---
title: Wan2.7 | Runware Docs
url: https://runware.ai/docs/models/alibaba-wan2-7
description: Multimodal video generation with reference consistency, video editing, and native audio
---
# Wan2.7

![Wan2.7](https://assets.runware.ai/covers/alibaba-wan2-7.jpg)

Wan2.7 is Alibaba's next-generation multimodal video model supporting text-to-video, image-to-video, reference-to-video, and video editing. It features multi-shot storytelling, subject-consistent multi-character generation, first-and-last-frame interpolation, video continuation, style transfer, instruction-based editing, and audio-conditioned generation with auto-dubbing. Output at 720p or 1080p, 30 FPS in multiple aspect ratios.

- **Status**: live
- **ID**: `alibaba:wan@2.7`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: April 3, 2026
- **Capabilities**: Text to Video, Image to Video, Video to Video, Audio to Video, Checkpoint, Audio

## Pricing

$0.10 from, per second · ~3m 7s per request

**Rates** (per second)

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

**5 example generations**

- [first-last-frame](https://runware.ai/docs/models/alibaba-wan2-7/examples#example-night-shift-lyric-video-segment) · 720p · 7s · audio: `$0.708` (~1m 6s)
- [first-frame](https://runware.ai/docs/models/alibaba-wan2-7/examples#example-urban-beekeeping-suit-showcase-reel) · 1080p · 5s · audio: `$0.756` (~51s)
- [audio-driven](https://runware.ai/docs/models/alibaba-wan2-7/examples#example-ice-core-archive-safety-presenter) · 720p · 8s: `$0.803` (~3m 7s)
- [reference-to-video](https://runware.ai/docs/models/alibaba-wan2-7/examples#example-natural-indigo-workshop-b-roll) · 1088×832 · 10s · audio: `$1.00` (~6m 40s)
- [text-to-video](https://runware.ai/docs/models/alibaba-wan2-7/examples#example-municipal-noir-limited-series-teaser) · 1080p · 15s · audio: `$2.25` (~6m 58s)

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

## Compatibility & Validation

Provide exactly one of: `inputs.frameImages` or `width/height`.

---

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

---

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

---

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

---

When `inputs.frameImages` is not provided, `positivePrompt` is required.

---

When `inputs.referenceImages` or `inputs.referenceVideos` is provided, `duration` must be at most `10`.

---

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

---

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

---

When `settings.shotType` is provided, `inputs.referenceImages` or `inputs.referenceVideos` is required.

---

When `settings.shotType` is `multi`, `settings.promptExtend` must be `true`.

---

`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-wan2-7#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/alibaba-wan2-7#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-wan2-7#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/alibaba-wan2-7#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-wan2-7#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-wan2-7#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-wan2-7#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-wan2-7#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-wan2-7#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/alibaba-wan2-7#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-wan2-7#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-wan2-7#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-wan2-7#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-wan2-7#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.

### [referenceImages](https://runware.ai/docs/models/alibaba-wan2-7#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `items: 1`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/alibaba-wan2-7#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`

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.
- **2 images**: First and last frames.

**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"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

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

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/alibaba-wan2-7#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-wan2-7#request-inputs-frameimages-format-2-frame)

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

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

### [referenceVideos](https://runware.ai/docs/models/alibaba-wan2-7#request-inputs-referencevideos)

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

List of reference videos (UUID or URL).

### [audio](https://runware.ai/docs/models/alibaba-wan2-7#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-wan2-7#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba:wan@2.7`

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-wan2-7#request-positiveprompt)

- **Type**: `string`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Max**: `5000`

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-wan2-7#request-negativeprompt)

- **Type**: `string`
- **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-wan2-7#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-wan2-7#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-wan2-7#request-resolution)

- **Type**: `string`
- **Default**: `1080p`

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-wan2-7#request-duration)

- **Type**: `integer`
- **Min**: `2`
- **Max**: `15`
- **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).

### [seed](https://runware.ai/docs/models/alibaba-wan2-7#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.

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [audio](https://runware.ai/docs/models/alibaba-wan2-7#request-settings-audio)

- **Path**: `settings.audio`
- **Type**: `boolean`
- **Default**: `true`

Generate native audio aligned with visual content.

