Reference-to-Video 2.6
/api/v1/video/generationHeader Parameters
Format: Authorization: Bearer sk-xxxxxx
Configuration parameters for asynchronous processing. HTTP requests only support asynchronous mode and must be set to enable.
Request Body
application/json
Model name, fixed value: wan2.6-r2v-flash wan2.6-r2v
"wan2.6-r2v-flash" | "wan2.6-r2v"Basic input information, such as prompts.
Text prompt. Used to describe the desired elements and visual characteristics to be included in the generated video. Supports Chinese and English; each Chinese character, letter, and punctuation mark counts as one character, and any excess is automatically truncated. wan2.6-r2v-flash: Maximum length of 1500 characters. wan2.6-r2v: Maximum length of 1500 characters. Character reference instructions: Use identifiers like "character1" and "character2" to reference characters, with each reference (video or image) containing only a single character. The model identifies characters in references solely through this method. Example value: character1 is happily watching a movie on the sofa.
Negative prompt, used to describe content that should not appear in the video frame, allowing you to restrict the video output. Supports both Chinese and English, with a maximum length of 500 characters; any excess will be automatically truncated. Example values: low resolution, errors, worst quality, low quality, deformed, extra fingers, bad proportions, etc.
An array of URLs for uploaded reference files, supporting both videos and images. Used to extract character appearance and voice (if applicable) to generate videos that match the reference features. Each URL can point to either an image or a video: Number of images: 0-5. Number of videos: 0-3. Total limit: images + videos ≤ 5. When multiple reference files are provided, the character order is defined by the array order. That is, the first URL corresponds to character1, the second to character2, and so on. Each reference file must contain only one main character. For example, character1 is a little girl, and character2 is an alarm clock.
Video processing parameters, such as setting video resolution, configuring video duration, enabling intelligent prompt rewriting, and adding watermarks.
Specifies the resolution of the generated video in the format of widthheight. The default value and available enumerated values for this parameter depend on the model parameter, with the following rules: wan2.6-r2v-flash: The default value is 19201080 (1080P). Available resolutions: all resolutions corresponding to 720P and 1080P. wan2.6-r2v: The default value is 19201080 (1080P). Available resolutions: all resolutions corresponding to 720P and 1080P. 720P tier: Available video resolutions and their corresponding aspect ratios are: 1280720: 16:9. 7201280: 9:16. 960960: 1:1. 1088832: 4:3. 8321088: 3:4. 1080P tier: Available video resolutions and their corresponding aspect ratios are: 19201080: 16:9. 10801920: 9:16. 14401440: 1:1. 16321248: 4:3. 1248*1632: 3:4.
The duration of the generated video, in seconds. wan2.6-r2v-flash: An integer in the range [2, 10]. Default value is 5. wan2.6-r2v: An integer in the range [2, 10]. Default value is 5. Example value: 5.
Specifies the shot type for the generated video, indicating whether the video consists of a single continuous shot or multiple cut shots. Parameter priority: shot_type > prompt. For example, if shot_type is set to "single", even if the prompt includes "generate a multi-shot video", the model will still output a single-shot video. Optional values: single: default value, outputs a single-shot video; multi: outputs a multi-shot video. Example value: single. Type, indicating whether the video consists of a single continuous shot or multiple cut shots. Parameter priority: shot_type > prompt. For example, if shot_type is set to "single", even if the prompt includes "generate a multi-shot video", the model will still output a single-shot video. Optional values: single: default value, outputs a single-shot video; multi: outputs a multi-shot video.
Supported models: wan2.6-r2v-flash. Whether to generate video with audio. Optional values: true: Default value, outputs video with audio. false: Outputs silent video.
Whether to add a watermark. The watermark is located in the bottom-right corner of the video, and the text is fixed as "AI Generated". false: Default value, no watermark is added. true: Add a watermark.
Random seed, with a value range of [0, 2147483647].
Response Body
application/json
Success
TypeScript Definitions
Use the response body type in TypeScript.
Status Code
Data Object
Result Set
Usage Information
Number of Images
Video Duration in Seconds
Input Token Count
Total Token Count
Output Token Count
Validity Period
Task ID
Task Status
Status Information
Request ID
curl -X POST "https://api.ygw.ai/api/v1/video/generation" \ -H "Authorization: string" \ -H "X-DashScope-Async: string" \ -H "Content-Type: application/json" \ -d '{ "model": "wan2.6-r2v-flash", "input": { "reference_urls": [ "string" ] }, "parameters": {} }'{
"code": 0,
"data": {
"urls": [
"string"
],
"usage": {
"images": 0,
"seconds": 0,
"input_tokens": 0,
"total_tokens": 0,
"output_tokens": 0
},
"expired": "string",
"task_id": "string",
"task_status": "string"
},
"message": "string",
"request_id": "string"
}