-
-
Notifications
You must be signed in to change notification settings - Fork 13
FAQ
MooshieUI does not use the classic __filename__ text-file wildcards or {red|blue|green} inline syntax. Wildcards are a mode of Prompt Presets.
- Open the bottom panel, go to the Artist Styles manager, then the Presets tab. Create a preset and put each choice on its own line (commas within a line stay grouped).
- Either activate the preset with a Wildcard (random) or Wildcard (in order) mode, or drop the inline token
@[Chunk Name](or@preset:<slug>) anywhere in your prompt to roll it at that exact spot.
Full details: Prompting Guide.
Drag or paste the PNG back into MooshieUI. It reads the embedded metadata and fills in your settings. If the image has no embedded metadata, use image interrogation to reverse-engineer tags. See Gallery and Metadata and Prompting Guide.
Use a Wildcard (in order) preset (the Generate button can queue the whole ordered run), or use the Compare Grid for explicit per-cell parameter sweeps.
Yes. Run MooshieUI in server mode and open it in your phone's browser; there is a dedicated mobile layout. See Server, LAN and Multi-User.
Yes, as a thin client against a remote ComfyUI. See the remote/cloud section of Installation.
Models are identified by SHA256 hash, not filename, so renames are fine. If an architecture is misdetected, check that it is one of the supported families in Models and the Model Hub. Architecture support grows between releases, so the in-app behavior is the source of truth.
A quantized model is saved in a particular format, and ComfyUI can only load the formats its own version knows about. If generation stops with a message naming a format such as int8_tensorwise or convrot_w4a4, the installed ComfyUI predates that format. Click Update ComfyUI under Settings > Performance to move to the version MooshieUI currently pins, or use a non-quantized version of the model.
Click the bug icon in the left sidebar (just below the connection indicator) to open Report a problem any time. Add a note and submit, and your app version, OS, and recent logs are bundled and filed as a GitHub issue for you, no GitHub account required. Nothing is sent unless you submit. If a problem is upscale or generation related, running the affected action first so it's captured in the logs helps a lot. See the diagnostics notes in Settings and Accessibility.
In the repo: README.md, push-instructions.md, and CHANGELOG.md.
Getting started
Prompting
Generation features
- NovelAI Backend
- Video Generation
- Upscaling and Face Fix
- ControlNet and Style Transfer
- Inpainting and the Canvas Editor
- Image Edit Mode
- Compare Grid
- Image Comparison
Models and output
Deployment
Help
Contributing