# P-Video

> PrunaAI's fast video generation model with built-in draft mode for rapid creative iteration, supporting text-to-video, image-to-video, and audio-to-video in a single endpoint

## Quick Reference

- Model ID: p-video
- Creator: PrunaAI
- Status: active
- Family: p-video
- Base URL: https://api.lumenfall.ai/v1

## Specifications

- Max Video Duration: 10 seconds
- Input Modalities: text, image, audio
- Output Modalities: video, audio
- Supported Modes: Text to Video, Image to Video

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/p-video?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Text prompt for video generation. Modes: Text to Video, Image to Video
- `seed` (integer): Random seed for reproducibility. Modes: Text to Video, Image to Video
- `duration` (number): Video duration in seconds. Modes: Text to Video, Image to Video

### Size & Layout

- `size` (string): Video dimensions as WxH pixels (e.g. "1920x1080") or aspect ratio (e.g. "16:9"). Values: 1365x768, 768x1365, 1254x836, 836x1254, 887x1182, 1024x1024, 1183x887. Modes: Text to Video, Image to Video
- `aspect_ratio` (string): Aspect ratio of the output video (e.g. "16:9", "1:1"). Values: 9:16, 2:3, 3:4, 1:1, 4:3, 3:2, 16:9. Modes: Text to Video, Image to Video
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: 1K. Modes: Text to Video, Image to Video

### Media Inputs

- `input_reference` (array) — REQUIRED: Input image(s) to animate into video. Modes: Image to Video

### Output & Format

- `n` (integer): Number of videos to generate. Default: 1. Modes: Text to Video, Image to Video

### Additional Parameters

- `audio` (string): Input audio to condition video generation. Supports flac, mp3, wav.. Modes: Text to Video, Image to Video. Only available via replicate
- `disable_safety_filter` (boolean): Disable safety filter for prompts (and input image). When disabled, prompts are not checked for unsafe content before generation.. Modes: Text to Video, Image to Video. Only available via replicate
- `draft` (boolean): Draft mode. Generates a lower-quality preview of the video.. Modes: Text to Video, Image to Video. Only available via replicate
- `fps` (integer): Frames per second of the video.. Modes: Text to Video, Image to Video. Only available via replicate
- `last_frame_image` (string): Reference image for the last frame of the video. Supports jpg, jpeg, png, webp.. Modes: Text to Video, Image to Video. Only available via replicate
- `no_op` (boolean): Health check mode - returns status without inference.. Modes: Text to Video, Image to Video. Only available via replicate
- `prompt_upsampling` (boolean): Use prompt upsampling to enhance the prompt.. Modes: Text to Video, Image to Video. Only available via replicate
- `save_audio` (boolean): Save the video with audio.. Modes: Text to Video, Image to Video. Only available via replicate


## Model Identifiers

- Primary Slug: p-video


## Tags

video-generation, text-to-video, image-to-video, audio-generation

## Available Providers

### Replicate

- Config Key: replicate/p-video
- Provider Model ID: prunaai/p-video
- Pricing: $0.020/second
  - Source: https://replicate.com/prunaai/p-video


## Performance Metrics

Provider performance over the last 30 days.

### replicate

- Median Generation Time (p50): 268ms
- 95th Percentile Generation Time (p95): 2633ms
- Average Generation Time: 829ms
- Success Rate: 100.0%
- Total Requests: 15


## Arena Benchmarks

### The Soul Gauntlet

- Elo: 1116
- Record: 4W / 3L / 0T (7 battles)
- Rank: #4 of 6

### Neon Rain Reverie

- Elo: 1041
- Record: 1W / 4L / 0T (5 battles)
- Rank: #4 of 6


## Image Gallery

4 images available for this model. Browse all at https://lumenfall.ai/models/prunaai/p-video/gallery

### Arena Video Results

- : Elo . Prompt: "Cinematic 16:9 wide shot of a cozy futuristic hobbyist workshop. In the center, a glowing hologra..."
- The Soul Gauntlet: Elo 1116. Prompt: "Extreme cinematic close-up of a beautiful young woman experiencing deep, raw emotion. Her express..."
- Neon Rain Reverie: Elo 1041. Prompt: "Hyper-realistic cinematic video of an elegant young woman in a flowing white silk dress dancing g..."
- The Will Smith Spaghetti Challenge: Elo 1000. Prompt: "A medium shot of Will Smith sitting at a cozy, dimly lit Italian restaurant, twirling a forkful o..."

## Example Prompt

The following prompt was used to generate an example video in our playground:

Cinematic 16:9 wide shot of a cozy futuristic hobbyist workshop. In the center, a glowing holographic interface displays the text "P-Video" in shimmering blue light. Slow camera zoom and pan across a workbench filled with glowing transistors and vintage tools. In the soft-focus background, a capybara wearing small reading glasses sits calmly on a velvet stool, nibbling on a sprig of parsley, completely ignored by the busy robotic arms assembling a gadget in the foreground. High detail, 4k.

