HenryNdubuaku/halo

A Library That Uses Quantized Diffusion Model With Clustered Weights For Efficiently Generating More Image Datasets On-Device.

27
/ 100
Experimental

Halo helps machine learning practitioners expand small image datasets into much larger ones. You provide a limited collection of images, and it generates many more diverse examples, which can then be used to train robust machine learning models. This is ideal for anyone developing image classification or understanding systems who struggles with scarce data.

No commits in the last 6 months.

Use this if you need to quickly generate additional synthetic images from a small, existing dataset to improve the training of your machine learning models.

Not ideal if you are looking for advanced image editing, manipulation, or style transfer, as its primary purpose is dataset expansion.

machine-learning dataset-generation computer-vision image-synthesis data-augmentation
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

Jun 09, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HenryNdubuaku/halo"

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