zju3dv/text_scene_motion

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

HY-Motion model for 3D human motion or 3D character animation generation.

A ComfyUI plugin based on HY-Motion 1.0 for text-to-3D human motion generation.

SnapMoGen: Human Motion Generation from Expressive Texts [NeurIPS 2025]

[CVPR 2025] Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression

A ComfyUI plugin that wraps [Kimodo](https://github.com/nv-tlabs/kimodo) — NVIDIA's kinematic motion diffusion model for generating high-quality 3D human and humanoid robot motions from text prompts with optional kinematic constraints.

[ICCV 2025] MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

[ECCV 2026] ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning

An open-source text language, parser, validator and Three.js renderer for inspectable 3D human movement.