经 AI Skill Hub 精选评估，本地AI工作室 获评「强烈推荐」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.0 分，适合有一定技术背景的用户使用。
本地AI工作室 是一款基于 JavaScript 开发的开源工具，专注于 image-generation、local-ai、stable-diffusion 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
本地AI工作室 是一款基于 JavaScript 开发的开源工具，专注于 image-generation、local-ai、stable-diffusion 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
# 方式一：npm 全局安装 npm install -g uncensored-local-studio # 方式二：npx 直接运行（无需安装） npx uncensored-local-studio --help # 方式三：项目依赖安装 npm install uncensored-local-studio # 方式四：从源码运行 git clone https://github.com/techjarves/Uncensored-Local-Studio cd Uncensored-Local-Studio npm install npm start
# 命令行使用
uncensored-local-studio --help
# 基本用法
uncensored-local-studio [options] <input>
# Node.js 代码中使用
const uncensored_local_studio = require('uncensored-local-studio');
const result = await uncensored_local_studio.run(options);
console.log(result);
# uncensored-local-studio 配置说明 # 查看配置选项 uncensored-local-studio --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export UNCENSORED_LOCAL_STUDIO_CONFIG="/path/to/config.yml"
<p align="center"> <strong>A premium, zero-configuration local AI studio and offline GUI for Stable Diffusion (Image Generation), LLMs (Chat), Whisper (Speech-to-Text), and Kokoro (Text-to-Speech). Powered by hardware-accelerated GPU and NPU execution on Windows, Linux, and macOS.</strong> </p>
<p align="center"> <img src="https://img.shields.io/badge/Offline-100%25-green?style=for-the-badge&logo=offline" alt="100% Offline" /> <img src="https://img.shields.io/badge/Platform-Windows%20%7C%20Linux%20%7C%20macOS-blue?style=for-the-badge" alt="Platforms" /> <img src="https://img.shields.io/badge/License-MIT-orange?style=for-the-badge" alt="License" /> </p>
<p align="center"> 🎥 <strong>Watch the Setup & Demo Video:</strong> <a href="https://youtu.be/qvamkqmLPn8">https://youtu.be/qvamkqmLPn8</a> </p>
<p align="center"> <a href="https://youtu.be/qvamkqmLPn8"> <img src="https://img.youtube.com/vi/qvamkqmLPn8/maxresdefault.jpg" alt="Uncensored AI Studio Video Tutorial" width="800" style="border-radius: 8px;" /> </a> </p>
---
---
git, cmake, make (or ninja), and a C++17 compiler (g++ / clang++).nvcc) must be on your PATH.Ensure you have a modern web browser installed. Follow the quick guide below for your platform:
1. Launch: Double-click windows.bat. > [!NOTE] > On the first run, the script will automatically download a portable Node.js runtime and configure pre-compiled GPU/CPU backend binaries. 2. Add Models: Drop .safetensors, .gguf, or .ckpt weights into app/models/ (or download them via the Model Manager tab in the UI). 3. Generate: Open http://localhost:1420 in your browser, select your model, and write a prompt.
1. Make executable: Open a terminal in the project folder and make the script executable:
chmod +x linux.sh
./linux.sh. - NVIDIA GPU Users: You will be prompted to set up the high-performance CUDA backend (downloads prebuilt or automatically compiles from source as a fallback). - AMD Radeon Performance: Run with ./linux.sh --max-perf to add the ROCm backend (~1.3 GB download). - Intel Core Ultra NPU: Run with ./linux.sh --setup-openvino to configure Intel NPU support (requires Intel Linux NPU driver). 3. Add Models: Drop your weights into app/models/ or download them via the Model Manager tab. 4. Generate: Open http://localhost:1420 in your browser.
1. Make executable: Open a terminal in the project folder and make the script executable:
chmod +x mac.sh
./mac.sh. > [!IMPORTANT] > The prebuilt macOS backend is optimized for Apple Silicon (M1 or newer) and uses Metal GPU acceleration. (macOS Intel hardware is completely unsupported). 3. Add Models: Drop your weights into app/models/ or download them via the Model Manager tab. 4. Generate: Open http://localhost:1420 in your browser.
