Ovi Image To Video

Ovi | Image to Video

Animate images into videos with audio using the Ovi model. Supports configurable inference steps, negative prompts for both video and audio, and seed-based reproducibility.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "ovi-image-to-video",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/nature-scene.jpg",
      "prompt": "Wind blows through the trees, leaves scatter across the ground",
      "num_inference_steps": 30
    }
  }'

Parameters

Examples

Detailed scene animation with custom quality:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "ovi-image-to-video",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/cafe-interior.jpg",
      "prompt": "People chatting at tables, a waiter carries drinks, steam rises from cups",
      "num_inference_steps": 40,
      "negative_prompt": "jitter, bad hands, blur, distortion, low quality",
      "audio_negative_prompt": "robotic, muffled, echo, distorted, noise"
    }
  }'

Reproducible animation:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "ovi-image-to-video",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/dog-in-park.jpg",
      "prompt": "The dog wags its tail and runs toward the camera playfully",
      "num_inference_steps": 30,
      "seed": "42"
    }
  }'

Related Models

• ovi-text-to-video - Text to video with Ovi

Documentation

• each::labs Docs
• API Reference