Pipeline: Style Transfer using AnimeGanV2

Authors: filip

Overview

The pipeline is used to animate images. It uses the AnimeGanV2 to cartoonize the images.

Interface

Input Arguments:

• img_path:
  • the input image path
  • supported types: str

Pipeline Output:

The pipeline returns a tuple Tuple[('styled_image', numpy.ndarray)] containing following fields:

• styled_image:
  • styled photo
  • data type: numpy.ndarray
  • shape: (3, x, x)
  • format: RGB
  • values: [0,1]

How to use

1. Install Towhee

$ pip3 install towhee

You can refer to Getting Started with Towhee for more details. If you have any questions, you can submit an issue to the towhee repository.

2. Run it with Towhee

>>> from towhee import pipeline

>>> img_path = 'path/to/your/image'
>>> embedding_pipeline = pipeline('filip-halt/style-transfer-animegan')
>>> embedding = embedding_pipeline(img_path)

How it works

This pipeline includes one operator: filip-halt/animegan-style-transfer. This operator stylizes the image.

Refer Towhee architecture for basic concepts in Towhee: pipeline, operator, dataframe.

References

Jie Chen, Gang Liu, Xin Chen "AnimeGAN: A Novel Lightweight GAN for Photo Animation." ISICA 2019: Artificial Intelligence Algorithms and Applications pp 242-256, 2019.