# AnimeGAN

**Repository Path**: milixiang/AnimeGAN

## Basic Information

- **Project Name**: AnimeGAN
- **Description**: A Tensorflow implementation of AnimeGAN for fast photo animation  ! This is the Open source of the paper <AnimeGAN: a novel lightweight GAN for photo animation>, which uses the GAN framwork to transform real-world photos into anime images.
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 2
- **Forks**: 2
- **Created**: 2020-03-27
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# AnimeGAN
A Tensorflow implementation of AnimeGAN for fast photo animation  !!!
  
-----  
This is the Open source of the paper <AnimeGAN: a novel lightweight GAN for photo animation>, which uses the GAN framwork to transform real-world photos into anime images.  
___  

## Requirements  
- python 3.6.8  
- tensorflow-gpu 1.8  
- opencv  
- tqdm  
- numpy  
- glob  
- argparse  
  
## Usage  
### 1. Download vgg19 or Pretrained model  
> [vgg19.npy](https://github.com/TachibanaYoshino/AnimeGAN/releases/tag/vgg16%2F19.npy)  
  
> [Pretrained model](https://github.com/TachibanaYoshino/AnimeGAN/releases/tag/Haoyao-style_V1.0)  

### 2. Download dataset  
> [Link](https://github.com/TachibanaYoshino/AnimeGAN/releases/tag/dataset-1)  

### 3. Do edge_smooth  
  eg. `python edge_smooth.py --dataset Haoyao --img_size 256`  
  
### 3. Train  
  eg. `python main.py --phase train --dataset Haoyao --epoch 101 --init_epoch 1`  
  
### 4. Test  
  eg. `python main.py --phase test --dataset Hayao`  
  or `python test.py --checkpoint_dir checkpoint/AnimeGAN_Hayao_lsgan_300_300_1_3_10 --test_dir dataset/test/real --style_name H`  
  
____  
## Results  
------> pictures from the paper 'AnimeGAN: a novel lightweight GAN for photo animation'  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/doc/sota.png)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/doc/e2.png)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/doc/e3.png)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/doc/e4.png)  

------> Photo  to  Hayao  Style  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(37).jpg)![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(37).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(1).jpg)![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(1).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(20).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(20).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(21).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(21).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(22).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(22).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(23).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(23).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(24).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(24).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(46).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(46).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(30).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(30).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(28).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(28).jpg)  
![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo/1%20(38).jpg) ![](https://github.com/TachibanaYoshino/AnimeGAN/blob/master/result/Hayao/photo_result/1%20(38).jpg)  
____  
## Acknowledgment  
This code is based on the [CartoonGAN-Tensorflow](https://github.com/taki0112/CartoonGAN-Tensorflow/blob/master/CartoonGAN.py) and [Anime-Sketch-Coloring-with-Swish-Gated-Residual-UNet](https://github.com/pradeeplam/Anime-Sketch-Coloring-with-Swish-Gated-Residual-UNet). Thanks to the contributors of this project.