xandergos/sCM-mnist

Unofficial implementation of "Simplifying, Stabilizing & Scaling Continuous-Time Consistency Models" for MNIST

36
/ 100
Emerging

This project provides a straightforward way to implement and experiment with a specific type of AI model called "Continuous-Time Consistency Models" for generating images. It takes raw image data, like the MNIST handwritten digits, and trains models to produce new, similar images. This is for researchers or students exploring advanced image generation techniques and model training.

No commits in the last 6 months.

Use this if you are an AI researcher or student wanting to quickly understand and adapt state-of-the-art image generation techniques, specifically consistency models, for your own datasets or experiments.

Not ideal if you are looking for a pre-trained, ready-to-use image generation tool or a high-level API without diving into the underlying model architecture and training process.

deep-learning-research generative-AI image-synthesis model-training machine-learning-education
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

89

Forks

8

Language

Python

License

MIT

Last pushed

Mar 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/xandergos/sCM-mnist"

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