A file server that supports static serving, uploading, searching, accessing control, webdav...

Desktop and web interface for OpenCode AI agent

The ultimate training toolkit for finetuning diffusion models

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Cross-platform AirDrop. File transfer between Android, iOS, Linux, macOS, and Windows over ad hoc WiFi. No network infrastructure required, just two devices with WiFi chips (and optionally Bluetoot…

SGLang is a high-performance serving framework for large language models and multimodal models.

Lightning fast C++/CUDA neural network framework

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Dead simple FLUX LoRA training UI with LOW VRAM support

Accessible large language models via k-bit quantization for PyTorch.

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Kolors Team

Fast, flexible LLM inference

Cross platform toy render engine supporting physically based rendering and hardware/software ray tracing

Your image is almost there!

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Industry leading face manipulation platform

Training materials associated with NVIDIA's CUDA Training Series (www.olcf.ornl.gov/cuda-training-series/)

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

A small C compiler

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

PhotoMaker [CVPR 2024]

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)