### [promptExtend](https://runware.ai/docs/models/alibaba-wan2-7#request-settings-promptextend)

- **Path**: `settings.promptExtend`
- **Type**: `boolean`
- **Default**: `true`

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

### [shotType](https://runware.ai/docs/models/alibaba-wan2-7#request-settings-shottype)

- **Path**: `settings.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-wan2-7#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-wan2-7#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-wan2-7#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/alibaba-wan2-7#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/alibaba-wan2-7#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/alibaba-wan2-7#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/alibaba-wan2-7#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-wan2-7#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/alibaba-wan2-7#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-wan2-7/aa7c2f60-d40d-457e-a6de-a36883dd2b51.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "5d33440c-55f7-4ac2-a7af-8820a5a7fa2b",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Create a finished 15-second cinematic title teaser for a prestige limited series called “THE MINUTES,” a municipal noir conspiracy drama centered on a city records archivist. Landscape 16:9. Photorealistic 35mm film texture, severe brutalist compositions, shallow focus, nicotine amber and oxidized green palette, deep blacks, restrained camera movement, ominous procedural realism.\n\n0–3 seconds: extreme macro shot of a dented metal microfilm reel beginning to rotate inside an old archive reader. Dust trembles in the projector beam. The camera creeps forward as tiny reversed council records flicker across the film. Synchronized audio: fluorescent electrical hum, reel mechanism engaging, dry film chatter.\n\n3–6 seconds: hard cut on a mechanical click to an overhead shot of gloved hands opening a water-damaged city council ledger on a scarred institutional desk. Several names are hidden beneath thick black redactions; damp paper fibers catch the amber task light. A rubber date stamp strikes the page once, precisely on the cut. Synchronized audio: paper drag, heavy stamp impact, low sub-bass pulse beginning beneath the room tone.\n\n6–9 seconds: match cut from the circular stamp to a corroded ceiling drain in an empty underground records corridor. A single drop falls toward the lens. Rows of olive filing cabinets recede symmetrically into darkness while fluorescent tubes switch off one by one from the far end toward camera. Slow backward dolly. Audio: isolated water drop, sequential ballast snaps, growing ventilation rumble.\n\n9–12 seconds: close tracking shot along drawer labels and evidence tags as an unseen force pulls one cabinet drawer open. Inside is a pristine cream envelope marked only with a small embossed city seal, no other readable text. The camera stops abruptly as the envelope edge enters a razor-thin shaft of light. Audio: metal drawer scrape, paper whisper, one distant gavel strike with a long architectural echo.\n\n12–15 seconds: cut to black for half a beat, then reveal the title “THE MINUTES” centered in large, sharply legible ivory condensed serif capitals, appearing as if pressed into black archival paper. A thin oxidized-green rule sits beneath the title. No subtitle, credits, logos, or additional words. Hold long enough to read. Audio resolves into a final projector click, the sub-bass cuts out, and only the fluorescent hum remains before sudden silence. Elegant editorial pacing, clean cuts motivated by sound, controlled suspense rather than horror.",
  "negativePrompt": "Fantasy imagery, futuristic technology, glossy sci-fi styling, action spectacle, visible faces, gore, comedy, blue-orange blockbuster grading, handheld shake, rapid montage, illegible title, misspelled words, extra captions, credits, logos, watermarks, interface elements, subtitles.",
  "width": 1920,
  "height": 1080,
  "duration": 15,
  "settings": {
    "audio": true
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-7/64cfc0f6-d9b4-413b-998e-68af84d17794.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "5b15003c-1045-4b7f-bc77-008301536db9",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Continue directly from the supplied first frame as a polished five-second vertical fashion showcase, preserving the same model, facial appearance, ivory beekeeping suit, copper-mesh hood, gloves, honey extractor, vermilion studio, lighting, and centered composition. The model makes a slow controlled quarter-turn while sliding one gloved hand along the reinforced cuff, revealing the suit's articulated sleeve, utility pocket, and tailored side profile. A gentle studio fan creates subtle movement in the fabric without disturbing the hood. The camera performs a smooth, restrained push-in with a slight clockwise arc, ending on a confident three-quarter pose as amber light travels cleanly across the copper mesh and brushed steel. Crisp editorial workwear cinematography, realistic textile physics, premium material detail, bold cream-vermilion-amber palette, stable anatomy, no text, no logo.",
  "negativePrompt": "Wardrobe changes, altered suit details, extra people, bees, distorted hands, broken mesh, warped extractor, flicker, jitter, sudden cuts, excessive camera shake, text, logos, watermarks",
  "resolution": "1080p",
  "duration": 5,
  "settings": {
    "audio": true
