Image
Flux 2 Flex
Text-to-image generation with FLUX.2 [flex] from Black Forest Labs. Features adjustable inference steps and guidance scale for fine-tuned control. Enhanced typography and text rendering capabilities.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Flux 2 Flex. Review your own result before publishing.
A starting point.
Describe the image or edit you want and upload any required source images.
Before you publish.
Inspect the full-size output and compare details and subject appearance with your source.
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.
Inputs and settings
Choose an image-size preset or enter custom dimensions within the provider limits. The quote accounts for the selected output size.
Supported inputs
These fields come from the current studio form for flux-2-flex. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1.5 · ≤ 10 |
num_inference_steps | Whole number | Optional | ≥ 2 · ≤ 50 |
output_format | Text | Optional | jpeg, png |
safety_tolerance | Text | Optional | — |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Flux 2 Flex through the API.
Start with this model ID for the endpoint featured on this page:
flux-2-flex
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.