# Seedance 2.5 Reference

> Video AI Model by ByteDance — available on Layer

Reference-guided Seedance 2.5 video with up to 30 images, 10 videos, and 10 audio files.

Seedance 2.5 Reference is the reference-guided mode of ByteDance's Seedance 2.5 model. It accepts up to 30 reference images, 10 video clips, and 10 audio files alongside a text prompt, enabling multi-modal control over style, character consistency, motion, and sound for clips up to 30 seconds at 480p, 720p, or 1080p.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ByteDance |
| Category | Video |
| Price | 9.07 / 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, 16s, 17s, 18s, 19s, 20s, 21s, 22s, 23s, 24s, 25s, 26s, 27s, 28s, 29s, 30s |

## Capabilities

- Audio Generation

---

[Try Seedance 2.5 Reference](https://next.app.layer.ai/me/session/new?baseModelId=SEEDANCE_V2_5_REFERENCE) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)