Skip to main content
The Image node turns a prompt into a still image, and doubles as the anchor for references, edits, and every image tool on the canvas.

​
Generate an image

Write a prompt in the node’s prompt bar, pick your settings, and click Run. Name the subject, the setting, the visual style, and the lighting: specific prompts give specific results. Reach for 1K when you’re drafting and iterating, and 4K when you need a crisp final output with detail to spare.
An Image node with a prompt, reference, and generation settings

An Image node: drop or upload a reference, write a prompt, and set aspect ratio and resolution before you Run

​
Reference images

Connect other Image nodes, generated or uploaded, as references, and describe in the prompt how to use them. References keep characters, products, and color palettes consistent across generations, and they’re how you do image edits: connect the source image, then prompt the change you want.

​
Modes

The Image node has two generation modes:
  • Standard. The normal path: text-to-image, image edits, and reference-conditioned generation.
  • Photobooth: connect a reference image of a product or subject, and the node generates a set of commercial photoshoot template variations from it. Add a text prompt to steer the direction. Photobooth needs the connected image first: a prompt alone won’t run.

​
Visual analysis

The AI assistant can inspect an Image node’s actual pixels, not only its prompt, so you can ask it to describe a result, critique a composition, or decide which of several variants to carry forward.

​
Edit with image tools

Every Image node connects into the canvas image tools: upscale, inpaint, outpaint, remove background, change angle, separate layers, and a set of local adjustments like crop, levels, and blur. Chain them after a generation to refine the result without leaving the canvas.
Last modified on August 29, 2026