Original Summary

VRM-native motion model project for interactive embodied avatars, aiming to generate continuous skeletal motion from text and dialogue context. Includes motion data preparation, VRM-centered representation, training pipelines, preview/evaluation tools, and runtime playback.

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：GitHub · AI 新项目
  • 发布时间：2026/9/26 12:57:57