ActionBlack Forest LabsUpdated September 2026
How do I generate an image with Flux?
Short answer: You can generate image with flux in Black Forest Labs by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Black Forest Labs Generate Image with Flux action to a workflow, map its 5 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.
Inputs
The fields this action accepts.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Model model | options | Required | Model. Options: Flux Pro 1.1 Ultra (best), Flux Pro 1.1, Flux Dev (cheap) … |
Prompt prompt | string | Required | Prompt (required) |
Width width | number | Optional | Width |
Height height | number | Optional | Height |
Prompt Upsampling prompt_upsampling | options | Optional | Prompt Upsampling. Options: No, Yes |
Sample request
{"model": "{{trigger.model}}","prompt": "{{trigger.prompt}}","width": "{{trigger.width}}","height": "{{trigger.height}}","prompt_upsampling": "{{trigger.prompt_upsampling}}"}
Returns
{"id": "task-abc123","polling_url": "https://api.bfl.ai/v1/get_result?id=task-abc123"}
Use these fields in downstream nodes for routing, logging, or error handling.
Triggered by
Apps that pair well as the trigger for Generate Image with Flux.
Any of these apps can fire this action as part of a workflow.
FAQ
Questions about Generate Image with Flux.
What does the Generate Image with Flux action do in Black Forest Labs?
Text-to-image generation across Flux variants (Schnell for fastest/cheapest, Dev for open-weights, Pro for highest quality, Ultra for strongest text rendering). Returns a task ID; poll Get Result for the finished image URL.
What inputs does Generate Image with Flux require?
Required: Model, Prompt. Every input accepts a static value or a variable from any upstream node in your workflow.
Can I use dynamic inputs from earlier workflow nodes?
Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.
What happens if Black Forest Labs returns an error?
The run history shows the failed step with its input and the error message Black Forest Labs returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.
Does Generate Image with Flux support batch operations?
Run Generate Image with Flux inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Black Forest Labs's rate limits.
More actions
Other Black Forest Labs actions.
Action
Edit Image with Kontext
Takes a source image plus a text instruction ("make the sky stormy", "remove the person on the left"). Flux Kontext preserves the unchanged parts and applies the requested edit. Better at "keep this thing, change that thing" than re-generating from scratch with a reference image.
ActionInpaint with Flux Fill
Mask-driven inpainting — pass an input image, a black-and-white mask (white = regenerate, black = preserve), and a prompt describing what should fill the white area. Flux Fill regenerates only the masked region while preserving everything else. The standard tool for removing unwanted objects or replacing specific areas.
ActionGet Generation Result
Polls a task ID for status; returns the image URL in result.sample once status is Ready. For production, configure BFL's webhook on the generation request to skip polling and get a push notification when ready.