Vae Python Packages

nnm

Neural Network Models

disent

🧶 Modular VAE disentanglement framework for python built with PyTorch Lightning ▸ Including metrics and datasets ▸ With strongly supervised, weakly supervised and unsupervised methods ▸ Easily configured and run with Hydra config ▸ Inspired by disentanglement_lib

mlx-taef

Tiny AutoEncoders (TAESD family) for diffusion latents on Apple Silicon — pure MLX. Live previews + low-memory decode for FLUX.1, FLUX.2 Klein, SD1.x, SDXL.

pythae

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

ciss-vae

Python package for CISS-VAE.

human-body-prior

VPoser: Variational Human Pose Prior

moai-mdk

moai is a PyTorch-based AI Model Development Kit (MDK) created to improve data-driven model workflows, design and reproducibility.

numpy-ml

Machine learning, in numpy

cadl

Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"

isograph

Python toolkit for discovering isoform-switch and splicing modules from bulk RNA-seq using gene-aware latent network inference.

pi-vae-pytorch

Implementation of Poisson Identifiable VAE (pi-VAE) in Pytorch

pyroved

Invariant representation learning from imaging and spectral data

hyperion-ml

Python toolkit for speech processing

bucketsampler

Aspect ratio bucketing for diffusion training. PyTorch native, DDP correct, no training-framework lock-in.

omniinfer-client

Python SDK for Stable Diffusion API (Txt2Img/Img2Img/ControlNet/VAE)

easyvae

Python implementation of a Classical and Variational Autoencoders using Numpy

rapidae

Explore, compare and develop autoencoder models with a back-end agnostic framework

tsgm

Generation and evaluation of synthetic time series datasets (also, augmentations, visualizations, a collection of popular datasets) NeurIPS'24

daisyrec

Official code for "DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation" (TPAMI2022) and "Are We Evaluating Rigorously? Benchmarking Recommendation for Reproducible Evaluation and Fair Comparison" (RecSys2020)

molgen

Lightweight toolkit for de novo molecular generation: SMILES & SELFIES tokenizers, CharRNN / MolGPT / VAE models, training, sampling, and MOSES-style metrics.

flexinet

flexinet: flexible torch neural network composition

rectokens

[Pytorch] Efficient tokenization for recommendations and generative retrieval. Inspired by STATIC decoding from "Vectorizing the Trie"

fastvae

A fast video VAE decoder for consumer Blackwell (sm_120). 2.4x over the eager Wan VAE decoder, no tiling.

pytorch-policy

This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch