Create app py

app py

@@ -0,0 +1,118 @@
+import gradio as gr
+import tensorflow as tf
+import tensorflow_hub as hub
+import numpy as np
+from PIL import Image, ImageEnhance, ImageFilter
+from rembg import remove
+
+# Load the neural style transfer model from TensorFlow Hub
+model = hub.load('https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2')
+
+# Function to convert tensor to image
+def tensor_to_image(tensor):
+    tensor = tensor * 255
+    tensor = np.array(tensor, dtype=np.uint8)
+    if np.ndim(tensor) > 3:
+        assert tensor.shape[0] == 1
+        tensor = tensor[0]
+    return Image.fromarray(tensor)
+
+# Function to separate foreground and background
+def separate_foreground_background(image):
+    if isinstance(image, np.ndarray):
+        image = Image.fromarray(image)
+
+    output_image = remove(image)
+    input_rgb = np.array(image.convert('RGB'))
+    output_rgba = np.array(output_image)
+
+    alpha = output_rgba[:, :, 3]
+    alpha3 = np.dstack((alpha, alpha, alpha))
+    background_rgb = input_rgb.astype(np.float32) * (1 - alpha3.astype(np.float32) / 255)
+    background_rgb = background_rgb.astype(np.uint8)
+
+    foreground = Image.fromarray(output_rgba)
+    background = Image.fromarray(background_rgb)
+    return foreground, background
+
+# Style transfer function
+def apply_style_transfer(content_image, style_image, intensity=1.0):
+    content_image = content_image.astype(np.float32)[np.newaxis, ...] / 255.0
+    style_image = style_image.astype(np.float32)[np.newaxis, ...] / 255.0
+
+    style_image = style_image * intensity
+    outputs = model(tf.constant(content_image), tf.constant(style_image))
+    stylized_image = outputs[0]
+
+    return tensor_to_image(stylized_image)
+
+# Function to enhance the image to make it glistening
+def enhance_image(image):
+    # Convert to Image for processing
+    if isinstance(image, np.ndarray):
+        image = Image.fromarray(image)
+
+    # Enhance color
+    enhancer = ImageEnhance.Color(image)
+    image = enhancer.enhance(1.5)  # Increase color saturation
+
+    # Enhance contrast
+    enhancer = ImageEnhance.Contrast(image)
+    image = enhancer.enhance(1.3)  # Increase contrast
+
+    # Apply a slight blur to simulate glow
+    image = image.filter(ImageFilter.GaussianBlur(radius=2))
+
+    # Optionally add noise (uncomment to use)
+    # noise = np.random.normal(0, 25, (image.height, image.width, 3))
+    # noise_image = np.array(image) + noise
+    # image = Image.fromarray(np.clip(noise_image, 0, 255).astype(np.uint8))
+
+    return image
+
+# Function to process image
+def process_image(content_image, style_image):
+    # Ensure style_image is a PIL Image
+    if isinstance(style_image, np.ndarray):
+        style_image = Image.fromarray(style_image)
+
+    foreground, background = separate_foreground_background(content_image)
+
+    # Resize all images to the same size
+    target_size = (512, 512)  # Example size, adjust as needed
+    foreground = foreground.resize(target_size, Image.LANCZOS)
+    background = background.resize(target_size, Image.LANCZOS)
+    style_image = style_image.resize(target_size, Image.LANCZOS)
+
+    # Convert to RGB format by removing the alpha channel
+    foreground_rgb = np.array(foreground.convert('RGB'))
+    background_rgb = np.array(background)
+
+    styled_foreground = apply_style_transfer(foreground_rgb, np.array(style_image.convert('RGB')), intensity=1.0)
+    styled_background = apply_style_transfer(background_rgb, np.array(style_image.convert('RGB')), intensity=0.3)
+
+    styled_foreground_np = np.array(styled_foreground)
+    styled_background_np = np.array(styled_background)
+
+    # Extract the alpha channel from the foreground
+    alpha = np.array(foreground)[:, :, 3] / 255.0
+    combined_image_np = (styled_foreground_np * alpha[..., np.newaxis] +
+                         styled_background_np * (1 - alpha[..., np.newaxis]))
+
+    combined_image = Image.fromarray(np.clip(combined_image_np, 0, 255).astype(np.uint8))
+
+    # Apply enhancement to make it glistening
+    enhanced_image = enhance_image(combined_image)
+
+    return enhanced_image
+
+# Gradio interface setup
+image1 = gr.Image(label="Content Image")
+image2 = gr.Image(label="Style Image")
+stylizedimg = gr.Image(label="Result")
+gr.Interface(
+    fn=process_image,
+    inputs=[image1, image2],
+    outputs=stylizedimg,
+    
+).launch()