# app.py
import streamlit as st
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import torch

st.title("AI Image Caption Generator")
st.write("Upload an image and get a caption generated by an AI model!")

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

if uploaded_file:
    image = Image.open(uploaded_file).convert('RGB')
    st.image(image, caption="Uploaded Image", use_column_width=True)

    st.write("Generating caption...")

    processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
    model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

    inputs = processor(image, return_tensors="pt")
    out = model.generate(**inputs)
    caption = processor.decode(out[0], skip_special_tokens=True)

    st.success(f"📝 Caption: {caption}")