kling-video-o1-std/refrence-to-video

POST

/openapi/v2/kling-video-o1-std/refrence-to-video

Kling Omni Video O1 (Reference-to-Video) is a groundbreaking multi-modal model from Kuaishou, designed to generate creative scenarios while maintaining absolute subject identity. By utilizing advanced feature extraction from multiple reference viewpoints, it preserves the consistent appearance of characters, props, and scene elements throughout the video. This "Identity Lock" technology allows creators to place familiar subjects into entirely new environments with fresh poses and camera movements. It offers unparalleled creative freedom by balancing stable character replication with dynamic motion control, making it an essential tool for high-end, subject-driven video production.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "mode": "std",
    "prompt": "A wide-angle landscape shot showing two distinct characters in the wet cyberpunk street scene from the reference video. Character 1 (The Intruder): Based on the image reference, a martial arts hero stands within the scene.  Character 2 (The Original): The original mecha character from the reference video is also present, standing further back in the mid-ground. The mecha character has stopped walking and is turned around, staring at the Daxia. Crucial: Do not replace the mecha character; both subjects must be visible simultaneously in a tense standoff. The camera does not move, capturing both figures under the neon rain.",
    "aspectRatio": "9:16",
    "duration": "5",
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=cb2937df1e9e8539d3f2557cae93ecd186e6f2d3e96689bfe8d969728002bf14.jpg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NjkyMzg5MTg3MzIsInRzIjoxNzY4NjM0MTE4NzMyLCJzaWduIjoiYjYyZDhjNDA2MmUyNGJmOGZlNTBiNzc1ZjFmYjJhMjAifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.20447935963965114"
    ],
    "videoUrl": "https://www.runninghub.cn/view?filename=ca0eebc3bbbccd4955fbb94fc1d894cc877af789eb459e1c06c93d2386c9e143.mp4&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NjkyMzg5MTg3MzIsInRzIjoxNzY4NjM0MTE4NzMyLCJzaWduIjoiYjYyZDhjNDA2MmUyNGJmOGZlNTBiNzc1ZjFmYjJhMjAifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.9694981195130881",
    "keepOriginalSound": true
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://www.runninghub.ai/openapi/v2/kling-video-o1-std/refrence-to-video' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "mode": "std",
    "prompt": "A wide-angle landscape shot showing two distinct characters in the wet cyberpunk street scene from the reference video. Character 1 (The Intruder): Based on the image reference, a martial arts hero stands within the scene.  Character 2 (The Original): The original mecha character from the reference video is also present, standing further back in the mid-ground. The mecha character has stopped walking and is turned around, staring at the Daxia. Crucial: Do not replace the mecha character; both subjects must be visible simultaneously in a tense standoff. The camera does not move, capturing both figures under the neon rain.",
    "aspectRatio": "9:16",
    "duration": "5",
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=cb2937df1e9e8539d3f2557cae93ecd186e6f2d3e96689bfe8d969728002bf14.jpg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NjkyMzg5MTg3MzIsInRzIjoxNzY4NjM0MTE4NzMyLCJzaWduIjoiYjYyZDhjNDA2MmUyNGJmOGZlNTBiNzc1ZjFmYjJhMjAifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.20447935963965114"
    ],
    "videoUrl": "https://www.runninghub.cn/view?filename=ca0eebc3bbbccd4955fbb94fc1d894cc877af789eb459e1c06c93d2386c9e143.mp4&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NjkyMzg5MTg3MzIsInRzIjoxNzY4NjM0MTE4NzMyLCJzaWduIjoiYjYyZDhjNDA2MmUyNGJmOGZlNTBiNzc1ZjFmYjJhMjAifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.9694981195130881",
    "keepOriginalSound": true
}'

Responses

🟢200成功

application/json

Task result query endpoint: /openapi/v2/query

Body

Examples

Submit response exampleTask success response example

{
    "taskId": "2013508786110730241",
    "status": "RUNNING",
    "errorCode": "",
    "errorMessage": "",
    "results": null,
    "clientId": "f828b9af25161bc066ef152db7b29ccc",
    "promptTips": "{\"result\": true, \"error\": null, \"outputs_to_execute\": [\"4\"], \"node_errors\": {}}"
}

Modified at 2026-03-10 12:42:16

seedance-2.0-fast/multimodal-video

seedance-v1-lite-reference-to-video