---
title: PixVerse V5.5 | Runware Docs
url: https://runware.ai/docs/models/pixverse-v5-5
description: PixVerse V5.5 multi shot text to video with synced audio
---
# PixVerse V5.5

![PixVerse V5.5](https://assets.runware.ai/covers/pixverse-v5-5.jpg)

PixVerse V5.5 is a director focused video model for story driven clips. It supports multi image fusion for character continuity, multi shot sequences, and native audio. It delivers smooth motion, refined cinematic control, and precise text guided video generation for complex scenes.

- **Status**: live
- **ID**: `pixverse:1@6`
- Try in Playground
- **Creator**: PixVerse
- **Release Date**: December 1, 2025
- **Capabilities**: Text to Video, Image to Video, Checkpoint, Audio

## Pricing

$0.133 from, per run · ~1m 45s per request

**Rates** (per run)

*360p*

- 5s: `$0.133`
- 8s: `$0.265`
- 10s: `$0.292`

*540p*

- 5s: `$0.133`
- 8s: `$0.265`
- 10s: `$0.292`

*720p*

- 5s: `$0.177`
- 8s: `$0.354`
- 10s: `$0.389`

*1080p*

- 5s: `$0.354`
- 8s: `$0.707`

**4 example generations**

- [first-frame](https://runware.ai/docs/models/pixverse-v5-5/examples#example-tidal-oyster-percussion-music-segment) · 720p · 8s: `$0.354` (~1m 37s)
- [first-last-frame](https://runware.ai/docs/models/pixverse-v5-5/examples#example-glass-plate-archive-title-sequence) · 1080p · 5s · audio: `$0.383` (~1m 49s)
- [text-to-video](https://runware.ai/docs/models/pixverse-v5-5/examples#example-forensic-entomology-docuseries-teaser) · 1080p · 5s · audio: `$0.471` (~1m 55s)
- [text-to-video](https://runware.ai/docs/models/pixverse-v5-5/examples#example-heritage-tile-restoration-reel) · 1080p · 5s · audio: `$0.471` (~1m 40s)

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`.

---

Parameter constraints vary based on the configuration:

| Dimensions | duration |
| --- | --- |
| `1920x1080` | `5` `8` |
| `1440x1080` | `5` `8` |
| `1080x1080` | `5` `8` |
| `1080x1440` | `5` `8` |
| `1080x1920` | `5` `8` |
| `Other` | `5` `8` `10` |

---

`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 |
| --- | --- |
| `360p (16:9)` | `640x360` |
| `360p (4:3)` | `480x360` |
| `360p (1:1)` | `360x360` |
| `360p (3:4)` | `360x480` |
| `360p (9:16)` | `360x640` |
| `540p (16:9)` | `960x540` |
| `540p (4:3)` | `720x540` |
| `540p (1:1)` | `540x540` |
| `540p (3:4)` | `540x720` |
| `540p (9:16)` | `540x960` |
| `720p (16:9)` | `1280x720` |
| `720p (4:3)` | `960x720` |
| `720p (1:1)` | `720x720` |
| `720p (3:4)` | `720x960` |
| `720p (9:16)` | `720x1280` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (4:3)` | `1440x1080` |
| `1080p (1:1)` | `1080x1080` |
| `1080p (3:4)` | `1080x1440` |
| `1080p (9:16)` | `1080x1920` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/pixverse-v5-5#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/pixverse-v5-5#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/pixverse-v5-5#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#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).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/pixverse-v5-5#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `pixverse:1@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/pixverse-v5-5#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `2048`

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/pixverse-v5-5#request-negativeprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `2048`

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/pixverse-v5-5#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/pixverse-v5-5#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/pixverse-v5-5#request-resolution)

- **Type**: `string`
- **Default**: `720p`

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

**Allowed values**: `360p` `540p` `720p` `1080p`

### [duration](https://runware.ai/docs/models/pixverse-v5-5#request-duration)

- **Type**: `integer`

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/pixverse-v5-5#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.pixverse\` object.

### [audio](https://runware.ai/docs/models/pixverse-v5-5#request-providersettings-pixverse-audio)

- **Path**: `providerSettings.pixverse.audio`
- **Type**: `boolean`

Enable audio generation.

