yang-song/score_sde
JAX/Flax implementation of score-based diffusion models via stochastic differential equations for high-fidelity image generation.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official implementation of score-based generative modeling through stochastic differential equations, a unified framework that generalizes diffusion models. The method transforms data to noise via continuous-time stochastic processes and reverses the process for generation using learned score functions. It supports unconditional generation, class-conditional generation, inpainting, colorization, and latent code manipulation, achieving FID of 2.20 on CIFAR-10 and high-fidelity 1024px CelebA-HQ generation.
Frequently asked
- What is yang-song/score_sde?
- JAX/Flax implementation of score-based diffusion models via stochastic differential equations for high-fidelity image generation.
- Is score_sde open source?
- Yes — yang-song/score_sde is open source, released under the Apache-2.0 license.
- What language is score_sde written in?
- yang-song/score_sde is primarily written in Jupyter Notebook.
- How popular is score_sde?
- yang-song/score_sde has 1.8k stars on GitHub.
- Where can I find score_sde?
- yang-song/score_sde is on GitHub at https://github.com/yang-song/score_sde.