andylolu2/jax-vqvae-gpt

Implementation of VQ-VAE with a GPT-style sampler in the JAX and Haiku ecosystem.

27
/ 100
Experimental

This project helps machine learning practitioners generate new images from a dataset. It takes an existing collection of images, learns their features, and then creates novel, synthetic images that resemble the originals. It's designed for researchers or developers experimenting with generative AI models and image synthesis.

No commits in the last 6 months.

Use this if you are a machine learning researcher or developer working with JAX and Haiku and need to implement and experiment with a VQ-VAE model for image generation using a GPT-style sampler.

Not ideal if you are an end-user looking for a ready-to-use image generation application without needing to code or manage machine learning model training.

generative-ai image-synthesis machine-learning-research deep-learning-development computer-vision-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Last pushed

Nov 23, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/andylolu2/jax-vqvae-gpt"

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