thudzj/Calibrated-DPMs

Official code for "On Calibrating Diffusion Probabilistic Models"

19
/ 100
Experimental

This project offers a method to enhance the quality and reliability of images generated by Diffusion Probabilistic Models. It takes existing image generation models and refines them to produce more accurate and realistic outputs, specifically improving how well the generated images match desired characteristics. Machine learning researchers and practitioners working on advanced image synthesis and generative AI would find this useful.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer looking to improve the fidelity and trustworthiness of images generated by diffusion models for tasks like synthetic data creation or content generation.

Not ideal if you are an end-user needing a simple, out-of-the-box image generation tool without diving into model calibration or research.

generative AI image synthesis machine learning research model calibration diffusion models
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

30

Forks

1

Language

Python

License

Last pushed

Feb 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/thudzj/Calibrated-DPMs"

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