PangzeCheung/Discrete-Probability-Flow

[NeurIPS 2023] Formulating Discrete Probability Flow Through Optimal Transport

22
/ 100
Experimental

This project offers a method for generating clear and well-defined images and other discrete data. It takes in a dataset (like images or synthetic patterns) and can produce new, high-quality samples or smoothly blend between existing ones. Image and data scientists working with generative models who need more precise and controllable outputs would find this useful.

No commits in the last 6 months.

Use this if you are developing or experimenting with generative models and need a method to produce more certain and controllable discrete data samples, especially for tasks like image generation or latent space interpolation.

Not ideal if you are looking for an out-of-the-box application for general image editing or content creation, as this is a foundational research tool for generative model development.

generative-AI image-synthesis machine-learning-research data-generation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

21

Forks

2

Language

Python

License

Last pushed

Jan 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PangzeCheung/Discrete-Probability-Flow"

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