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.show more

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.show more

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.show more

Cartwheel Character Rigging is here! It converts a character... image or an existing 3D mesh into a fully rigged 3D model. Clean skeleton, bones placed precisely, ready to receive motion data immediately. No manual rigging required.show more

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)show more

A new stable motion transfer workflow for Seedance 2.0!... We built a video-to-depth-video + skeleton-binding Skill based on "Depth-Anything-V2" for motion transfer. Tell your agent to help me create a Skill that converts a normal video into a depth video with skeleton binding. Motion transfer can be achieved with only the following prompt + content description:show more

From flat image to animated 3D models in Spaces... → Generate 3D models from an image or a prompt → Retexture, remesh, convert and UV unwrap on the canvas → Auto-rig your characters and apply animations → Snapshot any model into your image or video workflow Now on Magnificshow more

China just dropped an open source model that turns... any phone into a 3D scanner you point it at a room and walk through it the whole space builds itself into a 3D point cloud in real time as the camera moves, no LiDAR and no depth sensor anywhere it held a full 13 minute walkthrough at 25,000 frames without the map drifting or collapsing > ~20 fps on a single GPU > works indoors and outdoors from plain footage > the scan normally needs a $50,000 rig and a technician > Apache 2.0 and runs fully offline on your machine repo in the replyshow more

Using Blender camera animation with Seedance 2.0 gives you... a lot more control over your shots. By keyframing the camera in Blender, you can precisely define movement, rotation, and framing, then bring that motion into Seedance. It's a great workflow for previs-style blockouts or any shot where intentional camera movement matters. To try this workflow, link below 👇show more

SAM 3D Body turns video into motion capture, full-body... 3D mesh from footage. Runs in ComfyUI, locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, link below 👇show more

ViewCrafter can generate high-quality 3D views from single or... few images using a video diffusion model! It allows for precise camera control and is useful for real-time rendering and turning text into 3D scenes. Links ⬇️show more

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 3060show more

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)show more

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 2.0show more

New fal workflow: video restyling with Video Depth Anything... and Seedance 2.0 - Restyle the first frame into your target look - Extract consistent depth across the source video - Use that depth to guide Seedance 2.0 through the full sequence - Preserve the original motion and composition while transforming the visual style A simple workflow for turning existing footage into stylized video.show more

Google has open-sourced GNM Head, its parametric model for... generating 3D human heads The model, based on real-world scan data, provides 250 controls for head shape, and 380+ for facial expressions A free add-on integrates it into Blender #B3Dshow more

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 #AIshow more

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. 🔗show more