# Ovi | Image to Video

Ovi is an advanced image-to-video model that transforms a single image and text input into ultra-realistic, smoothly animated video sequences with synchronized audio, natural motion, lighting, and depth.

## API Information

- **Model Slug:** ovi-image-to-video
- **Branded URL:** https://www.eachlabs.ai/openvision/ovi/ovi-image-to-video
- **Provider:** OpenVision
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Fixed pricing: $0.2 per request
- **Estimated Processing Time:** 50 seconds
- **Last Updated:** 2026-04-16
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/ovi-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.2000
- **Pricing Details:** Fixed pricing: $0.2 per request

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Fixed pricing: $0.2 per request |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The text prompt to guide video generation. |
| image_url | string | Yes | - | - | The image URL to guide video generation. |
| negative_prompt | string | No | jitter, bad hands, blur, distortion | - | Negative prompt for video generation. |
| audio_negative_prompt | string | No | robotic, muffled, echo, distorted | - | Negative prompt for audio generation. |
| num_inference_steps | integer | No | 30 | 1–50 | The number of inference steps. |
| seed | string | No | - | - | Random seed for reproducibility. If None, a random seed is chosen. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ovi-image-to-video",
  "input": {
    "prompt": "A close-up shot of a young woman speaking softly in a dimly lit room. Her expression is calm but emotional as she says: “I just need to breathe.”\nInclude synchronized lip movement and natural room ambience — faint breathing, subtle reverb, and a distant hum. Soft cinematic lighting, shallow depth of field, 24 FPS.",
    "image_url": "https://storage.googleapis.com/magicpoint/inputs/ovi-image-to-video-input.png"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**ovi-image-to-video — Image-to-Video AI Model**

Transform static images into ultra-realistic video sequences with synchronized audio using ovi-image-to-video, OpenVision's cutting-edge image-to-video AI model from the ovi family. This model excels at generating smoothly animated videos from a single image and text prompt, capturing natural motion, dynamic lighting, depth effects, and integrated soundscapes—ideal for creators seeking "image to video AI" solutions that deliver professional-grade results without complex editing. Developers and designers turn to **ovi-image-to-video** for its ability to produce high-fidelity outputs in minutes, solving the challenge of breathing life into photos for social media, marketing, or app integrations.

Part of OpenVision's ovi series, ovi-image-to-video stands out in the competitive landscape of image-to-video tools by prioritizing audio synchronization and realistic physics simulation, enabling seamless transitions from stills to cinematic clips.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.