Generate Image

Overview#

Generate images with Gemini or OpenAI.

Use this block when its responsibility is clear in the graph. Give it a name that describes the work it performs, then test it with representative input before publishing.

Working examples#

These are complete starting points, not decorative diagrams. Every graph is also available in the main template library and is checked by the workflow compiler.

1. Editorial hero image#

You will build: A landscape hero illustration.

Keeps art direction reusable across an editorial series. A fixed aspect ratio avoids layout surprises.

Open this template and adapt the labels, prompts, or credentials to your own workflow.

2. Product moodboard tile#

You will build: A square product moodboard tile.

Provides a consistent visual exploration artifact. One-image output and a square ratio keep batches predictable.

Open this template and adapt the labels, prompts, or credentials to your own workflow.

3. Vertical campaign concept#

You will build: A vertical concept for mobile placements.

Tests a campaign idea in its intended shape. The 9:16 constraint prevents accidental landscape renders.

Open this template and adapt the labels, prompts, or credentials to your own workflow.

Ports#

• Input: Prompt (in): string, optional, single.
• Output: Generated media (out): image, optional, single.

Inspector#

• Prompt: key prompt; textarea; default: "".
• Model: key model; select; options: gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, gemini-3.1-flash-lite-image, gpt-image-1-mini, gpt-image-2, gpt-image-1.5; default: "gemini-3.1-flash-image-preview".
• Aspect ratio: key aspectRatio; select; options: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1; default: "1:1".
• Quality: key quality; select; options: low, medium, high; default: "medium".
• Timeout (ms): key timeout; number; range: 30000 to 600000; default: 180000.
• expanded-text editor: manages prompt with edit, expand support.

Behavior#

• Input requirement: Provide one of ports in or config fields prompt.
• Execution: Handled by the handler using llm-image.
• Timeout: 180000 ms by default (30000 to 600000 ms).

Cost#

Uses an image-model provider and contributes model usage to the run cost.

Security#

• Uses a runner-provided model API key. Secret values are not part of the published graph.
• The node reads from an external service without intentionally mutating it.

Retry#

The runtime may retry this node according to the compiled execution policy.

Production checklist#

• Test the happy path and one malformed or empty input.
• Keep credentials out of prompts and published graph configuration.
• Set a timeout and retry policy that matches the operation's side effects.
• Name the final result so a runner can tell what success looks like.