---
title: PixVerse V6 | Runware Docs
url: https://runware.ai/docs/models/pixverse-v6
description: Multi-shot cinematic video generation with native audio, 20+ camera controls, and character consistency
---
# PixVerse V6

![PixVerse V6](https://assets.runware.ai/covers/pixverse-v6.jpg)

PixVerse V6 is a video generation model focused on multi-shot storytelling with native synchronized audio. It provides over 20 cinematic camera controls including focal length, aperture, depth of field, lens distortion, and vignetting. It features improved character consistency across shots using multi-image references, supports 1080p output at up to 15 seconds, and includes multilingual text rendering in frames.

- **Status**: live
- **ID**: `pixverse:1@8`
- Try in Playground
- **Creator**: PixVerse
- **Release Date**: March 30, 2026
- **Capabilities**: Text to Video, Image to Video, Video to Video, Edit, Checkpoint, Audio

## Pricing

$0.025 from, per second · ~59s per request

**Rates** (per second)

- 360p without audio: `$0.025`
- 360p with audio: `$0.035`
- 540p without audio: `$0.035`
- 540p with audio: `$0.045`
- 720p without audio: `$0.045`
- 720p with audio: `$0.06`
- 1080p without audio: `$0.09`
- 1080p with audio: `$0.115`

**5 example generations**

- [video-edit](https://runware.ai/docs/models/pixverse-v6/examples#example-cabaret-emcee-motion-portrait-retouch) · 720p: `$0.225` (~1m 18s)
- [text-to-video](https://runware.ai/docs/models/pixverse-v6/examples#example-harbor-pilot-motion-headshot) · 720p · 5s: `$0.225` (~38s)
- [first-last-frame](https://runware.ai/docs/models/pixverse-v6/examples#example-luthiery-exhibition-engraving-teaser) · 540p · 8s: `$0.28` (~59s)
- [first-frame](https://runware.ai/docs/models/pixverse-v6/examples#example-museum-entomology-set-extension) · 720p · 6s · audio: `$0.36` (~50s)
- [multi-shot](https://runware.ai/docs/models/pixverse-v6/examples#example-period-kitchen-background-replacement) · 720p · 10s: `$0.45` (~1m 29s)

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

## Compatibility & Validation

Provide at least one of `inputs.frameImages`, `inputs.referenceImages`, `inputs.referenceVideos`, and `inputs.video`, or `width/height`, but not both.

---

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

---

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

---

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

---

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

---

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

---

When `inputs.frameImages` has 2 or more items, `settings.thinking` is limited to `enabled`, `disabled`.

---

When `inputs.referenceVideos` is provided, `duration` cannot be used.

---

When `inputs.video` is provided, `width/height`, `settings.style`, `settings.multiClip`, and `settings.thinking` cannot be used.

---

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

---

When `resolution` is provided, `inputs.frameImages`, `inputs.referenceImages`, `inputs.referenceVideos`, or `inputs.video` 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-v6#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/pixverse-v6#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-v6#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/pixverse-v6#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-v6#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-v6#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-v6#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-v6#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-v6#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/pixverse-v6#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-v6#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-v6#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-v6#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/pixverse-v6#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/pixverse-v6#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`
- **File size (each)**: `up to 5 MB`

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

### [frameImages](https://runware.ai/docs/models/pixverse-v6#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-v6#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-v6#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).

### [video](https://runware.ai/docs/models/pixverse-v6#request-inputs-video)

- **Path**: `inputs.video`
- **Type**: `string`

Video input (UUID or URL). Source video for video-to-video generation. Dimensions and duration are derived from the input video.

### [referenceVideos](https://runware.ai/docs/models/pixverse-v6#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `2`
- **Size (each)**: `up to 3839 px`
- **Duration (total)**: `up to 15s`

List of reference videos (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/pixverse-v6#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `pixverse:1@8`

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-v6#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **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/pixverse-v6#request-negativeprompt)

- **Type**: `string`
- **Min**: `1`
- **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-v6#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceImages and inputs.referenceVideos and inputs.video are 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-v6#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceImages and inputs.referenceVideos and inputs.video are 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-v6#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-v6#request-duration)

- **Type**: `integer`
- **Min**: `1`
- **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/pixverse-v6#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/pixverse-v6#request-settings-audio)

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

Enable audio generation.

