Datasets and pretrained Models for StyleGAN3 ...

Dear arfiticial friend, this is a collection of artistic datasets and models that we have put together during our ongoing stylegan3 trip at the lucid layers studios. You can use the model snapshots for instant fun, or you can work with the source datasets to train your own models.
Some models include multiple snapshots. these can give interesting variations.

tip: best viewed maximized

Updates

This Document will be updated frequently since a lot of models are still in training on higher resolutions. You find information on each update in the "releases" section. (you may "watch" this repo for getting notified on new models)

... based on Wombo Dream:

All source images in this category were generated with Wombo Dream. thanks to the cheesy api implementation of adri326 we could remotely generate thousands of images. these images were cropped to center and scaled to 1024x1024. datasets in resolutions of 256, 512 and 1024 were generated and are available for download.
Most datasets are tied to one single textpromt with some minor variations. But you may mix them together in new datasets to train multi domain models with style mixing.

Thanks to the wombo creators for their generous quota limits. since wombo is a free service, we like to share all batches that have been created.

1. Mechanical devices from the future

Dataset

Name	Mechanical devices from the future
Method	Wombo Dream via Wombot
Image count	2169
Dataset download	256, 512, 1024
Samples

Model: 256 px

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
29 kimg Download .pkl
05 kimg Download .pkl

2. Vivid Flowers

Dataset

Name	Vivid Flowers
Method	Wombo Dream via Wombot
Image count	793
Dataset download	256, 512, 1024
Samples

Model: 256 px

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
68 kimg Download .pkl
12 kimg Download .pkl

3. Alien with Sunglasses

Dataset

Name	Alien Sunglasses
Method	Wombo Dream via Wombot
Image count	1600
Dataset download	256, 512, 1024
Samples

Model: 256 px

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
38 kimg Download .pkl

4. forest daemons

Dataset

Name	forest daemons
Method	Wombo Dream via Wombot
Image count	794
Dataset download	256, 512, 1024
Samples

Model: 256 px

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
18 kimg Download .pkl
03 kimg Download .pkl

5. third eye watching you

Dataset

Name	third eye watching you
Method	Wombo Dream via Wombot
Image count	1363
Dataset download	256, 512, 1024
Samples

6. mars spaceport

Dataset

Name	mars spaceport
Method	Wombo Dream via Wombot
Image count	710
Dataset download	256, 512, 1024
Samples

7. scifi city

Dataset

Name	scifi city
Method	Wombo Dream via Wombot
Image count	1245
Dataset download	256, 512, 1024
Samples

Model: 256 px

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
210 kimg Download .pkl
018 kimg Download .pkl
013 kimg Download .pkl
008 kimg Download .pkl

8. scifi spaceship

Dataset

Name	scifi spaceship
Method	Wombo Dream via Wombot
Image count	1108
Dataset download	256, 512, 1024
Samples

Model: 256

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
168 kimg Download .pkl
128 kimg Download .pkl
13 kimg Download .pkl

9. yellow comic alien

Dataset

Name	yellow comic alien
Method	Wombo Dream via Wombot
Image count	3984
Dataset download	256, 512, 1024
Samples

Model 256x256

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
19 kimg Download .pkl

Model 512x512

Method	stylegan3-t, Transfer learning from affhq
Resolution	512x512
236 kimg Download .pkl
004 kimg Download .pkl

10. eternal planet earth

Dataset

Name	eternal planet earth
Method	Wombo Dream via Wombot
Image count	1323
Dataset download	256, 512, 1024
Samples

11. mechanical landscape madness

Dataset

Name	mechanical landscape madness
Method	Wombo Dream via Wombot
Image count	1269
Dataset download	256, 512, 1024
Samples

Model 256x256

Method	stylegan3-t, Transfer learning from Landscape256
Resolution	256x256
6 kimg Download .pkl
5 kimg Download .pkl

12. two aliens speaking

Dataset

Name	two_aliens_speaking
Method	Wombo Dream via Wombot
Image count	1159
Dataset download	256, 512, 1024
Samples

Usage

We recomend to install the official StyleGAN3 repo to your local machine. then use the "visualizer.py" to start the gui. The GUI is very comfortable to use and allows easy visual inspection of the models, in realtime. (RTX card recomended).
If you have troubles for installing on windows with anaconda, try this edited enviroment.yml file. this works with the current pytorch release (cuda11).
Alternatively you may use a colab notebook to generate images/videos from the model. Just copy the links from this page to your favorite colab notebook.
Here is a basic notebook, pre-configured for many of our models:

Progress

• prepare all datasets in resolutions 256, 512, 1024
• create a colab notebook for model testing
• train some datasets in 256
• train some datasets in 512
• train some datasets in 1024
• create multi domain datasets and models with style mixing

Contribution

If you do continue training on a model, or train a dataset in a high resolution, it would be great to include that in this list.
(please send me a link to your .pkl file in the "issues" tab)
Also, if you made some images or videos you like to share - we would love to see your work! put everything in the issues...

License

You are welcomed to use all files for your own purposes. please include a link to this repo in your work. Thank you.
(Terms and Conditions of Wombo, Nvidia and other contributors have to be considered seperately when doing commercial projects.)