Community程式設計與開發github.com

aradotso/kimodo-motion-diffusion

使用 Kimodo 生成高品質的 3D 人類與人形機器人動作,透過文字提示與運動學約束進行控制。

kimodo-motion-diffusion 是什麼?

這個技能讓 AI 代理(如 Claude Code)能夠利用 Kimodo 模型,從文字描述生成逼真的 3D 人類與人形機器人動作。Kimodo 是一種運動學運動擴散模型,能夠接受自然語言提示與可選的運動學約束(例如關節角度、接觸點),來產生流暢且物理合理的動畫。它支援多種平台,包括 Linux、macOS 與 Windows,並可整合至 Python 腳本或命令列工具中。透過將複雜的動作生成任務抽象化,此技能可大幅加速機器人模擬、遊戲開發、虛擬人製作等領域的創意與工程流程。用戶無需深入了解擴散模型的底層機制,即可輕鬆創造出高品質的動畫動作。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/aradotso/trending-skills/tree/main/skills/kimodo-motion-diffusion

Installed? Explore more 程式設計與開發 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

kimodo-motion-diffusion 是做什麼的?

使用 Kimodo 生成高品質的 3D 人類與人形機器人動作,透過文字提示與運動學約束進行控制。

概述

Kimodo 是一種創新的運動學運動擴散模型,專為生成細緻且物理合理的 3D 動作而設計。它接受文字提示作為輸入,並可結合額外的運動學約束(例如關鍵幀位置、關節限制或接觸點),以產生符合指定需求的動作序列。

支援平台

  • Linux
  • macOS
  • Windows

快速開始

安裝

pip install kimodo-motion-diffusion

基本使用

from kimodo import Kimodo

# 初始化模型
model = Kimodo()

# 使用文字提示生成動作
motion = model.generate("一個角色正在步行,然後跳躍")

# 儲存動作序列
motion.save("output.bvh")

進階功能

運動學約束

您可以指定額外的約束條件來引導動作生成:

constraints = {
    "foot_contacts": [1, 1, 0, 0],  # 左腳、右腳接觸地面
    "joint_positions": {
        "head": [0.0, 1.7, 0.0],
        "right_hand": [0.3, 1.2, 0.1]
    }
}

motion = model.generate("揮手姿勢", constraints=constraints)

模型架構

Kimodo 採用擴散模型架構,從雜訊逐步還原出清晰的動作序列。其核心創新在於將運動學約束直接整合至擴散過程中,確保生成的動作不僅符合文字描述,還能滿足特定物理或機械限制。

輸出格式

支援的輸出格式包括:

  • BVH (Biovision Hierarchy)
  • FBX
  • 自訂的關鍵幀 JSON 格式

常見問題

我需要 GPU 嗎?

雖然 Kimodo 可以在 CPU 上運行,但建議使用支援 CUDA 的 GPU 以獲得最佳效能。

如何調整動作長度?

可以透過設定 duration 參數來控制動作長度(以秒為單位):

motion = model.generate("奔跑動作", duration=3.0)

貢獻指南

歡迎提交問題報告與功能請求。若想貢獻程式碼,請先參閱我們的貢獻指南。

授權條款

本專案採用 MIT 授權條款。詳情請見 LICENSE 檔案。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

aradotso/724-office-ai-agent

Self-evolving AI agent system with 26 tools, three-layer memory, MCP plugins, and 24/7 self-repair in pure Python.

aradotso/agency-agents-ai-specialists

A collection of specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, and other AI coding tools — covering engineering, design, marketing, sales, and more.

aradotso/agent-browser-automation

Headless browser automation CLI for AI agents using native Rust binary with Chrome DevTools Protocol

aradotso/antigravity-manager

AI coding agent skill for Antigravity Manager — a Tauri v2 + Rust desktop app and Docker service that manages multiple Google/Anthropic accounts and proxies them as standard OpenAI/Anthropic/Gemini API endpoints with intelligent account rotation.

aradotso/aracli-deploy-management

Guide to deploying and managing OpenClaw-compatible AI agent systems across cloud, bare metal, and hybrid infrastructure.

aradotso/autoresearchclaw-autonomous-research

Fully autonomous research pipeline that turns a topic idea into a complete academic paper with real citations, experiments, and conference-ready LaTeX.

aradotso/autoresearch-genealogy

Structured prompts, vault templates, and autonomous research workflows for AI-assisted genealogy using Claude Code.

aradotso/brreg

Search and retrieve Norwegian company data from Brønnøysundregistrene (the Norwegian Business Registry). Access all ~1.2 million registered companies in Norway.

aradotso/chrome-cdp-live-browser

Give AI agents access to your live Chrome session via CDP — interact with open tabs, logged-in accounts, and current page state

aradotso/claude-hud-statusline

A Claude Code plugin that displays a real-time HUD showing context usage, active tools, running agents, and todo progress in your terminal statusline.

aradotso/claude-peers-mcp

Enable multiple Claude Code instances to discover each other and exchange messages in real-time via a local broker daemon and MCP server.

aradotso/clui-cc-claude-overlay

Command Line User Interface for Claude Code — a floating macOS desktop overlay with multi-tab sessions, permission approval UI, voice input, and skills marketplace.

aradotso/cmux-terminal-multiplexer

AI-native terminal multiplexer with programmable socket API, full Playwright-equivalent browser automation, and agent team coordination — built for Claude Code and autonomous agent workflows

aradotso/code-review-graph

Build a persistent knowledge graph of your codebase so Claude reads only what matters — up to 49x fewer tokens on coding tasks.

aradotso/codex-autoresearch-loop

Self-directed iterative research skill for Codex that continuously cycles through modify, verify, retain or discard, and repeat until a measurable goal is reached.

aradotso/copaw-ai-assistant

Personal AI assistant framework supporting multiple chat channels (DingTalk, Feishu, QQ, Discord, etc.) with extensible skills, local/cloud deployment, and cron scheduling.

aradotso/corridorkey-green-screen

AI-powered green screen keyer that unmixes foreground colors and generates clean linear alpha channels using neural networks

aradotso/crucix-intelligence-dashboard

Personal intelligence agent that aggregates 27 OSINT data sources into a self-hosted Jarvis-style dashboard with Telegram/Discord bots, LLM analysis, and real-time alerts.

aradotso/daily-stock-analysis

LLM-powered A/H/US stock intelligent analysis system with multi-source data, real-time news, AI decision dashboards, and multi-channel push notifications via GitHub Actions.

aradotso/deepseek-ocr

Expert skill for using DeepSeek-OCR, a vision-language model for optical character recognition with context optical compression supporting documents, PDFs, and images.

相關技能