Datasets and pretrained Models for StyleGAN3 ...

Overview

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
 network-snapshot-000029 pkl
05 kimg
Download .pkl
  network-snapshot-000005 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
network-snapshot-000067 pkl
12 kimg
Download .pkl
network-snapshot-000012 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
network-snapshot-000038 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
network-snapshot-000018 pkl
03 kimg
Download .pkl
network-snapshot-000003 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
Model: coming soon ...

coming soon ...

6. mars spaceport

Dataset
Name mars spaceport
Method Wombo Dream via Wombot
Image count 710
Dataset download 256, 512, 1024
Samples
Model: coming soon ...

coming soon ...

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
 network-snapshot-000210 pkl
018 kimg
Download .pkl
 network-snapshot-000018 pkl
013 kimg
Download .pkl
 network-snapshot-000013 pkl
008 kimg
Download .pkl
 network-snapshot-000008 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
network-snapshot-000162 pkl
128 kimg
Download .pkl
network-snapshot-000128 pkl
13 kimg
Download .pkl
network-snapshot-000013 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
network-snapshot-000019 pkl
Model 512x512
Method stylegan3-t, Transfer learning from affhq
Resolution 512x512
236 kimg
Download .pkl
network-snapshot-000236 pkl
004 kimg
Download .pkl
network-snapshot-000004 pkl

10. eternal planet earth

Dataset
Name eternal planet earth
Method Wombo Dream via Wombot
Image count 1323
Dataset download 256, 512, 1024
Samples
Model: coming soon ...

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
network-snapshot-000006 pkl
5 kimg
Download .pkl
network-snapshot-000005 pkl

12. two aliens speaking

Dataset
Name two_aliens_speaking
Method Wombo Dream via Wombot
Image count 1159
Dataset download 256, 512, 1024
Samples
Model: coming soon...

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:
Open In Colab

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.)

You might also like...
Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

This repository is a toolkit to do machine learning for programming languages. It implements tokenization, dataset preprocessing, model training and m

YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset
YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset

YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents Ultralytics open-source research int

Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.
Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.

Music Source Separation with Channel-wise Subband Phase Aware ResUnet (CWS-PResUNet) Introduction This repo contains the pretrained Music Source Separ

The PASS dataset: pretrained models and how to get the data -  PASS: Pictures without humAns for Self-Supervised Pretraining
The PASS dataset: pretrained models and how to get the data - PASS: Pictures without humAns for Self-Supervised Pretraining

The PASS dataset: pretrained models and how to get the data - PASS: Pictures without humAns for Self-Supervised Pretraining

Repository providing a wide range of self-supervised pretrained models for computer vision tasks.

Hierarchical Pretraining: Research Repository This is a research repository for reproducing the results from the project "Self-supervised pretraining

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Res2Net The official pytorch implemention of the paper "Res2Net: A New Multi-scale Backbone Architecture" Our paper is accepted by IEEE Transactions o

Pretrained models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet.
Pretrained models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet.

Pretrained models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet.

Using pretrained language models for biomedical knowledge graph completion.

LMs for biomedical KG completion This repository contains code to run the experiments described in: Scientific Language Models for Biomedical Knowledg

A library for finding knowledge neurons in pretrained transformer models.
A library for finding knowledge neurons in pretrained transformer models.

knowledge-neurons An open source repository replicating the 2021 paper Knowledge Neurons in Pretrained Transformers by Dai et al., and extending the t

Comments
  • Apply the model on a interactive art demo

    Apply the model on a interactive art demo

    Thank you so much for sharing your artistic model to the community. I'm a media art student new to machine learning. I'm currently apply your 'yellow comic alien 004 kimg' model on a interactive art demo. It looks pretty cool and I'm really appriciate your time and effort! Here is a video preview: https://youtu.be/lVJnj5PLghs

    opened by HarryGuan22 2
  • transfer learning params

    transfer learning params

    Yo! Can you post what sg3 params you used for transfer learning? The results are impressive even after 005 kimg! I personally never managed to make transfer learning work, from afhqv2, maybe my datasets were too big I guess.

    opened by betterftr 0
  • Lucid Stylegan Error

    Lucid Stylegan Error

    Using colab, lucid sonic dreams, stylegan3. The name of the folder is stylegan2, but it contains stylegan3. Downloaded womboflowers pkl (256x256, 05 kimg). How to fix that issue? Is it compatible? Used it as a style, receiving following error:

    Preparing style... Loading networks from /content/drive/MyDrive/LSD/lucid-sonic-dreams/womboflowers2.pkl...

    KeyError Traceback (most recent call last) in () 37 motion_randomness = 0.8, 38 motion_harmonic = True, ---> 39 motion_percussive = False, 40 #random_seed=100 41 #class_complexity = 1

    3 frames /content/drive/MyDrive/LSD/lucid-sonic-dreams/stylegan2/torch_utils/persistence.py in _reconstruct_persistent_obj(meta) 191 192 assert meta.type == 'class' --> 193 orig_class = module.dict[meta.class_name] 194 decorator_class = persistent_class(orig_class) 195 obj = decorator_class.new(decorator_class)

    KeyError: 'FullyConnectedLayer'

    Before it "module" was used here: line 190: module = _src_to_module(meta.module_src)

    opened by Ennorath 0
Releases(v1.0.1)
Owner
lucid layers
lucid layers
A GOOD REPRESENTATION DETECTS NOISY LABELS

A GOOD REPRESENTATION DETECTS NOISY LABELS This code is a PyTorch implementation of the paper: Prerequisites Python 3.6.9 PyTorch 1.7.1 Torchvision 0.

