zuko and normalizing_flows
These are competitors offering overlapping implementations of normalizing flow architectures (both include RealNVP and MAF), but Zuko is more actively maintained and integrated into PyTorch workflows (evidenced by its substantial monthly downloads), while the other is a dormant research repository.
About zuko
probabilists/zuko
Normalizing flows in PyTorch
About normalizing_flows
kamenbliznashki/normalizing_flows
Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows
Provides reference implementations for training normalizing flow models on both synthetic 2D datasets and real image/tabular data (CelebA, MNIST, UCI), with support for multi-GPU distributed training and gradient checkpointing for large models. Includes generative capabilities beyond density estimation, such as temperature-controlled sampling, latent space attribute manipulation, and conditional density estimation. Built entirely in PyTorch with modular architecture allowing interchange of flow components and straightforward integration into probabilistic inference pipelines.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work