app.py

import streamlit as st
from PIL import Image
from transformers import AutoFeatureExtractor, AutoModelForImageCaptioning, AutoTokenizer

# Load the image captioning model
model_name = "Salesforce/blip-image-captioning-large"
feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForImageCaptioning.from_pretrained(model_name)

# Streamlit app title and description
st.title("Image Information Extractor")
st.write("Upload an image, and this app will extract information from it.")

# Upload image
image = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])

if image:
    # Display the uploaded image
    st.image(image, use_column_width=True, caption="Uploaded Image")

    # Process the image and extract information
    image = Image.open(image)
    st.write("Extracting information from the image...")

    # Use the image captioning model to generate a description
    inputs = tokenizer(image, return_tensors="pt")
    with st.spinner("Generating caption..."):
        captions = model.generate(**inputs)
    caption = tokenizer.decode(captions[0], skip_special_tokens=True)

    # Display the image description
    st.write("Image Description:")
    st.write(caption)

    # You can add more processing or explanations here if needed

st.sidebar.text("Built with ❤️ by Your Name")