siglip2-base-patch16-naflex

from transformers import pipeline

# load pipeline
ckpt = "google/siglip2-base-patch16-naflex"
image_classifier = pipeline(model=ckpt, task="zero-shot-image-classification")

# load image and candidate labels
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
candidate_labels = ["2 cats", "a plane", "a remote"]

# run inference
outputs = image_classifier(image, candidate_labels)
print(outputs)

import torch
from transformers import AutoModel, AutoProcessor
from transformers.image_utils import load_image

# load the model and processor
ckpt = "google/siglip2-base-patch16-naflex"
model = AutoModel.from_pretrained(ckpt, device_map="auto").eval()
processor = AutoProcessor.from_pretrained(ckpt)

# load the image
image = load_image("https://huggingface.co/datasets/merve/coco/resolve/main/val2017/000000000285.jpg")
inputs = processor(images=[image], return_tensors="pt").to(model.device)

# run infernece
with torch.no_grad():
    image_embeddings = model.get_image_features(**inputs)    

print(image_embeddings.shape)

@misc{tschannen2025siglip2multilingualvisionlanguage,
      title={SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features}, 
      author={Michael Tschannen and Alexey Gritsenko and Xiao Wang and Muhammad Ferjad Naeem and Ibrahim Alabdulmohsin and Nikhil Parthasarathy and Talfan Evans and Lucas Beyer and Ye Xia and Basil Mustafa and Olivier Hénaff and Jeremiah Harmsen and Andreas Steiner and Xiaohua Zhai},
      year={2025},
      eprint={2502.14786},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2502.14786}, 
}