FLUX models

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

The Flux model to use for generation.

Text prompt for image generation.

Number of images to generate. Supports for flux_dev and flux_schnell. Between 1 and 4.

The aspect ratio of generated images.

Random seed. Set for reproducible generation.

Number of denoising steps. Supports flux_dev and flux_schnell. For flux_dev between 1 and 50, with a default value of 28. For flux_schnell between 1 and 4, with a default value of 4. For flux_pro between 1 and 50, with a default value of 25.

Controls the balance between adherence to the text prompt and image quality/diversity. Higher values make the output more closely match the prompt but may reduce overall image quality. Lower values allow for more creative freedom but might produce results less relevant to the prompt. Supports flux_pro and flux_dev. Between 2 and 5 for flux_pro. Between 0 and 10 for flux_dev.

Interval is a setting that increases the variance in possible outputs letting the model be a tad more dynamic in what outputs it may produce in terms of composition, color, detail, and prompt interpretation. Setting this value low will ensure strong prompt following with more consistent outputs, setting it higher will produce more dynamic or varied outputs. Only supports flux_pro. Between 1 and 4.

Safety tolerance, 1 is most strict and 6 is most permissive. Only supports flux_pro. Between 1 and 6.

An array of generated image URLs.