---
title: Wan2.6 | Runware Docs
url: https://runware.ai/docs/models/alibaba-wan2-6
description: Multimodal video generation with multi-shot and native sound
---
# Wan2.6

![Wan2.6](https://assets.runware.ai/covers/alibaba-wan2-6.jpg)

Wan2.6 is a multimodal video model for text to video and image to video generation with support for multi-shot sequencing and native sound. It emphasizes temporal stability, consistent visual structure across shots, and reliable alignment between visuals and audio in short form video generation.

- **Status**: live
- **ID**: `alibaba:wan@2.6`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: December 16, 2025
- **Capabilities**: Text to Video, Image to Video, Video to Video, Audio to Video, Checkpoint, Audio

## Pricing

$0.10 from, per second · ~1m 51s per request

**Rates** (per second)

- 720p: `$0.10`
- 1080p: `$0.15`

**5 example generations**

- [reference-to-video](https://runware.ai/docs/models/alibaba-wan2-6/examples#example-heritage-seed-documentary-title-sequence) · 1088×832 · 5s: `$0.50` (~1m 38s)
- [text-to-video](https://runware.ai/docs/models/alibaba-wan2-6/examples#example-inline-magnetic-separator-demo) · 1080p · 5s · audio: `$0.751` (~1m 51s)
- [audio-driven](https://runware.ai/docs/models/alibaba-wan2-6/examples#example-avalanche-patrol-series-teaser) · 960×960 · 10s: `$1.00` (~1m 51s)
- [first-frame](https://runware.ai/docs/models/alibaba-wan2-6/examples#example-marine-robotics-logo-loop) · 1080p · 10s: `$1.50` (~1m 36s)
- [multi-shot](https://runware.ai/docs/models/alibaba-wan2-6/examples#example-archive-flood-recovery-presenter-clip) · 1080p · 15s · audio: `$2.26` (~2m 52s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Either provide `inputs.frameImages`, or specify `width/height`.

---

Inside `inputs`, `frameImages` cannot be used with `referenceVideos`.

---

Inside `inputs`, `audio` cannot be used with `referenceVideos`.

---

`inputs.audio` cannot be used with `providerSettings.alibaba.audio`.

---

When `providerSettings.alibaba.shotType` is provided, `providerSettings.alibaba.promptExtend` must be `true`.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.frameImages` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `720p (16:9)` | `1280x720` |
| `720p (9:16)` | `720x1280` |
| `720p (1:1)` | `960x960` |
| `720p (4:3)` | `1088x832` |
| `720p (3:4)` | `832x1088` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (9:16)` | `1080x1920` |
| `1080p (1:1)` | `1440x1440` |
| `1080p (4:3)` | `1632x1248` |
| `1080p (3:4)` | `1248x1632` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/alibaba-wan2-6#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/alibaba-wan2-6#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/alibaba-wan2-6#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/alibaba-wan2-6#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/alibaba-wan2-6#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/alibaba-wan2-6#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/alibaba-wan2-6#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/alibaba-wan2-6#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/alibaba-wan2-6#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/alibaba-wan2-6#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/alibaba-wan2-6#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/alibaba-wan2-6#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/alibaba-wan2-6#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-wan2-6#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [frameImages](https://runware.ai/docs/models/alibaba-wan2-6#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `items: 1`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/alibaba-wan2-6#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/alibaba-wan2-6#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. This model only supports the first frame.

**Allowed values**:

- `first` First frame of the video.
- `0` Frame index 0 (first frame).

### [referenceVideos](https://runware.ai/docs/models/alibaba-wan2-6#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`

List of reference videos (UUID or URL).

### [audio](https://runware.ai/docs/models/alibaba-wan2-6#request-inputs-audio)

- **Path**: `inputs.audio`
- **Type**: `string`
- **Duration**: `0s to 30s`

Audio input (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/alibaba-wan2-6#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba:wan@2.6`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/alibaba-wan2-6#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `1500`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [negativePrompt](https://runware.ai/docs/models/alibaba-wan2-6#request-negativeprompt)

- **Type**: `string`
- **Min**: `1`
- **Max**: `500`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

- [Prompts: Negative Prompts](https://runware.ai/docs/learn/prompts#negative-prompts) (learn)

### [width](https://runware.ai/docs/models/alibaba-wan2-6#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/alibaba-wan2-6#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/alibaba-wan2-6#request-resolution)

- **Type**: `string`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `720p` `1080p`

### [duration](https://runware.ai/docs/models/alibaba-wan2-6#request-duration)

- **Type**: `integer`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

**Allowed values**: `5` `10` `15`

### [seed](https://runware.ai/docs/models/alibaba-wan2-6#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.alibaba\` object.

### [audio](https://runware.ai/docs/models/alibaba-wan2-6#request-providersettings-alibaba-audio)

- **Path**: `providerSettings.alibaba.audio`
- **Type**: `boolean`
- **Default**: `true`

Generate native audio aligned with visual content.

