# Pruna P-Video 2

> Pruna's quality-focused successor to P-Video. Generates video from text, a starting image, or an audio track, with native-speech lip-sync, sharp close-ups and strong identity consistency, up to 1080p / 48 fps, plus a low-cost draft mode for fast iteration.

- **Provider**: replicate
- **Model ID**: prunaai/p-video-2
- **Category**: video_generation
- **Credits**: 350 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `disable_safety_filter` (boolean, optional): Disable safety filter for prompts (and input image). When disabled, prompts are not checked for unsafe content before generation. (Default: `True`)
- `image` (string, optional): Optional. Input image to generate video from (image-to-video). Supports jpg, jpeg, png, webp.
- `aspect_ratio` (string, optional): Aspect ratio of the video. Ignored when an input image is provided. (Default: `16:9`; Options: `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `1:1`)
- `save_audio` (boolean, optional): Save the video with audio. (Default: `True`)
- `seed` (integer, optional): Random seed. Set for reproducible generation.
- `last_frame_image` (string, optional): Optional. Reference image for the last frame of the video. Supports jpg, jpeg, png, webp.
- `fps` (integer, optional): Frames per second of the video. 24 fps is recommended at 1080p, 48 fps at 720p for smoother motion. (Default: `24`; Options: `24`, `48`)
- `resolution` (string, optional): Resolution of the video. (Default: `720p`; Options: `720p`, `1080p`)
- `duration` (integer, optional): Duration of the video in seconds (1-20). Defaults to 5 when omitted. Ignored when audio is provided. (Default: `5`; Range: min: 1, max: 20)
- `draft` (boolean, optional): Draft mode. Generates a faster, lower-cost preview of the video. (Default: `False`)
- `prompt_upsampling` (boolean, optional): Use prompt upsampling to enhance the prompt. (Default: `True`)
- `audio` (string, optional): Optional. Input audio to condition video generation. Supports flac, mp3, wav. The output length follows the audio, so duration is ignored.
- `prompt` (string, **required**): Text prompt for video generation. Describe subject, action and scene; add camera, lighting, style and dialogue (for native speech) as needed.

## Example Request

```json
{
  "model": "prunaai/p-video-2",
  "input": {
    "duration": 5,
    "aspect_ratio": "16:9",
    "save_audio": true,
    "draft": false,
    "fps": 24,
    "prompt": "A lone astronaut walks steadily toward the camera across a vast rust-colored alien desert under a colossal ringed gas giant. The camera tracks backward at walking speed. Cinematic, photorealistic, continuous single shot.",
    "resolution": "720p"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

prunaai, video-generation, draft-mode, text-to-video, image-to-video, audio-to-video, lip-sync

## Documentation

https://replicate.com/prunaai/p-video-2