TF Hub Wrapper - Style Transfer

This package contains functions to properly load and process images for input to Google's TensorFlow Hub v2 model for fast arbitrary image style transfer and obtain a style-transferred output image.

Usage:

First, install the package with pip:

pip install tfhub-styletransfer-wrapper

Then import the package:

from tfhub_styletransfer_wrapper import StyleHub

And call the hub evaluation function:

stylehub = StyleHub()
stylehub.load_content(content_image_filename, 512)
stylehub.load_style(style_image_filename, 256)
stylized_image = stylehub.evaluate(True)

This will "re-draw" the input image specified by "input_image.jpg" in a style similar to that found in the image specified by "style_image.jpg".

Note that while different style sizes can be used, the TensorFlow Hub v2 model was trained on 256x256 images, so increasing the style_size parameter any higher than 256 is not recommended.

More examples