Infer

mode

string

enum

Defaults to Image Generation

NIM inference mode. If Image Editing is selected an image input is required

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.

height

integer

enum

Defaults to 1024

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

width

integer

enum

Defaults to 1024

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

cfg_scale

number

0 to 0

Defaults to 0

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

image

null

Preview API NIM supports only a predefined set of images. The image should be in form of data:image/png;example_id,{example_id} with example_id in a range [0,3].

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

steps

integer

1 to 4

Defaults to 4

The number of diffusion steps applied to generate an output image.

200Successful Response

422Validation Error