README.md

---
license: apache-2.0
tags:
- stylegan2
- image-generation
---

# AniCharaGAN: Anime Character Generation with StyleGAN2

[![GitHub Repo stars](https://img.shields.io/github/stars/eugenesiow/practical-ml?style=social)](https://github.com/eugenesiow/practical-ml)

This model uses the awesome lucidrains’s [stylegan2-pytorch](https://github.com/lucidrains/stylegan2-pytorch) library to train a model on a private anime character dataset to  generate full-body 256x256 female anime characters.

Here are some samples:

![Samples of anime characters and styles generated by the model](images/samples1.jpg "Samples of anime characters and styles generated by the model")

## Model description
The model generates 256x256, square, white background, full-body anime characters. It is trained using [stylegan2-pytorch](https://github.com/lucidrains/stylegan2-pytorch). It is trained to 150 epochs.

## Intended uses & limitations
You can use the model for generating anime characters and than use a super resolution library like [super_image](https://github.com/eugenesiow/super-image) to upscale.

### How to use

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/eugenesiow/practical-ml/blob/master/notebooks/Anime_Character_Generation_with_StyleGAN2.ipynb "Open in Colab")

Install the dependencies:
```bash
pip install -q stylegan2_pytorch==1.5.10
```
Here is how to generate images:
```python
import torch
from torchvision.utils import save_image
from stylegan2_pytorch import ModelLoader
from pathlib import Path

Path('./models/ani-chara-gan/').mkdir(parents=True, exist_ok=True)
torch.hub.download_url_to_file('https://huggingface.co/eugenesiow/ani-chara-gan/resolve/main/model.pt',
                               './models/ani-chara-gan/model_150.pt')
torch.hub.download_url_to_file('https://huggingface.co/eugenesiow/ani-chara-gan/resolve/main/.config.json',
                               './models/ani-chara-gan/.config.json')

loader = ModelLoader(
    base_dir = './', name = 'ani-chara-gan'
)

noise   = torch.randn(1, 256).cuda() # noise
styles  = loader.noise_to_styles(noise, trunc_psi = 0.7)  # pass through mapping network
images  = loader.styles_to_images(styles) # call the generator on intermediate style vectors

save_image(images, './sample.jpg')
```

## BibTeX entry and citation info

The model is part of the [practical-ml](https://github.com/eugenesiow/practical-ml) repository.

[![GitHub Repo stars](https://img.shields.io/github/stars/eugenesiow/practical-ml?style=social)](https://github.com/eugenesiow/practical-ml)