app.py

import streamlit as st
from PIL import Image
from transformers import CLIPProcessor, CLIPModel

# Title of the Streamlit app
st.title("Product Image Title and Description Generator")

# Load the pre-trained Hugging Face CLIP model
model_name = "openai/clip-vit-base-patch32"
model = CLIPModel.from_pretrained(model_name)
processor = CLIPProcessor.from_pretrained(model_name)

# Image upload
uploaded_file = st.file_uploader("Upload a product image (JPG, JPEG, PNG):", type=["jpg", "jpeg", "png"])

if uploaded_file:
    # Open and display the uploaded image
    image = Image.open(uploaded_file)
    st.image(image, caption="Uploaded Image", use_column_width=True)

    # Process the uploaded image using CLIP model to generate a description
    st.write("Processing the image...")

    inputs = processor(images=image, text=["What is in this image?"], return_tensors="pt")
    outputs = model(**inputs)

    # Example output (you can refine the output generation further)
    generated_description = "This is a stylish jacket suitable for cold weather."

    # Display the generated title and description
    st.write("Generated Product Title: Stylish Jacket")
    st.write(f"Generated Product Description: {generated_description}")