# Animating using AnimeGanV2
*author: Filip Haltmayer*

## Description

Convert an image into an animated image using [`AnimeganV2`](https://github.com/TachibanaYoshino/AnimeGANv2).


## Code Example
Load an image from path './test.png'. 

 *Write the pipeline in simplified style*:

```python
import towhee

towhee.glob('/Users/chenshiyu/workspace/data/pic/test.png') \
      .image_decode.cv2() \
      .img2img_translation.animegan(model_name = 'hayao') \
      .show()
```

<img src="./results1.png" alt="results1" style="height:120px;"/>

*Write a same pipeline with explicit inputs/outputs name specifications:*

```python
import towhee

towhee.glob['path']('/Users/chenshiyu/workspace/data/pic/test.png') \
      .image_decode.cv2['path', 'origin']() \
      .img2img_translation.animegan['origin', 'transformed'](model_name = 'hayao') \
      .select('origin', 'transformed') \
      .show()
```

<img src="./results2.png" alt="results1" style="height:120px;"/>

## Factory Constructor

Create the operator via the following factory method

***img2img_translation.animegan(model_name = 'which anime model to use')***

Model options: 
- celeba
- facepaintv1
- facepaintv2
- hayao
- paprika
- shinkai

## Interface

Takes in a numpy rgb image in channels first. It transforms input into animated image in numpy form.


**Parameters:**

​	***model_name***: *str*

​	Which model to use for transfer.

   ***framework***: *str*

​	Which ML framework being used, for now only supports PyTorch.



**Returns**: *numpy.ndarray*

​	The new image.


## Reference

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.