# Wan 2.7 I2V - Core.Today AI API

> Alibaba Wan 2.7 image-to-video model. Animates a first frame (and optional last frame or continuation clip) with audio synchronization, up to 15 seconds, at 720p or 1080p.

- **Provider**: Alibaba
- **Model ID**: wan-video/wan-2.7-i2v
- **Category**: Video Generation
- **Credits**: 1740 per second, tiered by resolution
- **Speed**: Medium
- **Quality**: High

## Features
- Image-to-video animation from a first frame
- Optional last-frame targeting or continuation from an existing video clip
- Audio synchronization for voice and music (auto-generated or user-supplied)
- Automatic prompt expansion
- 720p/1080p output, up to 15 seconds

## Use Cases
- Animating product photos or illustrations into short video clips
- First-and-last-frame video generation for controlled transitions
- Extending an existing short video clip with a new continuation
- Multilingual voice-synced content driven by a static image

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Optional
- **prompt**: string - Text prompt for video generation
- **first_frame**: string - First frame image to animate into video (jpg/png/bmp/webp, ≤20MB)
- **last_frame**: string - Last frame image for first-and-last-frame video generation (jpg/png/bmp/webp, ≤20MB). Requires first_frame.
- **first_clip**: string - Video clip to continue from (mp4/mov, 2-10s, ≤100MB). Cannot be combined with first_frame.
- **audio**: string - Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization. If not provided, the model auto-generates matching audio.
- **negative_prompt**: string - Negative prompt — describes content that should not appear in the video
- **resolution**: string (default: 1080p) - Output video resolution
  Options: 720p, 1080p
- **duration**: integer (default: 5) - Duration of the generated video in seconds
- **enable_prompt_expansion**: boolean (default: true) - Automatically expand and optimize the prompt for better results. Improves quality for short prompts but increases latency.
- **seed**: integer - Random seed for reproducible generation. Range: 0-2147483647

## Examples

### Animate a product photo
Turn a static product image into a short animated video clip.
```json
{
  "model": "wan-video/wan-2.7-i2v",
  "input": {
    "first_frame": "https://example.com/product-shot.jpg",
    "prompt": "The product slowly rotates on a reflective surface as soft studio light sweeps across it.",
    "resolution": "1080p",
    "duration": 5
  }
}
```

### First-and-last-frame transition
Generate a controlled transition between two images using first and last frame anchors.
```json
{
  "model": "wan-video/wan-2.7-i2v",
  "input": {
    "first_frame": "https://example.com/scene-day.jpg",
    "last_frame": "https://example.com/scene-night.jpg",
    "prompt": "Time gradually shifts from day to night over the same landscape.",
    "duration": 8
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- first_clip lets you continue an existing video instead of starting from a single frame — but it can't be combined with first_frame.
- last_frame requires first_frame to already be set; use both together for controlled first-and-last-frame transitions.
- Leave `audio` empty to let the model auto-generate matching sound.
- duration can go up to 15 seconds, billed proportionally more at the per-second rate for longer clips.

## Documentation
https://replicate.com/wan-video/wan-2.7-i2v