Vidu Q3 Ad

Vidu Q3 Ad

Playground

Vidu Q3 Ad Video generates commercial ad videos from 1 to 7 reference images with prompt guidance, supporting 720P / 1080P output and synchronized audio for product ads, brand campaigns, marketing creatives, and promotional videos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q3 Ad

Vidu Q3 Ad generates ad-oriented videos from one or more reference images and a text prompt. It is designed for product, character, and commercial scene generation, where uploaded references guide the subject appearance, visual style, and overall consistency of the generated video.

Why Choose This?

• Ad-focused reference video generation
  Use reference images to guide product, character, or scene appearance for commercial-style videos.

• Multi-image reference support
  Upload 1 to 7 images to provide visual references for the generated video.

• Flexible video length
  Generate clips from 3 to 16 seconds.

• 720p and 1080p output
  Choose 720p for lower-cost iteration or 1080p for higher-quality ad output.

• Optional synchronized audio
  Generate audio together with the video when the prompt calls for ambience, speech, or sound effects.

Parameters

How to Use

1. Upload reference images — Provide 1 to 7 clear images that define the product, character, or visual style.
2. Write the prompt — Describe the ad scene, subject action, composition, camera movement, and target mood.
3. Choose aspect ratio — Select the output layout for your target placement.
4. Choose resolution — Use 720p for lower-cost iteration or 1080p for higher-quality output.
5. Set duration — Choose a clip length between 3 and 16 seconds.
6. Configure audio optional — Keep generate_audio enabled when synchronized audio is needed.
7. Submit — Generate the ad video and retrieve the output URL.

Pricing

Pricing is based on selected resolution and duration.

Best Use Cases

• Product ads — Generate short product-focused videos from reference photos.
• Commercial storyboards — Prototype ad scenes before production.
• Social ads — Create vertical or horizontal videos for campaign testing.
• Brand visuals — Maintain subject and product consistency from reference images.
• Creative iteration — Test multiple ad directions with the same references.
• Character-based ads — Create commercial scenes using consistent reference characters.

Pro Tips

• Use reference images that are clear, high-quality, and visually distinct.
• Keep the prompt focused on ad action, camera movement, product presentation, and target mood.
• Use 720p for prompt iteration before switching to 1080p.
• Provide clean product or subject images for better consistency.
• Use a fixed seed when you need to reproduce or compare variations.
• Keep the ad concept concise and visually direct for stronger commercial output.

<ApiPage model={model}>
  ## Authentication

  For authentication details, please refer to the [Authentication Guide](/docs-authentication).

  ## API Endpoints

  ### Submit Task & Query Result

  ## Parameters

  ### Task Submission Parameters

  #### Request Parameters

  #### Response Parameters

  <SubmitResponse />

  #### Result Request Parameters

  | Parameter | Type | Required | Default | Description |
  |-----------|------|----------|---------|-------------|
  | id | string | Yes | - | Task ID |

  #### Result Response Parameters

  | Parameter | Type | Description |
  |-----------|------|-------------|
  | code | integer | HTTP status code (e.g., 200 for success) |
  | message | string | Status message (e.g., "success") |
  | data | object | The prediction data object containing all details |
  | data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
  | data.model | string | Model ID used for the prediction |
  | data.outputs | string | Array of URLs to the generated content. |
  | data.urls | object | Object containing related API endpoints |
  | data.urls.get | string | URL to retrieve the prediction result |
  | data.status | string | Status of the task: `created`, `processing`, `completed`, or `failed` |
  | data.created_at | string | ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z") |
  | data.error | string | Error message (empty if no error occurred) |
  | data.timings | object | Object containing timing details |
  | data.timings.inference | integer | Inference time in milliseconds |

</ApiPage>