butteraugli estimates the psychovisual difference between two images

C++ bindings for box2d 3.x physics engine (aka box2c)

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

llama.cpp clone with additional SOTA quants and improved CPU performance

🫧 An ImGui-based UI system to defenestrate all others

A simple gettext replacement that works directly on .po files

Translations editor for Mac, Windows and Unix

UE5's Nanite implementation using WebGPU. Includes the meshlet LOD hierarchy, software rasterizer and billboard impostors. Culling on both per-instance and per-meshlet basis.

A simple converter of models for stable-diffusion-cpp

🛏 An HTML to Markdown converter written in JavaScript

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

A digital twin of the city of Colombo, Sri Lanka, implemented in Cities: Skylines, based on real data. Nearly 1:1 in terms of geography and population.

ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

Kolors Team

Port of Funasr's Sense-voice model in C/C++

An open source re-implementation of Caesar III

An open source re-implementation of Caesar III

WIP example collection for the SDL_Gpu API proposal

WebAssembly binding for llama.cpp - Enabling in-browser LLM inference

GGUF Quantization support for native ComfyUI models

🌋🐎 Project Island is an experimental, hot-reloading Vulkan Renderer for Linux and Windows, written in C/C++.

(VST3/CLAP) A shimmer reverb plugin. Made with nih-plug + faust

Use Direct3D shaders with other 3D rendering APIs.

The Quite OK Package Format

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

Code execution exploit for Tony Hawk's video game series