### [multiClip](https://runware.ai/docs/models/pixverse-v6#request-settings-multiclip)

- **Path**: `settings.multiClip`
- **Type**: `boolean`

Enable multi-shot generation with varying camera angles.

### [style](https://runware.ai/docs/models/pixverse-v6#request-settings-style)

- **Path**: `settings.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-v6#request-settings-thinking)

- **Path**: `settings.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-v6#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-v6#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-v6#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/pixverse-v6#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/pixverse-v6#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/pixverse-v6#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/pixverse-v6#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-v6#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/pixverse-v6#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-v6/3c3a367e-90c2-46f0-b9aa-3e328cf83b37.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "9a4dc7ab-7f40-472a-a007-303fb2c7bdb2",
  "model": "pixverse:1@8",
  "positivePrompt": "Create a premium professional motion headshot of a 58-year-old Filipina woman who is a chief harbor pilot, filmed inside a working ship bridge at blue-hour dawn. Landscape composition, chest-up framing. She wears a crisp navy maritime jacket with no insignia or logos, short silver-streaked hair, and a calm, authoritative expression. Begin in three-quarter profile as she watches tugboats through a rain-speckled bridge window. In one continuous shot, the camera makes a smooth rightward lateral dolly and subtle push-in while she turns toward the lens, squares her shoulders, takes a quiet breath, and settles into a restrained, confident half-smile. Keep her eyes sharply focused and her face dominant throughout. Cool slate-blue harbor light shapes one side of her face; soft amber bridge light provides warm separation on the other. Out-of-focus cranes, navigation lights, and slowly passing tugboats create controlled background motion. High-end editorial headshot enhancement: even but natural skin tone, softened temporary redness and under-eye shadows, preserved pores, fine lines, facial structure, and authentic age; tidy flyaway hairs, subtle eye catchlights, clean fabric detail, realistic teeth and eyes. Cinematic 70mm portrait-lens character, shallow depth of field, gentle highlight rolloff, restrained navy, steel blue, and amber palette. Stable anatomy and identity, physically realistic motion, no cuts, no angle changes, no captions, no logos, no interface elements.",
  "negativePrompt": "plastic skin, beauty-filter face, excessive smoothing, de-aging, altered ethnicity, distorted facial features, asymmetrical eyes, warped hands, duplicate person, exaggerated smile, glamour makeup, fashion pose, camera shake, jump cut, montage, rapid zoom, focus hunting, oversaturated neon, text, subtitles, watermark, logo, UI",
  "width": 1280,
  "height": 720,
  "duration": 5,
  "settings": {
    "multiClip": false,
    "thinking": "auto"
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/pixverse-v6/97bb6350-7e82-477a-8478-54511452f7d5.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "ee49c2d1-62fb-4dfc-97ad-02d66512c272",
  "model": "pixverse:1@8",
  "positivePrompt": "Create a polished generative set-extension shot for a natural history museum exhibition film. Begin exactly from the supplied first frame and continue it naturally as one uninterrupted six-second take. The camera makes a slow, steady lateral slider move to the right with a subtle forward drift, traveling beyond the original photograph’s right edge and revealing a plausible unseen continuation of the same entomology drawer: additional carefully spaced moth specimens, blank cream accession cards, aged wooden dividers, clean glass, and the far corner of the oak examination table. Preserve the specimen anatomy, pin placement, drawer construction, lighting direction, scale, reflections, color palette, and shallow depth of field established in the opening frame. Use foreground brass hardware and glass reflections for gentle parallax while the collection itself remains completely still. Restrained, observational museum-documentary cinematography; cool sage, ivory, tobacco brown, and muted amber tones; crisp focal plane with soft falloff; no cuts or sudden reframing. Native audio: quiet conservation-room ambience, low ventilation hum, a faint wooden floor creak, distant soft cart wheels, and the nearly inaudible mechanical glide of the camera slider; no music or speech.",
