app.py

import streamlit as st
from transformers import CLIPProcessor, CLIPModel
import torch
from PIL import Image

st.title("Text to Image Generation with CLIP")

# Load pretrained models
clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch16")
clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch16")

text = st.text_area("Enter a description:")
if st.button("Generate Image") and text:
    # Process text and get CLIP features
    text_features = clip_processor(text, return_tensors="pt", padding=True)

    # Use CLIP's encode_image method to obtain the image features
    image_representation = clip_model.encode_image(text_features.pixel_values)

    # For visualization, you can convert the image representation back to an image
    image_array = image_representation.squeeze().permute(1, 2, 0).cpu().numpy()
    image = Image.fromarray((image_array * 255).astype('uint8'))

    # Display the generated image
    st.image(image, caption="Generated Image", use_column_width=True)