app.py

import gradio as gr
import tensorflow as tf
import tensorflow_hub as hub
import matplotlib.pylab as plt
import numpy as np

hub_model = hub.load('https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2')

def stylize(content_image_path, style_image_path):
    content_image = plt.imread(content_image_path)
    style_image = plt.imread(style_image_path)
    content_image = content_image.astype(np.float32)[np.newaxis, ...] / 255.
    style_image = style_image.astype(np.float32)[np.newaxis, ...] / 255.
    style_image = tf.image.resize(style_image, (256, 256))
    
    stylized_image = hub_model(tf.constant(content_image), tf.constant(style_image))[0]
    return tensor_to_image(stylized_image)
    
    
# Load content and style images (see example in the attached colab).
#content_image = plt.imread(content_image_path)
#style_image = plt.imread(style_image_path)

# Convert to float32 numpy array, add batch dimension, and normalize to range [0, 1]. Example using numpy:
#content_image = content_image.astype(np.float32)[np.newaxis, ...] / 255.
#style_image = style_image.astype(np.float32)[np.newaxis, ...] / 255.

# Optionally resize the images. It is recommended that the style image is about
# 256 pixels (this size was used when training the style transfer network).
# The content image can be any size.
# style_image = tf.image.resize(style_image, (256, 256))


iface = gr.Interface(fn=stylize, inputs=["image", "image"], outputs="image")
iface.launch()