# Seedance 1 Lite - Core.Today AI API

> A lightweight ByteDance video generation model offering text-to-video and image-to-video support for 4-12 second videos at 480p, 720p, or 1080p resolution.

- **Provider**: ByteDance
- **Model ID**: bytedance/seedance-1-lite
- **Category**: Video Generation
- **Credits**: 420 per 5s 720p video — billed per second (480p 42/s, 720p 84/s, 1080p 168/s)
- **Speed**: Fast
- **Quality**: Standard

## Features
- Text-to-video and image-to-video generation in one model
- 4-12 second duration range with per-second billing
- 480p / 720p / 1080p resolution options
- Reference images (1-4) for character, avatar, or environment guidance
- Fixed-camera mode and last-frame conditioning

## Use Cases
- Short-form social clips from a text prompt
- Animating a product or portrait photo into a brief video
- Character-consistent shots using reference images
- Fast, low-cost previews before using the Pro tier
- Fixed-camera product showcase shots

## 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 prompt for video generation

### Optional
- **fps**: integer (default: 24) - Frame rate (frames per second)
  Options: 24
- **seed**: integer - Random seed for reproducible generation
- **image**: string - Input image for image-to-video generation
- **duration**: integer (default: 5) - Video duration in seconds (4-12). Billed per second of output
- **resolution**: string (default: 720p) - Video resolution
  Options: 480p, 720p, 1080p
- **aspect_ratio**: string (default: 16:9) - Video aspect ratio. Ignored if an image is used
  Options: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21
- **camera_fixed**: boolean (default: false) - Whether to fix camera position
- **last_frame_image**: string - Last frame image (requires a first frame image)
- **reference_images**: array - Reference images (1-4) for character/avatar/environment consistency. Not compatible with 1080p or first/last frame images

## Examples

### Text-to-Video (720p)
Simple text-to-video generation at the default 720p resolution
```json
{
  "model": "bytedance/seedance-1-lite",
  "input": {
    "prompt": "a woman walks in the park",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}
```

### 1080p Long-Form Clip
Higher resolution, longer 10-second clip for higher-quality output
```json
{
  "model": "bytedance/seedance-1-lite",
  "input": {
    "prompt": "a golden retriever puppy running along a sunny beach, waves rolling in behind it",
    "duration": 10,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }
}
```

## 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
- Billing is per second of output — start at 720p / 5s while iterating on prompts
- 1080p costs 2x the 720p rate and disables reference_images — use it for final renders only
- Reference images (1-4) help keep characters/products consistent across generations
- Duration can range from 4 to 12 seconds; the default 5s is the cheapest common choice

## Documentation
https://replicate.com/bytedance/seedance-1-lite