正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

💚 NVIDIA has released the MotionBricks weights on the Hugging Face Hub! MotionBricks generates real-time motion for game characters and humanoid robots. Give it a character's recent poses and the poses it should reach next, and it generates the movement in between, at 15,000 FPS with 2 ms latency.... show more

Alvaro Bartolome

2,516 subscribers

201,716 次观看 • 12 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

37 条评论

Alvaro Bartolome 的头像

Alvaro Bartolome12 天前

Find the weights on the Hugging Face Hub, and start building with the MotionBricks framework today!

Alvaro Bartolome 的头像

Alvaro Bartolome12 天前

Or check their project page for more information, insights and deep-dives on the model and framework!

Toby VirtualFilmer 的头像

Toby VirtualFilmer12 天前

@NVIDIAAI @nvidia “Just”?? This was release months ago

Alvaro Bartolome 的头像

Alvaro Bartolome12 天前

@NVIDIAAI @nvidia They just released the *open weights* on the @huggingface Hub, as it reads in "💚 NVIDIA has released the MotionBricks weights on the Hugging Face Hub!"

Root 的头像

Root12 天前

@NVIDIAAI @nvidia Stil waaaaay off from a good hand crafted animation.

Alvaro Bartolome 的头像

Alvaro Bartolome12 天前

@NVIDIAAI @nvidia no machine can surpass hand crafted stuff, but some get really really close imo

Trying my best :-) 的头像

Trying my best :-)12 天前

@NVIDIAAI @nvidia yeah the best body animations I have seen in a virtual environment by far.

ashen 的头像

ashen11 天前

@NVIDIAAI @nvidia yo @xikhar

Komm 的头像

Komm11 天前

@NVIDIAAI @nvidia looks better than gta6's locomotion system ngl. this looks promising.

Soran 的头像

Soran12 天前

@NVIDIAAI @nvidia finally euphoria for all!

Dominik 的头像

Dominik12 天前

@NVIDIAAI @nvidia one model driving both a game character and a unitree g1 is the interesting bit. does the same primitive set hold up on the real robot?

Nidal Nijm 的头像

Nidal Nijm12 天前

@NVIDIAAI @nvidia Amazing and this will not "kill" animators. Rather Animators will need to learn how to use these tools and adapt their workflow to survive and stand out.

ttywisp 的头像

ttywisp12 天前

@NVIDIAAI @nvidia can it hop on one leg

Mason Dudley 的头像

Mason Dudley12 天前

@NVIDIAAI @nvidia Thats actually really cool

Toby VirtualFilmer 的头像

Toby VirtualFilmer12 天前

@NVIDIAAI @nvidia @grok my understanding was that Nvidia released this many months ago- is there a new release now? Can you explain it?

₽ⱤΞΞ₮Ⱨ△M ₭Ɏ△И△M 的头像

₽ⱤΞΞ₮Ⱨ△M ₭Ɏ△И△M12 天前

@NVIDIAAI @nvidia This is highkey very very cool

Muhammad Subhan Imran 的头像

Muhammad Subhan Imran12 天前

@NVIDIAAI @nvidia @zaiggy007 Animations upgrade incoming

Owais 的头像

Owais11 天前

@NVIDIAAI @nvidia hey @grok can you check is it free and open source to use?

Adamanthys 的头像

Adamanthys11 天前

@NVIDIAAI @nvidia That looks RD2 level or better. No excuse for stiff animations anymore.

JL 的头像

JL12 天前

@NVIDIAAI @nvidia HOLY SMOKES

goktug 的头像

goktug11 天前

@NVIDIAAI @nvidia 15000 FPS?

PhantasyWave 的头像

PhantasyWave12 天前

@NVIDIAAI @nvidia What are the exportable formats? Or is it even possible to export animations? I will look into it anyways thanks for sharing

Rusty Shackleford 的头像

Rusty Shackleford11 天前

@NVIDIAAI @nvidia I prefer games having unrealistic but plausible movement over this slow ass "☝🤓 Technically more accurate" bullshit. Movie games are ass.

Æ̾̾̾̾̾̾̾x 的头像

Æ̾̾̾̾̾̾̾x11 天前

@NVIDIAAI @nvidia this is the coolest thing ever

Roberto Bifulco 的头像

Roberto Bifulco12 天前

@NVIDIAAI @nvidia I guess it is time for the next toy project then 😅

Chiki-Briki 的头像

Chiki-Briki11 天前

@NVIDIAAI @nvidia Круто, нас ждут игры с одинаковыми анимациями?)

