Generate Image

A guide on how to use the Generate Image action to create original images from a text prompt using models like DALL-E 3.

The Generate Image Action allows you to create completely new and original images from a text description using powerful text-to-image AI models.

Configuration

You configure the action by providing a prompt and selecting the desired model and output settings.

Input Parameters

Parameter	Type	Description
Model	Dropdown	The text-to-image model you want to use (e.g., dall-e-3).
Prompt	Text	A detailed description of the image you want to create. Be as specific as possible for the best results.
Resolution	Dropdown	The dimensions of the output image (e.g., 1024x1024, 1792x1024). Available options may vary by model.
Quality	Dropdown	The quality of the generated image. hd provides better detail but may take longer, while standard is faster.

Example Configuration

{
  "model": "dall-e-3",
  "prompt": "A photorealistic image of an astronaut riding a horse on Mars.",
  "resolution": "1792x1024",
  "quality": "hd"
}

Output

The action outputs the generated image data, including a URL where the image can be accessed.

Output Parameter

Parameter	Type	Description
data	JSON	A JSON object containing the url of the generated image and other metadata. You can use {{generate_image_action.data.url}} to access the image link.