jinaai/jina-clip-v2 · Using a slow image processor as `use_fast` is unset

Running on Linux, CPU-only, python 3.13., I get this error when running with transformers.
Apparently the transformers code is using a slow image processor. How to use the fast one?

Using a slow image processor as use_fast is unset and a slow processor was saved with this model. use_fast=True will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with use_fast=False.

# !pip install transformers einops timm pillow
from transformers import AutoModel

# Initialize the model
model = AutoModel.from_pretrained('jinaai/jina-clip-v2', trust_remote_code=True)

# Choose a matryoshka dimension, set to None to get the full 1024-dim vectors
truncate_dim = 512

all_images = ['https://i.ibb.co/nQNGqL0/beach1.jpg', 'https://i.ibb.co/r5w8hG8/beach2.jpg']
image_embeddings = model.encode_image(
    all_images[:2], truncate_dim=truncate_dim
)

jinaai
/

jina-clip-v2

Using a slow image processor as `use_fast` is unset - Transformers issue