Chron 的头像

Chron12 天前

@NVIDIAAI @nvidia Nvidia Single-Handedly will kill the gaming industry hardware wise and software wise

JOSEMAXIMUS2 🇪🇸🇪🇸 的头像

JOSEMAXIMUS2 🇪🇸🇪🇸12 天前

@NVIDIAAI @nvidia this is huge, now we need physics too

Six 的头像

Six12 天前

@NVIDIAAI @nvidia MotionBricks on the Hub is huge for realtime character/robot motion — 15k samples/s interpolation is wild for game NPCs.

Kuldeep Pisda 的头像

Kuldeep Pisda11 天前

@NVIDIAAI @nvidia for the G1 weights, is there a tracking controller in the release to turn poses into torques or is that bring your own?

Roman Kowalski 的头像

Roman Kowalski12 天前

@NVIDIAAI @nvidia i want my AC mod for gta5 do it cloude, make no mistakes

빚갚는 n잡러 的头像

빚갚는 n잡러11 天前

@NVIDIAAI @nvidia 이걸로 게임 다 만들겠습니다!

Micah 的头像

Micah12 天前

@NVIDIAAI @nvidia looks like assassins creed 2019 era

Zippy 的头像

Zippy12 天前

@NVIDIAAI @nvidia Ubisoft still gonna make it jank somehow.

zynx 的头像

zynx12 天前

@NVIDIAAI @nvidia how does it compare with ARDY?

Sebastiano Mandalà 的头像

Sebastiano Mandalà12 天前

@NVIDIAAI @nvidia this is old news right? Are these baked animation or selected at real time by the policy?

Orn 的头像

Orn12 天前

@NVIDIAAI @nvidia Any word on the UE5 plugin?

相关视频

NVIDIA has released MotionBricks, an AI that generates character motion at a reported 15,000 frames per second with just 2ms latency on an RTX 5090. Trained on 350,000+ motion clips, it lets developers build new interactions for game characters and humanoid robots without retraining.

NVIDIA has released MotionBricks, an AI that generates character motion at a reported 15,000 frames per second with just 2ms latency on an RTX 5090. Trained on 350,000+ motion clips, it lets developers build new interactions for game characters and humanoid robots without retraining.

Chubby♨️

83,530 次观看 • 10 天前

NVIDIA MotionBricks brings humanoid robots closer to natural, fluid movement The system combines a modular latent generative model with Smart Primitives, packing more than 350,000 motion skills into a single backbone. It runs in real time at up to 15,000 FPS with just 2ms latency. Navigation, object interaction, sitting, jumping, obstacle crossing, and even different movement styles can be composed zero-shot, like reusable motion modules. It is already being used for whole-body control on the Unitree G1 and serves as the motion layer for NVIDIA GR00T Whole-Body Control. What makes this interesting is the move from training individual behaviors toward building a shared library of motion capabilities. If that approach scales, robot movement could become more modular, transferable, and easier to deploy across different tasks and environments.

NVIDIA MotionBricks brings humanoid robots closer to natural, fluid movement The system combines a modular latent generative model with Smart Primitives, packing more than 350,000 motion skills into a single backbone. It runs in real time at up to 15,000 FPS with just 2ms latency. Navigation, object interaction, sitting, jumping, obstacle crossing, and even different movement styles can be composed zero-shot, like reusable motion modules. It is already being used for whole-body control on the Unitree G1 and serves as the motion layer for NVIDIA GR00T Whole-Body Control. What makes this interesting is the move from training individual behaviors toward building a shared library of motion capabilities. If that approach scales, robot movement could become more modular, transferable, and easier to deploy across different tasks and environments.

CyberRobo

11,227 次观看 • 4 个月前

This is wild. NVIDIA just dropped MotionBricks at SIGGRAPH 2026. This AI makes game characters and robots move with 350,000+ motion skills. 15,000 FPS. 2ms latency. 1. Smart locomotion - Characters can now switch movement styles on the fly.

This is wild. NVIDIA just dropped MotionBricks at SIGGRAPH 2026. This AI makes game characters and robots move with 350,000+ motion skills. 15,000 FPS. 2ms latency. 1. Smart locomotion - Characters can now switch movement styles on the fly.

