Short answer: Drop the "Black Forest Labs → Edit Image with Kontext" 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 |
|---|---|---|---|
Model model | options | Optional | Model. Options: Flux Kontext Pro, Flux Kontext Max |
Edit Prompt prompt | string | Required | make the sky purple at sunset |
Input Image (base64 or URL) input_image | string | Required | Input Image (base64 or URL) (required) |
Aspect Ratio aspect_ratio | string | Optional | Aspect Ratio |
{"model": "{{trigger.model}}","prompt": "make the sky purple at sunset","input_image": "{{trigger.input_image}}","aspect_ratio": "{{trigger.aspect_ratio}}"}
{"id": "task_abc","polling_url": "https://api.bfl.ai/v1/get_result?id=task_abc"}
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.