# Wan 2.5 I2V Fast - Core.Today AI API

> Fast image-to-video variant of Wan 2.5, optimized for rapid generation of animated videos from still images.

- **Provider**: Alibaba
- **Model ID**: wan-video/wan-2.5-i2v-fast
- **Category**: Video Generation
- **Credits**: 790 per video
- **Speed**: Medium
- **Quality**: High

## Features
- Faster generation than Wan 2.5 I2V
- Image-to-video animation
- Good motion quality
- Lip sync support
- Cost-effective option

## Use Cases
- Quick photo animation tests
- Rapid portrait animation
- Iterative image-to-video testing
- Social media animated content
- Batch image animation

## 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

### Required
- **prompt**: string - Text description of the desired motion and animation
- **image**: string - Input image for video generation

### Optional
- **seed**: integer - Random seed for reproducibility
- **audio**: string - Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization
- **duration**: integer (default: 5) - Video duration in seconds
  Options: 5, 10
- **resolution**: string (default: 720p) - Video resolution
  Options: 720p, 1080p
- **negative_prompt**: string - Negative prompt to avoid certain elements
- **enable_prompt_expansion**: boolean (default: true) - If set to true, the prompt optimizer will be enabled

## Examples

### Quick Portrait Test
Fast portrait animation test
```json
{
  "model": "wan-video/wan-2.5-i2v-fast",
  "input": {
    "prompt": "Person nodding gently and blinking naturally, subtle smile, realistic head movement",
    "image_url": "https://example.com/portrait.jpg",
    "aspect_ratio": "9:16",
    "duration": 5
  }
}
```

## 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
- Use for rapid iteration before switching to Wan 2.5 I2V for final output
- One-third the credit cost of the standard I2V version
- Ideal for testing different prompts with the same source image
- Same seed produces consistent results across fast and standard models