app.py

import gradio as gr
from PIL import Image, ImageDraw, ImageFont
import random

# Placeholder function for image generation (replace with actual model inference if desired)
def generate_image(text_description):
    # Create a blank image
    img = Image.new('RGB', (512, 512), color=(random.randint(0, 255), random.randint(0, 255), random.randint(0, 255)))
    draw = ImageDraw.Draw(img)
    
    # Add text to the image (simulating a generated image based on description)
    try:
        font = ImageFont.truetype("arial.ttf", 40)
    except:
        font = ImageFont.load_default()
    
    # Wrap text description if too long
    text = text_description if len(text_description) < 30 else text_description[:27] + "..."
    draw.text((20, 20), f"Generated: {text}", font=font, fill=(255, 255, 255))
    
    # Here you could integrate a real model like Stable Diffusion
    # Example (commented out):
    # from diffusers import StableDiffusionPipeline
    # pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
    # img = pipe(text_description).images[0]
    
    return img

# Gradio interface
with gr.Blocks(title="Text-to-Image Generator") as demo:
    gr.Markdown("# Text-to-Image Generator")
    gr.Markdown("Enter a description below and generate an image!")
    
    with gr.Row():
        with gr.Column():
            text_input = gr.Textbox(label="Description", placeholder="Type your image description here...")
            generate_btn = gr.Button("Generate Image")
        with gr.Column():
            output_image = gr.Image(label="Generated Image")
    
    # Connect the button to the function
    generate_btn.click(fn=generate_image, inputs=text_input, outputs=output_image)

# Launch the app
demo.launch()