Update README.md

README.md

@@ -1 +1,20 @@
-OpenCLIP-VIT-g image encoder extracted from [https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/tree/main/image_encoder](https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/tree/main/image_encoder)
+OpenCLIP-VIT-g image encoder extracted from [https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/tree/main/image_encoder](https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/tree/main/image_encoder)
+
+```python
+from PIL import Image
+import requests
+from transformers import AutoProcessor, CLIPVisionModelWithProjection
+from transformers import CLIPVisionModelWithProjection,  CLIPImageProcessor
+
+model_name = "Jiayi-Pan/SD-v2-1-Image-Encoder"
+model = CLIPVisionModelWithProjection.from_pretrained(model_name)
+processor = transformers.CLIPImageProcessor.from_pretrained(model_name)
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+inputs = processor(images=image, return_tensors="pt")
+
+outputs = model(**inputs)
+image_embeds = outputs.image_embeds
+```