A Collection of Variational Autoencoders (VAE) in PyTorch.

Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)

Experiments for understanding disentanglement in VAE latent representations

Pytorch implementation of β-VAE

Easy generative modeling in PyTorch

Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)

Replicating "Understanding disentangling in β-VAE"

Predicting image frames using autoencoder and LSTM

An implementation of Denoising Variational AutoEncoder with Topological loss

Official PyTorch implementation on ID-GAN: High-Fidelity Synthesis with Disentangled Representation by Lee et al., 2020.

Pytorch implementation of SCAN: Learning Hierarchical Compositional Visual Concepts, Higgins et al., ICLR 2018

Disentangling the latent space of a VAE.

Implementation of VAE in pytorch.

Variational Autoencoder and a Disentangled version (beta-VAE) implementation in PyTorch-Lightning

Pytorch implementation of a simple beta vae on dsprites data

A PyTorch implementation of a β-Variational Autoencoder (β-VAE) for disentangled representation learning and image generation on the Fashion-MNIST dataset. This repository showcases how β-VAE can achieve disentanglement in its latent space, a crucial concept for interpretability in generative models.

Fancy brand new letters with generative models

A flexible framework of neural networks for deep learning