# Wan 3.0 Reference

> Video AI Model by Alibaba — available on Layer

Reference-guided Wan 3.0 video with up to 10 images, 5 videos, and 5 audio files.

Wan 3.0 Reference is the reference-guided mode of Alibaba's Wan 3.0 video model. It accepts up to 10 reference images, 5 video clips, and 5 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. Reference media can be addressed positionally in the prompt (e.g. Image 1, Video 1), making it ideal for brand-consistent series and multi-shot production.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Alibaba |
| Category | Video |
| Price | 4.5 / megapixel second per megapixel_per_second |
| Aspect Ratios | 16:9, 9:16, 4:3, 3:4, 1:1 |
| Durations | 2s, 3s, 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 Wan 3.0 Reference](https://next.app.layer.ai/me/session/new?baseModelId=WAN_30_REFERENCE) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)