---
title: P-Video-Edit | Runware Docs
url: https://runware.ai/docs/models/prunaai-p-video-edit
description: Instruction-based video editing with reference-guided control and preserved motion, structure, and audio
---
# P-Video-Edit

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

P-Video-Edit is Pruna AI's instruction-based video editing model for changing an existing clip while preserving its motion, scene structure, and audio. Give it a source video and a text instruction to make attribute, object, or environment edits; up to four reference images can guide identity, style, or other supported changes. A draft mode supports faster iteration before rendering the final edit at full quality.

- **Status**: live
- **ID**: `prunaai:p-video@edit`
- Try in Playground
- **Creator**: Pruna AI
- **Release Date**: September 3, 2026
- **Capabilities**: Image to Video, Video to Video, Edit, Checkpoint

## Pricing

$0.025 from, per second · ~1m 38s per request

**Rates** (per second)

- Draft: `$0.025`
- Standard: `$0.045`

**4 example generations**

- [reference-to-video](https://runware.ai/docs/models/prunaai-p-video-edit/examples#example-seaweed-hatchery-inspection-b-roll): `$0.204` (~1m 52s)
- [video-edit](https://runware.ai/docs/models/prunaai-p-video-edit/examples#example-architectural-prosthetic-cover-showcase-reel): `$0.204` (~1m 33s)
- [video-edit](https://runware.ai/docs/models/prunaai-p-video-edit/examples#example-sage-espresso-machine-colorway-film): `$0.204` (~1m 30s)
- [reference-to-video](https://runware.ai/docs/models/prunaai-p-video-edit/examples#example-pearlescent-fencing-mask-colorway-reel): `$0.204` (~1m 44s)

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

## Notes

Output dimensions are not configurable. The model preserves the source aspect ratio and snaps the result to a fixed size, so the source resolution does not carry through. A 1080p clip and a 4K clip of the same shape return identical dimensions.

**Output dimensions by source aspect ratio:**

| Aspect Ratio | Width × Height |
| --- | --- |
| 16:9 | 848 × 480 |
| 9:16 | 480 × 848 |
| 1:1 | 624 × 624 |
| 4:3 | 736 × 544 |
| 3:4 | 544 × 736 |
| 3:2 | 768 × 512 |
| 2:3 | 512 × 768 |
| 21:9 | 848 × 368 |
| 9:21 | 368 × 848 |

Output frame rate is always 25 fps and output duration matches the input. `settings.draft` changes neither the dimensions nor the frame rate.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

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

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

Video output type.

**Allowed values**: `URL`

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

- **Type**: `boolean`

Include task cost in the response.

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

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `4`

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

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

- **Path**: `inputs.video`
- **Type**: `string`
- **Required**: true
- **Duration**: `up to 15s`

Video input (UUID or URL). The output follows the source aspect ratio and duration, always at 25 fps. Output size is fixed per aspect ratio and never exceeds 848 pixels on the long edge, regardless of the source resolution.

**Core Parameters**

Primary parameters that define the task output.

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

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

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-edit#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

### [seed](https://runware.ai/docs/models/prunaai-p-video-edit#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/prunaai-p-video-edit#request-settings-audio)

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

Include audio in the generated video output.

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

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

Enable draft mode for a faster, lower-quality preview billed at the draft rate. The output resolution is unchanged.

### [promptUpsampling](https://runware.ai/docs/models/prunaai-p-video-edit#request-settings-promptupsampling)

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

Automatically enhance the prompt for improved results.

## Response Parameters

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

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

UUID of the output video.

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

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

URL of the output video.

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

- **Type**: `string`

Base64-encoded video data.

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

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

Data URI of the output video.