Min Choi

111,816 次观看 • 4 个月前

NVIDIA just revealed MotionBricks, a new AI model trained on more than 350,000 motion clips. What’s really impressive is that the same model can animate a digital character and control a humanoid robot in the real world.

NVIDIA just revealed MotionBricks, a new AI model trained on more than 350,000 motion clips. What’s really impressive is that the same model can animate a digital character and control a humanoid robot in the real world.

Justin Ryan

85,343 次观看 • 3 个月前

New Open-Source AI Animator: Text-to-Animation for Humans, Animals, Creatures, Robots & More UniMate generates motion from text prompts for rigged 3D characters. Describe an action and turn it into animation. Highlights: • One model, different skeletons—no separate retraining for each rig. • Generate transitions between existing keyframes. • Edit motion with text while keeping selected joints unchanged. • Extend animations with a sequence of prompts. • Export animated meshes as FBX and GLB. • MIT-licensed code + downloadable preview weights.

New Open-Source AI Animator: Text-to-Animation for Humans, Animals, Creatures, Robots & More UniMate generates motion from text prompts for rigged 3D characters. Describe an action and turn it into animation. Highlights: • One model, different skeletons—no separate retraining for each rig. • Generate transitions between existing keyframes. • Edit motion with text while keeping selected joints unchanged. • Extend animations with a sequence of prompts. • Export animated meshes as FBX and GLB. • MIT-licensed code + downloadable preview weights.

Stefan 3D AI

246,925 次观看 • 1 个月前

Ropedia just released W0, an open world model trained on ~10,000 hours of egocentric human video. One set of weights predicts first-person views for humans, robot arms, and humanoids (Unitree G1, Fourier GR-1) using a shared camera + skeleton representation. Adding a new robot only requires its URDF. It leads Cosmos 3 and DreamDojo across every benchmark tested. After distillation it runs at 21.3 FPS, enough for real-time VR control, and can roll out minute-long continuous loco-manipulation. Human pretraining transfers: the model with zero robot data already beats robot-trained baselines on several humanoid tests. In practice it can rank policies, pick better actions at runtime, and transfer to new robots without large-scale data collection. Paper, code, weights, and demos are all out.

Ropedia just released W0, an open world model trained on ~10,000 hours of egocentric human video. One set of weights predicts first-person views for humans, robot arms, and humanoids (Unitree G1, Fourier GR-1) using a shared camera + skeleton representation. Adding a new robot only requires its URDF. It leads Cosmos 3 and DreamDojo across every benchmark tested. After distillation it runs at 21.3 FPS, enough for real-time VR control, and can roll out minute-long continuous loco-manipulation. Human pretraining transfers: the model with zero robot data already beats robot-trained baselines on several humanoid tests. In practice it can rank policies, pick better actions at runtime, and transfer to new robots without large-scale data collection. Paper, code, weights, and demos are all out.

The Humanoid Hub

10,446 次观看 • 18 天前

Made a demo for MotionBricks running 100% in your browser. You steer a robot, change its walking style or approach an obstacle. The app turns that into target poses, and the model uses its recent poses to generate the motion connecting them. It outputs 3D joint motion, runs locally on your CPU.

Made a demo for MotionBricks running 100% in your browser. You steer a robot, change its walking style or approach an obstacle. The app turns that into target poses, and the model uses its recent poses to generate the motion connecting them. It outputs 3D joint motion, runs locally on your CPU.

Victor M

23,840 次观看 • 10 天前

Today we're releasing Trinity-Large-Thinking. Available now on the Arcee API, with open weights on Hugging Face under Apache 2.0. We built it for developers and enterprises that want models they can inspect, post-train, host, distill, and own.

Today we're releasing Trinity-Large-Thinking. Available now on the Arcee API, with open weights on Hugging Face under Apache 2.0. We built it for developers and enterprises that want models they can inspect, post-train, host, distill, and own.

Arcee.ai

727,828 次观看 • 7 个月前

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

109,958 次观看 • 1 个月前

Nvidia is now a humanoid robot designer. That's the real takeaway from this news. Nvidia is acquiring Hugging Face for $12.93B. Hugging Face is the largest open-model and dataset hub, the "GitHub of AI," with 3M+ models and 18M+ developers, robotics included. But here's the interesting part: Hugging Face has a serious robotics team from its acquisition of Pollen Robotics, which designs and builds open-source hardware platforms for robots, including humanoids (Reachy). Pollen team now gets the backing of the world's most valuable company. $NVDA

Nvidia is now a humanoid robot designer. That's the real takeaway from this news. Nvidia is acquiring Hugging Face for $12.93B. Hugging Face is the largest open-model and dataset hub, the "GitHub of AI," with 3M+ models and 18M+ developers, robotics included. But here's the interesting part: Hugging Face has a serious robotics team from its acquisition of Pollen Robotics, which designs and builds open-source hardware platforms for robots, including humanoids (Reachy). Pollen team now gets the backing of the world's most valuable company. $NVDA

The Humanoid Hub

10,755 次观看 • 2 个月前

NVIDIA announces the first open humanoid robot reference design built for robotics research. The NVIDIA Isaac GR00T Reference Humanoid Robot combines the Unitree H2 humanoid robot, Sharpa Wave five-fingered hands for dexterous manipulation, Jetson Thor onboard compute, and Isaac GR00T open software and models, giving researchers a full-stack platform from data capture to model deployment. Read the #NVIDIAGTC Taipei announcement:

NVIDIA announces the first open humanoid robot reference design built for robotics research. The NVIDIA Isaac GR00T Reference Humanoid Robot combines the Unitree H2 humanoid robot, Sharpa Wave five-fingered hands for dexterous manipulation, Jetson Thor onboard compute, and Isaac GR00T open software and models, giving researchers a full-stack platform from data capture to model deployment. Read the #NVIDIAGTC Taipei announcement:

NVIDIA Robotics

175,627 次观看 • 5 个月前

Big day for open source. MiniMax Music 3 is undeniably a state of the art open weights Music Generation model and a real alternative to Suno. My favorite part about open weights: the best is yet to come. Once the community starts playing with the model and training LoRAs, this model only gets better and allows for more control.

Big day for open source. MiniMax Music 3 is undeniably a state of the art open weights Music Generation model and a real alternative to Suno. My favorite part about open weights: the best is yet to come. Once the community starts playing with the model and training LoRAs, this model only gets better and allows for more control.

rob - comfyui

324,108 次观看 • 2 个月前

Nvidia has just announced Alpamayo 2 Super, an open 34 billion parameter reasoning vision-language-action model designed to accelerate the development of autonomous vehicles. This new model combines the NVIDIA Cosmos 3 Super reasoning model with a 2 billion parameter diffusion-based action expert model, and is post trained with reinforcement learning. The model can return multiple outputs: future trajectory plans, reasoning traces, grounded answers to questions about the scenes, and auto label generation. The model weights are now available for anyone to download on Hugging Face, and the inference code has been posted to GitHub. Distilled models can be deployed commercially without any further permission from Nvidia, and model outputs carry no license conditions. Automakers can distill down a compact version of this model that can run on the Nvidia computer in the car. Major kudos to Nvidia and Jensen Huang for advancing the state of the industry by releasing this as an open model with permissive licensing. Jensen isn't just paying lip service to the idea of open models, Nvidia is actually contributing to the ecosystem — and it's great for their business, because it helps sell more Thor computers that go in the car. Anyone can go download the model and play with it. If you do, let me know what you think. Personally I think it's so cool that we have open weights models that are this advanced, for anyone to download.

Nvidia has just announced Alpamayo 2 Super, an open 34 billion parameter reasoning vision-language-action model designed to accelerate the development of autonomous vehicles. This new model combines the NVIDIA Cosmos 3 Super reasoning model with a 2 billion parameter diffusion-based action expert model, and is post trained with reinforcement learning. The model can return multiple outputs: future trajectory plans, reasoning traces, grounded answers to questions about the scenes, and auto label generation. The model weights are now available for anyone to download on Hugging Face, and the inference code has been posted to GitHub. Distilled models can be deployed commercially without any further permission from Nvidia, and model outputs carry no license conditions. Automakers can distill down a compact version of this model that can run on the Nvidia computer in the car. Major kudos to Nvidia and Jensen Huang for advancing the state of the industry by releasing this as an open model with permissive licensing. Jensen isn't just paying lip service to the idea of open models, Nvidia is actually contributing to the ecosystem — and it's great for their business, because it helps sell more Thor computers that go in the car. Anyone can go download the model and play with it. If you do, let me know what you think. Personally I think it's so cool that we have open weights models that are this advanced, for anyone to download.

