smsharma/minified-generative-models

Bare-bones implementations of some generative models in Jax: diffusion, normalizing flows, consistency models, flow matching, (beta)-VAEs, etc

34
/ 100
Emerging

This project provides straightforward, minimal examples of generative models like VAEs, diffusion models, and normalizing flows. It takes common data structures and demonstrates how these models can generate new, similar data or learn underlying data distributions. It's designed for machine learning researchers, students, or practitioners who want to understand the core mechanics of various generative models without excessive complexity.

141 stars. No commits in the last 6 months.

Use this if you are studying or experimenting with generative artificial intelligence models and need clear, unembellished reference implementations to grasp their fundamental principles.

Not ideal if you need a production-ready library for deploying large-scale generative AI applications or require extensive features and optimizations beyond basic model implementations.

generative-ai-research machine-learning-education model-understanding artificial-intelligence-prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

141

Forks

7

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 20, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/smsharma/minified-generative-models"

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