app.py

# Import libraries
!pip install gradio transformers
!pip install -q gradio
!pip install -q openai
!pip install -q gTTS

import gradio as gr
from transformers import pipeline
from gtts import gTTS
from io import BytesIO
from PIL import Image
from diffusers import DiffusionPipeline

# Use a pipeline as a high-level helper for text generation
vision_alpha_pipe = pipeline("text-generation", model="NousResearch/Nous-Hermes-2-Vision-Alpha")

# Initialize DiffusionPipeline for text-to-image
image_generation_pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-video-diffusion-img2vid-xt")

# Set the context for the storyteller
messages = [{"role": "system", "content": "You are a magical storyteller, creating wonderful tales for kids. Make them imaginative and full of joy!"}]

# Initialize page number
current_page = 0

# Define the Storyteller function
def StorytellerNous(character, child_name, lesson_choice, tell_story, _):
    global current_page
    
    # Set the characters and lesson based on user choices
    character_info = f"Once upon a time, {child_name} met {character}. "
    lesson_info = f"Today's lesson is about {lesson_choice}. "
    
    messages.append({"role": "user", "content": tell_story})
    
    # Generate story using Nous-Hermes-2-Vision-Alpha
    input_text = character_info + lesson_info + tell_story
    story_reply = vision_alpha_pipe(input_text, max_length=150, num_return_sequences=1, no_repeat_ngram_size=2, top_k=50, top_p=0.95)[0]['generated_text']

    messages.append({"role": "assistant", "content": story_reply})
    
    # Convert text to speech
    tts = gTTS(text=story_reply, lang='en', slow=False)
    audio_io = BytesIO()
    tts.save(audio_io)
    audio_io.seek(0)

    # Convert text to image using DiffusionPipeline
    image_reply = image_generation_pipe(story_reply)
    
    # Display the story on separate pages
    story_pages = story_reply.split("\n\n")  # Split the story into pages
    current_page = min(current_page, len(story_pages) - 1)  # Ensure the current_page is within bounds
    
    return story_pages[current_page], Audio(data=audio_io.read(), autoplay=True), image_reply

# Create the Gradio Interface with styling
demo = gr.Interface(
    fn=StorytellerNous,
    inputs=[
        gr.Textbox("text", label="Child's Name"),
        gr.Dropdown(["unicorn", "dragon", "wizard"], label="Choose a Character"),
        gr.Dropdown(["kindness", "creativity", "bravery"], label="Choose a Lesson"),
        gr.Textbox("text", label="Start the Story with"),
        gr.Button("Next Page"),
    ],
    outputs=["text", "audio", "image"],
    title="📖 Storytelling Magic",
    description="A magical storyteller app for kids! Choose characters, add your name, and select the lesson you want to learn.",
    live=True,  # Enable live updates for CSS changes
    css=f"""body {{
        background-image: url('https://www.bing.com/images/create/a-castle-ai-metaverse-style/1-657576205c7146f2b7f2f8d1c552810f?id=dZs6kpD2HfmH4eojx%2bHjdA%3d%3d&view=detailv2&idpp=genimg&FORM=GCRIDP&mode=overlay');
        background-size: cover;
        background-position: center;
        font-family: 'Comic Sans MS', cursive, sans-serif; /* Optional: Change the font */
    }}""",
)

# Launch the Gradio Interface
demo.launch()