SystemAnimatorOnline
XR Animator, AI-based Full Body Motion Capture and Extended Reality (XR) solution, powered by System Animator Online
Stars: 831
XR Animator is a video/webcam-based AI motion capture application designed for VTubing and the metaverse era. It uses machine learning solutions to detect 3D poses from a live webcam video, driving a 3D avatar as if controlled by the user's body. It supports full-body AI motion tracking, face tracking, and various XR/3D purposes. The tool can be used for VTubing, recording mocap motion, exporting motions to different formats, customizing backgrounds and scenes, and animating 3D models in other applications. It also supports AR on Android Chrome browser, AR selfie feature, and has relatively low system requirements for wide device compatibility.
README:
XR Animator, inherited from my previous desktop gadget project known as System Animator, is a video/webcam-based AI motion capture application designed for VTubing and the metaverse era. It uses the machine learning (ML) solution from MediaPipe and TensorFlow.js to detect the 3D poses from a live webcam video, which is then used to drive the 3D avatar (MMD/VRM model) as if you are controlling it with your body. It can be used for VTubing and various XR/3D purposes.
It has a variety of motion tracking options. You can choose to track the face, full body, or something in between (any combination of face/body/hands).
The web app version works on all major web browsers both on desktop and smartphone. On browsers supporting both web worker and OffscreenCanvas (e.g. Chrome), it can achieve 60fps visual rendering and 30fps body pose detection on a mediocre PC. On smartphones with limited processing power, you may want to use limit its usage on face tracking.
The Windows/Linux app version (powered by Electron) is also availabe for download, which provides a few extra features (e.g. VMC-protocol, transparent background) available only in a native-OS environment.
-
Support full-body AI motion tracking using a single webcam or media file (image/video)
-
Support "Perfect Sync"/ARKit-compatible 52 blendshapes for realistic face tracking
-
Support using any MMD/VRM model as your 3D avatar
-
Record mocap motion and export it to BVH or VMD motion format
-
Support loading VMD/FBX/BVH format 3D motions
-
Export FBX/BVH motions to VMD format
-
Customize the background and 3D scene with 2D image/video , 3D panorama and 3D objects (.x/.glb format)
-
Support VMC-protocol to animate a 3D model elsewhere in other VMC-enabled applications such as VSeeFace, Unity and Unreal Engine (Electron mode only)
-
Support frameless window with transparent background on video capture apps such as OBS (Electron mode only) (*)
-
Support AR (Augmented Reality) on Android Chrome browser
Check out these YouTube video demos and watch XR Animator in action!
(*) - To capture the web app version of XR Animator on OBS without the browser UI, you have to open XR Animator on OBS browser. A few extra command line parameters on OBS are required to allow camera access. Details
XR Animator has relatively low system requirements, making it usable on a wide range of devices, including laptops and even smartphones. On an entry-level PC with GTX1650-class GPU running XR Animator with full body mocap, you can expect 20+ fps on pose/fingers tracking, 40+ fps (capped at 30) on face tracking, and 60fps on 3D rendering.
However, if you are using a laptop but you are experiencing lower-than-expected frame rate, the app may be using the slower integrated GPU. This is a pretty common problem for laptop users. Configure your graphics card settings and make sure that the faster dedicated GPU is used. Check out the article below if you don't know how.
How to Force Windows to Use Dedicated Graphics
XR Animator and some other demos of System Animator Online support the "Augmented Reality" (AR) mode on mobile phones, which renders the 3D models that appear as if they exist in the real world. The AR mode requires mobile phones that support Google's ARCore technology, Chrome browser and the new WebXR API. Follow the steps below.
-
Check here for a list of ARCore-supported devices and see if your device is supported.
-
Install Google Play Services for AR (ARCore) on Google Play.
-
Install Chrome browser for Android.
Are you ready for the AR experience? Check out the online version of XR Animator on your Android Chrome browser!
