# Seedance 2 Fast Reference

> Video AI Model by ByteDance — available on Layer

Fast reference-guided video generation with multi-modal inputs and synchronized audio.

Seedance 2 Fast Reference is the accelerated reference-guided variant of ByteDance's Seedance 2 model. It accepts up to 9 reference images, 3 video clips, and 3 audio files alongside a text prompt for multi-modal guidance, enabling consistent character and style control across scenes — at a lower cost and faster speed than the standard Seedance 2 Reference model.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ByteDance |
| Category | Video |
| Price | 5.6 / megapixel second per megapixel_per_second |
| Aspect Ratios | 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 |
| Durations | 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s |

## Capabilities

- Audio Generation

---

[Try Seedance 2 Fast Reference](https://next.app.layer.ai/me/session/new?baseModelId=SEEDANCE_V2_FAST_REFERENCE) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)