Skip to main content
POST
/
v1
/
images
/
generations
Image generations
curl --request POST \
  --url http://localhost:8000/v1/images/generations \
  --header 'Content-Type: application/json' \
  --data '{
  "guidance_scale": 3.5,
  "num_inference_steps": 10,
  "prompt": "An orange Lamborghini driving down a hill road at night with a beautiful ocean view in the background."
}'
{
  "image": "<base64 encoded image>"
}
Given a description, the model generates image.

Body

application/json
prompt
string
required

A text description of the desired image.

num_inference_steps
integer
required

The number of inference steps to use during image generation. Supported range: [1, 50].

guidance_scale
number
required

Adjusts the alignment of the generated image with the input prompt. Higher values (e.g., 8-10) make the output more faithful to the prompt, while lower values (e.g., 1-5) encourage more creative freedom. This parameter may be irrelevant for certain models, such as FLUX.Schnell.

model
string | null

Routes the request to a specific adapter.

Examples:

"(adapter-route)"

seed
integer | null

The seed to use for image generation.

response_format
enum<string> | null
default:jpeg

The format in which the generated image will be returned. One of raw and jpeg.

Available options:
raw,
jpeg
control_images
ImageInput · object[] | null

Optional input images used to condition or guide the generation process (e.g., for ControlNet or image editing models). This field is only applicable when using ControlNet or image editing models.

controlnet_weights
number[] | null

A list of weights that determine the influence of each ControlNet model in the generation process. Each value must be within [0, 1], where 0 disables the corresponding ControlNet and 1 applies it fully. When multiple ControlNet models are used, the list length must match the number of control images. If omitted, all ControlNet models default to full influence (1.0). This field is only applicable when using ControlNet models.

Response

Successfully generated image.

image
file
required

The base64-encoded image.