Stars
pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
Krea Realtime 14B. An open-source realtime AI video model.
Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.
Kandinsky 5.0: A family of diffusion models for Video & Image generation
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
Official Code for "Rethinking Diffusion Model in High Dimension"
Flash Attention Triton kernel with support for second-order derivatives
HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation
Official Github Repo for Neurips 2024 Paper Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Foundation Model for Multiplex Spatial Proteomic Images
TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance (ICCV 2025)
Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.
PyTorch re-implementation for MeanFlow
[ICML 2025 Spotlight] Direct Discriminative Optimization: Supercharging Diffusion/Autoregressive with GAN-type Discrimination
[NeurIPS 2025] Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".
Analyze computation-communication overlap in V3/R1.
Pytorch implementation of MeanFlow on ImageNet and CIFAR10
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.
interview-coder-withoupaywall-opensource
[NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
flash attention tutorial written in python, triton, cuda, cutlass