stylegan3

by NVlabs · Developer Tools

Official PyTorch implementation of StyleGAN3

New0 ratings6,939 starsActive
Developer ToolsDeveloper ToolPythonCuda
GitHub⚑ Report
stylegan3 — image 1
stylegan3 — image 2
stylegan3 — image 3
1 / 3

About this project

Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation of the NeurIPS 2021 paper Alias-Free Generative Adversarial Networks Tero Karras, Miika Aittala, Samuli Laine, Erik Härkönen, Janne Hellsten, Jaakko Lehtinen, Timo Aila https://nvlabs.github.io/stylegan3 Abstract: We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of depicted objects. We trace the root cause to careless signal processing that…

Technologies

PythonC++DockerfileCuda

Project health

Inactive for over a year
Last update2 years ago
Contributors3
Latest release
Open issues & PRs192
LicenseOther
On GitHubsince 2021

GitHub

6,939
stars
1,239
forks
3
contributors
192
open issues & PRs
Python
language
2 years ago
last commit
View on GitHub ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review stylegan3.

Built by

NVlabs
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain NVlabs/stylegan3? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like