amirzenoozi / argan

[Open Source]. ARGAN - The improved version of AnimeGAN. Landscape photos/videos to anime

ARGANv1

[Open Sourc]. The improved version of AnimeGANv2.
AnimeGANv2 | Landscape photos/videos to anime

**Focus:**

Anime style	Film	Picture Number	Quality	Download Style Dataset
Miyazaki Hayao	The Wind Rises	1752	1080p	Link
Makoto Shinkai	Your Name & Weathering with you	1445	BD
Kon Satoshi	Paprika	1284	BDRip

___

---

Results

Requirements

You Can Use requirements file to install all packages that you need.

Usage

1. Download Pretrained Model

• Models

2. Download Train/Val Photo dataset

Download

3. Do edge_smooth

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

4. Calculate the three-channel(BGR) color difference

python data_mean.py --dataset Hayao

5. Train

python main.py --phase train --dataset Hayao --data_mean [13.1360,-8.6698,-4.4661] --epoch 101 --init_epoch 10

For light version:

python main.py --phase train --dataset Hayao --data_mean [13.1360,-8.6698,-4.4661]  --light --epoch 101 --init_epoch 10

6. Extract the weights of the generator

python get_generator_ckpt.py --checkpoint_dir  ../checkpoint/ARGANv1_Hayao_lsgan_300_300_1_2_10_1  --style_name Hayao

7. Inference

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

8. Convert video to anime

python video2anime.py  --video input.mp4  --checkpoint_dir  checkpoint/generator_Paprika_weight

---

License

This repo is made freely available to academic and non-academic entities for non-commercial purposes such as academic research, teaching, and scientific publications. Permission is granted to use the ARGANv1 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.

Citation

If you find our work useful in your research or publications, please consider citing the main paper:

@INPROCEEDINGS{9738752,
  author={Zenoozi, Amirhossein Douzandeh and Navi, Keivan and Majidi, Babak},
  booktitle={2022 International Conference on Machine Vision and Image Processing (MVIP)}, 
  title={ARGAN: Fast Converging GAN for Animation Style Transfer}, 
  year={2022},
  volume={},
  number={},
  pages={1-5},
  doi={10.1109/MVIP53647.2022.9738752}
}

And This Repository:

@software{Douzandeh_Zenoozi_ARGAN_GitHub_Repository_2023,
   author = {Douzandeh Zenoozi, Amirhossein},
   doi = {10.5281/zenodo.8075534},
   month = jun,
   title = {{ARGAN GitHub Repository}},
   url = {https://github.com/amirzenoozi/ARGAN},
   version = {1.0.0},
   year = {2023}
}

Author

Amirhossein Douzandeh Zenoozi