bryandlee/malnyun_faces
A StyleGAN-based image generator fine-tuned on 500 cartoon face images from webcomics to produce new cartoon faces at 256x256 resolution.

This project fine-tunes a pre-trained StyleGAN model (originally trained on FFHQ human faces) on a small dataset of 500 manually annotated cartoon face images extracted from webcomics. It uses the FreezeD technique, which freezes early discriminator layers during fine-tuning to preserve learned semantic features while adapting to the new cartoon domain. The model was trained for about 50k steps on a single RTX 2080ti GPU over roughly 10 hours.
Frequently asked
- What is bryandlee/malnyun_faces?
- A StyleGAN-based image generator fine-tuned on 500 cartoon face images from webcomics to produce new cartoon faces at 256x256 resolution.
- Is malnyun_faces open source?
- Yes — bryandlee/malnyun_faces is an open-source project tracked on heatdrop.
- How popular is malnyun_faces?
- bryandlee/malnyun_faces has 902 stars on GitHub.
- Where can I find malnyun_faces?
- bryandlee/malnyun_faces is on GitHub at https://github.com/bryandlee/malnyun_faces.