app.py

import os
import streamlit as st
import tensorflow as tf
import numpy as np
from huggingface_hub import HfApi, hf_hub_download
from PIL import Image
from io import BytesIO
import requests

# Hugging Face credentials
api = HfApi()

# Set your Hugging Face username and model repository name
username = "Hammad712"
repo_name = "CycleGAN-Model"
repo_id = f"{username}/{repo_name}"

# Download model files from Hugging Face
local_dir = "CycleGAN"  # Changed to a relative path
os.makedirs(local_dir, exist_ok=True)
for file in api.list_repo_files(repo_id=repo_id, repo_type="model"):
    hf_hub_download(repo_id=repo_id, filename=file, local_dir=local_dir)

# Load the model
custom_objects = {'InstanceNormalization': tf.keras.layers.Layer}  # Adjust custom objects as needed
loaded_model = tf.keras.models.load_model(local_dir, custom_objects=custom_objects)

# Helper functions
def load_and_preprocess_image(image):
    img = image.resize((256, 256))
    img = np.array(img)
    img = (img - 127.5) / 127.5  # Normalize to [-1, 1]
    img = np.expand_dims(img, axis=0)  # Add batch dimension
    return img

def infer_image(model, image):
    preprocessed_img = load_and_preprocess_image(image)
    generated_img = model(preprocessed_img, training=False)
    generated_img = tf.squeeze(generated_img, axis=0)  # Remove batch dimension
    generated_img = (generated_img * 127.5 + 127.5).numpy().astype(np.uint8)  # De-normalize to [0, 255]
    return generated_img

def load_image_from_url(url):
    response = requests.get(url)
    img = Image.open(BytesIO(response.content))
    return img

# Custom CSS
combined_css = """
    .main, .sidebar .sidebar-content { background-color: #1c1c1c; color: #f0f2f6; }
    .block-container { padding: 1rem 2rem; background-color: #333; border-radius: 10px; box-shadow: 0px 4px 10px rgba(0, 0, 0, 0.5); }
    .stButton>button, .stDownloadButton>button { background: linear-gradient(135deg, #ff7e5f, #feb47b); color: white; border: none; padding: 10px 24px; text-align: center; text-decoration: none; display: inline-block; font-size: 16px; margin: 4px 2px; cursor: pointer; border-radius: 5px; }
    .stSpinner { color: #4CAF50; }
    .title {
        font-size: 3rem;
        font-weight: bold;
        display: flex;
        align-items: center;
        justify-content: center;
    }
    .colorful-text {
        background: -webkit-linear-gradient(135deg, #ff7e5f, #feb47b);
        -webkit-background-clip: text;
        -webkit-text-fill-color: transparent;
    }
    .black-white-text {
        color: black;
    }
    .small-input .stTextInput>div>input {
        height: 2rem;
        font-size: 0.9rem;
    }
    .small-file-uploader .stFileUploader>div>div {
        height: 2rem;
        font-size: 0.9rem;
    }
    .custom-text {
        font-size: 1.2rem;
        color: #feb47b;
        text-align: center;
        margin-top: -20px;
        margin-bottom: 20px;
    }
"""

# Streamlit application
st.set_page_config(layout="wide")

st.markdown(f"<style>{combined_css}</style>", unsafe_allow_html=True)

st.markdown('<div class="title"><span class="colorful-text">Photo</span> <span class="black-white-text">to Van Gogh</span></div>', unsafe_allow_html=True)
st.markdown('<div class="custom-text">Convert photos to Van Gogh style using AI</div>', unsafe_allow_html=True)

# Streamlit UI
uploaded_file = st.file_uploader("Choose an image...", type="jpg")
image_url = st.text_input("Or enter an image URL:")

image = None
if uploaded_file is not None:
    image = Image.open(uploaded_file)
elif image_url:
    try:
        image = load_image_from_url(image_url)
    except Exception as e:
        st.error(f"Failed to load image from URL: {e}")

if image is not None:
    if st.button("Run Inference"):
        # Perform inference
        with st.spinner('Processing...'):
            generated_image = infer_image(loaded_model, image)
        
        # Display the original and generated images side by side
        st.markdown("### Result")
        col1, col2 = st.columns(2)

        with col1:
            st.image(image, caption='Original Image', use_column_width=True)
        with col2:
            st.image(generated_image, caption='Generated Image', use_column_width=True)
        
        # Provide a download button for the generated image
        img_byte_arr = BytesIO()
        Image.fromarray(generated_image).save(img_byte_arr, format='JPEG')
        img_byte_arr = img_byte_arr.getvalue()

        st.download_button(
            label="Download Generated Image",
            data=img_byte_arr,
            file_name="generated_image.jpg",
            mime="image/jpeg"
        )

        st.success("Image processed successfully!")