  "negativePrompt": "Jump cuts, morphing specimens, moving insects, fluttering wings, duplicate moths, warped drawer geometry, changing lighting, camera shake, people, hands, readable labels, captions, logos, music, narration",
  "resolution": "720p",
  "duration": 6,
  "settings": {
    "audio": true
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/47773453-71d4-44fa-9e53-c50b13906ecd.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/pixverse-v6/e3bfb907-844a-4433-8179-efbdc3c3252d.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "f07266f7-76bc-4a17-8c7c-49bf18ab4bce",
  "model": "pixverse:1@8",
  "positivePrompt": "Create one continuous, compositionally locked style-transfer transition from the opening documentary photograph to the closing hand-colored copperplate engraving. Preserve the luthier's identity, charcoal apron, facial features, hands, brush, violin anatomy, padded cradle, bench, window, and tool-wall layout throughout. Begin in tactile photorealism with warm window light, visible wood grain, floating dust, and shallow natural depth of field. The woman draws the varnish brush slowly from the violin's upper bout toward the lower bout. Follow the wet brushstroke as the amber sheen spreads: fine engraved contour lines emerge first inside the fresh varnish, then flow organically across her hands, apron, bench, tools, walls, and window. Photographic shadows resolve into delicate copperplate crosshatching while the color palette simplifies into parchment, oxblood, verdigris, lampblack, and luminous amber. Make the transformation material and progressive rather than a dissolve or abrupt cut. Add a very subtle forward camera drift toward the instrument, keeping the original 16:9 framing stable and the violin centered. End on the fully realized period engraving with the brush at the lower bout and the newly varnished violin glowing as the visual focal point. Intimate, scholarly, quietly celebratory museum-campaign mood.",
  "negativePrompt": "Text, captions, logos, borders, split screen, abrupt cuts, extra people, duplicated hands, extra fingers, warped violin, changing identity, changing workshop layout, floating tools, exaggerated fantasy effects, cartoon comedy, neon colors, camera shake.",
  "resolution": "540p",
  "duration": 8,
  "settings": {
    "thinking": "enabled"
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/8582c130-ce1a-431b-9fb4-c897102859a5.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/ea960250-d1cb-4dfd-9582-cae302ad9de3.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/pixverse-v6/5f686215-f042-463d-aaeb-118d2d1f6660.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "846d52df-c953-47b6-8b31-85cd7f7ed777",
  "model": "pixverse:1@8",
  "positivePrompt": "Create a finished widescreen music-video performance segment for an electronic-flamenco single. Preserve the lead performer's recognizable face, close-cropped black hair, cobalt tailored suit, proportions, and poised intensity from the reference image. Translate the exact choreographic rhythm and body mechanics of the reference video—heel drag, two sharp stamps, spiraling arms, quarter turn, forward step, held profile pose—into a vast working coastal saltworks at blue hour.\n\nOpen with a symmetrical wide shot: the performer stands on a narrow white salt ridge between shallow geometric evaporation ponds. The water reflects cold cyan sky; crystalline salt piles rise behind them; one distant conveyor crosses the horizon. Cut to a low 35mm tracking shot moving parallel with the heel drag, salt crystals scattering realistically beneath the boots. On the two stamps, cut rhythmically between an intimate 85mm portrait and a top-down view revealing concentric ripples in the brine. Finish with a slow push toward the held profile pose as wind catches the suit jacket and fine salt dust streams past. Keep geography, wardrobe, facial identity, lighting direction, and movement continuity consistent across every shot.\n\nArt direction is austere coastal industrialism rather than fantasy: chalk white salt, cobalt fabric, cyan water, a narrow band of sulfur-yellow work lights, subtle 16mm grain, restrained halation, crisp mineral texture, deep twilight atmosphere. Cinematic exposure, natural motion blur, shallow depth of field in close shots, no logos or captions.\n\nGenerate synchronized original audio: tense electronic flamenco at approximately 104 BPM, dry palmas, boot stamps locked precisely to the visible footwork, nylon-string guitar fragments, granular conveyor percussion, restrained sub-bass, wind across open ponds, and realistic salt crunch underfoot. The performer sings one intimate Spanish line in a low, breathy voice, synchronized naturally to the close portrait: “De la sal nace mi voz.” End on the sustained vocal tail, wind, and the final profile pose.",
