R2V (Reference-Generated Video)

POST

/aliyun/api/v1/services/aigc/video-generation/video-synthesis

Supported models:
wan2.6-r2v (supports generating videos with multiple shots and maintains subject consistency during shot transitions)

Detailed explanation of some parameters

Parameter name	Type	Core description & constraint rules
input.negative_prompt	string	Optional, excludes unwanted elements in the画面 to optimize generation quality ✅ Supports Chinese and English, with characters ≤ 500; excess will be automatically truncated 📌 It is recommended to accurately describe negative features such as image quality, composition, and characters
parameters.shot_type	string	Optional, specifies the shot structure, with higher priority than `input.prompt` ✅ Only `single` (single shot, default) / `multi` (multiple shots) are optional 📌 When set to `single`, the multi-shot description in the prompt is ignored
parameters.watermark	boolean	Optional, controls whether to add the official watermark ✅ Only `false` (no watermark, default) / `true` (add watermark) are optional 📌 The watermark is fixed at the bottom right corner, with the text "AI generated", which cannot be customized

Asynchronous processing
This interface adopts an asynchronous processing mode:

After calling the interface, a task_id is returned immediately

Use task_id to poll and query the task status

Obtain the video result after the task is completed

The task usually takes 1-5 minutes to complete, and the specific time depends on the queue situation and service load.

Price:
wan2.6-r2v 720P 0.1ptc/second, 1080p 0.15ptc/second

Request

Header Params

Body Params application/json

Example

{
    "model": "wan2.6-r2v",
    "input": {
        "prompt": "the dog (reference1) is in the room(reference2)",
        "negative_prompt": "Low resolution, errors, worst quality, low quality, incompleteness, extra fingers, poor proportions, etc.",
        "reference_video_urls": [
            "https://file.302.ai/gpt/resource302db/20251217/8a35dc989353434a897c7e65aa1e9b94.mp4",
            "https://file.302.ai/gpt/resource302db/20251217/ea3188010b7e4c779115e5dc80a69532.mp4"
        ]
    },
    "parameters": {
        "size": "1920*1080",
        "duration": 5,
        "shot_type": "single",
        "watermark": false,
        "seed": 12345
    }
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/aliyun/api/v1/services/aigc/video-generation/video-synthesis' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "wan2.6-r2v",
    "input": {
        "prompt": "the dog (reference1) is in the room(reference2)",
        "negative_prompt": "Low resolution, errors, worst quality, low quality, incompleteness, extra fingers, poor proportions, etc.",
        "reference_video_urls": [
            "https://file.302.ai/gpt/resource302db/20251217/8a35dc989353434a897c7e65aa1e9b94.mp4",
            "https://file.302.ai/gpt/resource302db/20251217/ea3188010b7e4c779115e5dc80a69532.mp4"
        ]
    },
    "parameters": {
        "size": "1920*1080",
        "duration": 5,
        "shot_type": "single",
        "watermark": false,
        "seed": 12345
    }
}'

Responses

🟢200success

application/json

Body

Example

{
    "request_id": "10350f4f-7e3b-4866-93fd-80f82591fb77",
    "output": {
        "task_id": "7e6aa5a6-6189-46e9-a963-8c144ad38bd8",
        "task_status": "PENDING"
    }
}

Modified at 2025-12-18 06:50:52

T2V (Text-to-Video Alibaba Cloud)

wan2.2-animate-move(Image-to-Motion)