A WIP port of Quake (1996) to Three.js.

JavaScript animation engine

Worlds first open-source real-time end-to-end spoken dialogue model with personalized voice cloning.

Seamless operability between C++11 and Python

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

Stable Diffusion and Flux in pure C/C++

Native and Compact Structured Latents for 3D Generation

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

SAM 3D Objects

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Minimal CLI coding agent by Mistral

RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards.

One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

Light-X: Generative 4D Video Rendering with Camera and Illumination Control

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Taming large-scale full-parameter few-step training with self-adversarial flows! 👏🏻

Official inference repo for FLUX.2 models

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

Depth Anything 3

Fast and memory-efficient exact attention

Port of OpenAI's Whisper model in C/C++

LLM inference in C/C++