lightningpixel / modly

查看原文 / View Original 编辑 / Edit

lightningpixel / modly

Modly is a local, open-source, AI-powered image-to-3D mesh generation tool. Turn any photo into a 3D model using open-source AI models running entirely on your GPU. Modly is a desktop application for Windows, Linux, and Apple Silicon macOS. Created by Lightning Pixel. Modly 是一款本地、开源、由 AI 驱动的图像转 3D 网格生成工具。它利用完全在 GPU 上运行的开源 AI 模型，将任何照片转换为 3D 模型。Modly 是适用于 Windows、Linux 和 Apple Silicon macOS 的桌面应用程序，由 Lightning Pixel 开发。

Download

下载

Head to the Releases page to download the latest installer for Windows, Linux, or Apple Silicon macOS. Alternatively, you can clone the repository and run the app directly without installing: 前往 Releases 页面下载适用于 Windows、Linux 或 Apple Silicon macOS 的最新安装程序。或者，你也可以克隆代码仓库并直接运行应用程序，无需安装：

# Windows
launch.bat

# Linux / macOS
./launch.sh

Getting started

入门指南

  1. Install JS dependencies: npm install

  2. Set up Python backend: cd api python -m venv .venv .venv\Scripts\activate # Windows source .venv/bin/activate # Linux / macOS pip install -r requirements.txt

  3. Run in development: npm run dev

  4. Test: npm test / ./node_modules/.bin/tsc --noEmit -p tsconfig.node.json / npm run build

  5. 安装 JS 依赖：npm install

  6. 设置 Python 后端： cd api python -m venv .venv .venv\Scripts\activate # Windows source .venv/bin/activate # Linux / macOS pip install -r requirements.txt

  7. 开发模式运行：npm run dev

  8. 测试：npm test / ./node_modules/.bin/tsc --noEmit -p tsconfig.node.json / npm run build

Platform notes

平台说明

macOS support targets Apple Silicon only. macOS uses native window controls. Windows and Linux keep the existing custom controls. The top bar includes a live RAM indicator sourced from the main process. Workflow wiring is validated before run; invalid graphs stay in place and surface inline/toast warnings instead of dropping the current mesh view. Package Apple Silicon macOS with npm run package:mac. Imported meshes can be smoothed and decimated in-app; optimized results are written back into the workspace. macOS 支持仅针对 Apple Silicon。macOS 使用原生窗口控件，而 Windows 和 Linux 保留现有的自定义控件。顶部栏包含一个来自主进程的实时内存（RAM）指示器。工作流连线在运行前会进行验证；无效的图表会保持原位并显示内联/提示警告，而不是丢弃当前的网格视图。使用 npm run package:mac 打包 Apple Silicon macOS 版本。导入的网格可以在应用内进行平滑和精简处理；优化后的结果会写回工作区。

Extension system

扩展系统

Modly supports external model and process extensions. Each extension is a GitHub repository containing a manifest.json plus the runtime entry files required by its type. Modly 支持外部模型和流程扩展。每个扩展都是一个 GitHub 仓库，包含一个 manifest.json 文件以及其类型所需的运行时入口文件。

Official extensions 官方扩展

ExtensionModelURL
modly-hunyuan3d-mini-extensionHunyuan3D 2 MiniLink
modly-hunyuan3d-mini-turbo-extensionHunyuan3D 2 Mini TurboLink
modly-hunyuan3d-mini-fast-extensionHunyuan3D 2 Mini FastLink
modly-triposg-extensionTripoSGLink
modly-trellis2-gguf-extensionTrellis2 GGUFLink

How to install an extension 如何安装扩展

  1. Go to the Models page and click “Install from GitHub”.
  2. Enter the HTTPS URL of the extension repository and confirm.
  3. If the extension exposes model nodes, download the model or one of its variants. Process extensions are ready once installation and setup complete.
  4. 前往 Models 页面并点击 “Install from GitHub”。
  5. 输入扩展仓库的 HTTPS URL 并确认。
  6. 如果扩展暴露了模型节点，请下载模型或其变体之一。流程扩展在安装和设置完成后即可使用。

Workflows

工作流

Start with a basic workflow first. For example, on the “Workflows” tab, try: Image -> Generate Mesh -> Add to Scene. Make sure there is a connection between each of the steps. Go to the “Generate” tab, make sure the workflow is selected, then click on “Generate 3D Model”. Click on “Settings/Logs/Errors” to see any issues. 先从基础工作流开始。例如，在 “Workflows” 选项卡上，尝试：Image -> Generate Mesh -> Add to Scene。确保每个步骤之间都有连接。前往 “Generate” 选项卡，确保选中了工作流，然后点击 “Generate 3D Model”。点击 “Settings/Logs/Errors” 查看是否有任何问题。

Modly CLI

Modly 命令行工具 (CLI)

Agents and scripts can call a running Modly desktop app without using the UI via the stdlib-only CLI. The CLI is a thin helper over Modly’s canonical automation concepts and keeps final machine-readable JSON on stdout. 代理和脚本可以通过仅使用标准库的 CLI 调用正在运行的 Modly 桌面应用，而无需使用 UI。该 CLI 是 Modly 规范化自动化概念的轻量级辅助工具，并将最终的机器可读 JSON 输出到标准输出（stdout）。

  • python tools/modly-cli/agent.py health
  • python tools/modly-cli/agent.py model list
  • python tools/modly-cli/agent.py workflow-run status <run_id>
  • python tools/modly-cli/agent.py generate --image ./input.png --output ./export.glb

Canonical commands are health, model, workflow-run, capability, and process-run. 规范命令包括 health、model、workflow-run、capability 和 process-run。

Community

社区

Join the Discord server to stay up to date with the latest news, report bugs, and share feedback. 加入 Discord 服务器以获取最新消息、报告错误并分享反馈。

Sponsors

赞助商

Thanks to our early sponsors for believing in Modly and helping make local AI 3D generation more accessible: DrHepa, benjapenjamin, iammojogo-sudo. 感谢我们的早期赞助商，感谢你们对 Modly 的信任，并帮助让本地 AI 3D 生成变得更加普及：DrHepa, benjapenjamin, iammojogo-sudo。

License

许可证

MIT License — see LICENSE for details. If you fork this project and build your own app from it, you must credit the original project and its creator: “Based on Modly by Lightning Pixel”. This is a requirement of the MIT license attribution clause. Please keep this credit visible in your app’s UI or documentation. MIT 许可证 — 详情请参阅 LICENSE。如果你分叉（fork）此项目并基于它构建自己的应用程序，你必须注明原项目及其创作者：“Based on Modly by Lightning Pixel”。这是 MIT 许可证署名条款的要求。请确保此署名在你的应用程序 UI 或文档中可见。

← 返回新闻列表 / Back to news list