Skip to content
Reduced motion is on. Play a preview to watch it.
Explore models

Image

FLUX.1 Krea [dev]

Explore a photographic scene from text with FLUX.1 Krea [dev].

  • Text to image
Create with FLUX.1 Krea [dev]
Preview for FLUX.1 Krea [dev]

Catalog preview for FLUX.1 Krea [dev]. Review your own result before publishing.

A starting point.

Explore a photographic scene from text with FLUX.1 Krea [dev]. Describe light, material and viewpoint in the brief.

Before you publish.

Inspect skin or material texture and local lighting rather than treating a photographic style as proof of realism.

Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.

How credits work · Use the API · Content guidelines

Settings and model questionsCheck the available settings and guidance when preparing your input.

Inputs and settings

Send prompt; this route is distinct from image-based Krea Redux.

Compare guidance_scale and num_inference_steps one at a time. Preserve acceleration and seed in your comparison record.

Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.

Supported inputs

These fields come from the current studio form for flux-1/krea. Other modes may require different inputs.

Input types, requirements and limits for flux-1/krea
InputTypeRequirementOptions and limits
promptTextRequired—
accelerationTextOptional—
enable_safety_checkerOn/offOptional—
guidance_scaleNumberOptional≥ 1 · ≤ 20
num_imagesWhole numberOptional≥ 1 · ≤ 4
num_inference_stepsWhole numberOptional≥ 1 · ≤ 50
output_formatTextOptionaljpeg, png
seedWhole numberOptional—

Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.

Use FLUX.1 Krea [dev] through the API.

Start with this model ID for the endpoint featured on this page:

flux-1/krea

Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.

Check the current model schema for supported inputs and options. Other tasks may use different model IDs.

From quote to result.

Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.

Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.