### [multiClip](https://runware.ai/docs/models/pixverse-v5-5#request-providersettings-pixverse-multiclip)

- **Path**: `providerSettings.pixverse.multiClip`
- **Type**: `boolean`

Enable multi-shot generation with varying camera angles.

### [style](https://runware.ai/docs/models/pixverse-v5-5#request-providersettings-pixverse-style)

- **Path**: `providerSettings.pixverse.style`
- **Type**: `string`

Artistic style aesthetic for video generation.

**Allowed values**:

- `anime` Japanese animation aesthetic.
- `3d_animation` Three-dimensional animated style with depth.
- `clay` Stop-motion clay animation appearance.
- `comic` Comic book or graphic novel visual style.
- `cyberpunk` Futuristic, neon-lit dystopian aesthetic.

### [thinking](https://runware.ai/docs/models/pixverse-v5-5#request-providersettings-pixverse-thinking)

- **Path**: `providerSettings.pixverse.thinking`
- **Type**: `string`
- **Default**: `auto`

Enhanced reasoning mode.

**Allowed values**:

- `enabled` Max understanding.
- `disabled` Faster generation.
- `auto` Automatic.

## Response Parameters

### [taskType](https://runware.ai/docs/models/pixverse-v5-5#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/pixverse-v5-5#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/pixverse-v5-5#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/pixverse-v5-5#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/pixverse-v5-5#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/pixverse-v5-5#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/pixverse-v5-5#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/pixverse-v5-5#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/pixverse-v5-5#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/pixverse-v5-5/3965d9a6-7d1e-4fef-947a-5b20de655200.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "5d08e550-30b7-44ef-8b70-af0d37420669",
  "model": "pixverse:1@6",
  "positivePrompt": "Create a cinematic 5-second portrait title sequence for a prestige forensic entomology docuseries titled \"THE QUIET WITNESS.\" Three precise, connected shots with restrained investigative tension. Shot 1: extreme macro of a translucent fly wing beneath a forensic microscope; the mechanical stage glides sideways while focus racks across branching veins, cold bone-white laboratory light, deep carbon-black shadows, tiny dust particles. Shot 2: match cut from the wing veins to thin black routes on an ivory evidence map viewed overhead; an oxidized-red case pin drops sharply into place beside a transparent measurement scale as the camera pushes closer. Shot 3: match cut to a pinned beetle specimen in profile; its long shadow expands across textured archival paper and becomes a clean dark field. The exact title THE QUIET WITNESS resolves in centered condensed ivory capitals, with no other wording. Compose every shot for a narrow 9:16 frame, strong central geometry, realistic macro optics, shallow depth of field, subtle 35mm grain, clinical museum-archive art direction, elegant rather than graphic. Synchronized generated audio: microscope stage click, faint fluorescent hum, crisp pin impact, delicate wing flutter, one low bowed-cello harmonic swelling into the title, then abrupt silence.",
  "negativePrompt": "Gore, corpse, blood, horror monster, neon lighting, cyberpunk, fantasy insects, cartoon imagery, cluttered composition, shaky camera, illegible title, misspelled words, subtitles, credits, logos, watermarks, extra text.",
  "width": 1080,
  "height": 1920,
  "duration": 5,
  "providerSettings": {
    "pixverse": {
      "audio": true,
      "multiClip": true,
      "thinking": "auto"
    }
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/pixverse-v5-5/9326413b-bb54-4252-aebd-58faa2f9cbc1.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "d86a7b2d-d6ec-456b-b51d-0c3afb6981ad",
  "model": "pixverse:1@6",
  "positivePrompt": "Create a polished 5-second vertical social media ad for a heritage tile restoration specialist, with three fast cinematic shots and realistic generated audio. Shot 1: extreme macro, looking straight down at a century-old encaustic hallway tile obscured by dull gray grime; a gloved hand draws a metal floor-cleaning wand into frame. Shot 2: low tracking close-up as the spinning brush and extraction head travel across the floor, dirty water rushing beneath the clear nozzle and revealing crisp rust-red, ochre, cream, and charcoal geometry in one continuous satisfying pass. Shot 3: rapid pullback to a symmetrical overhead reveal of the fully restored Victorian hallway, warm morning sunlight crossing the richly patterned floor as the technician steps neatly out of frame. Premium tactile documentary realism, warm earthy palette, natural window light, subtle film grain, precise material detail, energetic editorial cuts, strong center composition and safe portrait framing. Audio: bristly scrub, water extraction hiss, ceramic squeak, then a clean resonant finishing chime. No narration, captions, logos, or on-screen text.",
