stylegan2-ada VS awesome-pretrained-stylegan2

Compare stylegan2-ada vs awesome-pretrained-stylegan2 and see what are their differences.


StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation (by NVlabs)


A collection of pre-trained StyleGAN 2 models to download (by justinpinkney)
Our great sponsors
  • - Optimize your datasets for ML
  • Nanos - Run Linux Software Faster and Safer than Linux with Unikernels
  • Scout APM - A developer's best friend. Try free for 14-days
stylegan2-ada awesome-pretrained-stylegan2
18 5
1,421 769
4.4% -
1.3 1.0
9 months ago 4 months ago
Python Python
GNU General Public License v3.0 or later -
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.


Posts with mentions or reviews of stylegan2-ada. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2021-07-14.
  • AI will shape up the workflow of the future. Here's a simple implementation of NVidia's StyleGAN inside Blender! | 2021-09-13
    StyleGAN2-ADA is a neural network good at learning styles from images, you can give it a dataset and 'learn' its style into a file (a trained model). In this example, I load a model and given a random seed, generate a random texture which is applied to the object's material.
  • How do you generate those latent walk animations?
    I understand the concept you're describing, but I'm unsure how to implement it in practice. The documentation on Stylegan2's GitHub page doesn't mention anything on it I can see.
    You have to modify the code, it's line 60 in
  • [D] Do I need to apply spectral norm to my embedding matrix when training a conditional W-GAN?
  • Can I train a model on 100 images of homes and have it draw a couple "average" homes?
  • New 'The Sculpture 3'. 3d sculpting + neural network | 2021-04-27
    no i dont.. but as for training - i just use default tf stylegan2-ada repo ( )
  • [R] EigenGAN: Layer-Wise Eigen-Learning for GANs
    You should check stylegan-2 ada, it works on colab and can be trained less than 12 hours tensorflow implementation
  • gamma
  • I have been making art with deep neural networks lately, and at some point one of them started outputting these cosmic creatures, so I thought I'd share. | 2021-04-21
    This image looks awesome! And this process sounds really interesting, any more specific tips on where to get started? I studied Neuroscience, use Linux and Python for data analysis, but haven't done any image editing yet. I found the code but it seems like I need a GPU. Which I don't have, unless I use the servers at my university lol
  • An interpolation from an AI trained on liminal images
    with a process called ADA


Posts with mentions or reviews of awesome-pretrained-stylegan2. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2021-07-27.
  • Quick and Easy GAN Domain Adaptation explained: Sketch Your Own GAN by Sheng-Yu Wang et al. 5 minute summary
    Hi! That's the point, you actually don't need an entire dataset. Just a pretrained generator and a few sketches of the poses that you want to generate! For example, you can take any model from sketch a couple of target images and apply the "Sketch Your Own GAN" method. If you have any more questions, I'll try to answer them.
  • Pre-trained StyleGAN2 model
    For some more good pretrained StyleGAN2 weights: (unfortunately some of the download links are dead though)
  • Synthetic Pink Floyd
    I suspect it was WikiArt from justinpinkey's StyleGAN2 collection.
  • [P] Stylegan on ~5k images
    I found this page after a quick google search but if this one doesn't work there are others. You can also just use StyleGan (v1) and have great results, I'm not sure that the v2 is much better.
  • How to make a pretrained StyleGan model?
    like these models:

What are some alternatives?

When comparing stylegan2-ada and awesome-pretrained-stylegan2 you can also consider the following projects:

stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

stylegan2_pytorch - A Pytorch implementation of StyleGAN2

stylegan2 - StyleGAN2 - Official TensorFlow Implementation