Request generation

aspect_ratio

string

enum

Defaults to 1:1

Controls the aspect ratio of the generated image.

Allowed:

cfg_scale

number

≤ 9

Defaults to 5

The scale of classifier free guidance. Classifier free guidance is an approach that allows users to specify the alignment of the input prompts and negative prompts to the output image. Lower classifier free guidance will result in more diverse but less aligned outputs, while higher classifier free guidance will generate more less diverse but more aligned outputs.

mode

string

enum

Defaults to text-to-image

Controls the generation mode. Only mode=text-to-image is supported

Allowed:

model

string

enum

Defaults to sd3

The model to use for generation. Only model=sd3 is supported

Allowed:

negative_prompt

length ≤ 10000

A blurb of text describing what you do not wish to see in the output image. This is an advanced feature.

output_format

string

enum

Defaults to jpeg

Dictates the content-type of the generated image.

Allowed:

prompt

string

required

length ≤ 10000

What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.

seed

integer

≥ 0

Defaults to 0

The seed which governs generation. Changing the seed with other inputs fixed results in different outputs. (Use 0 for a random seed) 0 for a random seed

steps

integer

5 to 100

Defaults to 50

The number of diffusion steps applied to generate an output image. The more steps, the longer the call will take, and up to a point, the higher quality the image will be.

200Successful Response

422Validation Error