AI Image Generator

Generates one or more images from a text prompt using an AI image model and stores the results in an output variable.

Purpose

Use this task when a workflow needs to produce images dynamically based on runtime data, such as generating visuals for reports, presentations, or documents. It supports style guidance to steer the composition and tone of the generated image, and can optionally download the image file to the workflow's working folder for use by downstream file-handling tasks.

Inputs

Field	Type	Required	Description
Prompt	Multi-line Text	Yes	A description of the image to generate. More specific prompts yield better results.
Style Preset	Dropdown	No	An optional style applied to the prompt. Options: (none), marketing_infographic, realistic_render, technical_diagram, artistic_illustration, minimalist_design, vintage_poster, modern_ui, product_mockup.
Model	Dropdown	Yes	The image model to use: dall-e-3 (default) or dall-e-2. DALL-E 3 is limited to one image per request.
Size	Dropdown	No	Output image dimensions. Available options depend on the selected model (see Visibility Rules).
Quality	Dropdown	No	Rendering quality: standard (default) or hd.
Image Count	Text	No	Number of images to generate. Defaults to 1. When using DALL-E 3 this is always forced to 1.
Download Images	Checkbox	No	When checked, each generated image is saved to the workflow's working folder.

Visibility Rules

Size options shown when Model is dall-e-3: 1024x1024, 1024x1792, 1792x1024. Size options shown when Model is dall-e-2: 256x256, 512x512, 1024x1024.

Outputs

Name	Description
Result	An array of image result objects. Each object contains the image URL, the final prompt used by the model, and — if Download Images was enabled — the local file path where the image was saved. Downstream tasks can iterate over this array or reference individual entries.