FLUX 3 Image

Black Forest Labs FLUX 3 Image — text to image from 768px up to 4K (about 16 MP), 14 aspect ratios. Priced per image by resolution: the bigger the image, the higher the price.

Try FLUX 3 Image in the playground

Last updated View as MarkdownAgent setup

FLUX 3 Image

Node type: generate:flux_3_image
Category: generate

Description

FLUX 3 Image is Black Forest Labs' text-to-image model: wire your text into Prompt and each run returns one image as Generated Images, from 768px square up to 4K (about 16 MP) in 14 aspect ratios. You pay per image, set by Resolution: a bigger image costs more than the 1K default, and the widest and tallest shapes at 1K, 2K and 4K cost more too. With Aspect Ratio on Auto, the run reserves the dearest shape and refunds the difference once the image arrives. Prompt Expansion expands your prompt while keeping its intent, and Safety Tolerance runs from 0, the strictest, to 4, the most permissive. A 4K image can take several minutes. To change a result afterwards, wire it into FLUX 3 Image Edit.

Pricing

  • Cost: ~20 credits per image

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt TEXT (required) · multiline

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
resolution Resolution TEXT · options: 768sq, 1k, 2k, 4k
aspect_ratio Aspect Ratio TEXT · options: auto, 21:9, 2:1, 16:9, 3:2, +10
enable_prompt_expansion Prompt Expansion BOOLEAN — Expands the prompt while keeping its intent.
output_format Output Format TEXT · options: jpeg, png
safety_tolerance Safety Tolerance NUMBER · 0…4 — 0 is strictest, 4 is most permissive.

Outputs

ID Label Type
images Generated Images IMAGE

Pricing

Per image, set by Resolution: 768 square, 1K (about 1 MP, the default), 2K (about 4 MP) or 4K (about 16 MP). A bigger image costs more, and so do the widest and tallest shapes at 1K, 2K and 4K. On Auto the run reserves the dearest shape and refunds the difference once the image arrives. 4K can take several minutes. One image per run. To change a result afterwards, wire it into FLUX 3 Image Edit.


Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.