Vidu Q3 Drama

Vidu Q3 Drama

Playground

Vidu Q3 Drama generates complete script-driven drama videos from scripts and structured assets, including characters, scenes, tools, and references. It plans the narrative structure, scene pacing, and transitions to create a story-driven drama in one request, supporting up to 180 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q3 Drama generates a story-driven drama video from a script and a structured asset list. It is designed for one-click drama creation: provide the story, characters, scenes, tools, and references, and the model helps organize the narrative structure, scene pacing, and final video output.

Why Choose This?

• One-click drama generation
  Generate a complete drama-style video in a single request instead of producing isolated clips one by one.

• Script-driven storytelling
  Use content to describe the full drama plot, character actions, dialogue, emotions, camera movement, and scene details.

• Structured asset control
  Define characters, scenes, and tools with IDs, names, types, reference images, and descriptions.

• Reference-based consistency
  Use asset reference images to guide character identity, scene appearance, props, and visual details.

• Flexible placement control
  Use image and placement to guide positioning, panorama, or step-based references.

• Quality and layout options
  Choose quality, resolution, aspect ratio, and style to match your drama format and visual direction.

Properties

Image Requirements

• assets.image_uri supports image URL or Base64 image data.
• Supported image formats: PNG, JPEG, JPG, and WebP.
• Base64 input should include the content type prefix, for example: data:image/png;base64,{base64_encode}.
• Each asset can correspond to one image.
• Keep image URLs publicly accessible.
• Keep images within the documented size, aspect ratio, and request body limits.

How to Use

1. Enter task name — Set name for the drama generation task.
2. Write the story — Add the full drama script or story in content.
3. Add assets — Provide characters, scenes, or tools in the assets list.
4. Set asset IDs — Use numeric strings such as 01, 02, 03, and so on.
5. Upload asset images — Provide image_uri for every asset.
6. Add asset descriptions optional — Describe identity, appearance, scene details, or tool details.
7. Add positioning reference optional — Provide image and choose placement if needed.
8. Choose output settings — Select quality, resolution, aspect ratio, duration, and style.
9. Submit — Generate the drama video.

Pricing

Pricing is based on the selected duration. The rate is $0.14 per second, calculated from $1.12 per 8 seconds.

Best Use Cases

• Short drama generation — Create story-driven drama videos from a complete script and asset list.
• Character-driven storytelling — Generate narrative clips with defined characters, scenes, tools, and references.
• Story ads — Produce short promotional stories with structured characters and plot progression.
• Serialized hooks — Create dramatic short-form hooks for episodic content or social platforms.
• Product storytelling — Use characters, scenes, and props to present a product through a narrative format.
• Creative prototyping — Quickly test story structure, scene pacing, and character presentation.

Pro Tips

• Use clear asset IDs such as 01, 02, and 03 to keep references organized.
• Provide 3–10 assets for better structure and easier scene planning.
• Write content as a complete story, including plot, actions, emotions, dialogue, camera movement, and scene details.
• Use detailed asset descriptions to clarify character identity, outfit, role, scene style, or tool appearance.
• Use high quality for a more polished drama result.
• Choose 9:16 for vertical short drama content and 16:9 for widescreen storytelling.
• Keep style concise, such as realistic, 3D modeling, or 2D animation.

## Authentication

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

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### 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 |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: `created`, `processing`, `completed`, or `failed` |
| data.created_at | string | ISO timestamp of when the request was created |
| 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 |