### [promptExtend](https://runware.ai/docs/models/alibaba-wan2-6#request-providersettings-alibaba-promptextend)

- **Path**: `providerSettings.alibaba.promptExtend`
- **Type**: `boolean`
- **Default**: `true`

Enable LLM-based prompt rewriting to expand and clarify inputs. Affects reproducibility.

### [shotType](https://runware.ai/docs/models/alibaba-wan2-6#request-providersettings-alibaba-shottype)

- **Path**: `providerSettings.alibaba.shotType`
- **Type**: `string`
- **Default**: `single`

Shot composition style.

**Allowed values**:

- `single` Continuous shot without transitions.
- `multi` Multiple shots with transitions.

## Response Parameters

### [taskType](https://runware.ai/docs/models/alibaba-wan2-6#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/alibaba-wan2-6#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/alibaba-wan2-6#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/alibaba-wan2-6#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/alibaba-wan2-6#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/alibaba-wan2-6#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/alibaba-wan2-6#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/alibaba-wan2-6#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/alibaba-wan2-6#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-6/634a88e8-5a85-4fd3-af43-ffbdaa454be3.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "6419fc26-48ba-4ccc-95cf-193744738d47",
  "model": "alibaba:wan@2.6",
  "positivePrompt": "Continuous single-shot industrial product demo in a clean food-processing test lab. A compact stainless-steel inline magnetic separator sits horizontally on a cobalt-blue support frame, with a transparent cutaway section revealing pale oat flakes flowing rapidly through the pipe. Begin in a three-quarter medium view, then make a smooth, slow camera push toward the clear chamber. A small dark steel fragment travels among the flakes; as it reaches the polished magnetic rod, it snaps firmly onto the rod while the uncontaminated flakes continue flowing into a collection bin. Keep the machine geometry stable and the capture action unmistakable. Bright diffuse daylight, crisp technical realism, restrained palette of stainless steel, cobalt blue, and warm oat beige, shallow but sufficient depth of field, no people, labels, logos, captions, or interface graphics. Synchronized native sound: steady low machinery hum, dry oat flakes softly rattling through the pipe, then a distinct metallic tick exactly when the fragment attaches to the magnet.",
  "negativePrompt": "Shot changes, transitions, camera shake, warped machinery, floating parts, duplicate fragments, clogged material, illegible text, logos, captions, interface overlays, music, voices.",
  "width": 1920,
  "height": 1080,
  "duration": 5,
  "providerSettings": {
    "alibaba": {
      "audio": true,
      "promptExtend": true,
      "shotType": "single"
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-6/d13fd194-3d56-4fe5-9d09-aa8f0b7e3cf7.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "c6667c9c-e1c7-42ad-a22e-1dff47c294a0",
  "model": "alibaba:wan@2.6",
  "positivePrompt": "Continue forward from the supplied finished logo frame as a polished ten-second motion identity. Hold the complete lockup briefly, then send the coral survey ping clockwise around the navy sonar emblem. Each pass emits a thin contour ring that expands smoothly, bends like a mapped depth line, and fades before reaching the wordmark. The emblem’s concentric lines subtly separate into layered bathymetric contours, drift with controlled fluid motion, then register back into their exact original geometry. Keep the PELAGIC ARRAY lettering and tagline perfectly stable, sharp, correctly spelled, and fully legible throughout. In the final seconds, the coral ping settles into its starting position and every contour resolves precisely to the supplied opening composition, creating a seamless first-to-last-frame loop. Locked camera, centered 16:9 layout, flat vector forms, warm off-white paper texture, deep navy and coral-orange palette, restrained Swiss oceanographic-chart art direction. Clean sonic ident: one soft hydrophone click, a low filtered sonar pulse synchronized to the expanding ring, and a quiet final water-drop tick at loop closure.",
  "resolution": "1080p",
  "duration": 10,
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/d3ebe851-4606-4da0-b84b-c35e857cb126.jpg"
    ]
  }
}
```

---

### reference-to-video (reference-to-video)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-6/d3d70201-7b0c-46c1-a606-ea508f7e9b6a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "07cc3252-7273-40b3-9b57-fe089e071fb2",
  "model": "alibaba:wan@2.6",
  "positivePrompt": "Create a 5-second cinematic opening title sequence for a prestige agricultural heritage documentary titled “THE SEED LEDGER.” Compose for 1088x832 landscape. Use reference video 1 only for its tactile archival materials, warm museum lighting, shallow-focus tracking movement and parchment, faded chlorophyll and oxidized-copper palette. Use reference video 2 only for its scientifically accurate germination detail and elegant branching motion; neither reference is footage to edit or reproduce. In one seamless macro shot, the camera glides over an aged seed-bank accession card beside a few heirloom bean seeds. A delicate root shadow grows naturally across the paper, guiding the eye toward a blind-embossed title that catches the raking light: THE SEED LEDGER. End on a composed, fully legible title frame with generous negative space. Photoreal practical textures, restrained prestige-documentary art direction, solemn but hopeful mood, subtle film grain. Native sound: drawer glide, dry seeds softly ticking on wood, faint paper friction, low bowed-cello swell resolving on the title.",
  "negativePrompt": "Illegible or misspelled title, extra words, logos, interface elements, neon colors, fantasy plants, aggressive camera shake, rapid montage, glossy commercial styling, distorted seeds, synthetic plastic textures, people or hands.",
  "width": 1088,
  "height": 832,
  "duration": 5,
  "inputs": {
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/0117ee1d-6961-4b16-a370-352ef5d56ba9.mp4",
      "https://assets.runware.ai/assets/inputs/30b4461c-16a6-4c00-9e69-7ac4cd544e3a.mp4"
    ]
  }
}
```

