The ultimate command center for AI prompting and tagging. Leverage modern LLMs to craft the perfect Stable Diffusion prompts in a sleek, high-performance desktop environment.
TagForge.mp4
📸 View Screenshots Gallery
Note
Looking for the WebUI Extension? ScribeNEO is now available! It brings the power of TagForge directly into your Stable Diffusion WebUI.
TagForge isn't just a wrapper—it's a purpose-built workspace for prompt engineering.
- 🎨 Multi-Model Tagging: Specialized generator for Stable Diffusion (tags) and FLUX/Midjourney (prose).
- 👁️ Multimodal Vision: Extract precise metadata from images or generate high-fidelity descriptive captions.
- 💬 Contextual Chat: Persistent, coding-capable assistant with real-time access to provider-specific features.
- 🎭 Persona System: Craft custom identities with dynamic
{input}injection and role-based behavioral templates. - 📜 Chat Rules: Modular behavioral control (Concise, Detailed, etc.) with a CRUD interface and live header switching.
- ⚙️ Agent Orchestrator: Comprehensive management of API keys, endpoints, and model parameters like Max Tokens.
- 🔒 Zero-Trust Security: Local-only encryption via Windows DPAPI. Your credentials never leave your device.
- ⚡ Ultra-Fast Core: Built on .NET 9 with optimized asynchronous threading for a responsive experience.
- 🌍 18+ Locales: Fully internationalized UI with deep support for technical AI terminology in 18 languages.
- 📦 Portable & Native: High-performance binaries for Windows, Linux, and macOS. No runtime installation required.
Connect to the best models in the world.
 |
Google Gemini | Native multimodal support for vision-based tagging and long-context reasoning. |
 |
OpenRouter | Unified access to Claude 3.5, GPT-4o, and Llama 3.1 via a single integration point. |
 |
Hugging Face | Serverless inference for 100k+ models via the low-latency Inference API. |
 |
LM Studio | Local-first inference for GGUF models with full privacy and zero latency. |
 |
Ollama | Optimized local execution of Llama, Mistral, and Phi models on home hardware. |
TagForge speaks your language. Support currently extends to 18 locales with full technical terminology.
 |
English (en-US) |
 |
Deutsch (de-DE) |
 |
Français (fr-FR) |
 |
Español (es-ES) |
 |
Italiano (it-IT) |
 |
Русский (ru-RU) |
 |
Português (pt-BR) |
 |
简体中文 (zh-CN) |
 |
日本語 (ja-JP) |
 |
한국어 (ko-KR) |
 |
हिन्दी (hi-IN) |
 |
العربية (ar-SA) |
 |
Türkçe (tr-TR) |
 |
Nederlands (nl-NL) |
 |
Polski (pl-PL) |
 |
Українська (uk-UA) |
 |
B. Indonesia (id-ID) |
 |
Tiếng Việt (vi-VN) |
Note
Help us improve! These localizations were initially AI-generated. If you find any inaccuracies, please refer to the Translation Guide and submit your file!
TagForge is built on .NET 9.0 and Avalonia UI for high-performance cross-platform execution.
- .NET 9.0 SDK: Required for compilation.
- C# / .NET Tooling: Visual Studio or VS Code with C# Dev Kit recommended.
Standard compilation for your current platform:
# Clone the repository
git clone https://github.com/SiliconeShojo/TagForge.git
cd TagForge
# Restore dependencies and build
dotnet build -c Release
Made with ❤️ for the AI community by SiliconeShojo