<a href=[email protected]"> 64 Jan 04, 2023
Jarvis Project is a basic virtual assistant that uses TensorFlow for learning.

Jarvis_proyect Jarvis Project is a basic virtual assistant that uses TensorFlow for learning. Latest version 0.1 Features: Good morning protocol Tell

Anze Kovac 3 Aug 31, 2022
Video Corpus Moment Retrieval with Contrastive Learning (SIGIR 2021)

Video Corpus Moment Retrieval with Contrastive Learning PyTorch implementation for the paper "Video Corpus Moment Retrieval with Contrastive Learning"

ZHANG HAO 42 Dec 29, 2022
eXPeditious Data Transfer

xpdt: eXPeditious Data Transfer About xpdt is (yet another) language for defining data-types and generating code for serializing and deserializing the

Gianni Tedesco 3 Jan 06, 2022
An implementation of the "Attention is all you need" paper without extra bells and whistles, or difficult syntax

Simple Transformer An implementation of the "Attention is all you need" paper without extra bells and whistles, or difficult syntax. Note: The only ex

29 Jun 16, 2022
Pytorch implementation of Distributed Proximal Policy Optimization: https://arxiv.org/abs/1707.02286

Pytorch-DPPO Pytorch implementation of Distributed Proximal Policy Optimization: https://arxiv.org/abs/1707.02286 Using PPO with clip loss (from https

Alexis David Jacq 163 Dec 26, 2022
Roadmap to becoming a machine learning engineer in 2020

Roadmap to becoming a machine learning engineer in 2020, inspired by web-developer-roadmap.

Chris Hoyean Song 1.7k Dec 29, 2022
用强化学习DQN算法,训练AI模型来玩合成大西瓜游戏,提供Keras版本和PARL(paddle)版本

用强化学习玩合成大西瓜 代码地址:https://github.com/Sharpiless/play-daxigua-using-Reinforcement-Learning 用强化学习DQN算法,训练AI模型来玩合成大西瓜游戏,提供Keras版本、PARL(paddle)版本和pytorch版本

72 Dec 17, 2022
This repository contains the implementation of the paper Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR Scans

Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR Scans This repository contains the implementation of the pap

Photogrammetry & Robotics Bonn 40 Dec 01, 2022
Testing and Estimation of structural breaks in Stata

xtbreak estimating and testing for many known and unknown structural breaks in time series and panel data. For an overview of xtbreak test see xtbreak

Jan Ditzen 13 Jun 19, 2022
MazeRL is an application oriented Deep Reinforcement Learning (RL) framework

MazeRL is an application oriented Deep Reinforcement Learning (RL) framework, addressing real-world decision problems. Our vision is to cover the complete development life cycle of RL applications ra

EnliteAI GmbH 222 Dec 24, 2022
CausalNLP is a practical toolkit for causal inference with text as treatment, outcome, or "controlled-for" variable.

CausalNLP CausalNLP is a practical toolkit for causal inference with text as treatment, outcome, or "controlled-for" variable. Install pip install -U

Arun S. Maiya 95 Jan 03, 2023
Sample and Computation Redistribution for Efficient Face Detection

Introduction SCRFD is an efficient high accuracy face detection approach which initially described in Arxiv. Performance Precision, flops and infer ti

Sajjad Aemmi 13 Mar 05, 2022
AI virtual gym is an AI program which can be used to exercise and can be used to see if we are doing the exercises

AI virtual gym is an AI program which can be used to exercise and can be used to see if we are doing the exercises

4 Feb 13, 2022
This repository implements WGAN_GP.

Image_WGAN_GP This repository implements WGAN_GP. Image_WGAN_GP This repository uses wgan to generate mnist and fashionmnist pictures. Firstly, you ca

Lieon 6 Dec 10, 2021
Code for the paper Learning the Predictability of the Future

Learning the Predictability of the Future Code from the paper Learning the Predictability of the Future. Website of the project in hyperfuture.cs.colu

Computer Vision Lab at Columbia University 139 Nov 18, 2022
Traffic4D: Single View Reconstruction of Repetitious Activity Using Longitudinal Self-Supervision

Traffic4D: Single View Reconstruction of Repetitious Activity Using Longitudinal Self-Supervision Project | PDF | Poster Fangyu Li, N. Dinesh Reddy, X

25 Dec 21, 2022
Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

Volume rendering + 3D implicit surface Showcase What? previous: surface rendering; now: volume rendering previous: NeRF's volume density; now: implici

Jianfei Guo 682 Jan 04, 2023
Accepted at ICCV-2021: Workshop on Computer Vision for Automated Medical Diagnosis (CVAMD)

Is it Time to Replace CNNs with Transformers for Medical Images? Accepted at ICCV-2021: Workshop on Computer Vision for Automated Medical Diagnosis (C

Christos Matsoukas 80 Dec 27, 2022
Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Improving Transferability of Representations via Augmentation-Aware Self-Supervision Accepted to NeurIPS 2021 TL;DR: Learning augmentation-aware infor

hankook 38 Sep 16, 2022