A tutorial explaining how to train and generate high-quality anime faces with StyleGAN 1+2 neural networks, and tips/scripts for effective StyleGAN use.
How to use StyleGAN-2, an improvement to StyleGAN released in December 2019, which removes the blob artifacts and is generally of somewhat higher visual quality.
StyleGAN 2 is tricky to use because it requires custom local compilation of optimized code. Aaron Gokaslan provided tips on getting StyleGAN 2 running and trained a StyleGAN 2 on my anime portraits, which is available for download and which I use to create TWDNEv3.
- Examples
- Background
- FAQ
- Training Requirements
- Data Preparation
- Training
- Sampling
- Models
- Transfer Learning
- Reversing StyleGAN To Control & Modify Images
- StyleGAN 2
- Future Work
- BigGAN
- See Also
- External Links
- Appendix