---
title: PixVerse V4.5 | Runware Docs
url: https://runware.ai/docs/models/pixverse-v4-5
description: PixVerse V4.5 cinematic text and image to video model
---
# PixVerse V4.5

![PixVerse V4.5](https://assets.runware.ai/covers/pixverse-v4-5.jpg)

PixVerse V4.5 generates stylized cinematic video from text prompts or reference images. It adds refined camera motion control, multi image fusion, and faster modes for iteration. Ideal for creators who need dynamic shots, complex motion, and consistent stylized outputs.

- **Status**: live
- **ID**: `pixverse:1@3`
- Try in Playground
- **Creator**: PixVerse
- **Release Date**: May 14, 2025
- **Capabilities**: Text to Video, Image to Video, Checkpoint

## Pricing

$0.0224 from, per second · ~50s per request

**Rates** (per second)

- 360p: `$0.0224`
- 540p: `$0.0224`
- 720p: `$0.03`
- 1080p: `$0.0598`

**4 example generations**

- [visual-effect](https://runware.ai/docs/models/pixverse-v4-5/examples#example-museum-after-dark-logo-sting) · 540p · 5s: `$0.112` (~1m 14s)
- [text-to-video](https://runware.ai/docs/models/pixverse-v4-5/examples#example-fish-market-percussion-music-video) · 720p · 5s: `$0.299` (~46s)
- [first-last-frame](https://runware.ai/docs/models/pixverse-v4-5/examples#example-technical-apiary-suit-fashion-reel) · 720p · 8s: `$0.299` (~42s)
- [first-frame](https://runware.ai/docs/models/pixverse-v4-5/examples#example-subsea-tidal-turbine-inspection-b-roll) · 1080p · 5s: `$0.299` (~55s)

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 `providerSettings.pixverse`, `cameraMovement` cannot be used with `effect`.

---

When `providerSettings.pixverse.motionMode` is `fast`, `duration` is limited to `5` and dimensions are limited to `640×360`, `480×360`, `360×360`, `360×480`, `360×640`, `960×540`, `720×540`, `540×540`, `540×720`, `540×960`, `1280×720`, `960×720`, `720×720`, `720×960` or `720×1280`.

---

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

---

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

---

When `resolution` or `width` or `height` is provided, `duration` is limited to `5`.

---

`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-v4-5#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/pixverse-v4-5#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-v4-5#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/pixverse-v4-5#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-v4-5#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-v4-5#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-v4-5#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-v4-5#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-v4-5#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/pixverse-v4-5#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-v4-5#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-v4-5#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-v4-5#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/pixverse-v4-5#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-v4-5#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-v4-5#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-v4-5#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-v4-5#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `pixverse:1@3`

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-v4-5#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-v4-5#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-v4-5#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-v4-5#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-v4-5#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-v4-5#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).

**Allowed values**: `5` `8`

### [seed](https://runware.ai/docs/models/pixverse-v4-5#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.

### [cameraMovement](https://runware.ai/docs/models/pixverse-v4-5#request-providersettings-pixverse-cameramovement)

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

Cinematic camera movement.

**Allowed values**:

- `horizontal_left` Horizontal pan to the left.
- `horizontal_right` Horizontal pan to the right.
- `vertical_up` Upward vertical movement.
- `vertical_down` Downward vertical movement.
- `zoom_in` Gradual zoom into the subject.
- `zoom_out` Gradual zoom away from the subject.
- `auto_camera` Automatic camera movement based on scene content.
- `crane_up` Upward crane shot movement.
- `quickly_zoom_in` Fast zoom into the subject.
- `quickly_zoom_out` Fast zoom away from the subject.
- `smooth_zoom_in` Gentle, smooth zoom into the subject.
- `camera_rotation` Rotating camera movement around the axis.
- `robo_arm` Mechanical, precise camera movement.
- `super_dolly_out` Dramatic outward dolly movement.
- `whip_pan` Quick, dynamic pan movement.
- `hitchcock` Classic Hitchcock-style dolly zoom effect.
- `left_follow` Camera follows subject moving left.
- `right_follow` Camera follows subject moving right.
- `pan_left` Horizontal pan to the left.
- `pan_right` Horizontal pan to the right.
- `fix_bg` Fixed background with foreground movement.

