import gradio as gr
from transformers import pipeline

# Load models
translation_pipeline = pipeline("translation", model="Helsinki-NLP/opus-mt-ta-en")
text_generation_pipeline = pipeline("text-generation", model="gpt2")

# Simulated image generation (replace with Hugging Face Diffusers or similar if needed)
def generate_image(prompt: str) -> str:
    # You can integrate actual image generation here
    return f"https://via.placeholder.com/512?text={prompt.replace(' ', '+')}"

# Main function
def multimodal_pipeline(tamil_text: str):
    # Step 1: Translate Tamil to English
    translated = translation_pipeline(tamil_text)[0]["translation_text"]

    # Step 2: Generate English text
    generated = text_generation_pipeline(translated, max_length=50, do_sample=True)[0]["generated_text"]

    # Step 3: Generate Image (simulate)
    image_url = generate_image(generated)

    return translated, generated, image_url

# Gradio Interface
interface = gr.Interface(
    fn=multimodal_pipeline,
    inputs=gr.Textbox(label="Enter Tamil Text", placeholder="உங்கள் தமிழ் உரையை இங்கே உள்ளிடவும்"),
    outputs=[
        gr.Textbox(label="English Translation"),
        gr.Textbox(label="Generated Prompt"),
        gr.Image(label="Generated Image"),
    ],
    title="Tamil to Image Multimodal App",
    description="This app translates Tamil to English, generates a descriptive sentence, and creates an image based on it."
)

if __name__ == "__main__":
    interface.launch()