Aki

streamdiffusion-mac. TeX

MemOS. Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

OpenManus. No fortress, purely open ground. OpenManus is Coming.

silero-vad. Silero VAD: pre-trained enterprise-grade Voice Activity Detector

pamiq-core. Framework for building AI agents with real-time adaptive learning capabilities.

minecraft_ros2. ros2 minecraft mod

Soft-Thinking. Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"

MMaDA. MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

verifiers. Our library for RL environments + evals

cubecl. Multi-platform high-performance compute language extension for Rust.

FramePack. Lets make video diffusion practical!

zmk-config-Keyball61.

imm. Official implementation of Inductive Moment Matching

PixelOE. Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.

Step-Video-T2V. Python

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

diffusion-literature-for-robotics. Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusion robotics papers.

swarm. Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

attention-gym. Helpful tools and examples for working with flex-attention

MiraData. Official repo for paper "MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions"

Mira. Python

Paints-UNDO. Understand Human Behavior to Align True Needs

ddim. Denoising Diffusion Implicit Models

election2024. 東京都知事選2024のリポジトリ

BasicPBC. Official Implementation of "Learning Inclusion Matching for Animation Paint Bucket Colorization"

StoryDiffusion. Accepted as [NeurIPS 2024] Spotlight Presentation Paper

motion-diffusion-model. The official PyTorch implementation of the paper "Human Motion Diffusion Model"

LlamaGen. Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

aesthetic-predictor-v2-5. SigLIP-based Aesthetic Score Predictor

streamv2v. Official Pytorch implementation of StreamV2V.

T2I-Adapter. T2I-Adapter

MotionLCM. [ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

taesd. Tiny AutoEncoder for Stable Diffusion (and other image models)

SpaTracker. [CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

faiss. A library for efficient similarity search and clustering of dense vectors.

torchtune. PyTorch native post-training library

cuda-introduction. Cuda

onnxsim. Simplify your onnx model

model-demo-notebooks. Notebooks for Stability AI models

semantic-draw. Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

grok. Python

MotionDiffuse. MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

StreamDiffusion-for-windows. StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Bert-VITS2. vits2 backbone with multilingual-bert

StreamDiffusion-NDI. Python

ComfyScript. A Python frontend and library for ComfyUI

ComfyUI-Diffusers. This repository is a custom node in ComfyUI. This is a program that allows you to use Huggingface Diffusers module with ComfyUI. Additionally, Stream Diffusion is also available.

ComfyUI_StreamDiffusion. This is a simple implemention StreamDiffusion for ComfyUI

StreamDiffusion-colab. Jupyter Notebook

StreamDiffusion. StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

MoCapAct. A Multi-Task Dataset for Simulated Humanoid Control

style-aligned. Official code for "Style Aligned Image Generation via Shared Attention"

ControlNet. Let us control diffusion models!

MineCLIP. Foundation Model for MineDojo

Real-Time-Latent-Consistency-Model. App showcasing multiple real-time diffusion models pipelines with Diffusers

faster-lcm. Faster LCM is a script which enables to transfer image styles at 45fps with RTX4090, 33fps with A100.

q-diffusion. [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.

Radiata. Stable diffusion webui based on diffusers.

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

TensorRT. NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Stable-Diffusion-WebUI-TensorRT. TensorRT Extension for Stable Diffusion Web UI

tensor-stream. A library for real-time video stream decoding to CUDA memory

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

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

openai-python. The official Python library for the OpenAI API

consistency_models. Official repo for consistency models.

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

pips2. PIPs++

heron. Heron is a library that seamlessly integrates multiple Vision and Language models, as well as Video and Language models.

ros2-for-unity. High-performance ROS2 solution for Unity3D

vall-e. PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

VITS. VITSによるテキスト読み上げ器&ボイスチェンジャー

seamless_communication. Foundational Models for State-of-the-Art Speech and Text Translation

VALL-E-X. An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

memorizing-transformers-pytorch. Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

STEVE-1. STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

chat-visual-novel. ChatVisualNovel - a fully customizable visual novel engine powered by ChatGPT. ChatVisualNovel —— 基于ChatGPT的定制化视觉小说引擎。

Retrieval-based-Voice-Conversion-WebUI. Easily train a good VC model with voice data <= 10 mins!

realtime_ja_en_translation. リアルタイム翻訳

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

the-algorithm. Source code for the X Recommendation Algorithm

Unity_TransparentWindowManager. Make Unity's window transparent and overlay on desktop.

ChatGPT-Wrapper-For-Unity. A ChatGPT API wrapper for Unity

Whisper-API-unity. A client library of OpenAI Whisper transcription and translation API for Unity.

ChatGPT-API-unity. A client library of ChatGPT chat completion API for Unity.

demucs. Code for the paper Hybrid Spectrogram and Waveform Source Separation

blog. Public repo for HF blog posts

nxbt. Control your Nintendo Switch through a website, terminal, or macro.

Monocular-Video-Odometery. Monocular odometry using OpenCV

Deep-Learning-for-Tracking-and-Detection. Collection of papers, datasets, code and other resources for object tracking and detection using deep learning

segmentation_models.pytorch. Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

locus. [ICRA 2021] This repository contains the code for "Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling".

gtsam. GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.

hdl_graph_slam. 3D LIDAR-based Graph SLAM

VINS-Fusion. An optimization-based multi-sensor state estimator

openvslam. OpenVSLAM: A Versatile Visual SLAM Framework

ObjectDeliverer. ObjectDeliverer is a data transmission / reception library for Unreal Engine (C ++, Blueprint).

Tech_UDPDemo. UE4でUDP通信を扱う際のデモプロジェクトです。

JSONQuery. JSON plugin for UE4

rpg_svo_example. Example node to use the SVO Installation.

librealsense. RealSense SDK

chainer-DCGAN. Chainer implementation of Deep Convolutional Generative Adversarial Network