## Code Examples

### Text to Video (/v1/videos/generations) — Async

#### cURL

# Step 1: Submit video generation request
VIDEO_ID=$(curl -s -X POST \
  https://api.lumenfall.ai/v1/videos \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "p-video",
    "prompt": "",
    "size": "1024x1024"
  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion
while true; do
  RESULT=$(curl -s \
    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \
    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')
  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then
    echo $RESULT | jq -r '.output.url'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo $RESULT | jq -r '.error.message'
    break
  fi

  sleep 5
done

#### JavaScript

const BASE_URL = 'https://api.lumenfall.ai/v1';
const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit video generation request
const submitRes = await fetch(`${BASE_URL}/videos`, {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'p-video',
    prompt: '',
    size: '1024x1024'
  })
});

const { id: videoId } = await submitRes.json();
console.log('Video ID:', videoId);

// Step 2: Poll for completion
while (true) {
  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {
    headers: { 'Authorization': `Bearer ${API_KEY}` }
  });
  const result = await pollRes.json();

  if (result.status === 'completed') {
    console.log('Video URL:', result.output.url);
    break;
  } else if (result.status === 'failed') {
    console.error('Error:', result.error.message);
    break;
  }

  await new Promise(r => setTimeout(r, 5000));
}

#### Python

import requests
import time

BASE_URL = "https://api.lumenfall.ai/v1"
API_KEY = "YOUR_API_KEY"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# Step 1: Submit video generation request
response = requests.post(
    f"{BASE_URL}/videos",
    headers=HEADERS,
    json={
        "model": "p-video",
        "prompt": "",
        "size": "1024x1024"
    }
)

video_id = response.json()["id"]
print(f"Video ID: {video_id}")

# Step 2: Poll for completion
while True:
    result = requests.get(
        f"{BASE_URL}/videos/{video_id}",
        headers=HEADERS
    ).json()

    if result["status"] == "completed":
        print(f"Video URL: {result['output']['url']}")
        break
    elif result["status"] == "failed":
        print(f"Error: {result['error']['message']}")
        break

    time.sleep(5)

### Image to Video (/v1/videos/generations) — Async

#### cURL

# Step 1: Submit image-to-video request
VIDEO_ID=$(curl -s -X POST \
  https://api.lumenfall.ai/v1/videos \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "p-video",
    "prompt": "",
    "image_url": "https://example.com/start-frame.jpg",
    "duration": "10",
    "aspect_ratio": "16:9"
  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion
while true; do
  RESULT=$(curl -s \
    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \
    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')
  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then
    echo $RESULT | jq -r '.output.url'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo $RESULT | jq -r '.error.message'
    break
  fi

  sleep 5
done

#### JavaScript

const BASE_URL = 'https://api.lumenfall.ai/v1';
const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit image-to-video request
const submitRes = await fetch(`${BASE_URL}/videos`, {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'p-video',
    prompt: '',
    image_url: 'https://example.com/start-frame.jpg',
    duration: '10',
    aspect_ratio: '16:9'
  })
});

const { id: videoId } = await submitRes.json();
console.log('Video ID:', videoId);

// Step 2: Poll for completion
while (true) {
  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {
    headers: { 'Authorization': `Bearer ${API_KEY}` }
  });
  const result = await pollRes.json();

  if (result.status === 'completed') {
    console.log('Video URL:', result.output.url);
    break;
  } else if (result.status === 'failed') {
    console.error('Error:', result.error.message);
    break;
  }

  await new Promise(r => setTimeout(r, 5000));
}

#### Python

import requests
import time

BASE_URL = "https://api.lumenfall.ai/v1"
API_KEY = "YOUR_API_KEY"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# Step 1: Submit image-to-video request
response = requests.post(
    f"{BASE_URL}/videos",
    headers=HEADERS,
    json={
        "model": "p-video",
        "prompt": "",
        "image_url": "https://example.com/start-frame.jpg",
        "duration": "10",
        "aspect_ratio": "16:9"
    }
)

video_id = response.json()["id"]
print(f"Video ID: {video_id}")

# Step 2: Poll for completion
while True:
    result = requests.get(
        f"{BASE_URL}/videos/{video_id}",
        headers=HEADERS
    ).json()

    if result["status"] == "completed":
        print(f"Video URL: {result['output']['url']}")
        break
    elif result["status"] == "failed":
        print(f"Error: {result['error']['message']}")
        break

    time.sleep(5)


## Frequently Asked Questions

### How much does P-Video cost?

P-Video starts at $0.02 per video through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use P-Video via API?

You can use P-Video through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "p-video". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer P-Video?

P-Video is available through Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

## Links

- Model Page: https://lumenfall.ai/models/prunaai/p-video
- About: https://lumenfall.ai/models/prunaai/p-video/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/prunaai/p-video/providers
- API Reference: https://lumenfall.ai/models/prunaai/p-video/api
- Benchmarks: https://lumenfall.ai/models/prunaai/p-video/benchmarks
- Use Cases: https://lumenfall.ai/models/prunaai/p-video/use-cases
- Gallery: https://lumenfall.ai/models/prunaai/p-video/gallery
- Playground: https://lumenfall.ai/playground?model=p-video
- API Documentation: https://docs.lumenfall.ai