Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

autocorrelation-based O(NlogN) pitch detection

A free tool for experimenting with WebGPU fragment shaders and the WebGPU Shader Language (WGSL) #wasm #webgpu

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

A C++20 library for fast serialization, deserialization and validation using reflection. Supports JSON, Avro, BSON, Cap'n Proto, CBOR, CSV, flexbuffers, msgpack, parquet, TOML, UBJSON, XML, YAML / …

diffusers implementation for node.js and browser

🎧 A simple, asynchronous Last.fm library written in TypeScript.

Node.js library for last.fm, with typescript support

A low footprint JavaScript engine for embedded systems

A TypeScript framework for building MCP servers.

[ICLR 2025] Codebase for "CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation"

Intuitive basic interface for interacting with multiple LLMs at the same time

Blazingly fast LLM inference.

Dual Diffusion is a generative diffusion model for music trained on video game soundtracks.

Official front-end implementation of ComfyUI

Official inference repo for FLUX.1 models

ControlNet++: All-in-one ControlNet for image generations and editing!

A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents

Tensor library for machine learning

llama3.cuda is a pure C/CUDA implementation for Llama 3 model.

Remote GUI for Transmission torrent daemon

[CVPR 2024] X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

A C++ bare metal environment for Raspberry Pi with USB (32 and 64 bit)

Multi-GPU Stable diffusion pipeline over webrtc

Typescript to lua transpiler. https://typescripttolua.github.io/

Premake

Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)

MagicEdit: High-Fidelity Temporally Coherent Video Editing