Short answer: Drop the "Nano Banana → Generate Image with Nano Banana" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Prompt prompt | string | Required | Describe the image you want to generate. Nano Banana handles legible text-in-image notably well — try poster mockups, logos with words, etc. |
Model model | options | Optional | Which Google image model to call. The stable Nano Banana is the safe default. Preview variants may produce sharper images but can be rate-limited or removed without notice. |
{"prompt": "A vintage poster of an astronaut riding a bicycle on Mars, retro 70s style, text reading 'MARS 2026' at the bottom","model": "{{trigger.model}}"}
{"url": "https://ccc.oute.app/MW_TOKEN/.../google-nano-banana-abc.png","byte_size": 1258624,"image_url": "https://ccc.oute.app/MW_TOKEN/.../google-nano-banana-abc.png","mime_type": "image/png","expires_at": "2026-05-15T13:59:00.704Z","model_version": "gemini-2.5-flash-image-preview"}
Use these fields in downstream nodes for routing, logging, or error handling.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.