alshedivat/diffusion-playground

A playground for experimenting with diffusion models 🌀

39
/ 100
Emerging

This is a specialized toolkit for machine learning researchers and engineers who are building or studying diffusion models. It provides modular components for training diffusion models and generating new data from them. You input datasets like images (e.g., MNIST, CIFAR10) or 3D point clouds, and it helps you generate new, similar data or analyze how these generative models work. It's designed for those actively engaged in deep learning model development.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner specifically working on developing, training, or experimenting with diffusion-based generative models for various data types.

Not ideal if you are looking for an off-the-shelf application to generate images or data without deep technical understanding or customization of diffusion model internals.

generative-ai deep-learning-research machine-learning-engineering image-synthesis data-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

26

Forks

7

Language

Python

License

MIT

Last pushed

Feb 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/alshedivat/diffusion-playground"

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