After the page has been fully loaded, click on the little phone button on the top-left (or bottom-left) menu to activate the AR mode. Once the AR mode is enabled, you will see what your phone's camera is showing. Move your camera around the ground where you want to place the 3D model, and a white circle should apppear. Double-tap on the screen, and the 3D model will be placed over the white circle. Double-tab again to re-summon the white circle if you want to place the model elsewhere.
Check out these YouTube videos for demonstration.
XR Animator also supports the AR selfie feature, using both the front camera (for AR) and the selfie camera, allowing you to take a selfie with the 3D avatar in AR mode.
Before you enter the AR mode, you need to double-click the "Selfie camera" icon and enable the selfie camera first. Then you can toggle the selfie camera at any time during the AR session. By default, avatar is always displayed in front of you in selfie mode. Double-click the "Segmentation AI" icon to enable the AI mode, which detects your shape inside the camera, allowing your avatar to blend into the background and appear behind you. Note that the AI mode is SLOW. You will probably need the latest Android phone to get a smooth frame rate.
You may also use the "Segmentation AI" on PC directly and display the avatar behind you without going through the AR mode.
Lastly, click the Snapshot icon and a still photo will be generated. This can be saved into your phone for whatever purpose you want, showing off to your friends perhaps!
Check out the following YouTube video for demonstration.
The future of XR Animator relies on your support🙇 Some IRL family issues have significantly increased my financial burden. While it was fun to develop the app, financial return was next to minimal. Reality forces me to evaluate the sustainability of this project, or soon I will have to give up...😢
If you like XR Animator, please consider making a donation🙇 Or even better, join my membership with perks such as EARLY ACCESS to the latest version XR Animator (at least one month ahead of the public release on GitHub), insider stories/tips and other benefits🎁 Sponsor us, and help keep this project free and sustainable🙏
XR Animator is currently sponsored by the following people❤️
- NewruGuru, Nymph, Shionay, shion, KuraiNoOni, MShade, Kai, ambyshard, Prajzis, LouLi Lou
- Other supporters
System Animator was originally a desktop gadget project, born more than 10 years ago. The latest version, System Animator Online, is a major version advancement with focus on working as a web app instead of being just a desktop gadget. It fully supports MikuMikuDance (MMD) models and motions, as well as the latest VRM models and FBX/BVH motions, to create an immersive 3D environment.
It's hard to describe what System Animator Online can do in a few words. From a simple animated CPU meter to an interactive 3D music visualizer, a simple AR gadget on your phone to a full-body motion tracking app on your PC, the possibility is endless.
For more information about the desktop gadget version of System Animator, please visit the following page. https://www.animetheme.com/sidebar/
System Animator was born more than 10 years ago as a personal and tiny 100-line-ish JavaScript desktop gadget project for Windows Vista which shows an animated rocket Anime girl as a CPU meter (the animation is still in XR Animator).
As time goes by, I decided to add more features, multi-purpose system meter, music visualizer, 3D/MMD support, animated wallpaper engine, RPG engine and eventually what you see in XR Animator. The codebase has grown exponentially while the core is still an Internet-Explorer-based JavaScript gadget, and things were becoming more and more clumsy, to a point when I had to decide whether to rewrite everything from scratch to match the modern coding standard (open source, module based, etc). However, I gave up and decided to carry on with what I have written, as a total restart would require too much time and efforts, probably not worthy as a personal project. Besides, as the rule of programming says, "If it works, don't touch it" LOL
Eventually, I decided to put the project on Github for my own convenience, but technically speaking you can consider it open source, though I have to admit that some of the codes are outdated, clumsy and confusing. Everything is fine if you are just an end-user of XR Animator/System Animator as an app, but if you want to build your own things from my codes, be warned that they can be pretty incomprehensible LOL
-
3D Miku The Dancer (drop any MP3 and she will dance for you)
-
3D Multiplayer RPG (up to 3 players)
All demos support the use of custom MMD (MikuMikuDance) model. Drop a zip of your favorite MMD model at the beginning, press the START button, and the demo will proceed with your model instead of the default one.
