://huggingface.co/Organika/sdxl-detector), and the [dataset](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) as relevant to your work.
|
|
|
config.json
CHANGED
|
@@ -1,63 +1,21 @@
|
|
| 1 |
{
|
| 2 |
-
"_num_labels": 2,
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
18,
|
| 11 |
-
2
|
| 12 |
-
],
|
| 13 |
-
"drop_path_rate": 0.1,
|
| 14 |
-
"embed_dim": 128,
|
| 15 |
-
"encoder_stride": 32,
|
| 16 |
-
"hidden_act": "gelu",
|
| 17 |
-
"hidden_dropout_prob": 0.0,
|
| 18 |
-
"hidden_size": 1024,
|
| 19 |
"id2label": {
|
| 20 |
"0": "artificial",
|
| 21 |
"1": "human"
|
| 22 |
},
|
| 23 |
-
"image_size": 224,
|
| 24 |
-
"initializer_range": 0.02,
|
| 25 |
"label2id": {
|
| 26 |
"artificial": 0,
|
| 27 |
"human": 1
|
| 28 |
},
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"num_channels": 3,
|
| 34 |
-
"num_heads": [
|
| 35 |
-
4,
|
| 36 |
-
8,
|
| 37 |
-
16,
|
| 38 |
-
32
|
| 39 |
-
],
|
| 40 |
-
"num_layers": 4,
|
| 41 |
-
"out_features": [
|
| 42 |
-
"stage4"
|
| 43 |
-
],
|
| 44 |
-
"out_indices": [
|
| 45 |
-
4
|
| 46 |
-
],
|
| 47 |
-
"padding": "max_length",
|
| 48 |
-
"patch_size": 4,
|
| 49 |
-
"path_norm": true,
|
| 50 |
-
"problem_type": "single_label_classification",
|
| 51 |
-
"qkv_bias": true,
|
| 52 |
-
"stage_names": [
|
| 53 |
-
"stem",
|
| 54 |
-
"stage1",
|
| 55 |
-
"stage2",
|
| 56 |
-
"stage3",
|
| 57 |
-
"stage4"
|
| 58 |
-
],
|
| 59 |
-
"torch_dtype": "float32",
|
| 60 |
-
"transformers_version": "4.53.2",
|
| 61 |
-
"use_absolute_embeddings": false,
|
| 62 |
-
"window_size": 7
|
| 63 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
+
"SwinFrequencyHybridDetector"
|
| 4 |
],
|
| 5 |
+
"base_model_name": "Organika/sdxl-detector",
|
| 6 |
+
"confidence_threshold": 0.9,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"early_exit_loss_weight": 0.25,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"id2label": {
|
| 10 |
"0": "artificial",
|
| 11 |
"1": "human"
|
| 12 |
},
|
|
|
|
|
|
|
| 13 |
"label2id": {
|
| 14 |
"artificial": 0,
|
| 15 |
"human": 1
|
| 16 |
},
|
| 17 |
+
"model_type": "swin-frequency-hybrid",
|
| 18 |
+
"num_classes": 2,
|
| 19 |
+
"transformers_version": "5.18.0",
|
| 20 |
+
"use_cache": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fdacd32fb5e09d511930644dd09b7c2d075286e956f53b2748b6bf2243472c7
|
| 3 |
+
size 350406456
|
preprocessor_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"do_convert_rgb": null,
|
| 3 |
"do_normalize": true,
|
| 4 |
"do_rescale": true,
|
| 5 |
"do_resize": true,
|
|
@@ -8,7 +7,7 @@
|
|
| 8 |
0.456,
|
| 9 |
0.406
|
| 10 |
],
|
| 11 |
-
"image_processor_type": "
|
| 12 |
"image_std": [
|
| 13 |
0.229,
|
| 14 |
0.224,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"do_normalize": true,
|
| 3 |
"do_rescale": true,
|
| 4 |
"do_resize": true,
|
|
|
|
| 7 |
0.456,
|
| 8 |
0.406
|
| 9 |
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
"image_std": [
|
| 12 |
0.229,
|
| 13 |
0.224,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c652b7a37918d0f29c76a9b471a8186106495fdcfbb2c3c719ebcb1f93f1a1ee
|
| 3 |
+
size 5201
|