app.py

# import part
import streamlit as st
from transformers import pipeline
import textwrap
import numpy as np
import soundfile as sf
import tempfile
import os
from PIL import Image
import string

# Initialize pipelines with caching
@st.cache_resource
def load_pipelines():
    captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
    storyer = pipeline("text-generation", model="aspis/gpt2-genre-story-generation")
    tts = pipeline("text-to-speech", model="facebook/mms-tts-eng")
    return captioner, storyer, tts

captioner, storyer, tts = load_pipelines()

# Function part
# Function to generate content from an image
def generate_content(image):
    pil_image = Image.open(image)
    
    # Generate caption
    caption = captioner(pil_image)[0]["generated_text"]
    st.write("**🌟 What's in the picture: 🌟**")
    st.write(caption)

    # Create prompt for story
    prompt = (
        f"Write a funny, warm children's story for ages 3-10, 50–100 words, "
        f"Completely and precisely centered on this scene {caption}\nStory:"
    )
    
    # Generate raw story
    raw = storyer(
        prompt,
        max_new_tokens=200,
        temperature=0.7,
        top_p=0.9,
        no_repeat_ngram_size=2,
        return_full_text=False
    )[0]["generated_text"].strip()

    # Define allowed characters to keep (removes symbols like * and ~)
    allowed_chars = string.ascii_letters + string.digits + " .,!?\"'-"
    
    # Clean the raw story by keeping only allowed characters
    clean_raw = ''.join(c for c in raw if c in allowed_chars)
    
    # Split into words and trim to 100 words
    words = clean_raw.split()
    story = " ".join(words[:100])
    
    st.write("**📖 Your funny story: 📖**")
    st.write(story)

    # Generate audio from cleaned story
    chunks = textwrap.wrap(story, width=200)
    audio = np.concatenate([tts(chunk)["audio"].squeeze() for chunk in chunks])

    # Save audio to temporary file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_file:
        sf.write(temp_file.name, audio, tts.model.config.sampling_rate)
        temp_file_path = temp_file.name

    return caption, story, temp_file_path

# Streamlit UI
st.title("✨ Magic Story Maker ✨")
st.markdown("Upload a picture to make a funny story and hear it too! 📸")

uploaded_image = st.file_uploader("Choose your picture", type=["jpg", "jpeg", "png"])

if uploaded_image is None:
    st.image("https://example.com/placeholder_image.jpg", caption="Upload your picture here! 📷", use_column_width=True)
else:
    st.image(uploaded_image, caption="Your Picture 🌟", use_column_width=True)

if st.button("✨ Make My Story! ✨"):
    if uploaded_image is not None:
        with st.spinner("🔮 Creating your magical story..."):
            caption, story, audio_path = generate_content(uploaded_image)
            st.success("🎉 Your story is ready! 🎉")
            st.audio(audio_path, format="audio/wav")
            os.remove(audio_path)
    else:
        st.warning("Please upload a picture first! 📸")