OpenCLIP-VIT-g image encoder extracted from https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/tree/main/image_encoder
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