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

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

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

- **Type**: `float`

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

## Examples

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

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-edit/971f8b2d-d62a-4e86-bd05-313d32cfd856.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "0f13b3fc-d3bb-4f34-b358-782d54c36c1b",
  "model": "prunaai:p-video@edit",
  "positivePrompt": "Edit the source clip into authentic documentary b-roll of a technician inspecting juvenile kelp inside a commercial seaweed hatchery. Use reference image 1 to transform the nursery into the same Nordic marine cultivation facility, matching its white fiberglass seawater tanks, blue hoses, stainless fittings, overhead grow lights, cool teal-gray palette, and diffuse skylight. Use reference image 2 to replace the lifted culture tray with the same wet seeded-twine tray covered in olive-green juvenile kelp, including realistic dripping water and blue nitrile gloves. Keep the technician's identity, walk, hand positions, inspection gesture, original camera tracking, framing, timing, physical contact, and ambient audio coherent throughout. Maintain photorealistic aquaculture details, restrained editorial color, clean unbranded surfaces, and one continuous natural shot.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/beeaa19f-9a0d-4bf0-ba62-123463b85b02.mp4",
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/91563b89-d4e5-4627-8f7f-cf0360369fc8.jpg",
      "https://assets.runware.ai/assets/inputs/c54a210f-6928-4049-a472-bdb4d9d08cad.jpg"
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-edit/414a01b7-b891-44cd-a464-a651bec443e2.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "01877be2-95a7-444d-80a5-f26ed68c3aa4",
  "model": "prunaai:p-video@edit",
  "positivePrompt": "Edit the source video into a finished colorway showcase by changing only the athlete’s matte-black fencing mask to the exact product appearance shown in both reference images. Match reference image 1 for the frontal design and palette: pearlescent aubergine steel mesh with subtle plum-to-copper iridescence, a warm bone-white padded bib, and narrow acid-chartreuse binding. Match reference image 2 for the side construction, black rear strap, stitching, material texture, and reflection behavior. Track the new colorway consistently through every head turn, lunge, parry, motion blur, blade crossing, shadow, and partial occlusion. Keep the mask’s original shape, fit, mesh geometry, and protective construction unchanged. Preserve the athlete, white uniform, opponent, blades, fencing salle, camera movement, timing, lighting, and original audio exactly; do not add logos, text, accessories, or new objects.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/8b5f295a-dadb-4044-a87c-9e5234baaad0.mp4",
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/e9246d6a-b051-4bf6-8d46-1b090becd16f.jpg",
      "https://assets.runware.ai/assets/inputs/c2aac77c-3ad6-47c3-9721-e7daa838ff99.jpg"
    ]
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-edit/b2035cc4-47f5-4792-b904-0869d38b5b21.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "915af686-9d0a-4c13-ad5d-86aedb116215",
  "model": "prunaai:p-video@edit",
  "positivePrompt": "Transform this footage into a premium adaptive-fashion product showcase. Replace only the plain white right prosthetic cover with a precisely fitted architectural exoskeleton cover made from translucent amber resin, featuring elegant curved ribs, polished edges, subtle internal highlights, and visible craftsmanship. Change the neutral studio into a dark mineral-toned gallery with a glossy charcoal floor, narrow warm spotlights, and restrained amber reflections. Keep the same model, black outfit, right-leg placement, prosthetic structure, walk, pause, turn, camera movement, framing, timing, foot contact, and scene continuity. The new cover must remain securely aligned to the prosthesis through every step without warping or switching legs. Refined museum-like art direction, deep charcoal and glowing amber palette, crisp product detail, realistic materials, no lettering, logos, or graphics.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/04ab17e8-a34e-4e83-bb48-54f0a138ece8.mp4"
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-edit/03ecd975-cf57-4458-b832-9255f2939c01.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "fe1c7a03-030f-4e34-8c11-b0d50f5253ed",
  "model": "prunaai:p-video@edit",
  "positivePrompt": "Recolor only the espresso machine's cherry-red painted outer housing and side panels to a sophisticated muted sage-green enamel colorway. Keep the brushed stainless-steel front, chrome steam wand, black controls, portafilter, cup, counter, hand, and background unchanged. Preserve the exact camera arc, hand movement, timing, scene continuity, material reflections, shadows, and original audio. The new sage finish should look factory-applied, with consistent coverage and realistic glossy enamel highlights across every frame.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/3de5bc92-113c-48e6-a885-e16aadf341fc.mp4"
  }
}
```