Workspace
7 articles
- How do I pick a reference from my library in the Workspace?Open the library drawer at the bottom of the Workspace and drag a file onto a reference slot, or right-click it and choose Use as Reference; you can also drop a file from your desktop or paste an image straight onto a slot.
- How do I read and copy a transcript?Run a speech-to-text model with an audio or video file in its slot; the result opens in a transcript viewer with the text, its word count and a Copy button, and the .txt is saved in your project like any other file so you can download it.
- How do I set the aspect ratio and the number of outputs?The aspect-ratio tiles above the parameters show only the ratios the selected model supports, and the number of outputs is a pill switch in the parameters panel whose choices come from the model itself — usually 1 to 4 for image models, one clip for video — with the estimate multiplying accordingly.
- How do I use reference images, videos and audio?Reference slots appear under the prompt whenever the selected model accepts input media; drop a file in, or pick one from your Library, and mention it in the prompt with the @Image chip the Workspace inserts.
- What do the progress bar and queue position mean?Queue: n means the provider has n jobs ahead of yours; Generating means the model is rendering, with the bar easing towards 95 % on the model's typical time; Finalizing means the result is being stored — and a job that produces nothing within 45 minutes is marked failed and never charged.
- What does the feather button next to the prompt do?The feather opens LuviTransLex, LUVI's prompt check: it lists what the selected model is known to mishandle in your prompt and fixes it in one click, and can optionally rewrite the whole prompt in that model's dialect — free of charge, and never without your say-so.
- When is there a negative prompt?The Negative Prompt field appears for every image and video model that takes a prompt and is hidden for audio and avatar models; what you type is sent to the provider, but some models do not read it, so their prompting guide tells you to describe what you want instead.