SilkDock
APIVideo Generation

Kling 2.6

Configurable fields and supported values for kling-2.6.

Model ID

kling-2.6

Capabilities

CapabilitySupported value
Text-to-videoYes
Image-to-videoYes
Multi-image / reference videoMotion reference only
Start/end framesNo
Motion transferYes
Audio inputNo
Generated audioYes
Resolution720p, 1080p
Aspect ratio16:9, 9:16
Duration (seconds)Any integer from 5 to 10

Configurable fields

FieldRequiredNotes
modelYesMust be kling-2.6.
promptYesVideo description or transformation instruction.
secondsNoMust use the supported range or fixed values above.
input_referenceConditionalSingle reference image URL; provide for image-to-video and omit for text-to-video.
sizeNoLegacy pixel dimensions. Prefer extra_body.resolution and extra_body.aspect_ratio.
extra_body.resolutionNoSelect one supported resolution above.
extra_body.aspect_ratioNoSelect one supported ratio above; omit when the ratio follows the reference image.
extra_body.motion_ref_urlNoMotion reference video URL for motion transfer.
extra_body.motion_ref_urlsNoMultiple motion-reference video URLs when supported.
extra_body.motion_modeNostd or pro.
extra_body.character_orientationNoimage or video.
extra_body.keep_original_soundNoPreserve sound from the motion-reference video.
extra_body.camera_controlNoMotion camera-control object.
extra_body.background_toleranceNoMotion background tolerance.
extra_body.generate_audioNoWhether to generate audio in the output video.
extra_body.negative_promptNoContent or visual traits to avoid.
extra_body.seedNoInteger random seed.

Do not send unsupported audio, frame, reference, or private provider fields. Account availability is determined by the model list API.

Example

{
  "model": "kling-2.6",
  "prompt": "A cinematic tracking shot through a coastal city",
  "seconds": 5,
  "extra_body": {
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }
}

Last updated on

On this page