---
title: P-Video-Replace | Runware Docs
url: https://runware.ai/docs/models/prunaai-p-video-replace
description: Character replacement for existing video using a reference image while preserving motion, timing, camera, and scene
---
# P-Video-Replace

![P-Video-Replace](https://assets.runware.ai/covers/prunaai-p-video-replace.jpg)

P-Video-Replace is a video transformation model that swaps the on-camera character in an existing video with the character from a reference image. It is built to preserve the original motion, timing, camera behavior, lighting, and background while changing who appears in the clip, making it useful for UGC ad variations, content localization, avatar or mascot insertion, and other scalable character-replacement workflows.

- **Status**: live
- **ID**: `prunaai:p-video@replace`
- Try in Playground
- **Creator**: Pruna AI
- **Release Date**: June 4, 2026
- **Capabilities**: Image to Video, Video to Video, Edit, Checkpoint

## Pricing

$0.03 from, per second · ~1m 47s per request

**Rates** (per second)

- 720p: `$0.03`
- 1080p: `$0.06`

**4 example generations**

- [video-edit](https://runware.ai/docs/models/prunaai-p-video-replace/examples#example-indoor-mushroom-farm-b-roll): `$0.362` (~1m 48s)
- [video-edit](https://runware.ai/docs/models/prunaai-p-video-replace/examples#example-cut-paper-curator-exhibition-teaser): `$0.362` (~3m 2s)
- [video-edit](https://runware.ai/docs/models/prunaai-p-video-replace/examples#example-night-rail-technician-recruitment-clip): `$0.362` (~1m 45s)
- [video-edit](https://runware.ai/docs/models/prunaai-p-video-replace/examples#example-coral-dive-computer-colorway-video): `$0.362` (~1m 2s)

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

## Compatibility & Validation

When `resolution` is provided, `inputs.referenceImages` or `inputs.video` is required.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/prunaai-p-video-replace#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/prunaai-p-video-replace#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/prunaai-p-video-replace#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/prunaai-p-video-replace#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/prunaai-p-video-replace#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/prunaai-p-video-replace#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/prunaai-p-video-replace#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/prunaai-p-video-replace#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/prunaai-p-video-replace#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/prunaai-p-video-replace#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/prunaai-p-video-replace#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/prunaai-p-video-replace#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/prunaai-p-video-replace#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/prunaai-p-video-replace#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/prunaai-p-video-replace#request-inputs-referenceimages)

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

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

### [video](https://runware.ai/docs/models/prunaai-p-video-replace#request-inputs-video)

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

Video input (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/prunaai-p-video-replace#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `prunaai:p-video@replace`

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/prunaai-p-video-replace#request-positiveprompt)

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

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

### [resolution](https://runware.ai/docs/models/prunaai-p-video-replace#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**: `720p` `1080p`

### [fps](https://runware.ai/docs/models/prunaai-p-video-replace#request-fps)

- **Type**: `integer`

Frames per second for video generation. Higher values create smoother motion but require more processing time.

**Allowed values**: `24` `48`

### [seed](https://runware.ai/docs/models/prunaai-p-video-replace#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.

### [preserveAudio](https://runware.ai/docs/models/prunaai-p-video-replace#request-settings-preserveaudio)

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

Preserve the source video audio track in the output.

### [sourceAudioSync](https://runware.ai/docs/models/prunaai-p-video-replace#request-settings-sourceaudiosync)

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

Drive lip and motion sync from the source video audio. Independent of `preserveAudio`, which controls audio in the final output.

### [turbo](https://runware.ai/docs/models/prunaai-p-video-replace#request-settings-turbo)

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

Enable turbo mode for faster generation. May reduce subtle details in complex tasks.

## Response Parameters

### [taskType](https://runware.ai/docs/models/prunaai-p-video-replace#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/prunaai-p-video-replace#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/prunaai-p-video-replace#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/prunaai-p-video-replace#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/prunaai-p-video-replace#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/prunaai-p-video-replace#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/prunaai-p-video-replace#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/prunaai-p-video-replace#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/prunaai-p-video-replace#response-cost)

