curl --request POST \
  --url https://api.modellix.ai/api/v1/skywork/skyreels-omni \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "@Actor-1 walks through a rainy neon street at night"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-skyreels-omni-001",
    "model_id": "skyreels/skyreels-omni",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-skyreels-omni-001"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: parameter 'prompt' is required"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

SkyReels Omni Reference Video

**[Core Function]** SkyReels Omni is a reference-driven video model that generates or edits video using reference images (@image) and/or a reference video (@video), bound by tags in the prompt. **[Strengths]** A single endpoint covers motion reference, subject/background replacement, object insertion/removal, local editing, and video extension. **[Best For]** Video subject or background swap, motion transfer onto an image, object add/remove, local video edits, and extending a reference video. **[Limitations]** Do NOT use this for pure text-to-video (use skyreels-t2v) or simple single-image animation (use skyreels-i2v). Each ref tag must appear in the prompt as @tag; ref_videos supports only one video (<=15s); a reference-type video may combine only with image-type ref_images, while an extend-type video cannot combine with ref_images. When ref_videos is provided, aspect_ratio is ignored (output matches the video). **[Routing]** Provide ref_images (type grid or image) for image references and/or a single ref_videos entry (type reference for motion/edit, type extend for continuation); the reference tags must be used in the prompt.

POST

skywork

skyreels-omni

curl --request POST \
  --url https://api.modellix.ai/api/v1/skywork/skyreels-omni \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "@Actor-1 walks through a rainy neon street at night"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-skyreels-omni-001",
    "model_id": "skyreels/skyreels-omni",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-skyreels-omni-001"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: parameter 'prompt' is required"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

Authorizations

Authorization

string

header

required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json

SkyReels Omni reference video request. prompt is required; provide ref_images and/or ref_videos to drive the reference-based task. Each ref tag must appear in the prompt as @tag.

prompt

string

required

Text description; must reference each ref tag via @tag (max 1280 tokens).

Minimum string length: 1

Example:

"The girl in @image1 mimics the gestures of the woman in @video1"

aspect_ratio

enum<string>

default:16:9

Video aspect ratio. Ignored when ref_videos is provided (output matches the reference video).

Available options:

16:9,

4:3,

1:1,

9:16,

3:4

Example:

"16:9"

duration

integer

default:5

Video duration in seconds. Overridden when ref_videos.type=reference (matches the reference video, up to 10s).

Required range: 3 <= x <= 15

Example:

5

ref_images

object[]

Reference image groups. All items must share the same type.

Show child attributes

ref_videos

object[]

A single reference video (<=15s).

Maximum array length: 1

Show child attributes

resolution

enum<string>

default:1080p

Output video resolution.

Available options:

480p,

720p,

1080p

Example:

"1080p"

mode

enum<string>

default:std

Quality/performance mode. fast is quicker (sound must be false); std balances speed and quality.

Available options:

fast,

std

Example:

"std"

sound

boolean

default:false

Whether to generate audio. Not effective when using a video reference (the reference video's audio is used).

Example:

false

prompt_optimizer

boolean

default:true

Enable automatic prompt expansion/optimization.

Example:

true

Response

Task submitted successfully

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Detailed data about the submitted asynchronous task.

Show child attributes

Segmented camera motion Video restyling