---
The setup script (scripts/setup/setup.sh) now automates building and setting up the CUDA backend from source when selected. If you want to manually build all backends (CPU, Vulkan, and CUDA) at once, you can run the included scripts/build/build_from_source.sh script.
For macOS, the included scripts/build/build_from_source.sh builds the Metal backend and copies it to app/backend/mac/sd.
```bash
cmake --build . --config Release -j$(getconf _NPROCESSORS_ONLN 2>/dev/null || sysctl -n hw.ncpu)
The app is designed around single-file local models that can be loaded directly by the bundled backend engines.
<details> <summary><strong> Reset Environment: If a build fails or you want to clear dependencies</strong></summary> <p>Run <code>scripts/reset/reset.ps1</code> (Windows) or <code>scripts/reset/reset.sh</code> (Linux/macOS). This will clear temporary compilation and package caches to repair your environment. <em>(Note: This preserves your model weights and generated output images).</em></p> </details>
<details> <summary><strong> Linux backends fail to start with <code>GLIBC_2.38 not found</code></strong></summary> <p>The prebuilt binaries require glibc 2.38+ (e.g. Ubuntu 24.04). If your distribution uses an older glibc version, you can upgrade your operating system or compile the backend from source (see the <a href="#building-from-source">Building From Source</a> guide below).</p> </details>
<details> <summary><strong> Port Conflicts: Default port address already busy</strong></summary> <p>The web user interface runs on port <code>1420</code> by default. The GPU backend manager attempts to bind to port <code>8080</code> first, then automatically detects and falls back to a free system port if <code>8080</code> is already occupied.</p> </details>
<details> <summary><strong> Linux ROCm not loading for AMD Radeon GPUs</strong></summary> <p>Ensure your AMD GPU hardware and host kernel are fully compatible with ROCm 7.13. If ROCm fails to initialize correctly, the application will automatically fall back to Vulkan acceleration.</p> </details>
<details> <summary><strong> Linux uses the integrated GPU instead of the discrete GPU</strong></summary> <p>On dual-GPU Linux systems, Vulkan device order can put the integrated Intel GPU at <code>vulkan0</code> and the discrete AMD/NVIDIA GPU at <code>vulkan1</code>. The launcher now tries to prefer a discrete Vulkan device when <code>vulkaninfo --summary</code> is available. To force a device manually, start the app with <code>SD_VULKAN_DEVICE=vulkan1 ./linux.sh</code> or use another index such as <code>vulkan0</code>/<code>vulkan2</code>.</p> </details>
<details> <summary><strong> Windows exits with code <code>3221225781</code> (0xC0000135)</strong></summary> <p>This code means Windows could not locate a required backend DLL:</p> <ul> <li><strong>For AMD/Intel Vulkan:</strong> Update your GPU driver to one with full Vulkan runtime support, then rerun the setup script to restore <code>app/backend/win/vulkan/</code>.</li> <li><strong>For NVIDIA CUDA:</strong> Install or update your NVIDIA graphics driver, then rerun the setup script to restore the CUDA runtime DLLs.</li> </ul> </details>
<details> <summary><strong> Generation shows "server is not responding or crashed"</strong></summary> <p>This indicates that the local backend engine process terminated. Check your launch terminal (where you executed <code>windows.bat</code>, <code>./linux.sh</code>, or <code>./mac.sh</code>) for the exact console error. Common causes include glibc version mismatches, missing Vulkan drivers, or system out-of-memory (OOM) issues.</p> </details>
---
功能强大，易于使用的本地AI图像生成工具
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
AI Skill Hub 点评：本地AI工作室 的核心功能完整，质量优秀。对于AI 技术爱好者来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | Uncensored-Local-Studio |
| Topics | image-generationlocal-aistable-diffusion |
| GitHub | https://github.com/techjarves/Uncensored-Local-Studio |
| License | MIT |
| 语言 | JavaScript |
收录时间：2026-06-27 · 更新时间：2026-06-27 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。