- **Type**: `float`

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

## Examples

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-replace/39486554-1ff4-4411-8002-e68d34c94968.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "7db064fc-3c36-41db-884c-23e89ce10392",
  "model": "prunaai:p-video@replace",
  "positivePrompt": "Replace the sole male cultivation technician in the source video with the older female mycologist depicted in the reference image. Preserve her recognizable facial features, age, skin tone, sage head wrap, ivory coveralls, body proportions, and professional presence consistently across every frame. Transfer the source subject's exact hand placement and complete inspection action: lifting the oyster mushroom cluster, rotating it, examining the gills, and returning it gently. Preserve the original medium-wide composition, slow lateral dolly, camera path, lens perspective, timing, body motion, rack geometry, mushrooms, humidity haze, cool diffused lighting, shadows, depth of field, and cream-silver-pale-green color grade. Keep the commercial grow room unchanged and photorealistic, with no added people, objects, logos, or text. Maintain exact source-audio synchronization with the gestures and movement while retaining the natural ventilation, water-drip, and clothing sounds. Finished 16:9 documentary stock b-roll suitable for controlled-environment agriculture editorial use.",
  "resolution": "1080p",
  "fps": 24,
  "settings": {
    "preserveAudio": true,
    "sourceAudioSync": true,
    "turbo": false
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/804836da-34dc-400c-a552-7d8d6e9727a1.jpg"
    ],
    "video": "https://assets.runware.ai/assets/inputs/4a5f692d-cdbe-4feb-89c8-864b8238d9d5.mp4"
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-replace/2e64e96c-b23b-4046-9fc6-a7c7348db593.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "063c044d-f8bf-4fff-ae8b-69abf4ddb9dd",
  "model": "prunaai:p-video@replace",
  "positivePrompt": "Replace the sole human curator in the source video with the exact articulated cut-paper curator depicted in the reference image, creating a sophisticated handcrafted folk-art character restyle for a museum exhibition teaser. Preserve the reference character's layered paper construction, floral cutouts, scalloped contours, visible fibers, brass joints, vermilion, mustard, forest-green, cream and charcoal palette, braided hair and patterned clothing. Animate the paper figure with the source curator's precise body movement, hand gestures, facial performance, gaze and interaction with the woven sample. Maintain accurate lip movement and source-audio synchronization. Preserve the original gallery, historic loom, lighting, shadows, camera slide, framing, timing and depth of field without restyling or altering the environment. Keep one consistently proportioned character with stable paper details throughout; no additional people, text or graphics.",
  "resolution": "1080p",
  "fps": 24,
  "settings": {
    "preserveAudio": true,
    "sourceAudioSync": true,
    "turbo": false
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/36b95a1f-e462-4f71-af9b-add9ba1cd00b.jpg"
    ],
    "video": "https://assets.runware.ai/assets/inputs/dc09e729-42c9-43d1-adc4-e6cb7e604f7c.mp4"
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-replace/39b62059-3e87-447d-93df-b20fefc408e9.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "befb5e2d-5872-441b-b8fe-ca17adcac7d5",
  "model": "prunaai:p-video@replace",
  "positivePrompt": "Replace the single male rail technician in the source video with the female rail technician depicted in the reference image. Preserve her recognizable face, hairstyle, body proportions, lime-yellow coveralls, hard hat, gloves, and boots while transferring the source performer’s exact walking pace, flashlight inspection gestures, head turn, posture, timing, and framing. Relight the replacement naturally for the nighttime depot: cyan overhead illumination, warm amber rim light, crisp reflections on safety strips, realistic flashlight spill, and deep directional shadows consistent with the original scene. Preserve the train, wheel assembly, damp concrete, background, camera tracking movement, lens perspective, composition, scene timing, and all environmental details without alteration. Preserve the source audio and synchronize the replacement technician’s mouth and facial motion precisely to the original spoken line. The result should look like footage captured with the replacement performer on location at night, with no compositing seams, flicker, identity drift, added people, logos, captions, or text.",
  "resolution": "1080p",
  "fps": 24,
  "settings": {
    "preserveAudio": true,
    "sourceAudioSync": true,
    "turbo": false
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/9e01de68-4bd8-4109-82f7-b6311851f1c0.jpg"
    ],
    "video": "https://assets.runware.ai/assets/inputs/df82f8a5-083b-45e7-8bab-5ecc8499c24c.mp4"
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-replace/627942b1-d31b-490e-9f8e-c1f3a96e2fd7.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "08090a86-f051-4a07-804d-59a6b0df34c6",
  "model": "prunaai:p-video@replace",
  "positivePrompt": "Replace the cobalt-blue dive computer in the source video with the coral-orange version shown in the reference image. Match the reference product faithfully: coral-orange silicone strap and bezel, dark graphite case, black glass display, identical rugged construction, buttons, proportions, and material finish. Preserve the source video's exact product position, scale, orientation, turntable rotation, camera movement, timing, perspective, reflections, water droplets, cyan rim light, wet slate surface, charcoal background, depth of field, and overall premium diving-equipment art direction. The replacement must remain geometrically stable and consistently detailed through every angle, with realistic contact, shadows, highlights, and reflections. Do not introduce people, hands, extra products, logos, captions, or scene changes. Preserve the original audio and keep the water drips and turntable sounds synchronized precisely to the source timing.",
  "resolution": "1080p",
  "fps": 24,
  "settings": {
    "preserveAudio": true,
    "sourceAudioSync": true,
    "turbo": false
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/e5296e16-68af-4b82-891a-35da0e5932c6.jpg"
    ],
    "video": "https://assets.runware.ai/assets/inputs/b4c6b33e-b58d-4fed-9e8d-28a6b6844bb3.mp4"
  }
}
```