### [effect](https://runware.ai/docs/models/pixverse-v4-5#request-providersettings-pixverse-effect)

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

Visual effect template.

**Allowed values**:

- `bikini up` Body transformation effect.
- `the tigers touch` Animal-themed transformation.
- `jiggle jiggle` Rhythmic movement effect.
- `hug your love` Romantic interaction template.
- `kiss me ai` Kiss interaction effect.
- `subject 3 fever` Energetic movement template.
- `fin-tastic mermaid` Mermaid transformation.
- `lets ymca` Dance movement template.
- `skeleton dance` Spooky dance effect.
- `kungfu club` Martial arts action template.
- `boom drop` Explosive impact effect.
- `vroom vroom step` Vehicle-themed movement.
- `creepy devil smile` Horror-themed facial effect.
- `pubg winner hit` Gaming victory celebration.
- `360 microwave` Spinning rotation effect.
- `eye zoom challenge` Close-up eye effect.
- `muscle surge` Body enhancement effect.
- `punch face` Impact reaction template.
- `balloon belly` Body inflation effect.
- `kiss kiss` Multiple kiss interaction.

### [motionMode](https://runware.ai/docs/models/pixverse-v4-5#request-providersettings-pixverse-motionmode)

- **Path**: `providerSettings.pixverse.motionMode`
- **Type**: `string`
- **Default**: `normal`

Motion intensity in the generated video.

**Allowed values**:

- `normal` Standard motion intensity and pacing.
- `fast` Increased motion speed.

### [style](https://runware.ai/docs/models/pixverse-v4-5#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.

## Response Parameters

### [taskType](https://runware.ai/docs/models/pixverse-v4-5#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-v4-5#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-v4-5#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/pixverse-v4-5#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/pixverse-v4-5#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/pixverse-v4-5#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/pixverse-v4-5#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-v4-5#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/pixverse-v4-5#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-v4-5/5fb8718e-0b6b-40d0-b725-e93e6a2cdc88.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "7f99b4ea-f619-4b37-a3e8-10d7804292bd",
  "model": "pixverse:1@3",
  "positivePrompt": "Finished 5-second landscape music-video shot for an industrial electronic single. Inside a closed midnight wholesale fish market, six fishmongers in cobalt waterproof aprons perform synchronized percussion using stainless-steel counters, empty plastic crates, cleavers and crushed ice. They strike the surfaces in rapid rhythm, slide crates across the wet floor, pivot in formation and throw sparkling ice upward on the final beat. One continuous kinetic shot with a fast lateral whip-pan following the performers, strong readable body movement, tightly choreographed action and crisp beat-driven pacing. Fluorescent acid-yellow ceiling lights, deep cobalt shadows, sharp red gloves, reflective puddles, chrome surfaces, light haze and hard direct-flash highlights. Gritty fashion editorial meets precision dance film, realistic people and materials, energetic but controlled composition, cinematic motion blur at the frame edges, no visible seafood, no logos, no captions, no on-screen text.",
  "negativePrompt": "fantasy scenery, pastoral landscape, instruments, audience, stage, gore, fish carcasses, illegible text, logos, watermarks, duplicated people, extra limbs, warped hands, floating props, chaotic framing, static pose, slow motion, camera shake, low detail",
  "width": 1280,
  "height": 720,
  "duration": 5,
  "providerSettings": {
    "pixverse": {
      "cameraMovement": "whip_pan",
      "motionMode": "fast",
      "style": "cyberpunk"
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/pixverse-v4-5/3a333201-9ee1-4964-a4bb-04fea9551825.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "e777d2f8-149c-40fa-b6c5-36cd3cfc681f",
  "model": "pixverse:1@3",
  "positivePrompt": "The underwater inspection scene continues as one seamless, photorealistic documentary stock shot. The yellow ROV advances slowly toward the tidal turbine while making tiny stabilizing corrections; its tether trails behind and sways naturally in the current. The turbine blades rotate at a slow, heavy, consistent pace. Twin inspection beams sweep subtly across the hub, revealing bolts, algae and weathered metal. Fine particles drift through the light cones, kelp fronds bend with the current, and a few distant fish cross the background. Camera glides gently forward alongside the ROV with stable professional underwater cinematography, preserving the original composition and realistic scale. Deep teal water, muted yellow machinery, soft volumetric light, credible marine physics, no cuts, no sudden changes.",
  "negativePrompt": "cartoon, fantasy, explosion, rapid turbine speed, violent camera shake, scene transition, jump cut, warped machinery, duplicated ROV, extra turbine blades, deformed fish, murky black frame, oversaturated neon colors, text, captions, watermark, logo",
  "resolution": "1080p",
  "duration": 5,
  "providerSettings": {
    "pixverse": {
      "cameraMovement": "smooth_zoom_in",
      "motionMode": "normal"
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/7e453529-c23d-4c39-9cad-36c7a77d6e9b.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/pixverse-v4-5/db9c1cee-5499-4ad4-8c65-9a6f95c09465.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "4a1b671d-01fd-4abb-b993-9557a8325e5c",
  "model": "pixverse:1@3",
  "positivePrompt": "Create a single continuous premium fashion showcase shot connecting the supplied endpoint images. The apiary-suit model takes two measured runway steps toward camera while the camera performs a smooth, precise dolly-in from the symmetrical full-body composition to the waist-up three-quarter composition. She pivots slightly left near the end, presenting the hood profile, sealed shoulder construction and orange hardware with calm authority. Preserve her identity, body proportions and every garment detail throughout: ivory ripstop coverall, graphite sealed seams, structured pockets, gauntlet gloves, black field boots and raised amber-mesh hood. Subtle ventilation airflow moves only the fine hood mesh and loose fabric folds. Keep the ultramarine decontamination tunnel rigid and consistent, with the sulfur-yellow floor stripe maintaining correct perspective. Crisp cyan practical lighting glides across the fabric and hardware as the camera advances. High-end technical workwear campaign, controlled choreography, realistic textile physics, confident industrial mood, sharp product visibility, no cuts, no garment morphing, no text or logos.",
  "negativePrompt": "Wardrobe changes, altered colors, disappearing hood, extra limbs, distorted hands, face changes, duplicate person, unstable background, melting fabric, abrupt cuts, camera shake, excessive motion blur, text, captions, logos, watermarks.",
  "resolution": "720p",
  "duration": 8,
  "providerSettings": {
    "pixverse": {
      "motionMode": "normal",
      "style": "clay"
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/4a718a99-50d6-4a1e-8424-83cc1f396df7.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/710a2ca3-0160-4e3b-9f35-273a76b69b73.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### visual-effect (visual-effect)

