byrkbrk/conditional-ddpm

A simple PyTorch implementation of conditional denoising diffusion probabilistic models (DDPM) on MNIST, Fashion-MNIST, and Sprite datasets

29
/ 100
Experimental

This tool helps machine learning engineers and researchers generate new, synthetic images based on a set of existing image examples. You provide a dataset of labeled images, and it outputs new images that resemble the originals but are entirely unique. This is useful for expanding datasets or creating novel visuals for testing.

No commits in the last 6 months.

Use this if you need to generate high-quality, diverse synthetic images conditionally based on specific categories or labels from a given image dataset.

Not ideal if you're looking for a user-friendly, drag-and-drop solution without any coding, or if your primary goal is image manipulation rather than generation.

synthetic-data-generation image-generation machine-learning-research dataset-expansion
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

88

Forks

9

Language

Python

License

Last pushed

May 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/byrkbrk/conditional-ddpm"

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