Request generation

height

integer

1024 to 1024

Defaults to 1024

Height of the image to generate, in pixels. Only height=1024 is supported

width

integer

1024 to 1024

Defaults to 1024

Width of the image to generate, in pixels. Only width=1024 is supported

text_prompts

array of objects

required

length between 1 and 2

An array of text prompts to use for generation

Text Prompts*

text

string

required

The prompt itself

weight

number

enum

Defaults to 1

Weight of the prompt, only weight=1.0 for prompt and weight=-1 for negative prompt is supported

Allowed:

cfg_scale

number

≤ 9

Defaults to 5

How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt).

clip_guidance_preset

string

enum

Defaults to NONE

clip guidance preset. Only clip_guidance_preset=NONE is supported

Allowed:

sampler

string

enum

Defaults to K_DPM_2_ANCESTRAL

The sampler to use for generation. Varying diffusion samplers will vary outputs significantly.

Allowed:

samples

integer

1 to 1

Defaults to 1

Number of images to generate. Only samples=1 is supported

seed

integer

≥ 0

Defaults to 0

The seed which governs generation. Omit this option or use 0 for a random seed

steps

integer

5 to 100

Defaults to 25

Number of diffusion steps to run

style_preset

string

enum

Defaults to none

Pass in a style preset to guide the image model towards a particular style. This list of style presets is subject to change. style_preset=none is supported

Allowed:

200Successful Response

422Validation Error