---

### audio-driven (audio-driven)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-6/b2350ca3-f22d-45dd-b8a6-85397e375d39.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "a0e6a58f-73c7-4912-bc46-3443148bc189",
  "model": "alibaba:wan@2.6",
  "positivePrompt": "Create a 10-second square cinematic teaser for a prestige factual series about an alpine avalanche-control crew, with every cut and action synchronized precisely to the supplied audio. 0:00–0:01: extreme macro of frost trembling on a red safety rope in blue predawn light; cut on the radio-static burst. 0:01–0:03: wide aerial view of two patrol workers in vivid vermilion jackets traversing a vast untouched white ridge, their scale tiny against the mountain; camera advances with each sub-bass pulse. At the metallic click around 0:03, cut to a gloved hand closing a weatherproof detonator case, shown as professional safety work without instructional detail. On the explosive impact at 0:04, hard cut to a distant telephoto view of a controlled charge releasing a monumental wall of powder across an empty mountainside. During the sudden quiet, hold in elegant slow motion as the snow cloud rolls through sunlight, revealing crystalline particles and pale cyan shadows. At the deep hit around 0:07.5, match-cut the white cloud into a clean white field and reveal the centered charcoal title “THE WHITE LINE” with smaller text “A DOCUMENTARY SERIES.” Restrained Swiss editorial typography, premium documentary cinematography, crisp natural textures, cold white, cyan, charcoal, and vermilion palette, tense and authoritative, generous square-safe composition.",
  "negativePrompt": "No casualties, buried people, reckless behavior, weapon imagery, instructional explosive assembly, fantasy mountains, ski-resort advertising, logos, interface elements, misspelled title text, extra captions, shaky camera, warped workers, duplicated limbs, flicker, or low-detail snow.",
  "width": 960,
  "height": 960,
  "duration": 10,
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/6e6ddef4-9eb2-4aa9-ada5-fd0e3a2998d8.mp3"
  }
}
```

---

### multi-shot (multi-shot)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-6/117900ed-1ffa-42a8-8c0b-d8a03d4bd04d.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "2840f98d-b67e-4ea7-8974-093ba56c9df6",
  "model": "alibaba:wan@2.6",
  "positivePrompt": "Create a polished 15-second vertical talking-head safety explainer in three distinct shots. Maintain perfect continuity: the same female paper conservator in her early 50s, medium-brown skin, short salt-and-pepper curls, cobalt work apron over a rust-colored shirt, and pale nitrile gloves; the same bright archive conservation lab with ivory walls, pale wood benches, blotting paper, and archival boxes. Calm, credible public-institution art direction with soft daylight and muted cobalt, rust, and warm ivory. Shot 1, 0–5 seconds: centered medium close-up, direct eye contact, she begins speaking reassuringly. Shot 2, 5–10 seconds: motivated match cut as her raised gloved hand lowers toward a damp book resting upright on absorbent paper; three-quarter waist-up angle, her face remains prominent as she gently fans several pages. Shot 3, 10–15 seconds: match cut back to a tighter frontal portrait; she finishes with a small confident nod. Natural gestures, precise lip sync, realistic blinking, stable facial identity, uninterrupted speech across cuts. She says exactly: “If a book gets wet, don’t force it open. Stand it upright, fan the pages gently, and freeze anything you can’t dry within forty-eight hours. That stops mold while you call a conservator.” Clean female voice, subtle paper movement and quiet ventilation room tone, no music, no captions, no logos.",
  "negativePrompt": "Identity changes, wardrobe changes, jumpy motion, distorted hands, damaged facial features, exaggerated gestures, theatrical acting, camera shake, noisy laboratory, background people, subtitles, labels, logos, watermarks, music.",
  "width": 1080,
  "height": 1920,
  "duration": 15,
  "providerSettings": {
    "alibaba": {
      "audio": true,
      "shotType": "multi",
      "promptExtend": true
    }
  }
}
```