xchhuang/bndm

Blue noise for diffusion models [SIGGRAPH 2024]

37
/ 100
Emerging

This project offers a new way to create more visually pleasing and detailed images using AI diffusion models. It takes existing diffusion models and applies a special 'blue noise' technique during the image generation process, resulting in higher quality outputs for tasks like creating new images or enhancing existing ones. Image researchers and AI artists seeking to improve the aesthetic quality and detail of their generated images would find this useful.

Use this if you are working with AI image generation or super-resolution and want to achieve visually smoother, more detailed, and less 'noisy' results than standard diffusion models provide.

Not ideal if you are looking for a general-purpose image editing tool or a solution for image classification or object detection.

AI Image Generation Image Super-Resolution Creative AI Visual Computing Diffusion Models
No License No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

53

Forks

8

Language

Python

License

Last pushed

Dec 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/xchhuang/bndm"

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