gabrielraya/symmetry_breaking_diffusion_models

Official repository of "Spontaneous symmetry breaking in generative diffusion models"

29
/ 100
Experimental

This project offers a new way to understand and improve generative diffusion models, focusing on how they create diverse synthetic images. It takes an existing diffusion model and applies a 'Gaussian late initialization' scheme, resulting in higher-quality generated images with better diversity. Researchers and engineers working on image generation and synthetic data would use this to enhance their model performance.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer looking to improve the performance and diversity of images generated by diffusion models, especially with fast samplers.

Not ideal if you are looking for an out-of-the-box solution for image generation without delving into the underlying model dynamics.

Generative AI Image Synthesis Diffusion Models Machine Learning Research Synthetic Data Generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

43

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

May 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/gabrielraya/symmetry_breaking_diffusion_models"

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