WAN 3.0 (by Alibaba)

Overview

Alibaba's successor to the WAN 2.x line. One model for text-to-video, image-to-video (optional end frame), and reference-to-video. Up to 30 seconds in one pass with native audio.

---

Quick facts

• Modes: Text → Video · Image → Video · Reference → Video

• Audio: Native sound generation

• Default: 720p · 5s

---

What it's great for

• Longer clips than WAN 2.x (up to 30s).

• Reference-guided video from images, video, or audio.

• Built-in sound without a separate audio pass.

---

Parameters

Control	Type	Default	Notes
Prompt	Text	—	Required
Aspect Ratio	Dropdown	auto	Model can decide
Resolution	Dropdown	720p	480p, 720p, 1080p
Duration	Dropdown	5s	Up to 30s

---

Modes

Mode	Estimated time	Required inputs	Typical use
Text → Video	~250s	Prompt	Long-form generation
Image → Video	~250s	Image, Prompt	Animate a still
Reference → Video	~250s	References	Guided generation

---