Name: Reference-to-Video Generator API (Wan 2.7)
Brand: magicapi
SKU: api-magicapi-generate-videos-from-images-wan-video-wan-2-7-r2v
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎥 Reference-to-Video Generator API (Wan 2.7)

## Overview
Wan 2.7 R2V is Alibaba's Wan 2.7 reference-to-video model. It generates a video from a text prompt and reference images or clips of a character or object, and Alibaba describes it as preserving the subject's identity. You send a `prompt` plus `reference_images` and/or `reference_videos`, and get back the URL of one video.

Only `prompt` is required by the schema. You choose the resolution (720p or 1080p), aspect ratio, duration (2 to 10 seconds) and shot type.

## Features
- **Reference images**: `reference_images` is a list of image URLs (jpg, png, bmp or webp) of the character or object to feature in the video.
- **Reference videos**: `reference_videos` is a list of video URLs (mp4 or mov) of the character or object to feature in the video.
- **Text prompt**: `prompt` (required) describes the video. `negative_prompt` describes content that should not appear.
- **Resolution**: `720p` or `1080p` (default `1080p`).
- **Aspect ratio**: `16:9`, `9:16`, `1:1`, `4:3` or `3:4` (default `16:9`).
- **Duration**: 2 to 10 seconds (default 5).
- **Shot type**: `single` (default) or `multi`, the shot structure of the video.
- **Seed**: set `seed` (0 to 2147483647) to reproduce a result.

## Use Cases
1. **Character videos**: put the same character or mascot into new scenes from a reference image, like the example below.
2. **Product videos**: feature a product from reference photos in a short clip described by your prompt.
3. **Social media clips**: create vertical (`9:16`) or square (`1:1`) videos of a recurring character.
4. **Storyboards and previews**: try different scenes, shot types and durations with the same subject.

## Visual Examples
This is a real request sent through api.market and the file it returned.

### Example Input
Prompt: "The astronaut walks across a red desert on Mars as dust swirls"

Reference image (`reference_images`), a toy-like astronaut figure on a grey background: [view the reference image](https://blog.api.market/wp-content/uploads/2026/09/kling-v2-6-motion-control-input-character-api-market.webp)

Settings: `resolution` `720p`. All other fields were left at their defaults (`duration` 5, `aspect_ratio` `16:9`, `shot_type` `single`).

### Example Output
[Watch the example video](https://blog.api.market/wp-content/uploads/2026/10/wan-2.7-r2v-output-api-market.mp4)

The request returned a 5 second 1280x720 MP4 video. The file linked here is a compressed copy of it.

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text prompt for video generation |
| `reference_images` | array of URLs | No | `[]` |  | Reference images of the character/object to feature in the video (jpg/png/bmp/webp) |
| `reference_videos` | array of URLs | No | `[]` |  | Reference videos of the character/object to feature in the video (mp4/mov) |
| `negative_prompt` | string | No | `""` |  | Negative prompt: describes content that should not appear in the video |
| `resolution` | string | No | `1080p` | `720p`, `1080p` | Output video resolution |
| `aspect_ratio` | string | No | `16:9` | `16:9`, `9:16`, `1:1`, `4:3`, `3:4` | Aspect ratio of the generated video |
| `duration` | integer | No | `5` | 2 to 10 | Duration of the generated video in seconds |
| `shot_type` | string | No | `single` | `single`, `multi` | Shot structure of the generated video |
| `seed` | integer | No | none | 0 to 2147483647 | Random seed for reproducible generation. Range: 0-2147483647 |

### Output
`output` is the URL of one MP4 video (a string).

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.125 per API unit.
- **1 API unit = 1 second of output video.** The seconds billed are the `duration` you request (default 5), so a request costs `duration` times $0.125.
- Resolution (`720p` or `1080p`), aspect ratio, shot type and the number of reference images or videos do not change the price.
- **Worked examples**:
  - 2 second video: 2 units, $0.25.
  - 5 second video (the default, as in the example above): 5 units, $0.625.
  - 10 second video: 10 units, $1.25.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** (GET /api/v1/magicapi/generate-videos-from-images-wan-video-wan-2-7-r2v/predictions/{id}) are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/generate-videos-from-images-wan-video-wan-2-7-r2v`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`. 201 means the request was accepted; it is not an error.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/generate-videos-from-images-wan-video-wan-2-7-r2v/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "00f2bfc4cadaa306f7d52b705c06aee00a53457f6a5aa5bd72a67e4e08627a41",
    "input": {
      "prompt": "The astronaut walks across a red desert on Mars as dust swirls",
      "reference_images": [
        "https://blog.api.market/wp-content/uploads/2026/09/kling-v2-6-motion-control-input-character-api-market.webp"
      ],
      "resolution": "720p"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "ufawqhfynnddngldkgtslldrkq",
  "version": "00f2bfc4cadaa306f7d52b705c06aee00a53457f6a5aa5bd72a67e4e08627a41",
  "status": "starting",
  "created_at": "2026-10-13T11:16:05.733Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/generate-videos-from-images-wan-video-wan-2-7-r2v/predictions/ufawqhfynnddngldkgtslldrkq" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "ufawqhfynnddngldkgtslldrkq",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/wan-2.7-r2v-output-api-market.mp4",
  "error": null,
  "created_at": "2026-10-13T11:16:05.733Z",
  "started_at": "2026-10-13T11:16:06.251Z",
  "completed_at": "2026-10-13T11:18:41.090Z"
}
```

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `prompt`, a `duration` outside 2 to 10, or a `resolution`, `aspect_ratio` or `shot_type` that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits

All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide

### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/generate-videos-from-images-wan-video-wan-2-7-r2v";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "00f2bfc4cadaa306f7d52b705c06aee00a53457f6a5aa5bd72a67e4e08627a41", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "prompt": "The astronaut walks across a red desert on Mars as dust swirls",
  "reference_images": [
    "https://blog.api.market/wp-content/uploads/2026/09/kling-v2-6-motion-control-input-character-api-market.webp"
  ],
  "resolution": "720p"
}).then((output) => console.log(output));
```

### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/generate-videos-from-images-wan-video-wan-2-7-r2v"

def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "00f2bfc4cadaa306f7d52b705c06aee00a53457f6a5aa5bd72a67e4e08627a41", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])

def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")

print(create_and_wait_for_prediction({
  "prompt": "The astronaut walks across a red desert on Mars as dust swirls",
  "reference_images": [
    "https://blog.api.market/wp-content/uploads/2026/09/kling-v2-6-motion-control-input-character-api-market.webp"
  ],
  "resolution": "720p"
}))
```

## FAQ
- **Which inputs do I need to send?**
  - `prompt` is required. Add the character or object you want in the video as `reference_images` (image URLs) and/or `reference_videos` (video URLs).
- **How long can a video be?**
  - From 2 to 10 seconds, set with `duration`. The default is 5 seconds.
- **Does 1080p cost more than 720p?**
  - No. Both are billed at $0.125 per second of video. A 5 second video costs $0.625 at either resolution.
- **How long does a prediction take?**
  - It varies by request. Poll every second and stop after 10 minutes.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us

If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Reference-to-video API: generate 2 to 10 second videos from reference images or clips and a prompt with Alibaba Wan 2.7 R2V, 720p or 1080p. $0.125 per second.