# PixVerse Swap

PixVerse Swap replaces a subject or object in an existing video with a reference image. Provide a video and the new image, and Swap automatically targets the primary detected subject (face, body, or object). v1 caveat: the first detected subject (mask_info[0]) is auto-picked. Up to 720p; the source video codec must be h.264 or h.265.

## API Information

- **Model Slug:** pixverse-swap
- **Branded URL:** https://www.eachlabs.ai/pixverse/pixverse-features/pixverse-swap
- **Provider:** PixVerse
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing scales with quality:• 360p / 540p — $0.045• 720p — $0.0601080p is not supported.Optional mask selection adds a one-time $0.01 per request.Example: a 5-second 720p swap = $0.30.
- **Estimated Processing Time:** 160 seconds
- **Last Updated:** 2026-04-27
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/pixverse-swap

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing scales with quality:• 360p / 540p — $0.045• 720p — $0.0601080p is not supported.Optional mask selection adds a one-time $0.01 per request.Example: a 5-second 720p swap = $0.30.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing scales with quality:• 360p / 540p — $0.045• 720p — $0.0601080p is not supported.Optional mask selection adds a one-time $0.01 per request.Example: a 5-second 720p swap = $0.30. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| video_url | string | Yes | - | - | Source video. Codec must be h.264 or h.265. |
| replacement_image_url | string | Yes | - | - | Image of the replacement subject. |
| keyframe_id | integer | No | 1 | - | Frame index used for mask detection. Default 1 (first frame). |
| quality | string | Yes | 720p | 360p,540p,720p | Output video resolution quality. Options: 360p, 540p, 720p. Default: 720p. |

## 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-swap",
  "input": {
    "video_url": "https://cdn-us.eachlabs.ai/defaults/4226d70610652b0c8d3802f03d35272988f6e679be987c2b615edacc233d828f.mp4",
    "replacement_image_url": "https://cdn-us.eachlabs.ai/defaults/83e89ab50536b92f049e5d828483543624eb6690b109797c4722566388174aa6.png",
    "quality": "720p"
  }
}'
```

## 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 | Swap | Object Swap in Video Overview**

PixVerse | Swap | Object Swap in Video is a specialized video-to-video AI model from Pixverse that enables seamless replacement of subjects or objects in existing videos using a reference image. Users upload a source video and a new image, and the model automatically detects and swaps the primary subject—such as a face, body, or object—while preserving motion and scene coherence. This stands out by auto-targeting the first detected subject (mask_info) for precise, effortless editing without manual masking.

Developed by Pixverse, known for advanced models like V6 and C1 with cinematic transitions and native audio, PixVerse | Swap | Object Swap in Video extends their video-to-video capabilities to practical object manipulation. Available via the PixVerse | Swap | Object Swap in Video API on platforms like each::labs, it supports up to 720p resolutions and requires H.264 or H.265 source codecs, making it ideal for quick video repurposing in content creation 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.