[ICCV 2025] This is the official PyTorch codes for the paper: "DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution"

[CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

A practical guide to diffusion models, implemented from scratch.

[NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

DiP: Taming Diffusion Models in Pixel Space

[NeurIPS 2025] Official implementation of ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion

Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”

Latent Diffusion Models with Masked AutoEncoders (LDMAE) official code

Official inference repo for FLUX.2 models

Official implementation for SSDD Single-Step Diffusion Decoder for Efficient Image Tokenization.

Official PyTorch implementation of FlowMo.

Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"

Benchmarking of machine learning and numerical weather prediction (MLWP & NWP) models, with a focus on extreme events.

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Official Code of the paper “Equivariant Sampling for Improving Diffusion Model-based Image Restoration“

PyTorch Image Quality Assessement package

Diffusion models in PyTorch

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

[CVPR 2025 Oral] Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing

Vite & Vue powered static site generator.

Learning in infinite dimension with neural operators.