kwaivgi/kling-video/3.0/omni/pro/reference-to-video
Generate a video from multiple reference images and text guidance with Kling 3.0 Omni Pro.
Input
Take @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Additional reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images + start image).
Video duration in seconds. Allowed values: 3, 4, 5, 6, 7, 8, 9, 10.
Elements (characters/objects) to include in the video. Reference in prompt as @Element1, @Element2, etc. Maximum 7 total (elements + reference images + start image).
The aspect ratio of the generated image. Allowed values: 16:9, 9:16, 1:1.
Idle
Example output — click Run to generate your own
Production endpoint
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
POST
https://api.sandbase.ai/v1/runModel ID
kwaivgi/kling-video/3.0/omni/pro/reference-to-video01
Input Schema
5 parameters · 2 required · 3 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
images | string[] | Required | Additional reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images + start image). |
prompt | string | Required | Take @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order. · Max length: 2500 |
duration | integer | Optional | Video duration in seconds. · Options: 3, 4, 5, 6, 7, 8, 9, 10 · Default: 5 345678910 |
elements | object[] | Optional | Elements (characters/objects) to include in the video. Reference in prompt as @Element1, @Element2, etc. Maximum 7 total (elements + reference images + start image). |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 16:9, 9:16, 1:1 16:99:161:1 |
02
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
03
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "kwaivgi/kling-video/3.0/omni/pro/reference-to-video",
"images": [
"https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/reference-to-video/input_images_0.png",
"https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/reference-to-video/input_images_1.png"
],
"prompt": "Take @Image1 as the start frame. Start with a high-angle satellite view of the ancient greenhouse ruin surrounded by nature. The camera swoops down and flies inside the building, revealing the character from @Element1 standing in the sun-drenched center. The camera then seamlessly transitions into a smooth 180-degree orbit around the character, moving to the back view. As the open backpack comes into focus, the camera continues to push forward, zooming deep inside the bag to reveal the glowing stone from @Element2 nestled inside. Cinematic lighting, hopeful atmosphere, 35mm lens. Make sure to keep it as the style of @Image2.",
"duration": 5,
"elements": [
{
"frontal_image_url": "https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/reference-to-video/input_element_0.png",
"reference_image_urls": [
"https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/reference-to-video/input_element_1.png",
"https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/reference-to-video/input_element_2.png"
]
},
{
"frontal_image_url": "https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/reference-to-video/input_element_3.png",
"reference_image_urls": [
"https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/reference-to-video/input_element_4.png"
]
}
]
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Kling 3.0 Omni Pro Reference to Video
Generate a video from multiple reference images and text guidance with Kling 3.0 Omni Pro.
Overview
- Model:
kwaivgi/kling-video/3.0/omni/pro/reference-to-video - Category: reference-to-video
- Best for subject or element reference workflows where several images guide the generated video.
Pricing
$0.112 per second. A 5s video costs $0.56.
API Information
- Input: Prompt, images reference array, optional aspect_ratio, and duration.
- Output: MP4 video URL.
- Execution: async queue submission with polling for the final result.