Lemon-cmd/Diffusion-Models-and-Associative-Memory

Memorization to Generalization: Emergence of Diffusion Models from Associative Memory

21
/ 100
Experimental

This project helps researchers and machine learning practitioners analyze how diffusion models learn to generate new images based on what they've been trained on. You input trained diffusion models and the original training images. The output helps you classify the model's generated images into categories like "memorized," "spurious," or "generalized," and provides insights into the model's learning process. This is ideal for those studying the fundamental properties of generative AI models.

No commits in the last 6 months.

Use this if you are a machine learning researcher studying how diffusion models learn and generalize, and you need to categorize and analyze the output images of these models.

Not ideal if you are looking for a tool to simply train or deploy diffusion models for practical image generation without deep analysis of their learning mechanisms.

generative-ai diffusion-models machine-learning-research model-analysis image-synthesis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

MIT

Last pushed

Jun 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Lemon-cmd/Diffusion-Models-and-Associative-Memory"

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