Light Mode

Create Task

POST/api/v1/task

This endpoint from PiAPI's Dream Machine API utilizes Dream Machine model by Luma Labs to produce text/image-to-video generation.

Request

Header Params

x-api-key

string

required

Your API Key used for request authorization

model

enum<string>

required

the model name

Allowed value:

luma

task_type

enum<string>

required

type of the task

Allowed values:

video_generationextend_video

input

object

required

the input param of the luma task

prompt

string

required

The prompt is a description that enables the Dream Machine API to produce a video.

expand_prompt

boolean

optional

The recommended value at this time is false. We have tested that the value false results in better quality.

Default:

false

loop

boolean

optional

Whether to loop the video.

Default:

false

key_frames

object

optional

If left null then the task would be a text-to-video task; if filled out, then the task would be an image-to-video or video-extend task.

In an image-to-video task, the type of the frame can only be set to image, you can choose to set to frame0 and/or frame1.

config

object

optional

webhook_config

object

optional

Webhook provides timely task notifications. Check PiAPI webhook for detail.

service_mode

enum<string>

optional

This allows users to choose whether this specific task will get processed under PAYG or HYA mode. If unspecified, then this task will get processed under whatever mode (PAYG or HYA)
the user chose on the workspace setting of your account.

public means this task will be processed under PAYG mode.
private means this task will be processed under HYA mode.

Allowed values:

publicprivate

{
  "model": "luma",
  "task_type": "video_generation",
  "input": {
    "prompt": "Fly fishing",
    "expand_prompt": true,
    "loop": true
  },
  "config": {
    "service_mode": "",
    "webhook_config": {
      "endpoint": "",
      "secret": ""
    }
  }
}

Request samples

Responses

Success(200)

HTTP Code: 200

Content Type : JSONapplication/json

code

integer

required

data

object

required

task_id

string

required

model

string

required

task_type

string

required

status

enum<string>

required

Hover on the "Completed" option and you coult see the explaintion of all status: completed/processing/pending/failed/staged

Allowed values:

CompletedProcessingPendingFailedStaged

input

object

required

output

object

required

meta

object

required

detail

null

required

logs

array [object]

required

error

object

required

message

string

required

If you get non-null error message, here are some steps you chould follow:

Check our common error message
Retry for several times
If you have retried for more than 3 times and still not work, file a ticket on Discord and our support will be with you soon.

{
  "code": 200,
  "data": {
    "task_id": "f7a6d8e5-249f-4a9e-a8f4-1e8af806ea15",
    "model": "luma",
    "task_type": "video_generation",
    "status": "pending",
    "config": {
      "service_mode": "public",
      "webhook_config": {
        "endpoint": "",
        "secret": ""
      }
    },
    "input": {},
    "output": {
      "prompt": "",
      "internal_state": "",
      "created_at": "",
      "video": null,
      "video_raw": null,
      "thumbnail": null,
      "last_frame": null
    },
    "meta": {},
    "detail": null,
    "logs": null,
    "error": {
      "code": 0,
      "raw_message": "",
      "message": "",
      "detail": null
    }
  },
  "message": "success"
}

Last modified: 2 months ago