gensbi.diffusion

This package provides tools and modules for working with diffusion-based generative models, including training, sampling, and evaluation routines. The implementation is inspired by and builds upon the foundational work of Karras et al. and the official EDM library:

• 20. Karras et al. “Elucidating the Design Space of Diffusion-Based Generative Models.” arXiv:2206.00364

• NVlabs/edm

Key features: * Score-based generative modeling using stochastic differential equations (SDEs) * EDM (Elucidating Diffusion Models) training and sampling * Modular solvers and schedulers for flexible experimentation

# If you use this package, please consider citing the EDM paper and library.

Submodules

• gensbi.diffusion.path
• gensbi.diffusion.solver