# Seedance 2.0 Fast - Core.Today AI API

> A faster, cheaper variant of Seedance 2.0 for quicker video generation with multimodal reference inputs (up to 9 images, 3 videos, 3 audios) and native audio, at 480p or 720p.

- **Provider**: ByteDance
- **Model ID**: bytedance/seedance-2.0-fast
- **Category**: Video Generation
- **Credits**: 1750 per 5s 720p video, text/image input — billed per second (480p 163/s, 720p 349/s; with reference videos 480p 186/s, 720p 396/s)
- **Speed**: Fast
- **Quality**: High

## Features
- Faster, lower-cost alternative to Seedance 2.0 (480p/720p only, no 1080p/4K)
- Native audio generation — dialogue, sound effects, and background music
- Multimodal reference inputs: up to 9 images, 3 videos, 3 audio files
- Intelligent duration mode (duration: -1) lets the model pick the best length
- Reference videos raise the per-second price (~14-17%) for motion transfer/editing

## Use Cases
- Fast, low-cost social clips with synced audio
- Outfit-change or product showcase videos with reference images
- Quick motion-transfer edits using a reference video
- Dialogue scenes with lip-synced speech at a lower price point than Seedance 2.0
- High-volume batch generation where 1080p/4K isn't needed

## 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
- **image**: string - Input image for image-to-video generation (first frame). Cannot combine with reference images
- **last_frame_image**: string - Last frame image (requires a first frame image; cannot combine with reference images)
- **reference_images**: array (default: []) - Up to 9 reference images for character consistency and scene composition
- **reference_videos**: array (default: []) - Up to 3 reference videos (total ≤15s) for motion transfer and editing. Raises the per-second price
- **reference_audios**: array (default: []) - Up to 3 reference audio files (total ≤15s) for audio-driven generation and lip-sync
- **duration**: integer (default: 5) - Video duration in seconds (1-15). Set to -1 for intelligent duration
- **resolution**: string (default: 720p) - Video resolution (480p or 720p only)
  Options: 480p, 720p
- **aspect_ratio**: string (default: 16:9) - Video aspect ratio. 'adaptive' lets the model choose based on inputs
  Options: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21, adaptive
- **generate_audio**: boolean (default: true) - Generate synchronized audio (dialogue, SFX, background music) at no extra charge
- **seed**: integer - Random seed for reproducible generation

## Examples

### Cozy Scene with Audio (720p)
Text-to-video with synchronized ambient audio at the default 720p resolution
```json
{
  "model": "bytedance/seedance-2.0-fast",
  "input": {
    "prompt": "A cozy cabin in a snowy forest at night, warm light glowing from the windows, gentle snowfall, camera slowly pushing in through the trees",
    "duration": 7,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```

### Motion Transfer from Reference Video (480p)
Using a reference video for motion transfer at the cheaper 480p tier
```json
{
  "model": "bytedance/seedance-2.0-fast",
  "input": {
    "prompt": "The character from [Image1] performs the dance from [Video1]",
    "duration": 5,
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "generate_audio": false
  }
}
```

## 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 with 5 seconds and 720p while iterating, then scale up
- This -fast variant only supports 480p/720p (no 1080p/4K) — use Seedance 2.0 for higher resolutions
- Reference videos raise the per-second price ~14-17% — use them only when you need motion transfer or editing
- duration: -1 (intelligent duration) is billed conservatively at the 15-second worst case since the actual output length isn't known upfront
- Audio generation is included at no extra charge, unlike some competing models

## Documentation
https://replicate.com/bytedance/seedance-2.0-fast