import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

# Initialize processor and model
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large").to("cuda")

# Function to process and caption an image from a URL
def caption_image(image_url):
    try:
        # Load image from the provided URL
        raw_image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
        
        # Conditional image captioning
        text = "a photography of"
        inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
        out = model.generate(**inputs)
        conditional_caption = processor.decode(out[0], skip_special_tokens=True)

        # Unconditional image captioning
        inputs = processor(raw_image, return_tensors="pt").to("cuda")
        out = model.generate(**inputs)
        unconditional_caption = processor.decode(out[0], skip_special_tokens=True)

        # Print the results
        print("Conditional Caption:", conditional_caption)
        print("Unconditional Caption:", unconditional_caption)
    
    except Exception as e:
        print(f"Error occurred: {e}")

# Get image URL from user input
image_url = input("Enter the image URL: ")
caption_image(image_url)