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/a9f85cad-c7a3-4472-9269-1b3c49ed4e3e.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-7/8b67f706-3404-49c1-b603-6ea4697112f8.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "fc8da50c-9131-4b3f-9880-bb202c5acc2f",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Create a finished seven-second lyric-video segment as one continuous overhead stop-motion shot, interpolating naturally between the supplied locked first and last frames. Begin with the exact phrase “WHEN THE CITY CLOCKS OUT” resting across the packing table. After a brief hold, the narrow conveyor rollers turn, a time clock arm stamps down on the beat, and thermal labels feed rapidly across the surface. The original paper letters peel up one by one, slide, rotate and fold with believable handmade frame-by-frame motion. Timecards shuffle into rhythmic rows while safety-orange scraps pulse outward like graphic sound waves. The moving pieces progressively reassemble into the exact final phrase “WE COME ALIVE”, completing the transformation cleanly before a confident final hold. Preserve the same tabletop, objects, palette and handcrafted risograph texture throughout: warm cream paper, charcoal typography, cobalt shadows, safety orange, coarse halftone ink, visible fibers and subtle print misregistration. Keep all motion purposeful and rhythmically accelerating, with stable overhead framing and only a very slight camera push-in. The typography must remain bold, centered and legible; introduce no additional text. Energetic, defiant night-shift mood, polished enough for an official post-punk lyric video.",
  "negativePrompt": "Misspelled lyrics, extra words, logos, branding, glossy CGI, photorealistic hands, camera cuts, side angles, illegible typography, warped letters, flickering background, duplicated objects, random symbols, neon cyberpunk lighting, excessive motion blur.",
  "resolution": "720p",
  "duration": 7,
  "settings": {
    "audio": true
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/3af384e9-a73b-42bf-a0e4-7d2da3771c1a.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/b5c4c99f-dd58-45ac-8345-919737036b63.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-7/650967e5-2f65-4069-b431-193bc303455a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "05765e76-50bb-4985-8650-e5b3eb782bac",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Create a new 10-second multi-shot landscape b-roll sequence for an editorial documentary about low-impact textile production. Preserve the technician's recognizable face, silver bob, amber safety glasses and rust-red apron from the reference image, along with the authentic hand movements, restrained handheld camera language, workshop materials and muted indigo-rust-cream grade established by the reference video. This must be a newly staged sequence, not a frame-by-frame recreation of either reference. Shot 1: a slow lateral medium-wide move past hanging undyed linen reveals the artisan lifting a circular bamboo resist frame from beside an open indigo fermentation vat; blue vapor and soft window light add depth. Shot 2: tactile macro close-up of her blue-stained gloves pressing folded linen beneath the glossy dye surface, with natural ripples, bubbles and pigment clinging to the fabric. Shot 3: waist-level three-quarter view as she raises the saturated cloth and unfolds it once over a wooden draining rack; the textile shifts from green-blue toward rich indigo as it meets the air, droplets falling back into the vat. Maintain subject identity, wardrobe continuity, believable workshop geography and physically accurate liquid and fabric motion across all shots. Premium documentary stock-footage finish, observational rather than promotional, gentle film grain, soft highlights, crisp material detail, calm methodical mood. Compose every shot for 1088x832 landscape with useful negative space and clean editorial framing. No captions, signage, logos, watermarks or direct address to camera.",
  "width": 1088,
  "height": 832,
  "duration": 10,
  "settings": {
    "shotType": "multi",
    "promptExtend": true,
    "audio": true
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/9455b0dc-3c94-4ada-87b9-269757491f43.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/e513b5ed-d59c-4684-9540-6c759462fa3e.mp4"
    ]
  }
}
```

---

### audio-driven (audio-driven)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-7/2735fa3c-0b35-4d9d-b264-46fbe56b8f84.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "6ebf3f37-11a5-4031-ac0f-765b58e4ab4f",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "A polished vertical talking-head safety presenter clip for a polar research institute. In one continuous medium close-up, a female ice-core archive manager in her early forties faces the camera inside a real subzero storage aisle. She wears a vivid safety-orange insulated jacket over navy cold-room workwear, with frost-softened steel shelving and translucent cylindrical ice-core sleeves receding behind her in cool cyan light. Her lip movements synchronize precisely with the supplied speech. She speaks with calm authority and natural facial movement. On the words “label and seal,” she lifts one gloved hand and points toward the sealed end of an ice-core sleeve beside her. At “Any frost inside,” her expression becomes briefly concerned and she indicates a faint frosted patch without blocking her face. On “stop,” she makes a small, clear open-palm halt gesture, then returns to steady eye contact for the final instruction. Restrained documentary realism, clean institutional training-film art direction, soft frontal key light, subtle cold vapor in the background, realistic skin and fabric texture, shallow depth of field, stable camera, centered portrait composition with comfortable headroom. No cuts, no captions, no logos, no visible writing, no interface elements.",
  "width": 720,
  "height": 1280,
  "duration": 8,
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/52984900-6239-4cb5-8c16-30a7932d223c.mp3"
  }
}
```