- License (CC BY-NC-SA 4.0) - http://creativecommons.org/licenses/by-nc-sa/4.0/
- This license applies if you are adapting XR Animator's source code for your own purpose, such as building another software or service.
- This license does not cover any third-party assets which may have incompatible licenses of their own.
- This license does not apply to content generated from the functionality of XR Animator, such as video content generated from the motion capture feature of System Animator using your own assets. XR Animator claims no right or responsibility over such content.
-
System Animator © Butz Yung/Anime Theme - http://www.animetheme.com/sidebar/
-
jThree v2 (NOTE: jThree has been discontinued. Its successor is known as "Grimoire.js")
-
ammo.js, a port of Bullet Physics to JavaScript, zlib licensed
-
JSZip (used under MIT license)
-
"Appearance Miku" MMD Model - Readme/License
-
Some texture/image/icon sources https://3dtextures.me/ https://opengameart.org/content/rpg-inventory https://opengameart.org/content/fantasy-icon-pack-by-ravenmore-0 https://opengameart.org/content/potion-bottles https://www.flaticon.com/ https://www.iconfinder.com/ https://icon-icons.com/en/pack/Social-Distancing/2274 https://github.com/icons8/flat-color-icons https://www.behance.net/gallery/41818673/FREE-SPORT-ICONS
-
Simple Explosion by Bleed https://remusprites.carbonmade.com/ https://opengameart.org/content/simple-explosion-bleeds-game-art
-
Various 3D background effects ported and modified from codes found on Shadertoy
-
Some icons and backgrounds from Freepik
-
For some other third-party programming libraries/3D data/assets used in System Animator, please refer to the corresponding script/readme for license and terms (can be found on the downloadable/Github version of System Animator).
-
もぐ式りょう/りく/りょく/りん by Mogg https://3d.nicovideo.jp/works/td55798 https://3d.nicovideo.jp/works/td55973 https://3d.nicovideo.jp/works/td56074 https://3d.nicovideo.jp/works/td56604
-
"Stranger Things" - A Remix ft. Michael Jobity https://soundcloud.com/foreignmachine/stranger-remix
-
Dragon Ball Super I Ultra Instinct OST I Clash of Gods Remix I Hip Hop Instrumental I @AndrezoWorks https://www.youtube.com/watch?v=KJ71dY4mkNo
-
Credits are given to the authors of any other image/media files used in System Animator.
-
Twitter: https://twitter.com/butz_yung
-
Discord: https://discord.gg/Xs4YEMVtkx
-
Ko-fi: https://ko-fi.com/butzyung
-
FANBOX: https://xra.fanbox.cc/
-
Homepage (System Animator): https://www.animetheme.com/sidebar/
-
Email: [email protected]
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for SystemAnimatorOnline
Similar Open Source Tools
SystemAnimatorOnline
XR Animator is a video/webcam-based AI motion capture application designed for VTubing and the metaverse era. It uses machine learning solutions to detect 3D poses from a live webcam video, driving a 3D avatar as if controlled by the user's body. It supports full-body AI motion tracking, face tracking, and various XR/3D purposes. The tool can be used for VTubing, recording mocap motion, exporting motions to different formats, customizing backgrounds and scenes, and animating 3D models in other applications. It also supports AR on Android Chrome browser, AR selfie feature, and has relatively low system requirements for wide device compatibility.
Generative-AI-Pharmacist
Generative AI Pharmacist is a project showcasing the use of generative AI tools to create an animated avatar named Macy, who delivers medication counseling in a realistic and professional manner. The project utilizes tools like Midjourney for image generation, ChatGPT for text generation, ElevenLabs for text-to-speech conversion, and D-ID for creating a photorealistic talking avatar video. The demo video featuring Macy discussing commonly-prescribed medications demonstrates the potential of generative AI in healthcare communication.
