import requests
from PIL import Image
from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor


image_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
image = Image.open(requests.get(image_url, stream=True).raw)

model = Pix2StructForConditionalGeneration.from_pretrained("google/pix2struct-ai2d-base")
processor = Pix2StructProcessor.from_pretrained("google/pix2struct-ai2d-base")

question = "What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud"

inputs = processor(images=image, text=question, return_tensors="pt")

predictions = model.generate(**inputs)
print(processor.decode(predictions[0], skip_special_tokens=True))