khawar-islam/diffuseMix

Official PyTorch implementation of DiffuseMix : Label-Preserving Data Augmentation with Diffusion Models (CVPR'2024)

34
/ 100
Emerging

This project helps machine learning practitioners expand small image datasets for training computer vision models. By taking your existing images and applying diffusion model techniques with specified prompts, it generates new, diverse images that retain their original labels. This is ideal for researchers or engineers working on image classification, object detection, or other vision tasks who need more data without manual collection.

132 stars.

Use this if you have a limited number of labeled images for your computer vision project and need to artificially increase your dataset's size and diversity to improve model performance.

Not ideal if you already have extensive, high-quality datasets or if your task doesn't involve image-based machine learning.

image-augmentation computer-vision dataset-expansion machine-learning-research model-training
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

132

Forks

9

Language

Python

License

Last pushed

Jan 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/khawar-islam/diffuseMix"

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