wan-2.6-reference-to-video-flash

Wan2.6-r2v-flash is the fast reference-driven video generation model from Alibaba's Tongyi Wanxiang 2.6 series. It supports uploading up to 5 URL to generate new videos based on character identity, style, and scene layout from the references. This version offers faster generation speed, supports both 720P and 1080P resolutions, offers 2-10 seconds duration options, can generate videos with or without audio, and supports both single-shot and multi-shot narrative modes.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "prompt": "Instruction: Use the uploaded video for the environment, lighting, and car reference. Use the uploaded line-art image for the character reference. Style: Cinematic, hyper-realistic, blockbuster movie aesthetic. Transform the line-art character into a fully textured, photorealistic human matching the lighting. Action Sequence: > 1. The young woman with the high ponytail and dagger (from the image) is already sitting in the driver's seat of the red convertible on the cliffside. 2. The scene retains the original stunning coastal sunset and crashing waves. 3. She confidently starts the engine. The car's headlights abruptly turn on, illuminating the rugged dirt road ahead. 4. The camera pans dynamically as she hits the gas, driving the red convertible forward and accelerating away along the coastal cliff road, leaving a trail of dust in the twilight.",
    "videoUrls": [
        "https://www.runninghub.cn/view?filename=d5df0be91e2ebb303524342a417ef0cbf9e176348e70e6c191ef7ae44baa5ce7.mp4&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzMxNDU2NTIzMTUsInRzIjoxNzcyNTQwODUyMzE1LCJzaWduIjoiMGJmN2E2OTc4MTZkMWQwMzY4YzJlMjEzY2U5YTJmMDMifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.9373392566245509"
    ],
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=035b95c2ce2cf2cf02ba1f26b9eca593096c23d8bf49003fd0584fe87d404d2f.jpg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzMxNDU2NTIzMTUsInRzIjoxNzcyNTQwODUyMzE1LCJzaWduIjoiMGJmN2E2OTc4MTZkMWQwMzY4YzJlMjEzY2U5YTJmMDMifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.04044039319468362"
    ],
    "size": "1920*1080",
    "duration": "5",
    "shotType": "single",
    "audio": 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/alibaba/wan-2.6/reference-to-video-flash' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "prompt": "Instruction: Use the uploaded video for the environment, lighting, and car reference. Use the uploaded line-art image for the character reference. Style: Cinematic, hyper-realistic, blockbuster movie aesthetic. Transform the line-art character into a fully textured, photorealistic human matching the lighting. Action Sequence: > 1. The young woman with the high ponytail and dagger (from the image) is already sitting in the driver'\''s seat of the red convertible on the cliffside. 2. The scene retains the original stunning coastal sunset and crashing waves. 3. She confidently starts the engine. The car'\''s headlights abruptly turn on, illuminating the rugged dirt road ahead. 4. The camera pans dynamically as she hits the gas, driving the red convertible forward and accelerating away along the coastal cliff road, leaving a trail of dust in the twilight.",
    "videoUrls": [
        "https://www.runninghub.cn/view?filename=d5df0be91e2ebb303524342a417ef0cbf9e176348e70e6c191ef7ae44baa5ce7.mp4&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzMxNDU2NTIzMTUsInRzIjoxNzcyNTQwODUyMzE1LCJzaWduIjoiMGJmN2E2OTc4MTZkMWQwMzY4YzJlMjEzY2U5YTJmMDMifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.9373392566245509"
    ],
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=035b95c2ce2cf2cf02ba1f26b9eca593096c23d8bf49003fd0584fe87d404d2f.jpg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzMxNDU2NTIzMTUsInRzIjoxNzcyNTQwODUyMzE1LCJzaWduIjoiMGJmN2E2OTc4MTZkMWQwMzY4YzJlMjEzY2U5YTJmMDMifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.04044039319468362"
    ],
    "size": "1920*1080",
    "duration": "5",
    "shotType": "single",
    "audio": 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\": {}}"
}