Stars
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
YODA: Yet Another One-step Diffusion-based Video Compression
imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video.
Open Source Implementation of Dual Modality MAGVIT2 Tokenizer
Implementation of MagViT2 Tokenizer in Pytorch
Taming Transformers for High-Resolution Image Synthesis
Tiny AutoEncoder for Stable Diffusion (and other image models)
This repo contains the code for 1D tokenizer and generator
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
SEED-Voken: A Series of Powerful Visual Tokenizers
Official JAX implementation of MAGVIT: Masked Generative Video Transformer
[ICCV 2025] StableCodec: Taming One-Step Diffusion for Extreme Image Compression
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
VVenC, the Fraunhofer Versatile Video Encoder
Official Implementation of GLC : Generative Latent Coding for Ultra-Low Bitrate Image Compression, CVPR 2024
SGLang is a high-performance serving framework for large language models and multimodal models.
Universal LLM Deployment Engine with ML Compilation
a language for fast, portable data-parallel computation
一个基于 Python Telegram Bot 的自动化认证工具，能够自动完成 SheerID 平台的学生/教师身份验证流程。
FlashInfer: Kernel Library for LLM Serving
Third-party implementation of DCVC-RT training code
Official Pytorch implementation for VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision
Official Pytorch implementation for DCVC-SDD: [Spatial Decomposition and Temporal Fusion Based Inter Prediction for Learned Video Compression](https://ieeexplore.ieee.org/document/10416688), in TCS…
Official Pytorch implementation for DCVC-B: Bi-Directional Deep Contextual Video Compression, in TMM 2025.