Kling 3.0 — Image-to-Video Elements

Generate videos with character reference elements using Kling 3.0 via PixelByte API

POST /v1/jobs/submit

Kling 3.0 — Image-to-Video Elements

cURL

curl --request POST \
  --url https://api.muvi.video/v1/jobs/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": {
    "prompt": "<string>",
    "image_url": "<string>",
    "elements": [
      {
        "characterImages": [
          {}
        ],
        "type": "<string>",
        "name": "<string>",
        "voice": "<string>"
      }
    ],
    "quality": "<string>",
    "duration": "<string>",
    "aspect_ratio": "<string>"
  }
}
'

200

{
  "jobId": "<string>",
  "status": "<string>",
  "estimatedCompletionTime": "<string>",
  "costMicroCents": 123
}

Generate videos from an input image, prompt, and character reference elements with Kling 3.0. Supports multi-character compositions, std/pro quality tiers, and durations from 3 to 15 seconds.

Property	Value
Provider	Kling
Model	Kling 3.0
Capability	Image-to-Video Elements
Base Cost	85,000 micro-cents/second ($0.085/sec)
Processing Time	~240 seconds

Request Body

model · string · required

Model slug. Use kling/kling-elements-i2v-v3/image-to-video-elements.

input · object · required

Input parameters for image-to-video elements generation.

Hide properties

prompt · string · required

Text description of the video to generate (max 2500 characters).

image_url · string · required

URL of the input scene image.

elements · array · required

Array of character reference elements used to compose the video.

Show element properties

characterImages · array · required

Character reference image URLs (1–4 items). The first image is the main reference; additional images provide extra angles.

type · string

Element type. Default: IMAGE. Options: IMAGE, VIDEO.

name · string

Element name (auto-generated if empty).

voice · string

Voice audio URL.

quality · string

Generation quality. Default: std. Options: std, pro.

duration · string

Video duration in seconds. Default: 5. Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.

aspect_ratio · string

Video aspect ratio. Default: 16:9. Options: 16:9, 9:16, 1:1.

webhookUrl · string

HTTPS URL to receive a webhook notification when the job completes or fails.

Pricing

Base cost: 85,000 micro-cents per second ($0.085/sec)

finalCost = baseCost × duration × quality

Factor	Option	Multiplier
Duration	3	3x
	4	4x
	5	5x
	6	6x
	7	7x
	8	8x
	9	9x
	10	10x
	11	11x
	12	12x
	13	13x
	14	14x
	15	15x
Quality	std	1x
	pro	1.5x

Default cost: 5 seconds, std quality = 85,000 × 5 × 1 = 425,000 micro-cents ($0.425)

Response

jobId · string

Unique identifier for the submitted job.

status · string

Initial job status. Always "pending" on successful submission.

estimatedCompletionTime · string

ISO 8601 timestamp of the estimated completion time.

costMicroCents · number

The cost of the job in micro-cents.

Code Examples

cURL

curl -X POST https://api.muvi.video/v1/jobs/submit \
  -H "Authorization: Bearer $PIXELBYTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling/kling-elements-i2v-v3/image-to-video-elements",
    "input": {
      "prompt": "Two friends greet each other and walk into a sunlit cafe",
      "image_url": "https://example.com/image.jpg",
      "elements": [
        {
          "characterImages": ["https://example.com/image.jpg"],
          "type": "IMAGE",
          "name": "Character A"
        }
      ],
      "quality": "std",
      "duration": "5",
      "aspect_ratio": "16:9"
    }
  }'