pages/textimage.py

import streamlit as st
import os
import random
import spaces
import numpy as np
import torch
from typing import Tuple
from datetime import datetime
from diffusers import PixArtAlphaPipeline, LCMScheduler

# Check if CUDA is available
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Define Hugging Face API details
API_URL = "https://api-inference.huggingface.co/models/Huzaifa367/chat-summarizer"
API_TOKEN = os.getenv("AUTH_TOKEN")
HEADERS = {"Authorization": f"Bearer {API_TOKEN}"}

# Initialize PixArtAlphaPipeline
pipe = PixArtAlphaPipeline.from_pretrained(
    "PixArt-alpha/PixArt-LCM-XL-2-1024-MS",
    torch_dtype=torch.float16,
    use_safetensors=True,
    device=device
)

# Function to generate image based on prompt
def generate_image(prompt: str) -> Tuple[str, int]:
    seed = random.randint(0, np.iinfo(np.int32).max)
    images = pipe(
        prompt=prompt,
        width=1024,
        height=1024,
        num_inference_steps=4,
        generator=torch.Generator().manual_seed(seed),
        num_images_per_prompt=1,
        use_resolution_binning=True,
        output_type="pil",
    ).images

    # Save image and return path and seed
    image_path = save_image(images[0])
    return image_path, seed

# Function to save image and return path
def save_image(img):
    unique_name = str(uuid.uuid4()) + ".png"
    img.save(unique_name)
    return unique_name

# Streamlit app
def main():
    st.set_page_config(layout="wide")
    st.title("Instant Image Generator")

    # Prompt input
    prompt = st.text_area("Prompt", "Enter your prompt here...")

    # Generate button
    if st.button("Generate Image"):
        if prompt:
            # Generate image based on prompt
            image_path, seed = generate_image(prompt)

            # Display the generated image
            st.image(image_path, use_column_width=True, caption=f"Seed: {seed}")

if __name__ == "__main__":
    main()