ProtoMotions
ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.
- 2.5k
- Python
- Apache-2.0
- 12 d ago
ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.
[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)
Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"
SkinTokens: A Learned Compact Representation for Unified Autoregressive Rigging
[SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation
Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data", CVPR 2024; 3D Avatar Generation and Animation
ZeroEGGS: Zero-Shot Example-Based Gesture Generation from Speech
Official implementation for SIGGRAPH 2023 paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"
Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered with Three.js.
Batched NVIDIA MotionBricks: generate the motion of hundreds of characters in one model call.
[NeurIPS 2020] Official PyTorch Implementation of "Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis". NeurIPS 2020.
[ACM MM 2026] AniCrafter: Customizing Realistic Human-Centric Animation via Avatar-Background Conditioning in Video Diffusion Models
Official Code for ECCV 2024 paper "EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere"
Local-first desktop studio for ComfyUI, built for AI short-drama production - zero-dependency 10MB exe: creation, gallery, 600+ templates, model hub, character assets (LoRA binding), episodic pipeline, MCP server
Maya is Autodesk's professional 3D animation, modeling, simulation, and rendering software. This repository provides an AWS Deadline Cloud submitter and OpenJD adaptor for Maya, making it easier to submit and render Maya workloads at scale in the cloud.
Validated WanVideoWrapper workflows for SCAIL/SCAIL-2 RGB-driven animation, identity-aware masking, multi-person tracking, replacement conditioning and optional NLF pose processing.
Animated Characters: create video from plain text or audio file in minutes, support up to 100+ languages and 350+ voice models.
Community driven mascots that show up in the OpenHuman app (Rive Files)
OpenUSD avatar runtime for motion, evaluation, state orchestration, and real-time character workflows.
OpenUSD plugins for MikuMikuDance models, motion, and interoperability