设计资源DESIGN· MOTION
img2threejs/img2threejs
把参考图变成可直接运行的3D模型,供AI编程助手使用。Recreate an object from a reference image as a code-only, animation-ready Three.js model, aimed at developers who build inside AI coding tools.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
拿一张参考图生成可旋转查看的3D模型
用同一张图反复生成保持比例和配色的模型
按角色插件要求做出带骨架和动作的模型
先用测试图跑通流程再处理正式图片
检查生成结果是否达到设定的质量标准
Generate a Three.js model directly from a reference image.
Keep the original proportions, silhouette, and colors.
Run quality checks before accepting a generated model.
Rebuild game-ready characters with rig and animation checks.
Confirm an install with a one-line status check.
上手GET STARTED
npx --yes img2threejs@latest install # links the skill into every agent it finds选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserreadme
- **Zero dependencies, zero install churn.** Every script is pure Python 3.10+ standard library. No pip, no PIL, no numpy, no Playwright. PN
02控制浏览器Controls a browserSKILL.md
whatever the host provides — native image reading, a browser MCP (playwright/chrome-devtools), the
静态扫描提示存在控制浏览器的代码路径(文档中提到通过浏览器 MCP 读取图片等),属中风险,安装或交给 agent 前建议审阅相关逻辑。仅核验官方页面,未审计服务端代码;数据处理和费用以官网为准。The static scan flagged a medium-risk note about controlling a browser. The README says the core scripts are pure Python with no Playwright, but the tool can use a browser MCP when the host provides one, so treat it as "review" and check what you run.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
27 OCT 202627 OCT 2026
增长GROWTH
+2.6%+2.6%
20k → 20k stars · 7 个快照20k → 20k stars · 7 snapshots
状态STATUS
持续活跃Active
质量 AQuality A
仓库近 7 天有 5 次提交,维护活跃。An active open-source repository with 19,608 stars and commits in the past week.
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …lump. It runs under Hermes, Claude Code, Codex, or OpenCode. It is ag…"
},
{
"agent": "opencode",
"evidence": "readme: …ermes, Claude Code, Codex, or OpenCode. It is agent-agnostic: wherev…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 6,
"ai-tools": 0,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 6,
"productivity": 0
},
"primary": "design",
"secondary": "motion"
},
"localRuntime": null,
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 3,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 1 markdown files",
"weight": 0.75
}
],
"scannedSources": [
"readme",
"SKILL.md"
],
"skillMdFetched": 1
}