Skip to content

openai/glow

Official

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

3,184 stars525 forksPythonUpdated July 2024
✅ Reviewed by My AI Guide

Our Review

  • Reproduces SOTA generative flow results
  • Supports large datasets and distributed training
  • Interactive demo for manipulations

Our Verdict

Reproduction code for Glow: generative flow model with invertible 1x1 convolutions. For ML researchers in density estimation. Key advantage: exact likelihoods over GANs.

Frequently Asked Questions

What is openai/glow used for?

It provides Python code to reproduce results from the Glow paper on generative flows using invertible 1x1 convolutions for tasks like image density estimation and generation.

What is glow?

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

How do I install glow?

Visit the GitHub repository at https://github.com/openai/glow for installation instructions.

What license does glow use?

glow uses the MIT license.

What are alternatives to glow?

Search My AI Guide for similar tools in this category.

🔒

Open source & community-verified

MIT licensed: free to use in any project, no strings attached. 3,184 developers have starred this, meaning the community has reviewed and trusted it.

Reviewed by My AI Guide for relevance, quality, and active maintenance before listing.