RTranslator
RTranslator is an almost open-source, free, and offline real-time translation app for Android. It offers Conversation mode for multi-user translations, WalkieTalkie mode for quick conversations, and Text translation mode. It uses Meta's NLLB for translation and OpenAi's Whisper for speech recognition, ensuring privacy. The app is optimized for performance and supports multiple languages. It is ad-free and donation-supported.
chatgpt-universe
ChatGPT is a large language model that can generate human-like text, translate languages, write different kinds of creative content, and answer your questions in a conversational way. It is trained on a massive amount of text data, and it is able to understand and respond to a wide range of natural language prompts. Here are 5 jobs suitable for this tool, in lowercase letters: 1. content writer 2. chatbot assistant 3. language translator 4. creative writer 5. researcher
ainodes-engine
aiNodes Engine is a Python-based AI image/motion picture generator node engine with a live execution chain, python code editor node, and plug-in support. It offers full modularity, colored background drop, and easy node creation with IDE annotations. The project is officially supported by Deforum and incorporates various open-source projects like ComfyUI. It is designed to be flexible, with an Unreal-like execution chain, supporting features such as Deforum, Stable Diffusion, Upscalers, Kandinsky, ControlNet, and more. The engine allows for background separation, human matting/masking, compositing, drag and drop, subgraphs, and graph saving/loading from image metadata. It aims to provide a unique, controllable manner of working with a strict user-declared execution chain.
OpenCat
OpenCat is an open-source Arduino and Raspberry Pi-based quadruped robotic pet framework developed by Petoi. It aims to foster collaboration in quadruped robotics research, education, and engineering development of agile and affordable quadruped robot pets. The project provides a base open source platform for creating programmable gaits, locomotion, and deployment of inverse kinematics quadruped robots, enabling simulations to the real world via block-based coding/C/C++/Python programming languages. Users have deployed various robotics/AI/IoT applications and the project has successfully crowdfunded mini robot kits, shipped worldwide, and established a production line for affordable robotic kits and accessories.
TagUI
TagUI is an open-source RPA tool that allows users to automate repetitive tasks on their computer, including tasks on websites, desktop apps, and the command line. It supports multiple languages and offers features like interacting with identifiers, automating data collection, moving data between TagUI and Excel, and sending Telegram notifications. Users can create RPA robots using MS Office Plug-ins or text editors, run TagUI on the cloud, and integrate with other RPA tools. TagUI prioritizes enterprise security by running on users' computers and not storing data. It offers detailed logs, enterprise installation guides, and support for centralised reporting.
Powerpointer-For-Local-LLMs
PowerPointer For Local LLMs is a PowerPoint generator that uses python-pptx and local llm's via the Oobabooga Text Generation WebUI api to create beautiful and informative presentations. It runs locally on your computer, eliminating privacy concerns. The tool allows users to select from 7 designs, make placeholders for images, and easily customize presentations within PowerPoint. Users provide information for the PowerPoint, which is then used to generate text using optimized prompts and the text generation webui api. The generated text is converted into a PowerPoint presentation using the python-pptx library.
MediaAI
MediaAI is a repository containing lectures and materials for Aalto University's AI for Media, Art & Design course. The course is a hands-on, project-based crash course focusing on deep learning and AI techniques for artists and designers. It covers common AI algorithms & tools, their applications in art, media, and design, and provides hands-on practice in designing, implementing, and using these tools. The course includes lectures, exercises, and a final project based on students' interests. Students can complete the course without programming by creatively utilizing existing tools like ChatGPT and DALL-E. The course emphasizes collaboration, peer-to-peer tutoring, and project-based learning. It covers topics such as text generation, image generation, optimization, and game AI.
supervisely
Supervisely is a computer vision platform that provides a range of tools and services for developing and deploying computer vision solutions. It includes a data labeling platform, a model training platform, and a marketplace for computer vision apps. Supervisely is used by a variety of organizations, including Fortune 500 companies, research institutions, and government agencies.
