import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
from gtts import gTTS
import io
from PIL import Image

# Load the image captioning model
caption_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

# Load the text generation model
text_generation_model = AutoModelForCausalLM.from_pretrained("gpt2")
tokenizer = AutoTokenizer.from_pretrained("gpt2")

def generate_caption(image):
    # Generate the caption for the uploaded image
    caption = caption_model(image)[0]["generated_text"]
    return caption

def generate_story(caption):
    # Generate the story based on the caption
    input_ids = tokenizer.encode(caption, return_tensors="pt")
    output = text_generation_model.generate(input_ids, max_length=100, num_return_sequences=1)
    story = tokenizer.decode(output[0], skip_special_tokens=True)
    return story

def convert_to_audio(story):
    # Convert the story to audio using gTTS
    tts = gTTS(text=story, lang="en")
    audio_bytes = io.BytesIO()
    tts.write_to_fp(audio_bytes)
    audio_bytes.seek(0)
    return audio_bytes

def main():
    st.title("Storytelling Application")
    
    # File uploader for the image (restricted to JPG)
    uploaded_image = st.file_uploader("Upload an image", type=["jpg"])
    
    if uploaded_image is not None:
        # Convert the uploaded image to PIL image
        image = Image.open(uploaded_image)
        
        # Display the uploaded image
        st.image(image, caption="Uploaded Image", use_column_width=True)
        
        # Generate the caption for the image
        caption = generate_caption(image)
        st.subheader("Generated Caption:")
        st.write(caption)
        
        # Generate the story based on the caption
        story = generate_story(caption)
        st.subheader("Generated Story:")
        st.write(story)
        
        # Convert the story to audio
        audio_bytes = convert_to_audio(story)
        
        # Display the audio player
        st.audio(audio_bytes, format="audio/mp3")

if __name__ == "__main__":
    main()