VinAIResearch/WaveDiff
Official Pytorch Implementation of the paper: Wavelet Diffusion Models are fast and scalable Image Generators (CVPR'23)
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.
Stars
435
Forks
35
Language
Python
License
AGPL-3.0
Category
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.
Higher-rated alternatives
xie-lab-ml/Golden-Noise-for-Diffusion-Models
[ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".
yulewang97/ERDiff
[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure...
UNIC-Lab/RadioDiff
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for...
pantheon5100/pid_diffusion
This repository is the official implementation of the paper: Physics Informed Distillation for...
zju-pi/diff-sampler
An open-source toolbox for fast sampling of diffusion models. Official implementations of our...