Other Generating
POST https://api.vidu.com/ent/v2/image2dance
Field | Type | Required | Description |
|---|---|---|---|
image_url | string | Required | User Input Image • File Format: JPG、JPEG、PNG、BMP、WEBP。 • Aspect_ratio: The width and height of the image are within the range of [200, 4096] pixels, and the aspect ratio is in the range of 1:3 to 3:1. • File Size: <= 5MB。 • Content: There is only one person in the picture, facing the camera, with a complete and unobstructed face, and a moderate proportion in the picture to avoid being too large or too small. |
video_url | string | Required | User Input Reference Action Video • File Format: MP4、AVI、MOV。 • Duration: 2~30s。 • Aspect_ratio: The width and height of the video are within the range of [200, 2048] pixels, with an aspect ratio ranging from 1:3 to 3:1. • File Size: <= 200MB。 • Content: There is only one person in the picture, facing the camera, with a complete and unobstructed face, and a moderate proportion in the picture to avoid being too large or too small. |
payload | String | Optional | transparent transmission parameters No processing, only data transmission, with a maximum length of 1048576 characters |
callback_url | String | Optional | Callback When creating a task, you need to actively set the callback_url with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the Get Generation API. The "status" in the callback response includes the following states: - processing: Task is being processed. - success: Task is completed (if sending fails, it will retry the callback three times). - failed: Task failed (if sending fails, it will retry the callback three times). Vidu uses a callback signature algorithm for verification, check out the details here: Callback Signature |
Field | Type | Description |
|---|---|---|
task_id | String | Vidu task_id |
state | String | It will be returned to a specific processing state: - created created task successfully - queueing task in queue - processing processing - success generation successful - failed task failed |
image_url | string | The image used for this call |
video_url | string | The video used for this call |
payload | String | The payload parameter used for this call |
credits | Int | The credits used for this call |
created_at | String | Task creation time |
{ "task_id": "your_task_id_here", "state": "created", "image_url": "your_image_url", "video_url": "your_video_url", "payload":"", "credits":credits_number, "created_at": "2025-01-01T15:41:31.968916Z" }
- Ensure that the input image has a similar proportion to the character frame in the reference video.
- Try to keep the body proportions of the characters in the pictures and videos consistent.
- Use high-definition materials, avoid blurry images and low frame rate videos, and ensure accurate detail recognition.
- The video resolution and scale are the same as the original image