多元探索 API多元探索 API
Official Format

Vidu Image-to-Video

Submit a first-frame image video generation task using `POST /vidu/ent/v2/img2video`.

POSThttps://zx1.deepwl.net/vidu/ent/v2/img2video
Request
curl -X POST https://zx1.deepwl.net/vidu/ent/v2/img2video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '
{
  "model": "viduq3-pro",
  "images": ["https://example.com/first-frame.png"],
  "prompt": "让人物向前走并微笑",
  "audio": true,
  "is_rec": false,
  "bgm": false,
  "duration": 5,
  "seed": 0,
  "resolution": "720p",
  "off_peak": false,
  "watermark": false
}'
Response
{
  "task_id": "48038932-0ff5-4251-8b4b-7a76c09fd114",
  "status": "processing",
  "created_at": 1774494511
}

The official Vidu image-to-video API, submitted as application/json, supports first-frame image video generation. After a successful submission, the task task_id and status are returned; poll the result later with Query Task.

Supported Models

  • viduq3-pro: Efficiently generates high-quality audio and video content, making videos more vivid, realistic, and three-dimensional
  • viduq2-pro / viduq2-turbo: New models with good results and rich details
  • viduq2-pro-fast: Lowest price, fast generation speed
  • viduq1 / viduq1-classic: Clear visuals, stable camera movement
  • vidu2.0: Fast generation speed

Request Headers

Authorizationstring必填

Authentication header. Uses a Bearer token, e.g. Bearer YOUR_API_KEY.

Content-Typestring必填

Request content type, must be application/json.

Request Body

modelstring必填

Model name. Supports viduq3-pro, viduq2-pro, viduq2-turbo, viduq2-pro-fast, viduq1, viduq1-classic, and vidu2.0.

imagesarray必填

First-frame image. Only 1 image is supported. Supports image Base64 encoding or image URL. Image formats: png, jpeg, jpg, webp. The image ratio must be less than 1:4 or 4:1, and the image size must not exceed 50 MB.

promptstring

Text prompt. The text description for video generation. If you use the is_rec recommended prompt parameter, the model will ignore the prompt entered in this parameter.

audioboolean

Audio and video direct output. true: output a video with dialogue and background sound; false: output a silent video.

voice_idstring

Voice ID. Used to determine the voice timbre in the video. If empty, the system will automatically recommend one. Note: does not take effect for q3 models.

is_recboolean

Whether to use recommended prompts. true: the system automatically recommends prompts (number of recommended prompts = 1); false: generate video based on the input prompt.

bgmboolean

Background music. true: the system will automatically select suitable music from the preset BGM library and add it; false: do not add BGM.

durationinteger

Video duration (seconds). viduq2 series: default 5 seconds, optional 1-10 seconds.

seedinteger

Random seed. If not provided or set to 0, a random number is used. If manually set, the specified seed is used.

resolutionstring

Resolution. The default value depends on the model and video duration. viduq2 (1-10 seconds): default 720p, optional 540p, 720p, 1080p.

off_peakboolean

Off-peak mode. true: generate video during off-peak hours; false: generate video immediately.

watermarkboolean

Whether to add a watermark. true: add watermark; false: do not add watermark.

wm_positioninteger

Watermark position. 1: top-left; 2: top-right; 3: bottom-right; 4: bottom-left.

wm_urlstring

Watermark image URL. If not provided, the default watermark "Content generated by AI" is used.

payloadstring

Pass-through parameter. No processing is performed; data is only transmitted.

meta_datastring

Metadata identifier. A JSON-formatted string, pass-through field.

Request Examples

Response Examples

Response Fields

task_idstring

Task ID, used to query the task status.

statusstring

Task status. Possible values: processing (in progress), failed (failed), completed (completed).

created_atinteger

Creation timestamp (Unix timestamp).