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
| π€ Agent Orchestrator | π¬ Intelligent Chat | π History Management |
|---|---|---|
| π Live Console | βοΈ Configuration | π¨ Prompt Generator |
TagForge isn't just a wrapperβit's a purpose-built workspace for prompt engineering.
- π¨ Specialized Generator: Turn vague ideas into optimized, comma-separated tag lists for Stable Diffusion or rich prose for FLUX/Midjourney.
- ποΈ Vision Analysis: Drag-and-drop images to extract tags or generate detailed captions using multimodal models.
- π¬ Contextual Chat: A coding-capable assistant with persistent session history and markdown rendering.
- π Zero-Trust Security: API keys are encrypted at rest using Windows DPAPI. Keys never leave your device except to hit the API endpoint.
- β‘ Native Performance: Built on .NET 9 with heavy threading. The UI stays buttery smooth, even while generating complex batches.
Connect to the best models in the world.
Customize the AI's identity to fit your workflow:
- ποΈ System Roles: Define the AI's expertise (e.g., "You are a Danbooru tagging expert").
- π Dynamic Injection: Use the
{input}placeholder to create reusable templates. - βοΈ Built-in Presets:
- Tag Prompts: The classic tagging engine for Stable Diffusion.
- Natural Prompts: For generating rich, descriptive prose.
- Tag Vision: Inspects images and generates tag lists.
- Natural Vision: Inspects images and generates detailed captions.
TagForge speaks your language.
Note
Want to help? Check out the Translation Guide. Adding a language takes minutes, and all contributors are credited!
TagForge is built on .NET 9.0 and Avalonia UI for cross-platform performance.
Important
You must have the .NET 9.0 SDK installed to build this project from source.
To produce a clean, standalone executable:
dotnet publish -c Release -r win-x64 -p:PublishSingleFile=true --self-contained true -o ./publish/windotnet publish -c Release -r linux-x64 -p:PublishSingleFile=true --self-contained true -o ./publish/linuxdotnet publish -c Release -r osx-arm64 -p:PublishSingleFile=true --self-contained true -o ./publish/mac-armdotnet publish -c Release -r osx-x64 -p:PublishSingleFile=true --self-contained true -o ./publish/mac-intelTip
The build commands above generate a portable executable in the ./publish folder with all dependencies embedded. No installation required!
- LLM Model Icons: LobeHub
- UI Icons: The Noun Project