AI Generation

Virse can generate images and text directly on the canvas. The generation interface appears in context based on what is selected.

Generate into an element

Select a single image or text element. A chat bar appears at the bottom of the canvas. Enter a prompt and press Enter or click Generate. The element shows a loading state and then updates with the result.

You can also drag reference images from the canvas into the chat bar as visual inputs.

Generate a batch

When nothing is selected, the anchored chat bar at the bottom can generate multiple images at once. Set batch size, choose a model, and generate. Results are placed on the canvas and positioned to avoid overlap.

Models

Parameters

• Model: which generation model to use.
• Aspect ratio: controls output dimensions.
• Style: applies a trained style from your library.
• Aesthetic memory: lets LAMM steer output toward your taste profile.

Inpaint, outpaint, and upscale

• Inpaint: regenerate a painted local region.
• Outpaint: extend the image beyond its current edges.
• Upscale: increase image resolution.