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
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ model-index:
|
|
| 25 |
type: xhlulu/140k-real-and-fake-faces
|
| 26 |
metrics:
|
| 27 |
- type: accuracy
|
| 28 |
-
value: 0.
|
| 29 |
name: Accuracy
|
| 30 |
---
|
| 31 |
|
|
@@ -45,7 +45,7 @@ As generative AI (like SDXL, DALL路E, and Midjourney) becomes more accessible, t
|
|
| 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)**.
|
| 49 |
|
| 50 |
## Training Approach
|
| 51 |
|
|
|
|
| 25 |
type: xhlulu/140k-real-and-fake-faces
|
| 26 |
metrics:
|
| 27 |
- type: accuracy
|
| 28 |
+
value: 0.86
|
| 29 |
name: Accuracy
|
| 30 |
---
|
| 31 |
|
|
|
|
| 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 **86%**.
|
| 49 |
|
| 50 |
## Training Approach
|
| 51 |
|