Sample Request

curl --request POST \
     --url https://cloud.leonardo.ai/api/rest/v2/generations \
     --header 'accept: application/json' \
     --header 'authorization: Bearer <YOUR_API_KEY>' \
     --header 'content-type: application/json' \
     --data '
{
  "model": "motion_2.0-fast",
  "public": false,
  "parameters": {
    "prompt": "A koala and a cat playing together in a sunlit meadow",
    "quantity": 1,
    "width": 1024,
    "height": 1024,
    "mode": "RESOLUTION_480"
  }
}
'

Recipe

API Request Endpoint, Headers, Parameters

Endpoint

https://cloud.leonardo.ai/api/rest/v2/generations

Headers

--header "accept: application/json" \
--header "authorization: Bearer <YOUR_API_KEY>" \
--header "content-type: application/json"

Body Parameters

Parameter	Type	Definition
controls	`array`	Optional. An array of Motion Control items (same format, but are defined separately from Motion Elements). Maximum 1 item.
elements	`array`	Optional. An array of Motion Elements (same format, but are defined separately from Motion Control!).
frame_interpolation	`boolean`	Optional. Whether the video generation will smoothly blend frames. Defaults to `True`.
guidances	`object`	Optional. Object defining guidance inputs (e.g. reference images, start/end frames) that influence the result.
guidances.start_frame	`array`	Optional. Creative reinterpretation of vibe or structure from a reference image. Maximum 1 item. Each item includes image.id and image.type (`INIT`, `GENERATION`, `UPLOADED`, `GENERATED`, `VARIATION`).
height	`string`	Optional. Height of the output in pixels.
mode	`string`	Optional. Resolution mode for the generation. Accepts `RESOLUTION_480`, `RESOLUTION_720`. Defaults to `RESOLUTION_480`.
model	`string`	Required. Specifies the model used for generation. Set to `motion_2.0-fast`.
negative_prompt	`string`	Optional. The negative prompt to use for the generation. Maximum 1000 characters.
prompt	`string`	Required. The prompt to use for the generation. Maximum 9999 characters.
prompt_enhance	`string`	Optional. Whether to enhance the prompt or not. Accepts `AUTO`, `ON`, `OFF`. Defaults to `AUTO`.
public	`boolean`	Optional. Controls whether the generation is public (`true`) or private (`false`).
quantity	`number`	Optional. The number of outputs to generate. Defaults to `1`. Range 1-1.
seed	`number`	Optional. The seed value for video generation.
style_ids	`array`	Optional. An array of zero or more style UUIDs for video models (vibe, lighting, color). Defaults to `[]`.
width	`string`	Optional. Width of the output in pixels.

Dimensions

The API accepts integer width and height values in pixels.

The mode parameter accepts: RESOLUTION_480, RESOLUTION_720.