Theme
Vidu start-end frame to video
Submit a start-and-end frame video generation task.
http
POST /vidu/ent/v2/start-end2videoAvailable models
| Model | Description |
|---|---|
| Q3 flagship; direct audio/video output | |
| Q2 Pro | |
| Q2 turbo | |
| Q2 Pro fast | |
| Clear visuals, stable camera | |
| Q1 classic | |
| Version 2.0 |
Headers
| Name | Type | Required | Description |
|---|---|---|---|
| string | Yes | Request authentication. Use a Bearer Token, for example: . | |
| string | Yes | Request content type; must be . |
Request body
| Name | Type | Required | Description |
|---|---|---|---|
| string | Yes | Model name. See Available models above. | |
| array | Yes | Images (first + last frame). Two images: the first is the start frame, the second is the end frame. Note 1: resolutions must be similar; start/end resolution ratio must be between 0.8 and 1.25. Note 2: aspect ratio must be less extreme than 1:4 or 4:1. Note 3: Base64 or image URL. Note 4: formats png, jpeg, jpg, webp. Note 5: max 50 MB each. Note 6: HTTP POST body max 20 MB; Base64 encoding must include a content-type prefix, for example: . | |
| string | No | Text prompt. Text description of the video. Ignored when recommended prompts are used. | |
| boolean | No | Direct audio/video output. : video with dialogue and ambient audio; : silent video. | |
| string | No | Voice ID for the video audio. Auto-recommended when empty. Note: ignored for q3 models. | |
| boolean | No | Whether to use recommended prompts. : system auto-recommends prompts; : generate from the input prompt. | |
| boolean | No | Background music. : pick suitable music from the preset BGM library; : no BGM. | |
| integer | No | Video duration in seconds. series: default 5s, range 1–10s. | |
| integer | No | Random seed. Omit or pass 0 for a random seed; set manually to use a fixed seed. | |
| string | No | Resolution. Default depends on model and duration. (1–10s): default 720p; options 540p, 720p, 1080p. | |
| boolean | No | Off-peak mode. : generate during off-peak hours; : generate immediately. | |
| boolean | No | Whether to add a watermark. : add watermark; : no watermark. | |
| integer | No | Watermark position. : top-left; : top-right; : bottom-right; : bottom-left. | |
| string | No | Watermark image URL. Default watermark when omitted: "AI-generated content". | |
| string | No | Passthrough parameter. Not processed; transmitted as-is. | |
| string | No | Metadata identifier. JSON string; passthrough field. |
Request example
bash
curl -X POST https://octopusx.ai/vidu/ent/v2/start-end2video \
-H "Authorization: Bearer <token>" \
-H "Content-Type: application/json" \
-d '
{
"model": "viduq3-pro",
"images": [
"https://example.com/first-frame.png",
"https://example.com/last-frame.png"
],
"prompt": "Smooth transition",
"audio": false,
"is_rec": false,
"bgm": false,
"duration": 5,
"seed": 0,
"resolution": "720p"
}'Response example
json
{
"task_id": "48038932-0ff5-4251-8b4b-7a76c09fd114",
"status": "processing",
"created_at": 1774494511
}Response fields
| Name | Type | Description |
|---|---|---|
| string | Task ID, used to query task status. | |
| string | Task status. Options: (in progress), (failed), (completed). | |
| integer | Creation timestamp (Unix timestamp). |