All models

FLUX.2 [flex]

black-forest-labs/flux-2-flex
Black Forest Labs Image GenerationImage EditingTypographyTunable

FLUX.2 [flex] is Black Forest Labs' fine-grained control variant of FLUX.2 — exposes tunable inference steps, guidance, and prompt upsampling for typography-heavy and production workflows.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "black-forest-labs/flux-2-flex",
    "prompt": "<your prompt>"
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "black-forest-labs/flux-2-flex", "prompt": "<your prompt>"}'

Examples

example
example
example

Parameters

Input
prompt string required

Text prompt for image generation or editing.

guidance number optional

Classifier-free guidance scale (1.5–10). Higher values follow the prompt more strictly at the cost of realism.

height integer optional

Height of the generated image in pixels (minimum 64). Omit to let BFL pick.

input_images array optional

Up to 8 reference images for editing or multi-image composition. Each entry is an HTTPS URL or a data:image/...;base64,... URI.

output_format string optional

Output image format. Defaults to jpeg.

prompt_upsampling boolean optional

Whether BFL should expand short prompts before generation. Defaults to true on flex.

safety_tolerance integer optional

Tolerance for input/output moderation. 0 is the strictest, 5 the most permissive. Defaults to 2.

seed integer optional

Optional seed for reproducible generation.

steps integer optional

Number of denoising steps (1–50). Higher steps yield more detail at the cost of latency.

width integer optional

Width of the generated image in pixels (minimum 64). Omit to let BFL pick.

Output
image: URL to the generated image