app.py

import streamlit as st
from PIL import Image
import requests
from transformers import BlipProcessor, BlipForConditionalGeneration

# Load the model and processor outside the main function to avoid reloading on every run
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

def generate_caption(img_url):
    raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

    # Conditional image captioning
    text = "a photography of"
    inputs = processor(raw_image, text, return_tensors="pt")
    out = model.generate(**inputs)
    conditional_caption = processor.decode(out[0], skip_special_tokens=True)

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

    return conditional_caption, unconditional_caption

def main():
    st.title("Image Captioning App")
    
    img_url = st.text_input("Enter the image URL:")
    if img_url:
        try:
            # Display the image
            image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
            st.image(image, caption='Input Image', use_column_width=True)
            
            # Generate captions
            conditional_caption, unconditional_caption = generate_caption(img_url)
            
            # Display captions
            st.subheader("Conditional Image Caption")
            st.write(conditional_caption)
            
            st.subheader("Unconditional Image Caption")
            st.write(unconditional_caption)
        except Exception as e:
            st.error(f"Error processing the image: {e}")

if __name__ == "__main__":
    main()