# vidu/q3/drama

> 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.

## Overview

- **Endpoint**: `https://api.wavespeed.ai/api/v3/vidu/q3/drama`
- **Polling/result URL**: `https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result`
- **Model ID**: `vidu/q3/drama`
- **Category**: image-to-video

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
The API is asynchronous: submit a prediction, then poll its result URL until it completes.

### Input Schema

The API accepts the following input parameters:

- **`name`** (`string`, _required_):
  The name of the drama generation task.

- **`content`** (`string`, _required_):
  Drama content or script. Supports up to 5000 characters.

- **`assets`** (`array of object`, _required_):
  Asset list. Asset IDs are generated automatically by order as 01, 02, 03, and so on.

- **`image`** (`string`, _optional_):
  The positioning reference map uploaded by the user.

- **`placement`** (`string`, _optional_):
  Placement mode: upload, panorama, or step. Upload is the default and fastest mode. Panorama and step only take effect when upload_image_url is empty. Panorama uses a panoramic reference image. Step uses a sequential reference: pass the previous shot's four-panel grid to the next shot.
  - Default: `"panorama"`
  - Options: "panorama", "upload", "step"

- **`duration`** (`integer`, _optional_):
  Select the fixed duration for this drama clip. This model is designed for short drama fragments, storyboard shots, and scene-level clips. Supported values are 8, 9, 10, 11, and 12 seconds only. Choose the exact clip length you want to generate.
  - Default: `8`
  - Range: `2` to `30`

- **`resolution`** (`string`, _optional_):
  Video resolution.
  - Default: `"1080p"`
  - Options: "720p", "1080p"

- **`aspect_ratio`** (`string`, _optional_):
  The aspect ratio of the generated media.
  - Default: `"9:16"`
  - Options: "9:16", "16:9"

- **`style`** (`string`, _optional_):
  Video style. You can enter styles such as 3D modeling style, 2D animation style, etc. Limited to 30 characters. No punctuation allowed. Default: live action photorealistic.



**Required Parameters Example**:

```json
{
  "name": "example",
  "content": "A clear example input",
  "assets": []
}
```

**Full Example**:

```json
{
  "name": "example",
  "content": "A clear example input",
  "assets": [],
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "placement": "panorama",
  "duration": 8,
  "resolution": "1080p",
  "aspect_ratio": "9:16",
  "style": "example"
}
```

### Result Data Schema

The `data` object returned by the API has the following fields:

- **`created_at`** (`string (date-time)`, _optional_):
  ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z").

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction, the ID of the prediction to get.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`outputs`** (`array of string | object`, _optional_):
  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.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example `data` Object**:

```json
{
  "created_at": "example",
  "id": "example",
  "model": "example",
  "outputs": [],
  "status": "example",
  "urls": {}
}
```

## Usage Examples

The examples use `jq` to read JSON. Set your API key first:

```bash
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
```

### 1. Submit a prediction

```bash
REQUEST_BODY=$(cat <<'JSON'
{
  "name": "example",
  "content": "A clear example input",
  "assets": []
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url https://api.wavespeed.ai/api/v3/vidu/q3/drama \
  --header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  --header "Content-Type: application/json" \
  --data "${REQUEST_BODY}")

printf '%s\n' "${SUBMIT_RESPONSE}" | jq .
```

The response contains the prediction ID in `data.id`.

### 2. Poll until complete and read `outputs`

```bash
PREDICTION_ID=$(printf '%s' "${SUBMIT_RESPONSE}" | jq -r '.data.id')
if [ -z "${PREDICTION_ID}" ] || [ "${PREDICTION_ID}" = "null" ]; then
  printf 'Submission response did not contain data.id\n' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    --request GET \
    --url "${RESULT_URL}" \
    --header "Authorization: Bearer ${WAVESPEED_API_KEY}")

  RESULT=$(printf '%s' "${RESPONSE}" | jq -e '.data')
  STATUS=$(printf '%s' "${RESULT}" | jq -er '.status')
  case "${STATUS}" in
    completed)
      # Generated files are returned in the outputs array.
      printf '%s\n' "${RESULT}" | jq '.outputs'
      break
      ;;
    failed|cancelled|timeout|deleted)
      printf '%s\n' "${RESULT}" | jq '{status, error, code}'
      exit 1
      ;;
    *)
      sleep 2
      ;;
  esac
done
```

## Additional Resources

### Documentation

- [Model Playground](https://wavespeed.ai/models/vidu/q3/drama)
- [API Documentation](https://wavespeed.ai/docs/docs-api/vidu/vidu-q3-drama)