Wan 3.0 AI video generator

VideoWan 3.0ResolutionAspect ratioDuration
Create now

Alibaba's Wan 3.0 is here. What it does, and where to use it.

Every video model

One workspace

Video on Morphic

Generate now

Key features

Native 30-second clips

One continuous run reaches 30 seconds, double Wan 2.7's 15, with intelligent duration matched to the prompt.

Video from documents

Feed it a doc, sheet, deck, pdf, or webpage and Wan 3.0 reads it and builds video from the content. An industry first.

Omni-Reference

Up to 20 references, spanning image, video, audio, documents, and webpages, held consistent across the clip.

Reality-grade rendering

More expressive faces and micro-expressions, steadier references, and cleaner on-screen text and digital content.

Audio in the same pass

Sound is generated with the picture in one pass, so a clip comes back scored rather than silent.

Precision video editing

Instruction- and reference-based editing: reselect a time interval and regenerate just that part, dialogue included.

Generate a video in three steps

  1. 01

    Open Morphic

    Sign up and start generating on a free-flowing, infinite visual canvas.

  2. 02

    Write the shot as an arc

    Subject, action, camera move, light. Say how the frame changes across the take, not just what is in it.

  3. 03

    Generate and refine

    Render in minutes. Reuse a reference to hold a character across shots, and compare takes on the Canvas.

Generate now

Related workflows

Cinematic scene

One image to a 9-scene cinematic video.

Try this workflow

Time-freeze effect

Cinematic time-freeze short film for any scene

Try this workflow

Short film creator

Go from any idea to a finished short film with scenes, visuals, video, and music.

Try this workflow

Renovation timelapse

Photo of any real-estate becomes a cinematic renovation timelapse video with construction SFX and music.

Try this workflow

Motion transfer

Pair a character image with a reference video. Your character picks up that exact motion.

Try this workflow

Video style transfer

Restyle any video in a completely new visual style. Every frame transforms, all motion stays intact.

Try this workflow

All on Morphic

Your complete video stack

Models

Wan 2.7, Seedance 2.5, Kling 3.0, Veo 3.1, and more. Pick the one that fits the shot and swap mid-project.

Frames to video

Set 2 to 5 keyframes, describe the motion, and Morphic fills the in-between. Time Control tunes how long each frame holds.

Camera rig

Pick the camera body, lens, and focal length like a DP. Color, contrast, and texture shift to match. Same scene, three looks.

Workflows

Turn a finished sequence into a one-click Workflow. Rerun it, share the link, or favorite it for fast reuse.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

900 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3200 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6200 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24000 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

Can I use a Wan 3.0 AI video generator right now?
Wan 3.0 is live in public beta, but on Alibaba's own platforms: Alibaba Cloud Model Studio and Qwen Cloud, as the model wan3.0-video, with access on wan.video rolling out to members. It is not in the Morphic catalog. You can generate video right now on Morphic with the models it does run, and any random site claiming a free Wan 3.0 generator is likely serving a different model behind the label.
What does Wan 3.0 do?
Wan 3.0 generates native 1080p clips up to 30 seconds in a single run, with audio in the same pass. Its standout feature is Omni-Reference: alongside text, image, audio, and video it reads documents, spreadsheets, slides, pdfs, and webpages and builds video from them. It also does instruction- and reference-based editing, so you can reselect a time interval and regenerate just that part.
Has Wan 3.0 launched?
Yes. Alibaba launched Wan 3.0 in public beta on 6 August 2026. This corrects earlier speculation from July, when the model was only a rumor: the API model ID, the 480p, 720p, and 1080p resolution tiers, and per-second pricing are all now published. There is still no 4K tier, and no open weights.
Will the Wan 3.0 generator be free?
Not on Alibaba's platforms. Wan 3.0 is a paid API, billed per second by resolution, and its beta is metered. Alibaba's open weights stop at Wan 2.2, which is free to download and self-host; Wan 3.0 itself is closed. Morphic offers a free tier so you can start generating video today with the models in its catalog.
What can I use instead of Wan 3.0 today?
Wan 2.7 is the newest Wan generation available for self-hosting-friendly workflows, with text-to-video, image-to-video, and reference-to-video at up to 1080p. Beyond the Wan line, Morphic runs Seedance, Kling, Veo, and others in one workspace, so you can compare takes across models on the same prompt and pick the one that suits the shot.
How do I generate a video online without installing anything?
Everything runs in the browser on Morphic, with no download or install. Type the prompt, generate, and the render lands on your Canvas, from any laptop, including machines with no GPU.

You might also like