Vidu Q3 Reference To Video Mix

From 84 credits/sec
ae_vidu_q3_reference_to_video_mix

Create a short video from a text prompt and one to four reference images to help keep subjects or scenes consistent, with optional sound.

VideoImageAudio
From 84 credits/sec

Pricing

From 84 credits/sec
ResolutionCharge
360p / 540p84 credits/second
720p / 1080p / Not specified185 credits/second

When duration is omitted, billing is based on five seconds. Starting price applies to Resolution: 360p.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNoRandom seed for reproducibility. If None, a random seed is chosen.—
request_body.audiobooleanNoWhether to use direct audio-video generation. When true, outputs video with sound.true
request_body.promptstringYesText prompt for video generation, max 2000 characters—
request_body.durationintegerNoDuration of the video in seconds (1-16 for Q3 models)5
request_body.resolutionenum (360p | 540p | 720p | 1080p)NoOutput video resolution720p
request_body.aspect_ratioenum (16:9 | 9:16 | 4:3 | 3:4 | 1:1)NoThe aspect ratio of the output video16:9
request_body.reference_image_urlsarrayYesURLs of 1 to 4 reference images used to keep subjects or scenes consistent—

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_vidu_q3_reference_to_video_mix' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "aspect_ratio": "9:16",
      "audio": true,
      "duration": 5,
      "prompt": "A middle-aged East Asian man with round glasses, a dark navy three-piece suit and a small yellow rubber duck pin on his left chest stands in an auditorium with rows of dark chairs under warm side light. Fixed locked-off camera, fixed medium shot, absolutely no zoom, no pan, no cut, only this one person in frame. He calmly speaks this Chinese line aloud: \"局长,散场。\" His lips move in sync with the words, then he stays still and completely serious. No subtitles, no text, no watermark. The synchronized audio contains only this one Chinese male speaking voice, no background music.",
      "reference_image_urls": [
        "https://file.gw.xnetwk.net/file/d4775013-985a-48db-b41f-59ab1ab5d8d5.png",
        "https://file.gw.xnetwk.net/file/4264eec3-ac0a-4743-b6d3-adc2d398b4f5.png",
        "https://file.gw.xnetwk.net/file/477237e6-cae9-4050-ad53-61abe68b563f.png"
      ],
      "resolution": "1080p",
      "seed": 42
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "c9bac033-6e79-4e90-b3f4-1d8f9c127e40"
}