darioShar/pytorch-md4

Pytorch Implementation of MD4: Simplified and Generalized Masked Diffusion for Discrete Data

20
/ 100
Experimental

This project offers a straightforward way for machine learning researchers and practitioners to experiment with a novel generative model called MD4. It takes discrete datasets, like binary images, and learns to create new, similar data from scratch. The output consists of newly generated samples that resemble the training data, allowing for exploration of data distribution and synthesis.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer working with discrete data and want to explore generative modeling using a simplified diffusion process.

Not ideal if you need to generate continuous data, work with extremely large-scale datasets, or are looking for a pre-trained model for immediate real-world application without custom training.

generative-modeling discrete-data-synthesis diffusion-models machine-learning-research image-generation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Python

License

Last pushed

Feb 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/darioShar/pytorch-md4"

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