stylegan VS stylegan2

Umm, StyleGAN was the first decent image generation model, and it was producing great images from random seeds 5 years ago. Now, that's with the obvious caveat that each model was trained to produce one specific type of image and it helped immensely if the training images were all aligned the same. Diffusion models are certainly the trendy current architecture for image generation, but AFAIK there's no fundamental theoretical limitation to the output quality of any architecture except the general rule that more parameters is better.

PDF link Landing page

Code: https://github.com/NVlabs/stylegan

https://arxiv.org/abs/1812.04948 (A Style-Based Generator Architecture for Generative Adversarial Networks)

Check out the PDF here I've been calling this "the first spiritual guidebook written by an AI". The text was written almost entirely with GPT-3, minus the couple of paragraphs I wrote as prompt. The art was made with various tools - for instance, the cover was made in part with Aphantasia (CLIP+FFT), the title page is an old public domain photo colorized with DeOldify, the faces made with StyleGAN, both standalone and via Artbreeder. Let me know what you think - I have a couple bigger projects building off of the techniques I used, and I would appreciate any feedback!

stylegan this is the tech behind all those "this ___ does not exist" sites. it's actually surprisingly easy to use if you know how to use the terminal (and preferably a little bit of python).

Clone stylegan

I don't know. If you're really curious, you can just try it: https://github.com/NVlabs/stylegan2

> The denoising part of a denoising autoencoder refers to the noise applied to its input

Agree, it converts a noisy image to a denoised image. But the odd thing is, when you put a noisy image into a StyleGAN2 encoder, you get latents which the decoder will turn into a de-noised image. So in practical use, you can take a trained StyleGAN2 encoder/decoder pair and use it as if it was a denoiser.

> These differences lead to learned distributions in the latent space that are entirely different

I also agree there. The training for a denoising auto-encoder and for a GAN network is different, leading to different distributions which are sampled for generating the images. But the architecture is still very similar, meaning the limits of what can be learned should be the same.

> Beyond that the comparison just doesn't work, yes there are two networks but the discriminator doesn't play the role of the AE's encoder at all

Yes, the discriminator in a GAN won't work like an encoder. But if you look at how StyleGAN 1/2 are used in practice, people combine it with a so-called "projection", which is effectively an encoder to convert images to latents. So people use a pipeline of "image to latent encoder" + "latent to image decoder".

That whole pipeline is very similar to an auto-encoder. For example, here's an NVIDIA paper about how they round-trip from image to latent to image with StyleGAN: https://arxiv.org/abs/1912.04958 My interpretation of what they did in that paper is that they effectively trained a StyleGAN-like model with the image L2 loss typically used for training a denoising auto-encoder.

This is the result of two different models. The first looks like a latent space interpolation of StyleGan2 and the mouth movements are without a doubt from wav2lip.

Code for training your own [original] [simple] [light]

StyleGAN2 (Dec 2019) - Karras et al. and Nvidia

Check the license here, but it looks like anything based on stylegan2 can't be used commercially. Google brought me to this page which seems to also be based on stylegan, but I guess they are paying for a commercial license for it? So you could use it or maybe even reach out to nvidia directly.

StyleGAN2 (Dec 2019) - Karras et al. and Nvidia. More: https://github.com/NVlabs/stylegan2)

2. https://www.deepl.com/translator (translate text in 20 languages including idioms and phrases)

3. https://remove.bg/ (remove any background)

4. regex101.com (self explanatory)

5. Photopea.com (a free web-based Photoshop alternative

6. https://tineye.com/ , http://fotoforensics.com/ Do you want to know if an image is shopped, cropped or otherwise altered? Using these two tools you've got a good chance of finding out. Tineye is reverse image search on steroids and foto forensics provides free image analysis tools:

7. https://thenounproject.com/ (Icons and Photos for everything)

If you’d like to know more, here’s a video explaining the method and the paper: https://arxiv.org/abs/1912.04958

The implementation and trained models are available on the StyleGAN2 GitHub repo.