import streamlit as st
import requests
from PIL import Image
import numpy as np
import io

# Function to apply deepfake-like transformation using an API
def apply_deepfake(image):
    # Convert PIL image to bytes
    image_bytes = io.BytesIO()
    image.save(image_bytes, format='JPEG')
    image_bytes = image_bytes.getvalue()

    # Call the Hugging Face API
    api_url = "https://api-inference.huggingface.co/models/spaces/dalle-mini/dalle-mini"
    headers = {"Authorization": "Bearer YOUR_HUGGING_FACE_API_TOKEN"}
    response = requests.post(api_url, headers=headers, files={"file": image_bytes})

    # Convert response to image
    response_image = Image.open(io.BytesIO(response.content))
    return response_image

st.title("Image Processing MVP")

uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png", "jpeg"])

if uploaded_file is not None:
    image = Image.open(uploaded_file)
    st.image(image, caption='Uploaded Image.', use_column_width=True)
    st.write("")
    st.write("Processing...")

    action = st.radio("Choose an action:", ('A', 'B', 'Deepfake'))

    if action == 'A':
        # Just display the original image
        st.image(image, caption='Original Image.', use_column_width=True)
    elif action == 'B':
        # Add noise to the original image
        image_np = np.array(image)
        noise = np.random.normal(0, 25, image_np.shape).astype(np.uint8)
        noisy_image = cv2.add(image_np, noise)
        st.image(noisy_image, caption='Image with Noise.', use_column_width=True)
    elif action == 'Deepfake':
        # Apply deepfake transformation
        deepfake_image = apply_deepfake(image)
        st.image(deepfake_image, caption='Deepfake Image.', use_column_width=True)