Victarry/Image-Generation-models

Generative models (GAN, VAE, Diffusion Models, Autoregressive Models) implemented with Pytorch, Pytorch_lightning and hydra.

31
/ 100
Emerging

Modular architecture decouples models, networks, and datasets through YAML configuration files, enabling rapid experimentation with grid search and multi-experiment execution via Hydra. Implements 15+ canonical architectures across GANs (WGAN, InfoGAN, BiGAN), VAEs (VQ-VAE, Beta-VAE, FactorVAE), diffusion models (DDPM), and autoregressive models (PixelCNN) with PyTorch Lightning for distributed training. Provides pre-trained results on MNIST, CIFAR-10, and CelebA, with composable command-line configuration for hyperparameter sweeps (`model.lr=1e-3,5e-4,1e-4`) and batch experiment execution.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

61

Forks

10

Language

Python

License

Last pushed

May 05, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Victarry/Image-Generation-models"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.