zalandoresearch/psgan
Periodic Spatial Generative Adversarial Networks
This tool generates new, unique visual textures from a single source image or a collection of images. You provide existing texture examples, and it creates a vast array of similar-looking but distinct texture patterns. This is ideal for graphic designers, game developers, or artists who need to quickly produce endless, varied background textures, material surfaces, or digital fabric patterns.
139 stars. No commits in the last 6 months.
Use this if you need to generate high-resolution, repetitive textures for digital environments, product design mockups, or artistic compositions, especially if you require variations that maintain a consistent aesthetic.
Not ideal if you need to generate entirely new, non-repetitive images from scratch, or if your primary goal is to modify or enhance existing photographs rather than create novel textures.
Stars
139
Forks
33
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 13, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zalandoresearch/psgan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
GANs-in-Action/gans-in-action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch