Loading video...

Video Failed to Load

Go Home

A 1-billion-parameter motion model trained on NVIDIA CUDA that converts webcam or video footage into real-time XYZ skeletal point data and rotation values, enabling a fast 3D animation workflow.

cyanpuppets's profile picture

CYANPUPPETS

9,937 subscribers

62,091 views • 7 months ago •via X (Twitter)

ArtsScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A 1-billion-parameter AI real-time motion model that connects to a 1080P camera or uploaded videos, supports UE/Unity/Blender, and requires 8GB of VRAM for real-time processing.
0:18

A 1-billion-parameter AI real-time motion model that connects to a 1080P camera or uploaded videos, supports UE/Unity/Blender, and requires 8GB of VRAM for real-time processing.

CYANPUPPETS

63,549 views • 3 months ago

Free Blender AI Motion Capture Plugin: Runs a 1-billion-parameter model on a GPU with 8GB VRAM, supporting real-time capture and video uploads — no cost required.
0:10

Free Blender AI Motion Capture Plugin: Runs a 1-billion-parameter model on a GPU with 8GB VRAM, supporting real-time capture and video uploads — no cost required.

CYANPUPPETS

15,761 views • 1 year ago

MotionStream Real-Time Video Generation with Interactive Motion Controls model runs in real time on a single NVIDIA H100 GPU (29 FPS, 0.4s Latency)
0:19

MotionStream Real-Time Video Generation with Interactive Motion Controls model runs in real time on a single NVIDIA H100 GPU (29 FPS, 0.4s Latency)

AK

22,304 views • 7 months ago

Upcoming features to be opened for free: exporting dance videos to 3D animation using local graphics card arithmetic, unlimited generation of FBX motion data. We are still working on the free version, and hope to accelerate the creative efficiency of individual creators.
0:16

Upcoming features to be opened for free: exporting dance videos to 3D animation using local graphics card arithmetic, unlimited generation of FBX motion data. We are still working on the free version, and hope to accelerate the creative efficiency of individual creators.

Cyanpuppets

53,844 views • 1 year ago

This is 3D animation powered by AI. No suits or markers needed. This 2D video was captured with GoPro cameras and converted to 3D motion data using Move Multi-Cam. #MadeWithMove
0:15

This is 3D animation powered by AI. No suits or markers needed. This 2D video was captured with GoPro cameras and converted to 3D motion data using Move Multi-Cam. #MadeWithMove

Move AI

182,792 views • 2 years ago

3dSen is a unique NES emulator that converts 2D NES games into 3D, voxel-style dioramas in real-time. It can also be played in VR.
0:12

3dSen is a unique NES emulator that converts 2D NES games into 3D, voxel-style dioramas in real-time. It can also be played in VR.

SuperSisi

77,010 views • 2 months ago

Just dropped on HF: kani-tts-370m A lightweight open-source text-to-speech model that sounds great and runs fast! > 370M parameters — efficient and deployable on consumer GPUs > NanoCodec + LFM2-350M > Natural & expressive voice trained with modern neural TTS techniques > Fast inference: real-time on a single RTX 3060
0:10

Just dropped on HF: kani-tts-370m A lightweight open-source text-to-speech model that sounds great and runs fast! > 370M parameters — efficient and deployable on consumer GPUs > NanoCodec + LFM2-350M > Natural & expressive voice trained with modern neural TTS techniques > Fast inference: real-time on a single RTX 3060

steven

34,558 views • 8 months ago

Ok... this is insane! Alibaba just dropped Wan2.2-S2V, a 14B parameter speech-to-video model. Turn audio into film-grade clips with lifelike motion and environment control. And it’s fully open-source. Examples below: (sound on)
0:14

Ok... this is insane! Alibaba just dropped Wan2.2-S2V, a 14B parameter speech-to-video model. Turn audio into film-grade clips with lifelike motion and environment control. And it’s fully open-source. Examples below: (sound on)

Angry Tom

66,072 views • 9 months ago

NVIDIA DROPPED A MOTION DIFFUSION MODEL FOR HUMANOID ROBOTS trained on 700 hours of mocap data kimodo generates high-quality 3D human and robot motions from text prompts you control it with: → full-body pose keyframes → end-effector positions/rotations → 2D paths and waypoints works on human skeletons and unitree G1 robot plug the outputs directly into mujoco or retarget to other robots using GMR has a web-based interactive demo with a timeline editor. runs locally needs ~17GB VRAM to run inference open source under apache 2.0
0:11

NVIDIA DROPPED A MOTION DIFFUSION MODEL FOR HUMANOID ROBOTS trained on 700 hours of mocap data kimodo generates high-quality 3D human and robot motions from text prompts you control it with: → full-body pose keyframes → end-effector positions/rotations → 2D paths and waypoints works on human skeletons and unitree G1 robot plug the outputs directly into mujoco or retarget to other robots using GMR has a web-based interactive demo with a timeline editor. runs locally needs ~17GB VRAM to run inference open source under apache 2.0

Vaishnavi

17,520 views • 2 months ago

Trained a simple world model for my robot arm. It predicts the future over 20000 times faster than real time on a single NVIDIA RTX 3090 GPU (128 batch -> 160x faster each).
0:11

Trained a simple world model for my robot arm. It predicts the future over 20000 times faster than real time on a single NVIDIA RTX 3090 GPU (128 batch -> 160x faster each).

Alexander Koch

39,700 views • 2 years ago

I trained this LoRA exclusively on real images extracted from video footage of "Joe," without any specific style. Then, using WAN 2.1 in ComfyUI, I can apply and modify the style as needed. This demonstrates that even a LoRA trained on real images can be dynamically stylized, providing great flexibility in animation.
0:14

I trained this LoRA exclusively on real images extracted from video footage of "Joe," without any specific style. Then, using WAN 2.1 in ComfyUI, I can apply and modify the style as needed. This demonstrates that even a LoRA trained on real images can be dynamically stylized, providing great flexibility in animation.

Lovis Odin

12,160 views • 1 year ago

CVPR Highlight #1 VGGT: Visual Geometry Grounded Transformer (best paper award) 🚀 Super-fast 3D scene reconstruction 🤗 Model and demo on Hugging Face The result is a GLB point cloud 👇
0:15

CVPR Highlight #1 VGGT: Visual Geometry Grounded Transformer (best paper award) 🚀 Super-fast 3D scene reconstruction 🤗 Model and demo on Hugging Face The result is a GLB point cloud 👇

dylan

19,325 views • 1 year ago

.Starcloud is bringing AI compute to orbit—cutting energy costs and enabling real-time insights from space.
0:16

.Starcloud is bringing AI compute to orbit—cutting energy costs and enabling real-time insights from space.

NVIDIA

136,777 views • 1 month ago

OPENAI 🔥: Codex now has a new Record & Replay plugin that captures your actions and converts your workflow into an executable skill. My workflow 👀 * Not available in EEA, UK, and Switzerland yet
0:18

OPENAI 🔥: Codex now has a new Record & Replay plugin that captures your actions and converts your workflow into an executable skill. My workflow 👀 * Not available in EEA, UK, and Switzerland yet

🚨 AI News | TestingCatalog

163,468 views • 4 days ago

1 billion voxels in real-time : testing the upcoming EmberGen sparse solver with the #Nvidia RTX Pro 6000 and #DellProMax
0:16

1 billion voxels in real-time : testing the upcoming EmberGen sparse solver with the #Nvidia RTX Pro 6000 and #DellProMax

Jason Key

65,101 views • 8 months ago

Eco Wave Power uses AI to model wave motion, optimizing floaters that convert wave movement into clean electricity at scale.
0:10

Eco Wave Power uses AI to model wave motion, optimizing floaters that convert wave movement into clean electricity at scale.

NVIDIA

78,029 views • 1 month ago

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI
0:15

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI

Muhammad Rizwan Munawar

30,677 views • 3 months ago

Amazing time-lapse footage of a day in the life of a pair of pot plants. Plants are so much more active than we usually imagine! We don't notice, though, because they move in slow motion (or, from the plant's point of view, we move in crazy-fast motion).
0:15

Amazing time-lapse footage of a day in the life of a pair of pot plants. Plants are so much more active than we usually imagine! We don't notice, though, because they move in slow motion (or, from the plant's point of view, we move in crazy-fast motion).

Steve Stewart-Williams

142,661 views • 3 years ago

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗
0:15

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗

NVIDIA AI

40,312 views • 8 months ago

this is the future of CGI this new OpenMagic AI can add image, video or 3D product into real life video seamlessly with one click and.. it can even turn product image into 3D model automatically 10 wild examples:
0:10

this is the future of CGI this new OpenMagic AI can add image, video or 3D product into real life video seamlessly with one click and.. it can even turn product image into 3D model automatically 10 wild examples:

el.cine

120,917 views • 1 year ago