app.py

import os
import streamlit as st
import requests
from transformers import pipeline
from typing import Dict
from together import Together
from utils import img2txt, txt2story, txt2speech, get_user_preferences


# Main function
def main():
    st.set_page_config(page_title="🎨 Image-to-Audio Story 🎧", page_icon="🖼️")
    st.title("Turn the Image into Audio Story")

    # Allows users to upload an image file
    uploaded_file = st.file_uploader("# 📷 Upload an image...", type=["jpg", "jpeg", "png"])

    # Parameters for LLM model (in the sidebar)
    st.sidebar.markdown("# LLM Inference Configuration Parameters")
    top_k = st.sidebar.number_input("Top-K", min_value=1, max_value=100, value=5)
    top_p = st.sidebar.number_input("Top-P", min_value=0.0, max_value=1.0, value=0.8)
    temperature = st.sidebar.number_input("Temperature", min_value=0.1, max_value=2.0, value=1.5)

    # Get user preferences for the story
    st.markdown("## Story Preferences")
    preferences = get_user_preferences()

    if uploaded_file is not None:
        # Reads and saves uploaded image file
        bytes_data = uploaded_file.read()
        with open("uploaded_image.jpg", "wb") as file:
            file.write(bytes_data)

        st.image(uploaded_file, caption='🖼️ Uploaded Image', use_column_width=True)

        # Initiates AI processing and story generation
        with st.spinner("## 🤖 AI is at Work! "):
            scenario = img2txt("uploaded_image.jpg")  # Extracts text from the image
            
            # Modify the prompt to include user preferences
            prompt = f"Based on the image description: '{scenario}', create a {preferences['genre']} story set in {preferences['setting']} in {preferences['continent']}. " \
                     f"The story should have a {preferences['tone']} tone and explore the theme of {preferences['theme']}. " \
                     f"The main conflict should be {preferences['conflict']}. " \
                     f"The story should have a {preferences['twist']} and end with a {preferences['ending']} ending."
            
            story = txt2story(prompt, top_k, top_p, temperature)  # Generates a story based on the image text, LLM params, and user preferences
            
            txt2speech(story)  # Converts the story to audio

            st.markdown("---")
            st.markdown("## 📜 Image Caption")
            st.write(scenario)

            st.markdown("---")
            st.markdown("## 📖 Story")
            st.write(story)

            st.markdown("---")
            st.markdown("## 🎧 Audio Story")
            st.audio("audio_story.wav")


if __name__ == '__main__':
    main()

# Credits
st.markdown("### Credits")
st.caption('''
            Made with ❤️ by @Aditya-Neural-Net-Ninja\n 
            Utilizes Image-to-Text, Text Generation, Text-to-Speech Transformer Models\n
            Gratitude to Streamlit, 🤗 Spaces for Deployment & Hosting
            ''')