pwnagotchi
Pwnagotchi is an AI tool leveraging bettercap to learn from WiFi environments and maximize crackable WPA key material. It uses LSTM with MLP feature extractor for A2C agent, learning over epochs to improve performance in various WiFi environments. Units can cooperate using a custom parasite protocol. Visit https://www.pwnagotchi.ai for documentation and community links.
bpf-developer-tutorial
This is a development tutorial for eBPF based on CO-RE (Compile Once, Run Everywhere). It provides practical eBPF development practices from beginner to advanced, including basic concepts, code examples, and real-world applications. The tutorial focuses on eBPF examples in observability, networking, security, and more. It aims to help eBPF application developers quickly grasp eBPF development methods and techniques through examples in languages such as C, Go, and Rust. The tutorial is structured with independent eBPF tool examples in each directory, covering topics like kprobes, fentry, opensnoop, uprobe, sigsnoop, execsnoop, exitsnoop, runqlat, hardirqs, and more. The project is based on libbpf and frameworks like libbpf, Cilium, libbpf-rs, and eunomia-bpf for development.
slide-deck-ai
SlideDeck AI is a tool that leverages Generative Artificial Intelligence to co-create slide decks on any topic. Users can describe their topic and let SlideDeck AI generate a PowerPoint slide deck, streamlining the presentation creation process. The tool offers an iterative workflow with a conversational interface for creating and improving presentations. It uses Mistral Nemo Instruct to generate initial slide content, searches and downloads images based on keywords, and allows users to refine content through additional instructions. SlideDeck AI provides pre-defined presentation templates and a history of instructions for users to enhance their presentations.
lollms-webui
LoLLMs WebUI (Lord of Large Language Multimodal Systems: One tool to rule them all) is a user-friendly interface to access and utilize various LLM (Large Language Models) and other AI models for a wide range of tasks. With over 500 AI expert conditionings across diverse domains and more than 2500 fine tuned models over multiple domains, LoLLMs WebUI provides an immediate resource for any problem, from car repair to coding assistance, legal matters, medical diagnosis, entertainment, and more. The easy-to-use UI with light and dark mode options, integration with GitHub repository, support for different personalities, and features like thumb up/down rating, copy, edit, and remove messages, local database storage, search, export, and delete multiple discussions, make LoLLMs WebUI a powerful and versatile tool.
HuggingFists
HuggingFists is a low-code data flow tool that enables convenient use of LLM and HuggingFace models. It provides functionalities similar to Langchain, allowing users to design, debug, and manage data processing workflows, create and schedule workflow jobs, manage resources environment, and handle various data artifact resources. The tool also offers account management for users, allowing centralized management of data source accounts and API accounts. Users can access Hugging Face models through the Inference API or locally deployed models, as well as datasets on Hugging Face. HuggingFists supports breakpoint debugging, branch selection, function calls, workflow variables, and more to assist users in developing complex data processing workflows.
Simulator-Controller
Simulator Controller is a modular administration and controller application for Sim Racing, featuring a comprehensive plugin automation framework for external controller hardware. It includes voice chat capable Assistants like Virtual Race Engineer, Race Strategist, Race Spotter, and Driving Coach. The tool offers features for setup, strategy development, monitoring races, and more. Developed in AutoHotkey, it supports various simulation games and integrates with third-party applications for enhanced functionality.
For similar tasks
SystemAnimatorOnline
XR Animator is a video/webcam-based AI motion capture application designed for VTubing and the metaverse era. It uses machine learning solutions to detect 3D poses from a live webcam video, driving a 3D avatar as if controlled by the user's body. It supports full-body AI motion tracking, face tracking, and various XR/3D purposes. The tool can be used for VTubing, recording mocap motion, exporting motions to different formats, customizing backgrounds and scenes, and animating 3D models in other applications. It also supports AR on Android Chrome browser, AR selfie feature, and has relatively low system requirements for wide device compatibility.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.