# P-Video Avatar

> PrunaAI's avatar/lipsync video model that generates talking-head videos from a single portrait image, driven either by a voice script (with built-in TTS) or an uploaded audio clip

## Quick Reference

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

## Specifications

- Max Resolution: 1920x1080
- Input Modalities: text, image, audio
- Output Modalities: video, audio
- Supported Modes: Image to Video

## Model Identifiers

- Primary Slug: p-video-avatar


## Tags

video-generation, image-to-video, audio-to-video, avatar, lipsync, audio-generation

## Available Providers

### Replicate

- Config Key: replicate/p-video-avatar
- Provider Model ID: prunaai/p-video-avatar
- Pricing: Free/second, Free/second
  - Note: Replicate currently lists both 720p and 1080p as free during launch campaign through Sunday night CET.
  - Note: Normal README pricing is 720p at $0.025/second and 1080p at $0.045/second.
  - Source: https://replicate.com/prunaai/p-video-avatar


## Image Gallery

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

### Arena Video Results

- : Elo . Prompt: "Create a short 10–12 second talking avatar video from the provided input image: a futuristic but ..."

## Example Prompt

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

Create a short 10–12 second talking avatar video from the provided input image: a futuristic but realistic female AI avatar with a small capybara sitting calmly on her shoulder.

Scene detail:
The avatar stands in a sleek futuristic command room with soft holographic interface panels glowing behind her. One floating holographic panel clearly displays the model slug: “p-image-avatar”. The text should be visible in the scene, integrated naturally into the sci-fi interface, not as a subtitle or overlay.

Camera directions:
- Start with a medium close-up, avatar centered, shoulders visible.
- Slow subtle push-in toward the avatar’s face as she speaks.
- Maintain steady eye contact with the camera.
- Add natural facial animation, lip sync, soft blinking, and slight head movement.
- The capybara stays perched on her shoulder, occasionally blinking or making a tiny head movement.
- Background remains softly out of focus, but the holographic “p-image-avatar” label should remain readable.
- Lighting: cool blue-white key light with gentle rim lighting, realistic skin and eye detail.
- End on a confident half-smile, with the capybara gently nuzzling closer.

Dialogue:
“Hello, human. I’m your next-generation AI companion. I analyze, adapt, and occasionally receive strategic advice from my capybara co-pilot. Together, we make the future feel a little calmer.”

Performance notes:
- Voice: warm, intelligent, calm, lightly playful.
- Pace: clear and conversational.
- Emotion: confident, friendly, subtly amused.
- No exaggerated gestures or cartoon movement.
- Keep the capybara cute but realistic.

## Code Examples

### 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-avatar",
    "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-avatar',
    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-avatar",
        "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 Avatar cost?

P-Video Avatar is free to use through Lumenfall's unified API.

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

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

### Which providers offer P-Video Avatar?

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

### What is the maximum resolution for P-Video Avatar?

P-Video Avatar supports videos up to 1920x1080 resolution.

## Links

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