# PixVerse v5 | Image to Video

Transform a still image into a short video. Animate photos and bring them to life with dynamic motion.

## API Information

- **Model Slug:** pixverse-v5-image-to-video
- **Branded URL:** https://www.eachlabs.ai/pixverse/pixverse-v5/pixverse-v5-image-to-video
- **Provider:** PixVerse
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** Image-to-video pricing depends on resolution and duration. A 5-second 540p video costs 45 credits ($0.28), 720p costs 60 credits ($0.38), and 1080p costs 120 credits ($0.75). 8-second videos cost roughly double.
- **Estimated Processing Time:** 25 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/pixverse-v5-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Image-to-video pricing depends on resolution and duration. A 5-second 540p video costs 45 credits ($0.28), 720p costs 60 credits ($0.38), and 1080p costs 120 credits ($0.75). 8-second videos cost roughly double.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Image-to-video pricing depends on resolution and duration. A 5-second 540p video costs 45 credits ($0.28), 720p costs 60 credits ($0.38), and 1080p costs 120 credits ($0.75). 8-second videos cost roughly double. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt describing the desired video motion and content. Max 2048 characters. |
| image_url | string | Yes | - | - | URL of the input image to animate into a video. Supported formats: JPEG, PNG, WEBP. |
| aspect_ratio | string | No | 16:9 | 16:9, 4:3, 1:1, 3:4, 9:16 | Video aspect ratio. |
| quality | string | Yes | 540p | 360p, 540p, 720p, 1080p | Output video resolution quality. Options: 360p, 540p, 720p, 1080p. Default: 540p. |
| duration | string | Yes | 5 | 5, 8 | Duration of the output video in seconds. Options: 5 or 8. Default: 5. |
| motion_mode | string | No | normal | normal | Motion intensity. Only normal mode is supported for v5. fast mode is available on v4/v4.5 models only. |
| negative_prompt | string | No | - | - | Text describing elements to avoid in the generated video. Max 2048 characters. |
| style | string | No | - | anime, 3d_animation, clay, comic, cyberpunk | Visual style preset for the video. Options: anime, 3d_animation, clay, comic, cyberpunk. If not set, no style preset is applied. |
| seed | integer | No | - | 1–2147483647 | Random seed for reproducible results. Range: 1-2147483647. If not provided, a random seed is chosen. |
| sound_effect_switch | boolean | No | false | - | Enable automatic sound effect generation for the video. Default: false. |
| sound_effect_content | string | No | - | - | Description of the desired sound effect to generate. Only used when sound_effect_switch is enabled. |
| lip_sync_switch | boolean | No | false | - | Enable lip sync with text-to-speech for characters in the video. Default: false. |
| lip_sync_tts_content | string | No | - | - | Text content for lip sync text-to-speech. Approximately 140 UTF-8 characters max. Only used when lip_sync_switch is enabled. |
| lip_sync_tts_speaker_id | string | No | - | auto, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14 | Speaker voice ID for lip sync TTS. Options: auto (automatic selection), or 1-14 for specific voices. Only used when lip_sync_switch is enabled. |

## 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": "pixverse-v5-image-to-video",
  "input": {
    "duration": 5,
    "image_url": "https://cdn-us.eachlabs.ai/defaults/771e2b062167e31b15bb434a0e95b991103bddb5bd671411b1274b5174761c23.webp",
    "prompt": "A man raises his sword, lightning flashes in the sky, and a dragon flies away, drone-style flyover",
    "quality": "540p"
  }
}'
```

## 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

**pixverse-v5-image-to-video — Image-to-Video AI Model**

Developed by Pixverse as part of the **pixverse-v5** family, **pixverse-v5-image-to-video** transforms static images into dynamic short videos up to 8 seconds long, bringing photos to life with smooth motion and high fidelity. This **image-to-video AI model** excels in maintaining subject consistency while adding cinematic animations, ideal for creators seeking quick, professional-grade clips without complex editing. Access **pixverse-v5-image-to-video** on Eachlabs for fast generation times around 30 seconds at 1080p resolution, supporting aspect ratios like 16:9 and 9:16 for versatile **Pixverse image-to-video** outputs.

## 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.