Domestic Video Model Generation

Submit domestic video tasks using `POST /v1/videos`.

POSThttps://zx1.deepwl.net/v1/videos
Request
curl -X POST https://zx1.deepwl.net/v1/videos \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '
{
  "model": "Kling-3.0-Omni",
  "prompt": "The camera circles around the building and uses a Hitchcock zoom",
  "seconds": "15",
  "size": "720x1280",
  "metadata": {
    "scene_type": "motion_control",
    "motion_level": "pro",
    "file_infos": [
      {
        "type": "Url",
        "category": "Video",
        "url": "https://example.com/motion-ref.mp4"
      }
    ],
    "output_config": {
      "duration": 15,
      "resolution": "720P",
      "aspect_ratio": "9:16",
      "audio_generation": "Enabled"
    }
  }
}'

Submit domestic video tasks via POST /v1/videos. Supports text-to-video, image-to-video, first/last frame, motion control, digital human, lip sync, template effects, and more. Extended parameters are passed through metadata.

Request Headers

Authorizationstring必填

Authentication header. Uses a Bearer token, e.g. Bearer YOUR_API_KEY.

Content-Typestring必填

Request content type, must be application/json.

Request Body

modelstring必填

Model name. You can pass either a base model directly or a bundled billing model.

promptstring必填

Prompt.

secondsstring | integer

Duration. The top-level seconds has the highest priority.

durationinteger

Duration compatibility field.

sizestring

Quick size field, such as 720x1280 or 1280x720.

imagestring

Single reference image or first-frame image.

imagesarray<string>

Multiple reference images.

input_referencestring | array<string>

Reference image input, compatible with URL, base64, data URI, and file upload.

metadataobject

Extended parameters. Commonly used metadata.output_config, scene_type, motion_level, offpeak, video_url, file_infos, ext_info.

Request Examples

Scenarios

ScenarioKey Fields
Text-to-videoprompt + seconds
Image-to-videoimage / images / input_reference
First and last frameimage + metadata.last_frame_url
Motion controlmetadata.scene_type=motion_control + video reference
Digital humanmetadata.scene_type=avatar_i2v
Lip syncmetadata.scene_type=lip_sync
Template effectsmetadata.scene_type=template_effect

Rules

  • seconds / duration can be placed at the top level or in metadata
  • The top-level duration has the highest priority
  • scene_type=motion_control must provide a video reference
  • scene_type=lip_sync is counted as 5 seconds if it is less than 5 seconds
  • FileInfos can contain up to 3 items

metadata.output_config

Common fields:

  • resolution
  • aspect_ratio
  • audio_generation
  • duration
  • person_generation
  • input_compliance_check
  • output_compliance_check
  • enhance_switch
  • frame_interpolate
  • logo_add