PixVerse v4.5 Fusion

PixVerse v4.5 | Fusion

Generate videos by fusing multiple reference images together, guided by a text prompt. Combine elements from different images into a cohesive video.

Quick Start

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v4-5-fusion",
    "version": "0.0.1",
    "input": {
      "prompt": "A character from the first image walking through the landscape from the second image",
      "image_references": ["https://example.com/character.jpg", "https://example.com/landscape.jpg"],
      "aspect_ratio": "16:9",
      "duration": 5,
      "quality": "720p"
    }
  }'

Parameters

Output

• Type: video

Examples

Character in Environment

{
  "model": "pixverse-v4-5-fusion",
  "version": "0.0.1",
  "input": {
    "prompt": "The character walks confidently through the futuristic city",
    "image_references": ["https://example.com/hero-character.jpg", "https://example.com/scifi-city.jpg"],
    "aspect_ratio": "16:9",
    "duration": 5,
    "quality": "1080p"
  }
}

Multi-Element Composition

{
  "model": "pixverse-v4-5-fusion",
  "version": "0.0.1",
  "input": {
    "prompt": "A mystical scene combining the elements from all reference images",
    "image_references": ["https://example.com/castle.jpg", "https://example.com/dragon.jpg", "https://example.com/wizard.jpg"],
    "aspect_ratio": "16:9",
    "duration": 5,
    "quality": "720p",
    "seed": 42
  }
}

Related Models

• PixVerse v5 Text to Video - Generate videos from text
• PixVerse v5 Image to Video - Animate single images
• PixVerse v5 Transition - Create transitions between images

Documentation

• EachLabs API Docs