05-Multi-Frame
Smart Multi-Frame
Document Version: v1.0.0 | Last Updated: 2026-06-11 This platform fully supports the official Vidu video generation APIs. Requests and responses are transparently proxied with identical parameter semantics.
POST https://platform.dataeyes.ai/vidu/ent/v2/multiframeRequest Parameters
Request Headers
| Header | Required | Description |
|---|---|---|
Content-Type | Yes | application/json |
Authorization | Yes | Bearer {API_KEY} |
Request Body
| Parameter | Sub-parameter | Type | Required | Description |
|---|---|---|---|---|
model | String | Yes | Model name. Options: viduq2-turbo, viduq2-pro | |
start_image | String | Yes | Start frame image. Supports Base64-encoded image or URL. Only 1 image is supported. Formats: png, jpeg, jpg, webp. Aspect ratio must be less than 1:4 or 4:1; size must not exceed 50 MB. POST body must not exceed 10MB; Base64 must include content type prefix. | |
image_settings | Array | Yes | Keyframe configuration. Minimum 2, maximum 9 keyframes per task. | |
prompt | String | Optional | Prompt for the video segment from the previous image to the current keyframe, controlling the extended video content. | |
key_image | String | Yes | Reference image for the intermediate/end frame (URL or Base64). Input order corresponds to the timeline order (from start frame to end frame). Formats: png, jpeg, jpg, webp; size must not exceed 50 MB. | |
duration | Int | Optional | Video duration between adjacent keyframes. Default 5s, range 2–7s. | |
resolution | String | Optional | Resolution. Default 720p. Options: 540p, 720p, 1080p. | |
watermark | Bool | Optional | Whether to add a watermark. Default is no watermark. | |
wm_url | String | Optional | Custom watermark image URL. | |
wm_position | String | Optional | Watermark position. Default bottom_left.Options: top_left (Top-left), top_right (Top-right), bottom_right (Bottom-right), bottom_left (Bottom-left) | |
meta_data | String | Optional | Metadata identifier, JSON format string, pass-through field. | |
payload | String | Optional | Pass-through parameter. Maximum 1048576 characters. | |
callback_url | String | Optional | Callback URL. |
Request Example
Response Parameters
| Field | Sub-field | Type | Description |
|---|---|---|---|
task_id | String | Task ID | |
state | String | Processing state: created, queueing, processing, success, failed | |
model | String | Model name used for this call | |
start_image | String | Start frame image | |
image_settings | Array | Multi-frame configuration | |
prompt | String | Prompt | |
key_image | String | Keyframe image | |
duration | Int | Duration | |
resolution | String | Resolution | |
watermark | Bool | Whether a watermark is used | |
wm_url | String | Watermark content | |
wm_position | String | Watermark position | |
meta_data | String | Metadata identifier | |
payload | String | Pass-through parameter | |
credits | Int | Number of credits consumed | |
created_at | String | Task creation time |
Response Example
{
"task_id": "{task_id}",
"state": "created",
"model": "viduq2-turbo",
"start_image": "https://example.com/start.png",
"image_settings": [
{
"key_image": "https://example.com/frame1.png",
"prompt": "camera slowly pans right",
"duration": 5
},
{
"key_image": "https://example.com/frame2.png",
"prompt": "zoom in on the subject",
"duration": 5
},
{
"key_image": "https://example.com/frame3.png",
"prompt": "fade to sunset scene",
"duration": 5
}
],
"resolution": "1080p",
"watermark": false,
"wm_url": "",
"wm_position": "bottom_left",
"meta_data": "",
"payload": "",
"credits": 40,
"created_at": "2025-01-01T15:41:31.968916Z"
}