zituitui/DiffusionFisher

[ICML 2025] Official implementation of "Efficiently Access Diffusion Fisher: Within the Outer Product Span Space".

22
/ 100
Experimental

This project helps researchers and developers working with advanced AI models by providing a more efficient way to calculate 'Fisher Information' in diffusion models. It takes in parameters from your diffusion models and outputs analytical formulations and algorithms for evaluating complex model properties. This is intended for machine learning researchers and practitioners focused on generative AI, model optimization, and theoretical advancements in deep learning.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer developing and optimizing diffusion models and need to efficiently analyze their statistical properties.

Not ideal if you are looking for a pre-trained model or a high-level API to generate images or text without deep involvement in model internals.

generative-ai deep-learning-research model-optimization machine-learning-theory diffusion-models
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

MIT

Last pushed

Jun 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zituitui/DiffusionFisher"

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