# Vidu 2.0 | Image to Video

Vidu 2.0 Image to Video generates realistic, high-quality videos from a single image with smooth motion and visual consistency.

## API Information

- **Model Slug:** vidu-2-0-image-to-video
- **Branded URL:** https://www.eachlabs.ai/vidu/vidu-2-0/vidu-2-0-image-to-video
- **Provider:** Vidu
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** Per second cost varies by resolution: 360p at $0.025 per second, 720p at $0.05 per second, 1080p at $0.125 per second
- **Estimated Processing Time:** 30 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/vidu-2-0-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per second cost varies by resolution: 360p at $0.025 per second, 720p at $0.05 per second, 1080p at $0.125 per second

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per second cost varies by resolution: 360p at $0.025 per second, 720p at $0.05 per second, 1080p at $0.125 per second |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| bgm | boolean | No | false | - | Whether to add background music to the generated video. Only supported when the final video duration is 4 seconds. |
| resolution | string | No | 720p | 360p, 720p, 1080p | Output video resolution. For 4s duration: 360p, 720p, 1080p. For 8s duration: 720p only. Default: 720p. |
| image_url | string | Yes | - | - | URL of the input image to use as the start frame. Supported formats: PNG, JPEG, JPG, WebP. Max 50MB. Aspect ratio must be less than 4:1 or 1:4. |
| prompt | string | No | - | - | Text description for video generation. Max 5000 characters. |
| duration | integer | No | 4 | 4, 8 | Video duration in seconds. Options: 4 or 8. Default: 4. |
| movement_amplitude | string | No | auto | auto, small, medium, large | Movement amplitude of objects in the frame. Default: auto. |
| seed | integer | No | - | - | Random seed for reproducible results. Leave empty for random output. |

## 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": "vidu-2-0-image-to-video",
  "input": {
    "image_url": "https://cdn-us.eachlabs.ai/defaults/ff33c1d78a19e1e1db60b67dd7ba3c6eedb9dd823b0810e5e02b9c4e3834c27e.jpg"
  }
}'
```

## 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

**vidu-2-0-image-to-video — Image-to-Video AI Model**

Transform static images into dynamic, realistic videos with **vidu-2-0-image-to-video**, Vidu's advanced image-to-video AI model from the vidu-2.0 family. This model excels at generating high-quality videos from a single reference image plus text prompts, delivering smooth motion, visual consistency, and cinematic effects ideal for creators seeking "image to video AI" solutions. Developed by Vidu, vidu-2-0-image-to-video stands out in the competitive landscape by leveraging upgraded physics engines for human-like micro-expressions and secondary motion, enabling lifelike animations that maintain character identity across frames.

Whether you're animating product photos or character art, this **image-to-video AI model** produces outputs up to 1080p resolution with durations reaching 8-16 seconds, breaking beyond short-loop limitations for more narrative-driven content. Access the power of Vidu image-to-video through Eachlabs for seamless integration into your workflows.

## 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.