gabrielraya/symmetry_breaking_diffusion_models
Official repository of "Spontaneous symmetry breaking in generative diffusion models"
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.
Stars
43
Forks
2
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
quantgirluk/aleatory
📦 Python library for Stochastic Processes Simulation and Visualisation
blei-lab/treeffuser
Treeffuser is an easy-to-use package for probabilistic prediction and probabilistic regression...
TuftsBCB/RegDiffusion
Diffusion model for gene regulatory network inference.
yuanchenyang/smalldiffusion
Simple and readable code for training and sampling from diffusion models
chairc/Integrated-Design-Diffusion-Model
IDDM (Industrial, landscape, animate, latent diffusion), support LDM, DDPM, DDIM, PLMS, webui...