Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,7 @@ pipeline_tag: image-classification
|
|
| 8 |
library_name: transformers
|
| 9 |
---
|
| 10 |
# **AI-vs-Deepfake-vs-Real-Siglip2**
|
|
|
|
| 11 |
**AI-vs-Deepfake-vs-Real-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 **distinguish AI-generated images, deepfake images, and real images** using the **SiglipForImageClassification** architecture.
|
| 12 |
|
| 13 |
The model categorizes images into three classes:
|
|
@@ -15,7 +16,7 @@ The model categorizes images into three classes:
|
|
| 15 |
- **Class 1:** "Deepfake" – The image is a manipulated deepfake, where real content has been altered.
|
| 16 |
- **Class 2:** "Real" – The image is an authentic, unaltered photograph.
|
| 17 |
|
| 18 |
-
# **Run with Transformers
|
| 19 |
|
| 20 |
```python
|
| 21 |
!pip install -q transformers torch pillow gradio
|
|
|
|
| 8 |
library_name: transformers
|
| 9 |
---
|
| 10 |
# **AI-vs-Deepfake-vs-Real-Siglip2**
|
| 11 |
+
|
| 12 |
**AI-vs-Deepfake-vs-Real-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 **distinguish AI-generated images, deepfake images, and real images** using the **SiglipForImageClassification** architecture.
|
| 13 |
|
| 14 |
The model categorizes images into three classes:
|
|
|
|
| 16 |
- **Class 1:** "Deepfake" – The image is a manipulated deepfake, where real content has been altered.
|
| 17 |
- **Class 2:** "Real" – The image is an authentic, unaltered photograph.
|
| 18 |
|
| 19 |
+
# **Run with Transformers🤗**
|
| 20 |
|
| 21 |
```python
|
| 22 |
!pip install -q transformers torch pillow gradio
|