  "negativePrompt": "split screen, before-and-after divider, visible branding, captions, typography, interface elements, neon lighting, fantasy imagery, warped tile patterns, rubbery hands, extra fingers, excessive water, shaky camera, flicker, low detail",
  "width": 1080,
  "height": 1920,
  "duration": 5,
  "providerSettings": {
    "pixverse": {
      "audio": true,
      "multiClip": true,
      "thinking": "auto"
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/pixverse-v5-5/00fdae56-15cb-4392-a182-e2eb5e785510.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "5e99fae9-71ab-4edb-8685-5bda69e7a1bc",
  "model": "pixverse:1@6",
  "positivePrompt": "Continue directly and naturally from the supplied opening frame as a polished music-video performance shot. The percussionist locks eyes with camera, swings the oyster basket down onto the stainless wash table on the first beat, and clean seawater erupts in a sharp silver fan while oysters rattle rhythmically inside. She repeats the physical basket percussion with confident, workmanlike choreography as two oyster farmers in muted waterproof gear step into the deep background and pull long grading rakes in synchronized strokes. Track smoothly sideways just above water level, then arc inward around her while preserving her appearance, clothing, location and realistic proportions. Each impact sends concentric ripples through the shallow water; droplets hang briefly in the cool dawn light. Finish with the camera rising slightly as she lifts the dripping basket toward frame, revealing geometric rows of timber oyster racks across the tidal flat. Grounded coastal documentary realism elevated by precise musical timing; tactile metal, shell and water textures; pearl gray, sea green, rust and safety orange palette; energetic but unsentimental mood. Native audio: driving frame drum and dry handclaps fused with basket rattles, shell clicks, boot splashes and distant gulls; no dialogue, no lyrics, no on-screen text.",
  "resolution": "720p",
  "duration": 8,
  "providerSettings": {
    "pixverse": {
      "style": "clay",
      "thinking": "enabled"
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/d398f344-53fe-48c4-a9de-f3ebe98afe75.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/pixverse-v5-5/8066963e-2470-4a72-8a6b-c01609c70c9a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "3ca9281e-e15e-4dca-83a3-c205bb7af02d",
  "model": "pixverse:1@6",
  "positivePrompt": "Create a five-second cinematic main-title reveal for a prestige genealogy documentary. Begin exactly on the supplied first frame: a locked overhead macro composition of the cloudy 1890s glass plate inside the black enamel developing tray under a crimson safelight. Developer pours gently from the upper right, spreading across the emulsion in one continuous, physically convincing sheet. Tiny ripples travel through reflected red light; suspended silver grains swirl and settle. As the liquid advances, the same Victorian woman's face gradually emerges from milky abstraction into a sharp luminous silver portrait, eyes appearing last. Make the transformation tactile and photographic, not supernatural. Use a restrained progression of close insert cuts while preserving screen direction and object continuity: liquid edge crossing glass, silver crystals blooming, brass timer hand twitching, then return to the original locked overhead framing. The ivory serif title NAMES IN SILVER resolves cleanly within the developed emulsion across the lower third, stable and legible without warping. End exactly on the supplied last frame. Art direction: archival darkroom realism, silver-black shadows, deep crimson practical light, warm walnut accents, shallow highlights, subtle 35mm grain, elegant and haunting rather than frightening.",
  "negativePrompt": "Modern laboratory equipment, digital screens, interface graphics, extra hands, extra objects, distorted face, supernatural effects, neon colors, camera shake, comedy, illegible lettering, misspelled title, duplicate text, warped typography, watermarks, logos, subtitles, credits.",
  "resolution": "1080p",
  "duration": 5,
  "providerSettings": {
    "pixverse": {
      "audio": true,
      "thinking": "auto"
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/de3e98ba-2d10-4db0-8b6c-131a54b82628.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/5314ad3b-73b2-427e-8563-60d437c377cd.jpg",
        "frame": "last"
      }
    ]
  }
}
```