News
(2020.12.25) AnimeGANv3 will be released along with its paper in the spring of 2021.
(2021.02.21) The pytorch version of AnimeGANv2 has been released, Be grateful to @bryandlee for his contribution.

Focus:

News:

The improvement directions of AnimeGANv2 mainly include the following 4 points:  

• 1. Solve the problem of high-frequency artifacts in the generated image.

• 2. It is easy to train and directly achieve the effects in the paper.

• 3. Further reduce the number of parameters of the generator network. (generator size: 8.17 Mb), The lite version has a smaller generator model.

• 4. Use new high-quality style data, which come from BD movies as much as possible.

        AnimeGAN can be accessed from here.

• python 3.6
• tensorflow-gpu 1.15.0 (GPU 2080Ti, cuda 10.0.130, cudnn 7.6.0)
• opencv
• tqdm
• numpy
• glob
• argparse
• onnxruntime (If onnx file needs to be run.)

python test.py --checkpoint_dir checkpoint/generator_Hayao_weight --test_dir dataset/test/HR_photo --save_dir Hayao/HR_photo

python video2anime.py --video video/input/お花見.mp4 --checkpoint_dir checkpoint/generator_Hayao_weight --output video/output

vgg19.npy

Link

python edge_smooth.py --dataset Hayao --img_size 256

python train.py --dataset Hayao --epoch 101 --init_epoch 10

python get_generator_ckpt.py --checkpoint_dir ../checkpoint/AnimeGANv2_Shinkai_lsgan_300_300_1_2_10_1 --style_name Shinkai

😍 Photo to Paprika Style

😍 Photo to Hayao Style

😍 Photo to Shinkai Style

This repo is made freely available to academic and non-academic entities for non-commercial purposes such as academic research, teaching, scientific publications. Permission is granted to use the AnimeGANv2 given that you agree to my license terms. Regarding the request for commercial use, please contact us via email to help you obtain the authorization letter.

Xin Chen