volotat/ConGAN
Continious Generative Adversarial Network
This tool helps creative professionals or researchers generate a wide variety of new, realistic images from a small set of existing examples. You provide a few images, like faces or shoes, and it creates many more diverse images that look similar but are entirely new. It's ideal for anyone needing to expand a limited visual dataset without manual effort.
No commits in the last 6 months.
Use this if you need to create many unique variations of images from a very small initial collection, such as for design inspiration, dataset augmentation, or artistic generation.
Not ideal if you need to generate images from text descriptions or if you require extremely high-resolution outputs for very specific commercial printing.
Stars
44
Forks
8
Language
Python
License
MIT
Category
Last pushed
Aug 18, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/volotat/ConGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zhangqianhui/Conditional-GAN
Tensorflow implementation for Conditional Convolutional Adversarial Networks.
mit-han-lab/data-efficient-gans
[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training
EugenHotaj/pytorch-generative
Easy generative modeling in PyTorch
kundan2510/pixelCNN
Theano reimplementation of pixelCNN architecture
shaohua0116/DCGAN-Tensorflow
A Tensorflow implementation of Deep Convolutional Generative Adversarial Networks trained on...