Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/ttop32/arcaneanimegan

AnimeGAN2 trained on Arcane
https://github.com/ttop32/arcaneanimegan

alignment anime animegan animegan2 animeganv2 arcanegan blending blur face-alignment fastai fine-tuning gan generative-adversarial-network image2image pytorch style-transfer stylegan stylegan3 torch weight

Last synced: 3 months ago
JSON representation

AnimeGAN2 trained on Arcane

Host: GitHub
URL: https://github.com/ttop32/arcaneanimegan
Owner: ttop32
License: mit
Created: 2021-12-24T03:46:19.000Z (about 3 years ago)
Default Branch: main
Last Pushed: 2022-01-06T06:42:05.000Z (about 3 years ago)
Last Synced: 2023-03-10T11:07:19.523Z (almost 2 years ago)
Topics: alignment, anime, animegan, animegan2, animeganv2, arcanegan, blending, blur, face-alignment, fastai, fine-tuning, gan, generative-adversarial-network, image2image, pytorch, style-transfer, stylegan, stylegan3, torch, weight
Language: Jupyter Notebook
Homepage:
Size: 32.3 MB
Stars: 22
Watchers: 1
Forks: 2
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # ArcaneAnimeGAN

[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1sBnFG9XR0euphD1LLspZOD2hxfyBwooN?usp=sharing)  

AnimeGAN2 trained on Arcane   

trying to follow bryandlee animegan2 training methodology   

  

# Result   

![result](doc/result0.2.png)    

# Training Workflow

- Get video data

- Split video into frames

- Align frame image using face-alignment

- Filter blurry image using opencv Laplacian

- Zip image dataset for fit into styleGAN

- Finetune FFHQ pretrained styleGAN using created zip dataset

- Blend findtuned styleGAN weight and pretrained styleGAN weight 

- Create data pair using blended styleGAN model and pretrained model

- Train animeGAN using paired data

  

# Change log

- 0.2

  - use anime-face-detector 

  - add color correction on data preprocessing

  - add aug_transforms() on batch transform

  - use l1_loss(vgg(g(x)), vgg(y)) and mse_loss(g(x), y) instead of vgg feature loss and gram matrix loss

- 0.1

  - first release

# To Do

- Use animegan vgg19[0,255] instead of vgg19_bn[0,1]

- Add canny edge method to gaussigan blur

- Background segmentation

  

# Required environment to run    

```python

!conda install pytorch torchvision cudatoolkit=11.1 -c pytorch -c nvidia -y

!sudo apt install ffmpeg

!pip install face-alignment

!pip install --upgrade psutil

!pip install kornia

!pip install fastai==2.5.3

!pip install opencv-python

!git clone https://github.com/NVlabs/stylegan3.git

!pip install openmim

!mim install mmcv-full mmdet mmpose -y

!pip install anime-face-detector --no-dependencies

```

  

# Acknowledgement and References  

- [AnimeGAN](https://github.com/TachibanaYoshino/AnimeGAN)  

- [AnimeGANv2](https://github.com/TachibanaYoshino/AnimeGANv2)  

- [animegan2-pytorch](https://github.com/bryandlee/animegan2-pytorch)  

- [animegan2-pytorch-Face-Portrait-v1](https://github.com/bryandlee/animegan2-pytorch/issues/3)  

- [pytorch-animeGAN](https://github.com/ptran1203/pytorch-animeGAN)  

- [AnimeGANv2_pytorch](https://github.com/wan-h/AnimeGANv2_pytorch)  

- [AnimeGAN_in_Pytorch](https://github.com/XuHangkun/AnimeGAN_in_Pytorch)  

- [AnimeGAN-torch](https://github.com/MrVoid918/AnimeGAN-torch)  

- [style_transfer_implementation](https://github.com/Snailpong/style_transfer_implementation)  

- [Anime-Sketch-Coloring](https://github.com/pradeeplam/Anime-Sketch-Coloring-with-Swish-Gated-Residual-UNet)  

- [CartoonGAN-Tensorflow](https://github.com/taki0112/CartoonGAN-Tensorflow)  

- [cartoon-gan](https://github.com/FilipAndersson245/cartoon-gan)  

- [pytorch-implementation-of-perceptual-losses](https://towardsdatascience.com/pytorch-implementation-of-perceptual-losses-for-real-time-style-transfer-8d608e2e9902)  

- [Artistic-Style-Transfer](https://kyounju.tistory.com/3)  

-   

- [animegan2-pytorch-arcane](https://github.com/bryandlee/animegan2-pytorch/issues/17)  

- [DeepStudio](https://github.com/bryandlee/DeepStudio)  

- [ArcaneGAN](https://github.com/Sxela/ArcaneGAN)  

- [stylegan3_blending](https://github.com/Sxela/stylegan3_blending)  

- [toonify](https://github.com/justinpinkney/toonify)  

- [BlendGAN](https://github.com/onion-liu/BlendGAN)  

- [Cartoon-StyleGAN](https://github.com/happy-jihye/Cartoon-StyleGAN)  

- [FFHQ-Alignment](https://github.com/happy-jihye/FFHQ-Alignment)  

- [FFHQ-dataset](https://github.com/NVlabs/ffhq-dataset)

- [face-alignment](https://github.com/1adrianb/face-alignment)  

- [stylegan3](https://github.com/NVlabs/stylegan3)  

- [FreezeD](https://github.com/sangwoomo/FreezeD)  

- [Image-Blur-Detection](https://github.com/priyabagaria/Image-Blur-Detection)  

- [Classifying_image_blur_nonblur](https://github.com/pranavAL/Classifying_image_blur_nonblur)

- [arcane](https://www.netflix.com/kr/title/81435684)

- [JoJoGAN](https://github.com/mchong6/JoJoGAN)

- [anime-face-detector](https://github.com/hysts/anime-face-detector)

- [color correction](https://github.com/luftj/MaRE/blob/4284fe2b3307ca407e87e3b0dbdaa3c1ef646731/simple_cb.py)

- [White-box-Cartoonization](https://github.com/SystemErrorWang/White-box-Cartoonization)