Whole Mars Catalog

45,595 次观看 • 3 个月前

Unitree Humanoid Robots Updated With Open-Source Full-Body Motion Dataset 🤗 We’ve adapted motion capture data for Unitree H1, H1-2, and G1 humanoid robots, using numerical optimization methods to make their movement trajectories more natural. Open-Source： #AI #OpenSourceDataset #Unitree #EmbodiedAI #Humanoid #DataCollection #AGI #Dance

Unitree Humanoid Robots Updated With Open-Source Full-Body Motion Dataset 🤗 We’ve adapted motion capture data for Unitree H1, H1-2, and G1 humanoid robots, using numerical optimization methods to make their movement trajectories more natural. Open-Source： #AI #OpenSourceDataset #Unitree #EmbodiedAI #Humanoid #DataCollection #AGI #Dance

Unitree

198,702 次观看 • 1 年前

What is missing to bring real-time motion research into AAA games and real-world robotics? We present MotionBricks, a step toward bridging this gap with two key components: - a single generative latent motion backbone covering 350,000+ motion skills, running at 15,000 FPS with 2 ms latency and substantially improved quality and reliability. - a unified smart primitive interface for locomotion, object / scene interaction, with fine-grained control over generated behaviors. Webpage: Code: Paper: (ACM TOG / SIGGRAPH 2026)

What is missing to bring real-time motion research into AAA games and real-world robotics? We present MotionBricks, a step toward bridging this gap with two key components: - a single generative latent motion backbone covering 350,000+ motion skills, running at 15,000 FPS with 2 ms latency and substantially improved quality and reliability. - a unified smart primitive interface for locomotion, object / scene interaction, with fine-grained control over generated behaviors. Webpage: Code: Paper: (ACM TOG / SIGGRAPH 2026)

tingwu.wang

154,801 次观看 • 6 个月前

MotionBricks by Nvidia, a new AI that generates realistic human and robot movements in real time

MotionBricks by Nvidia, a new AI that generates realistic human and robot movements in real time

AI Search

32,118 次观看 • 12 天前

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

PatronusAI

14,879 次观看 • 1 年前

MotionBricks by NVIDIA. the all-in-one brain for character movement. No manual rigging/animation, you just let this AI handle the physics and style in real-time. - 15k FPS on RTX 5090! You could run an entire city of unique NPCs without breaking a sweat. - Smart Primitives. The AI fills in the natural-looking motion automatically. - Zero-Shot Skills. - Glitch-Free. Keeps movements stable.

MotionBricks by NVIDIA. the all-in-one brain for character movement. No manual rigging/animation, you just let this AI handle the physics and style in real-time. - 15k FPS on RTX 5090! You could run an entire city of unique NPCs without breaking a sweat. - Smart Primitives. The AI fills in the natural-looking motion automatically. - Zero-Shot Skills. - Glitch-Free. Keeps movements stable.

Wildminder

23,296 次观看 • 4 个月前

LETS GOO! Generate full songs (4 min) with vocals in less than 10 seconds - open weights model! 🔥 It's crazy how much you can achieve from open models as of today! - going right for Suno and likes! VAE + Base model combined is < 2.5GB Open weights on the hub and a space to play around with it! 🤯

LETS GOO! Generate full songs (4 min) with vocals in less than 10 seconds - open weights model! 🔥 It's crazy how much you can achieve from open models as of today! - going right for Suno and likes! VAE + Base model combined is < 2.5GB Open weights on the hub and a space to play around with it! 🤯

Vaibhav (VB) Srivastav

64,204 次观看 • 1 年前

🚀 Galbot just released AstraBrain-WBC 0.5, the world’s first humanoid robot cerebellum foundation model. Trained on 20,000 hours of human motion data, it validates a Scaling Law for robot motion control and demonstrates zero-shot execution of unseen motions on real humanoids. The era of robot control foundation models is getting closer.

🚀 Galbot just released AstraBrain-WBC 0.5, the world’s first humanoid robot cerebellum foundation model. Trained on 20,000 hours of human motion data, it validates a Scaling Law for robot motion control and demonstrates zero-shot execution of unseen motions on real humanoids. The era of robot control foundation models is getting closer.

Eren Chen

10,270 次观看 • 4 个月前