AI - Image Generate

Type identifier: ai:image-generate Category: AI Operations

Description

The AI - Image Generate node creates images based on text prompts using AI image generation models. It returns the generated image as a file that can be used in Experiences or stored.

Input Handles

Handle	Type	Description
`trigger`	`control`	Starts image generation.
`prompt`	`string`	Text description of the desired image. Shown when Prompt is dynamic (the default).
`model`	`string`	Shown when Model is dynamic.
`quality`	`string`	Shown when Quality is dynamic.
`size`	`string`	Shown when Size is dynamic.

Output Handles

Handle	Type	Description
`image`	`file`	The generated image file.
`success`	`control`	Triggered when the image is generated.
`error`	`control`	Triggered when the node fails, if connected.

Configuration Options

Option	Type	Default	Description
Model	`string` or dynamic string	`openai:gpt-image-2`	Image model. See Models.
Prompt	`string` or dynamic string	-	Text description of the desired image, 1 to 32,000 characters.
Quality	`low`, `medium`, or `high`	`medium`	Detail level. Higher quality uses more output tokens and costs more.
Size	`string` or dynamic string	`auto`	Output size. See Size.

Size

auto (default): the provider chooses the size.
WIDTHxHEIGHT, for example 1024x1024, 1536x864, or 1024x1536:
- Each dimension must be at least 256 pixels and a multiple of 16.
- The total pixel count must be between 655,360 (for example 816x816) and 8,294,400.
- An invalid size fails the node.

Models

Available image generation models:

OpenAI GPT Image 2 (openai:gpt-image-2), the default

Earlier image model names (gpt-image-1, openai:dall-e-2, openai:dall-e-3) are deprecated and run as openai:gpt-image-2. Studio shows a deprecation notice with an upgrade button on nodes that use a deprecated name.

For the full list and deprecations, see AI - Model Reference — Image Generate Models and AI - Model Reference — Deprecated Models and Fallbacks.

Behaviour

Receives the text prompt from the prompt input, or from the node's Prompt setting when it is not dynamic
Sends the generation request to the image model with the selected quality and size
Outputs the generated image on image and triggers success

Each generation uses credits based on the selected quality and size.

Examples

Basic Image Generation

Input (prompt):

"A serene mountain landscape at sunset with a calm lake in the foreground"

Output: Generated image file matching the description.

Product Visualisation

Input (prompt):

"Professional product photo of a modern smartwatch on a white background"

Use case: Generate placeholder images for product mockups.

Dynamic Prompt Generation

Flow:

AI - Chat Message generates creative prompt
AI - Image Generate creates the image
Store result for user

AI - Chat Message

The AI - Chat Message node enables conversations with large language models (LLMs) from multiple providers including OpenAI, Anthropic, Google AI, and Groq. It supports dynamic message templates with variable interpolation, streaming responses, extended thinking, and AI actions (tool use).

Text - Template

Renders a rich-content template with variable substitution. Insert variables through the template editor, then connect each generated input handle to the value it should render. It generates dynamic content such as messages, emails, or prompts.