FoundationVision/BitVAE

official training and inference code of bitwise tokenizer

30
/ 100
Emerging

This project offers the tools to convert high-resolution images into a more compact, bitwise representation and then reconstruct them. It helps researchers and engineers working with large image datasets to efficiently process, store, or transmit visual information. You provide images, and it outputs a 'tokenized' version and can reconstruct images from these tokens.

No commits in the last 6 months.

Use this if you need to compress or represent high-resolution images in a compact, tokenized format while maintaining high visual quality.

Not ideal if you are looking for an off-the-shelf application to simply view or edit images, as this requires technical setup and scripting.

image-compression computer-vision-research image-generation visual-data-processing machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 4 / 25

How are scores calculated?

Stars

70

Forks

2

Language

Python

License

MIT

Last pushed

May 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FoundationVision/BitVAE"

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