Jiaming Song, Chenlin Meng and Stefano Ermon, Stanford
This repo contains the official implementation for the NeurIPS 2019 paper Generative Modeling by Estimating Gradients of the Data Distribution,
This project is a diffusion model training framework and image synthesis pipeline. It provides the tools necessary to train generative models to learn image data distributions through an iterative denoising process. The framework includes a generative model evaluation tool consisting of automated scripts used to measure the quality and accuracy of produced samples. The system covers model training pipelines and performance evaluation for generative diffusion models.
Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics
The main features of gnobitab/rectifiedflow are: Diffusion Foundations.
Open-source alternatives to gnobitab/rectifiedflow include: ermongroup/ddim — Jiaming Song, Chenlin Meng and Stefano Ermon, Stanford. ermongroup/ncsn — This repo contains the official implementation for the NeurIPS 2019 paper Generative Modeling by Estimating Gradients… hojonathanho/diffusion — This project is a diffusion model training framework and image synthesis pipeline. It provides the tools necessary to… sohl-dickstein/diffusion-probabilistic-models — Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics.