Awesome

Awesome Pretrained StyleGAN

A collection of pre-trained StyleGAN models trained on different datasets at different resolution.

For the equivalent collection for StyleGAN 2, see this repo

If you have a publically accessible model which you know of, or would like to share please see the contributing section. Hint: the simplest way to submit a model is to fill in this form.

Table of Contents

• Models

  • LSUN Bedrooms
  • LSUN Cars
  • LSUN Cats
  • CelebA HQ Faces
  • FFHQ Faces
  • Pokemon
  • Anime Faces
  • Anime Portraits
  • WikiArt Faces
  • Abstract Photos
  • Vases
  • Fireworks
  • Ukiyo-e Faces
  • Butterflies

• Contributing

LSUN Bedrooms

• Dataset: LSUN bedrooms
• Resolution: 256x256
• Author: karras
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: https://github.com/NVlabs/stylegan/blob/master/LICENSE.txt
• Source

LSUN Cars

• Dataset: LSUN cars
• Resolution: 512x384
• Author: karras
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: https://github.com/NVlabs/stylegan/blob/master/LICENSE.txt
• Source

LSUN Cats

• Dataset: LSUN cats
• Resolution: 256x256
• Author: karras
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: https://github.com/NVlabs/stylegan/blob/master/LICENSE.txt
• Source

CelebA HQ Faces

• Dataset: CelebAHQ
• Resolution: 1024x1024
• Author: karras
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: https://github.com/NVlabs/stylegan/blob/master/LICENSE.txt
• Source

FFHQ Faces

• Dataset: FFHQ
• Resolution: 1024x1024
• Author: karras
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: https://github.com/NVlabs/stylegan/blob/master/LICENSE.txt
• Source

Pokemon

• Dataset: Unknown
• Resolution: 256x256
• Author: Michael Friesen
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: Unknown
• Source

Anime Faces

• Dataset: Danbooru2017
• Resolution: 512x512
• Author: gwern
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: Unknown
• Source

Anime Portraits

• Dataset: Danbooru2017
• Resolution: 512x512
• Author: gwern
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: Unknown
• Source

WikiArt Faces

• Dataset: WikiArt
• Resolution: 512x512
• Author: ak9250
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: https://github.com/ak9250/stylegan-art/blob/master/LICENSE.txt
• Source

Abstract Photos

• Dataset: 1-2-3 Abstract Photography Flickr Group
• Resolution: 512x512
• Author: Michael Friesen
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: Unknown
• Source

Vases

• Dataset: Museum photos
• Resolution: 1024x1024
• Author: Derek Philip Au
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: Unknown
• Source

Fireworks

• Dataset: Unknown
• Resolution: 512x512
• Author: Jonathan Fly
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: Unknown
• Source

Ukiyo-e Faces

• Dataset: Museum photos
• Resolution: 512x512
• Author: Justin Pinkney
• Download link
• StyleGAN implementation: https://github.com/NVlabs/stylegan
• Licence: Unknown
• Source

Butterflies

• Dataset: London Natural History Museum butterflies
• Resolution: 256x256
• Author: Marian Kleineberg
• Download link
• StyleGAN implementation: https://github.com/marian42/style-based-gan-pytorch
• Licence: Unkown
• Source

Contributing

TLDR: You can either edit the models.csv file or fill out this form.

This readme is automatically generated using Jinja, please do not try and edit it directly. Information about the models is stored in models.csv please add your model to this file. Preview images are generated automatically and the process is used to test the link so please only edit the csv file.