zelaki/eqvae

[ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.

39
/ 100
Emerging

This project helps machine learning researchers and practitioners create higher-quality generative image models faster. It takes an existing image generation model, like a Stable Diffusion Variational Autoencoder (SD-VAE), and applies a special regularization that makes the internal representation of images (latent space) more organized. This results in an improved generative model that can produce better images more efficiently.

174 stars.

Use this if you are a researcher or developer working with generative image models and want to improve their performance and training efficiency, especially concerning image rotations and scaling.

Not ideal if you are a general user looking for an out-of-the-box image generation tool without diving into model training or optimization.

Generative AI Image Synthesis Machine Learning Research Deep Learning Training Computer Vision
No License No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

174

Forks

7

Language

Python

License

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zelaki/eqvae"

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