[Watch video](https://assets.runware.ai/examples/pixverse-v4-5/ebcd1158-b493-49f4-9aa0-934b1cce5055.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "a10b4391-c6b6-42a9-8ec4-ece1dbf4cdf9",
  "model": "pixverse:1@3",
  "positivePrompt": "Create a polished five-second animated logo sting from the supplied opening frame. The museum night guard remains centered and fully visible as he transforms cleanly into an anatomically recognizable bone-white skeleton, then performs a short, stylish two-step dance with swinging elbows, tapping feet and a playful shoulder shimmy. Keep the movement graphic, rhythmic and legible rather than frightening. Preserve the flat sulfur-yellow background and bold Swiss-modernist poster composition. Keep the black “NIGHT SHIFT” wordmark and smaller “NATURAL HISTORY AFTER DARK” line fixed, sharp and readable throughout. The bone-white circular emblem gives one subtle pulse in time with the final pose. Finish with the dancing skeleton standing directly beneath the logo in a confident symmetrical stance. Locked frontal camera, full body always in frame, crisp silhouettes, limited palette of sulfur yellow, matte black and bone white, premium cultural-event motion design, clean edges, no extra characters, no scenery, no gore.",
  "negativePrompt": "cropped body, missing feet, extra people, cluttered background, gore, horror violence, broken anatomy, duplicate limbs, illegible lettering, altered wordmark, camera shake, camera movement, photorealistic museum interior",
  "resolution": "540p",
  "duration": 5,
  "providerSettings": {
    "pixverse": {
      "effect": "skeleton dance",
      "motionMode": "normal"
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/e1bb3fb0-9861-41fd-8bd1-5fc86032c73c.jpg",
        "frame": "first"
      }
    ]
  }
}
```