Node Overview

Image Generation Node

The Image Node connects text and visual inputs, allowing you to iterate on design ideas, explore styles and colors, and combine multiple images to create a cohesive visual story.
For more details, see the Image Model section.

• Text to Image - Enter a text prompt to generate an image.
  You can describe footwear types, materials, sole structures, and colors using the integrated Shoe Dictionary for more accurate results.

  

  
  Use the Prompt Enhancement feature to refine or expand your initial concept.

  

• Image to Image - Input one or more images to generate new visuals.
  The list of available models automatically updates based on the number of connected image inputs.

  

Video Generation Node

The Video Node transforms static images into motion, enabling dynamic storytelling and immersive visual experiences.
For more details, see the Video Model section.

• Image to Video - Input an image and guide the motion output using a prompt.
  The model automatically interpolates frames to create smooth transitions.
  

  

Floating Toolbar

• When you hover over a node, a context-aware toolbar appears.

• Available options vary depending on the node type.

  

Resource Node

Drag and drop or upload images from your computer to the canvas.
These images can be used as inputs for generation nodes such as Image or Video.