Short answer: Drop the "Leonardo AI → Generate Leonardo Image" 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 | Prompt (required) |
Model modelId | options | Optional | Model. Options: Phoenix 1.0, Lightning XL, Kino XL |
Width width | string | Optional | Width |
Height height | string | Optional | Height |
Num Images num_images | string | Optional | Num Images |
{"prompt": "{{trigger.prompt}}","modelId": "{{trigger.modelId}}","width": "{{trigger.width}}","height": "{{trigger.height}}","num_images": "{{trigger.num_images}}"}
{"sdGenerationJob": {"generationId": "gen-abc","apiCreditCost": 4}}
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.