# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("microsoft/git-base")
model = AutoModelForCausalLM.from_pretrained("hieudinhpro/git-base-on-diffuision-dataset2")

# load image
from PIL import Image

image = Image.open('/content/image_3.jpg')

# pre image
inputs = processor(images=image, return_tensors="pt")
pixel_values = inputs.pixel_values

# predict 
generated_ids = model.generate(pixel_values=pixel_values, max_length=50)

# decode to text
generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_caption)