Image Classification
Transformers
Safetensors
English
siglip
OpenSDI
Spotting Diffusion-Generated Images in the Open World
AI-vs-Real
SigLIP2
SD2.1
Instructions to use prithivMLmods/OpenSDI-SD2.1-SigLIP2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/OpenSDI-SD2.1-SigLIP2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="prithivMLmods/OpenSDI-SD2.1-SigLIP2") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoProcessor, AutoModelForImageClassification processor = AutoProcessor.from_pretrained("prithivMLmods/OpenSDI-SD2.1-SigLIP2") model = AutoModelForImageClassification.from_pretrained("prithivMLmods/OpenSDI-SD2.1-SigLIP2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,9 @@ tags:
|
|
| 17 |
- SigLIP2
|
| 18 |
- SD2.1
|
| 19 |
---
|
|
|
|
|
|
|
|
|
|
| 20 |
# OpenSDI-SD2.1-SigLIP2
|
| 21 |
|
| 22 |
> OpenSDI-SD2.1-SigLIP2 is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for binary image classification. It is trained to detect whether an image is a real photograph or generated using Stable Diffusion 2.1 (SD2.1), using the SiglipForImageClassification architecture.
|
|
|
|
| 17 |
- SigLIP2
|
| 18 |
- SD2.1
|
| 19 |
---
|
| 20 |
+
|
| 21 |
+

|
| 22 |
+
|
| 23 |
# OpenSDI-SD2.1-SigLIP2
|
| 24 |
|
| 25 |
> OpenSDI-SD2.1-SigLIP2 is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for binary image classification. It is trained to detect whether an image is a real photograph or generated using Stable Diffusion 2.1 (SD2.1), using the SiglipForImageClassification architecture.
|