import streamlit as st
from transformers import pipeline, AutoTokenizer, AutoModel, AutoModelForCausalLM
import torch
from PIL import Image
import requests
from io import BytesIO
import io
from diffusers import DiffusionPipeline


# Initialize a pipeline for text-to-image generation
text_to_image = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0")

st.title('Image Captioning, Text Embedding, Text Generation, and Input Application')
typed_text = st.text_area("Type your sentence here:")

# Generate caption and process text button
if st.button('Generate Caption and Process Text'):
    # Generate image from text
    generated_image = text_to_image(typed_text)[0]
    image_data = generated_image['image']
    st.image(image_data, caption='Generated Image')