lightweight-gan VS HyperGAN

GAN details: I trained using the code from https://github.com/lucidrains/lightweight-gan, image size is 256, attn-res-layers is [32,64], disc_output_size is 5 and I trained with AMP.

Long short story, i trained AI called 'Lightweight' GAN with some image from the game (Steam version). The result isn't satisfying (either too similar with original image or distorted), but i decided to share it since it took 3-4 days.

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

Trained lightweight-gan on public domain nebulae images. The blogpost covers how it was assembled end-to-end, from data scraping, to model training, and finally deploying it as a web app using free cloud services only

https://github.com/lucidrains/stylegan2-pytorch is the simplest implementation I know of, and https://github.com/lucidrains/lightweight-gan is similar but designed for relatively lower performance machines.

I also regret using https://github.com/lucidrains/lightweight-gan over the standard StyleGAN2. The training time wasn't an issue for 128x128 images and I should have gone for the higher quality model.

It's hard to tell if the medicore results are due to the small dataset (~305 semi-aligned images, yes there's that many of these) or my own inexperience in GAN generation (i used https://github.com/lucidrains/lightweight-gan and the only changes i made from the defaults were to decrease the batch size and add color augmentation)

And then there's software already prebaked that can do it, but its really taxing on a pc, its called hyperGAN.

There is something called HyperGAN which builds generative adversarial networks (GANs) and those networks take some images as input and give those as output. Here is the GitHub page for that.