bot66/MNISTDiffusion

Implement a MNIST(also minimal) version of denoising diffusion probabilistic model from scratch.The model only has 4.55MB.

46
/ 100
Emerging

This project helps machine learning researchers and students understand and experiment with denoising diffusion probabilistic models on a very small scale. It takes noisy image data and learns to generate clear, new images, providing a hands-on way to see how diffusion models work without requiring significant computational resources. The output is a functional, lightweight model capable of generating digits.

143 stars. No commits in the last 6 months.

Use this if you are learning about diffusion models and want to train a basic, functional version quickly and efficiently on simple image data.

Not ideal if you need to generate high-resolution images or work with complex datasets beyond basic digits.

deep-learning-education generative-models image-synthesis model-training computational-efficiency
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

143

Forks

28

Language

Python

License

MIT

Last pushed

Dec 09, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bot66/MNISTDiffusion"

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