  "negativePrompt": "Extra dancers, duplicate performer, identity drift, wardrobe changes, fantasy architecture, neon cyberpunk styling, tropical beach imagery, oversaturated colors, malformed hands, broken limbs, sliding feet, weightless movement, incorrect reflections, random cuts, shaky camera, visible crew, text, subtitles, logos, watermarks, interface elements",
  "resolution": "1080p",
  "settings": {
    "style": "comic"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/07816c73-8e0c-40bf-a0c3-6cbeffca7235.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/c500df3e-1566-4ba2-add3-645842c42279.mp4"
    ]
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/pixverse-v6/95e49bc3-1880-4316-899e-af6d3d8f1bfd.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "3d39d0af-c97a-4af5-b288-a3d9a48f52b5",
  "model": "pixverse:1@8",
  "positivePrompt": "Transform the source into a premium motion headshot retouch for a cabaret performer’s press kit. Preserve the performer’s exact identity, age, facial geometry, body proportions, stage makeup, pencil moustache, clothing, gesture timing, gaze, expression and overall motion structure. Keep the continuous chest-up composition and locked camera. Replace the flat backstage wall with a softly defocused oxblood velvet theater curtain and subtle warm antique-brass practical lights. Convert the harsh fluorescent illumination into elegant portrait lighting: warm soft Rembrandt key, gentle fill, thin amber rim light and natural catchlights. Refine the burgundy tuxedo fabric, remove lint, tame stray hairs, balance complexion and reduce excess shine and under-eye shadows while retaining pores, smile lines and authentic mature skin texture. Rich oxblood, antique gold, cream and ink-black palette; poised, intimate, self-assured mood. Simulate an 85mm portrait lens with shallow depth of field and restrained cinematic contrast. The environmental and lighting transformation must remain stable and temporally coherent across every frame with no flicker, morphing or identity drift. No lettering or logos.",
  "negativePrompt": "plastic skin, aggressive beauty filtering, changed identity, younger face, altered ethnicity, missing moustache, distorted hands, warped lapels, unstable background, flickering lights, face morphing, duplicated features, exaggerated smile, camera movement, cuts, text, logos, watermarks",
  "resolution": "720p",
  "settings": {
    "audio": false
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/6a3444fa-d1ec-40e7-b7fa-4f4a2ce1027e.mp4"
  }
}
```

---

### multi-shot (multi-shot)

[Watch video](https://assets.runware.ai/examples/pixverse-v6/fd5e28dd-5d73-4ee7-8a25-1700dca6c08b.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "3567655e-ce73-4d47-81c5-dfedc2976fa6",
  "model": "pixverse:1@8",
  "positivePrompt": "Create a coherent 10-second vertical VFX location-replacement sequence centered on one consistent subject: a moustached Belle Époque pastry chef in an ivory double-breasted jacket, tall white toque and burgundy neckerchief, carefully pushing the same brass dessert trolley carrying an elaborate croquembouche. Preserve his face, wardrobe, trolley, pastry and continuous forward movement throughout. Begin with a medium frontal tracking shot on a sparse gray soundstage, visible floor marks and lighting stands establishing the unfinished production environment. As a practical foreground column wipes across frame, replace only the surroundings with a richly detailed 1898 Paris grand-hotel service corridor: glazed teal tiles, copper pans, swinging doors, warm gaslight and subtle kitchen steam. Cut to a purposeful waist-level side-tracking angle as he steadies the gently rattling trolley and passes busy period staff in soft background focus. Finish with a low three-quarter angle as he pushes through carved doors into an opulent amber-lit ballroom, crystal chandeliers and formally dressed guests revealed behind him; the camera eases backward while maintaining portrait composition and the croquembouche as the visual anchor. Photoreal historical-drama production design, elegant match cuts, convincing scene replacement, warm amber and deep teal palette, tactile brass and glazed ceramic surfaces, restrained cinematic motion, natural fabric movement, shallow depth of field, no captions, no logos, no modern objects in the completed environments.",
  "width": 720,
  "height": 1280,
  "duration": 10,
  "settings": {
    "multiClip": true,
    "thinking": "auto"
  }
}
```