VinAIResearch/WaveDiff

Official Pytorch Implementation of the paper: Wavelet Diffusion Models are fast and scalable Image Generators (CVPR'23)

41
/ 100
Emerging

WaveDiff helps researchers generate high-quality images much faster than traditional methods. It takes existing image datasets (like faces or churches) and uses a novel approach to create new, realistic images from scratch, which can be used by computer vision scientists working on synthetic data generation or creative AI applications.

435 stars. No commits in the last 6 months.

Use this if you need to rapidly generate large quantities of diverse and realistic images for your research or applications.

Not ideal if you need to perform image manipulation tasks like editing or style transfer on existing images, rather than generating new ones.

image-generation synthetic-data computer-vision generative-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

435

Forks

35

Language

Python

License

AGPL-3.0

Last pushed

Jul 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VinAIResearch/WaveDiff"

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