[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-83799":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":15,"stars7d":13,"stars30d":13,"stars90d":16,"forks30d":16,"starsTrendScore":17,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":10,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},83799,"Local-AI-Image-Generator","techjarves\u002FLocal-AI-Image-Generator","techjarves","A fully self-contained, offline AI image generation studio for Windows. Runs Stable Diffusion (Safetensors\u002FGGUF) locally with zero manual setup. Auto-configures CUDA for Nvidia GPUs and Vulkan for AMD\u002FIntel Arc cards. Zero system-wide dependencies required.","",null,"JavaScript",181,63,11,8,0,46,87.72,"MIT License",false,"main",true,[24,25,26],"image-generation","local-ai","stable-diffusion","2026-06-12 04:01:42","# 🖼️ Local AI Image Generator\n\n### An easy, zero-setup Stable Diffusion GUI for Windows. Run GGUF & Safetensors models offline without Python configuration.\n\n\n\n| **Generation Workspace** | **Model Library** | **Image Constraints** |\n| :---: | :---: | :---: |\n| \u003Cimg src=\"assets\u002Fdashboard.png\" width=\"100%\" style=\"border-radius: 6px;\"> | \u003Cimg src=\"assets\u002Fmodels.png\" width=\"100%\" style=\"border-radius: 6px;\"> | \u003Cimg src=\"assets\u002Fsettings.png\" width=\"100%\" style=\"border-radius: 6px;\"> |\n\n---\n\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Cp>🎥 \u003Cb>Watch the Setup & Demo Video:\u003C\u002Fb> \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FESELhY-G_9w\">https:\u002F\u002Fyoutu.be\u002FESELhY-G_9w\u003C\u002Fa>\u003C\u002Fp>\n  \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FESELhY-G_9w\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FESELhY-G_9w\u002Fmaxresdefault.jpg\" alt=\"Local AI Image Generator Video Tutorial\" style=\"width:100%; max-width:800px; border-radius: 8px; margin-top: 10px;\">\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n---\n\n## 📖 Overview\n**Local AI Image Generator** is a zero-configuration, portable desktop environment for running Stable Diffusion (Safetensors\u002FGGUF\u002FCKPT) offline on Windows. Double-clicking `start.bat` automatically handles dependency setup, GPU backend matching (CUDA\u002FVulkan), and launches a high-performance local web workspace.\n\n---\n\n## ⚡ Quick Start\n1. **Launch:** Double-click **`start.bat`** (downloads portable Node.js and pre-compiled GPU backend binaries on first run).\n2. **Add Models:** Drop `.safetensors`, `.gguf`, or `.ckpt` weights into `app\u002Fmodels\u002F` (or download them via the **Model Manager** tab in the UI).\n3. **Generate:** Open `http:\u002F\u002Flocalhost:1420` in your browser, select your model, and write a prompt.\n\n---\n\n## ✨ Features\n*   **100% Offline & Private:** Inference runs completely locally on your hardware.\n*   **Auto-Detected GPU Acceleration:** Configures **CUDA** for Nvidia cards, and **Vulkan** for AMD or Intel Arc GPUs.\n*   **Zero System Footprint:** Node.js is sandboxed inside the folder. No global environment paths are altered.\n*   **Integrated Model Manager:** Paste a Hugging Face URL to download weights directly, or drag-and-drop local weight files to import them.\n*   **Real-time Telemetry:** Monitor RAM, VRAM, CPU, and GPU load directly in the UI.\n*   **Local Gallery:** Saves generated PNGs alongside prompt metadata JSONs to `app\u002Foutputs\u002F`.\n\n---\n\n## 📁 Repository Structure\n```\nlocal-ai-image-generator\u002F\n├── start.bat                  # Main double-click entrypoint\n├── LICENSE                    # MIT Open Source license\n├── .gitignore\n├── README.md                  \n├── scripts\u002F\n│   ├── setup.ps1              # Automated GPU-detect and environment installer\n│   ├── reset.ps1              # Cleans runtime environments (keeps models & outputs)\n│   └── serve.cjs              # UI web server and backend lifecycle manager\n└── app\u002F\n    ├── frontend\u002F              # UI source code (Vite + React)\n    ├── models\u002F                # Place weights here (.safetensors, .gguf, .ckpt)\n    └── outputs\u002F               # Saved images and parameters metadata\n```\n\n---\n\n## 🖥️ GPU Compatibility Matrix\n\n| GPU Vendor | Tech | Status | Notes |\n| :--- | :--- | :--- | :--- |\n| **Nvidia** | CUDA | ✅ Native | Maps `sd-cuda.exe` with Nvidia SDK 12 optimizations. |\n| **AMD Radeon** | Vulkan | ✅ Native | Maps `sd-vulkan.exe` with Vulkan API acceleration. |\n| **Intel Arc** | Vulkan | ✅ Native | Maps `sd-vulkan.exe` for Intel hardware. |\n| **Integrated \u002F None** | CPU | ⚠️ Fallback | Runs on logical CPU threads (slow). |\n\n---\n\n## ⏱️ Performance Benchmarks\n\nTypical generation times for an image with **20 steps** (e.g. 512x512 resolution; actual times can vary depending on specific hardware specifications, clock speeds, and system load):\n\n*   **CUDA GPU (Nvidia RTX):** ~10 seconds.\n*   **Vulkan GPU (AMD \u002F Intel Arc):** ~89 seconds.\n*   **GTX Vulkan Fallback (Nvidia GTX):** ~30 seconds (Vulkan runs significantly faster on legacy GTX series cards since they lack Tensor Cores).\n*   **CPU (Fallback):** ~150 - 300+ seconds (highly dependent on processor core count, speed, and AVX instruction sets).\n\n---\n\n## 🛠️ Troubleshooting\n*   **Reset Environment:** If a build fails or you want to clear dependencies, run `scripts\u002Freset.ps1`. (This preserves your models and generated images).\n*   **Port Conflicts:** The frontend uses `1420` by default. The backend tries `8080` first, then automatically falls back to a free port if `8080` is already busy.\n\n---\n\n## 📝 License\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file. Bundles [stable-diffusion.cpp](https:\u002F\u002Fgithub.com\u002Fleejet\u002Fstable-diffusion.cpp) (MIT License). Model weights are subject to their respective creators' licenses.\n",2,"2026-06-11 04:11:29","CREATED_QUERY"]