Skip to main content
The Generate Image node creates images from a text prompt using AI models. You can supply reference images and brand context to steer the output.

When to use

  • Creating marketing visuals
  • Generating product mockups
  • Producing ad creatives
Common patterns: text_prompt → generate_image, or text_prompt → generate_image → upscale_image.

Inputs

Text Prompt
text
required
The prompt describing the image to generate. Required.
Reference Images
image
One or more images to guide the generation. Optional, accepts multiple.
Brand
brand
Brand context applied to the output. Optional, accepts multiple.
Context
any
Anything to include as additional context — scraper Results, text descriptions, or mixed bundles. Contents are described to the model in the prompt. Images in the bundle are passed as reference images where the selected model supports them. Optional, accepts multiple.
Element
element
Subject reference slots. Available only when the selected model supports subject references and you set element slots above zero.

Outputs

Image
image
The generated image.

Configuration

numberOfImages
number
default:"1"
How many images to generate per run (1–10).
instructions
string
default:""
Extra instructions prepended to the prompt before generation.
elementSlotCount
number
default:"0"
Number of subject-reference element slots to expose. Synced to the selected model’s capability.
Pick the model in the node’s config panel — see Image models for the options, and Model settings for what each setting does. Additional model-specific options (such as aspect ratio, resolution, and seed) appear depending on the model you choose. Runs consume credits.