The official PyTorch implementation for NCSNv2 (NeurIPS 2020)

Code for my Bachelor thesis on Semantic Image Synthesis with Score-Based Generative Models

A collection of SBM in PyTorch Lightning

Final project code of dgm-bo, Fall 2021

Official code for "Maximum Likelihood Training of Score-Based Diffusion Models", NeurIPS 2021 (spotlight)

This is keep-it-simple-and-stupid realization of Score-Based Generative Modeling through Stochastic Differential Equations.

Official PyTorch implementation of the paper Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis.

Unofficial re-implementation of NCSN, a Noise Conditional Score Network, in PyTorch

This work explores Score-Based Generative Modeling (SBGM), a new approach to generative modeling. Based on SBGM, we explore the possibilities of music generation based on the MAESTRO (MIDI and Audio Edited for Synchronous TRacks and Organization) database. To explore this framework, we rely heavily on the article of Yang Song and al.

Diffusion-driven Counterfactual Explanation for Functional MRI (https://arxiv.org/abs/2307.09547)

Combinatorial Complex Score-based Diffusion model using stochastic differential equations

[BMVC 2023 (Oral)] Score-PA: Score-based 3D Part Assembly

Official Code Repository for the paper "Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations" (ICML 2022)

Implementation of DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing

[ICLR 2022] Toy Experiments for Denoising Likelihood Score Matching for Conditional Score-based Data Generation

Official implementation of the Fourier-constrained diffusion bridges (FDB) model for MRI reconstruction

Noise Conditional Score Networks (NeurIPS 2019, Oral)

Code to reproduce the results in "Conditional score-based diffusion models for Bayesian inference in infinite dimensions", NeurIPS 2023

Minimal unofficial implementation of Consistency Trajectory models on a 1D toy task.

[CVPR 2024] G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping