Wan 3.0 Prompt Guide - Syntax, References, and Settings for the Perfect AI Videos

Wan 3.0 is Alibaba's creative video model, and you can use it on OpenArt's AI video generator. Wan 3.0 makes up to 30 seconds of video at once, takes 20 reference files, and makes audio at the same time as the picture, fully synced.

Alibaba published its own prompt formulas when the model launched, and this guide turns them into simple steps you can copy, along with how to get on-screen words right, and how it compares with other video models on OpenArt.

Key takeaways

• Start with a subject, a place, and a movement. Add the camera, the style, and the sound one at a time.
• Label every reference with @Image1, @Video1, or @Audio1, and give each shot a time range like [0-6s].
• Write voice lines, sound effects, and music separately, and say "no background music" when you do not want it.
• Put on-screen words in quotation marks and keep them short.
• Wan 3.0 makes videos from 2 to 30 seconds long at up to 1080p, and it is a strong pick for long videos built from many references.

What is Wan 3.0?

Wan 3.0 is Alibaba's newest AI video model. It turns a written prompt, a picture, or a mix of pictures, video clips, and audio clips into a video up to 30 seconds long, with sound included.

Wan 3.0 makes the whole video in one go, so the same face, product, and lighting carry through every second. On OpenArt you can start a Wan 3.0 video from text, from a starting picture, or from a set of reference files.

Wan 3.0 prompt guide: start with three things

Alibaba's starter formula is short. You need a subject, a place, and a movement.

"A red fox walks across a snowy field at sunrise." That prompt has all three, and it is enough to get a real video back.

Once that works, the fuller formula adds three more: how the shot looks, the style, and the sound. Add them one at a time so you can see what each one changed.

Label every reference with @ tags

Wan 3.0 takes up to 20 reference files, and OpenArt counts them for you at the top of the upload box.

Uploading them is only half the job. Wan 3.0 will not guess that picture 3 is the coffee shop and picture 4 is the jacket, so say it in the prompt with the @ label:

@Image1 is the woman. @Image2 is the coffee shop. @Audio1 is her voice. The woman from @Image1 sits by the window in @Image2 and orders a coffee.

Alibaba's own examples label every single reference this way. You can also name the same reference more than once in one prompt, which is how you control where it shows up.

Start and end frames work the same way. On OpenArt you can set the picture your video opens on and the picture it closes on, and still add reference files next to them.

Say in the prompt which picture is the opening frame, which is the closing frame, and what each reference is for.

Your video references can add up to 15 seconds, and your audio references another 15 seconds. To get the same person in video after video, save them once in OpenArt Characters and pick them for each new video.

Number your shots and give each one a time

Wan 3.0 makes up to 30 seconds at once, so tell it what happens from start to finish. Alibaba's format is a short summary first, then numbered shots with time ranges:

A short story about a girl who finds a stray cat.

Shot 1 [0-5s]: She walks home in the rain and stops under a doorway.

Shot 2 [5-12s]: Close up on a small wet cat looking up at her.

Shot 3 [12-20s]: She kneels down and holds out her hand.

Give each time range one clear thing to do. If a shot feels rushed in your first result, widen that one time range and leave the rest alone.

For a story longer than 30 seconds, OpenArt can plan the scenes and make the full video, up to 5 minutes long, in Director mode.

Write the sound as three separate things

Wan 3.0 makes the sound at the same time as the picture, so you can shape it with words. Alibaba splits sound into three parts, and it helps to write each one separately.

Voice lines. Say the line, then say how it is said. "She says, 'I told you this would happen.' Fast, a little annoyed, American English."

Sound effects. Name the thing, what it does, and the background noise. "A glass falls off the table and shatters on the wood floor, quiet room."

Music. Name the music and the style. "Slow piano under the whole scene."

Put on-screen words in quotation marks

Alibaba says Wan 3.0 shows app screens and moving graphics clearly, which helps with product demos and explainer ads. Alibaba also says the spelling of on-screen words is still improving, so a few habits make a big difference.

Put the exact words in quotes. Alibaba's own guide asks for this. "A coffee bag on a kitchen counter with the words 'MORNING ROAST' printed on the front."

Keep the words short. A brand name, a price, or a three-word title comes out cleaner than a full sentence.

Say where the words go. "A white title at the bottom of the screen" gives Wan 3.0 a clear place to put your text.

Start from a picture that already has the words. For a logo or a product label that must be exact, make the picture first with an image model built for text, like Nano Banana 2.1 or GPT Image 2.5.

Set it as your start frame, and Wan 3.0 begins the video from words that are already spelled right.

Fix a wrong letter with an edit. If one word comes out misspelled, ask for that one fix and say the rest of the video stays the same.

Three things Wan 3.0 auto decides for you

When you say nothing, Wan 3.0 still makes a choice. Here is how to take each one back.

Voice lines. Write out what someone says and Wan 3.0 keeps your exact words. Say nothing and it will make up voice lines of its own. Turn that off with "no voice lines in the whole video."

Music. Wan 3.0 picks background music based on what your video is about. Turn that off with "no background music."

Number of shots. Wan 3.0 decides on its own whether to cut between shots. Ask for one unbroken shot with "one continuous take."

Length and shape work the same way. Leave them blank and Wan 3.0 picks a length between 2 and 30 seconds, plus an aspect ratio that suits your scene.

Wan 3.0 resolution and length options

On OpenArt, Wan 3.0 makes video at 480p, 720p, or 1080p, in any length from 2 to 30 seconds. You can also leave the length to Wan 3.0, and it picks one that suits your prompt.

Resolution changes the price. A 1080p video costs about four times the credits of the same video at 480p, so test your prompt at 480p and make the final version at 1080p.

Longer videos cost more credits too. Set the exact length once you know how many shots you need.

Check four controls before you generate

On OpenArt, four settings sit around the prompt box, and each one changes what your words do.

Auto Polish. This rewrites your prompt before it runs. That helps when you have typed one loose sentence, but it can also reword the reference labels and time ranges you set on purpose. Switch it off once your prompt is exact.

Audio. Leave this on and Wan 3.0 makes sound with the picture. Switch it off for a silent clip, which is the quickest way to stop unwanted music.

Camera. Pick your camera move here. You get the same move every time, and your prompt stays shorter.

Mode. Standard and Prime set the quality level, and Prime costs more credits. Test your prompt on Standard, then make the version you like on Prime.

You can also run up to 8 videos at once. Change one thing in each version, run all 8, and compare them to see what each word is doing.

Say less when you start from a picture

When you upload a starting picture, that picture already shows who is in it, where they are, and how it all looks. Repeating that in the prompt just fights the picture you uploaded.

So write two things only: what moves, and what the camera does. "She turns toward the window and smiles. Slow push in."

If you want the camera to hold still, say "fixed shot." Otherwise Wan 3.0 will move the camera on its own.

Fix one thing with a plain edit

Wan 3.0 edits video from plain instructions, so one small problem takes one quick fix. Name what you want changed, then say the rest stays the same.

Remove the sunglasses. Her movement and everything else in the video stays the same.

The same wording works for adding something, changing the style, fixing the light, or swapping a voice line.

Four mistakes that waste generations

• Describing one still picture. Say what changes across the 30 seconds.
• Leaving references unlabeled. If you upload six files, say what each one is for.
• Stacking camera moves. One clear move beats three fighting each other.
• Forgetting to turn off sound you never asked for. Music and voice lines show up on their own.

Wan 3.0 quality verdict

Wan 3.0 is one of the best picks on OpenArt for 15 to 30 second videos built from many references. Because it makes the whole video at once, faces, products, and lighting stay steady from the first second to the last.

Faces look real and show small changes in expression, and early testers report that the same person holds up across a full 30 seconds. The sound comes out timed to the action, so a clip is ready to post with audio.

Plan around a few limits. The top resolution is 1080p, and Alibaba says sound texture and on-screen spelling are still improving.

Early testers also report two habits. Wan 3.0 sometimes adds a cut you did not ask for, so write "one continuous take" when you want a single shot.

Small details can also slip when many people and props share one scene. Keep each shot to a few key people and objects, and label every reference.

The verdict: use Wan 3.0 for ads, product videos, and story scenes where one person or product has to look the same the whole way through. For a short 4K clip, the comparison below points you to a better fit.

How Wan 3.0 compares to other models on OpenArt

OpenArt runs Wan 3.0 next to other top video models, so you can pick the right model for each job in one place.

Pick Seedance 2.5 when a story needs lots of characters and props, because it takes the most reference files. Pick Wan 3.0 when your reference is a document or a web page, like a product page or a slide deck.

Pick Kling 3.0 or Veo 3.1 when the final file must be 4K and the video is short. Pick MiniMax H3 for realistic movement in clips up to 15 seconds, and Grok Imagine 1.5 when speed matters most.

Start making Wan 3.0 videos

Wan 3.0 follows clear, labeled prompts closely. Start with a subject, a place, and a movement, then label every reference and give each shot a time.

Spell out the sound and the on-screen words you want, and test at 480p before you make the final version. Write your first prompt with Wan 3.0 on OpenArt.

Frequently asked questions

How many references can Wan 3.0 use?

Wan 3.0 takes up to 20 references in one video: 10 images, 5 video clips, and 5 audio clips. You can add one document or web page on top of that, so a character, a product, a location, and a voice can all guide the same shot. Your video references can add up to 15 seconds, and your audio references another 15 seconds.

How long can a Wan 3.0 video be?

A Wan 3.0 video can be any length from 2 to 30 seconds. If you leave the length blank, Wan 3.0 picks a length that suits your prompt.

What resolution does Wan 3.0 support?

Wan 3.0 makes video at 480p, 720p, or 1080p, and 1080p is the top setting. On OpenArt, 480p costs the fewest credits, so it is the best setting for testing a prompt before you make the final 1080p version.

Does Wan 3.0 make sound?

Yes. Wan 3.0 makes voice lines, sound effects, and music at the same time as the picture. Describe the sound you want in the prompt, or switch audio off if you want a silent clip.

Can Wan 3.0 put text in a video?

Yes. Wan 3.0 can show titles, labels, prices, and app screens in a video, and it spells them best when you put the exact words in quotation marks and keep them short. For a logo or label that must be spelled perfectly, make a picture with the words first and use it as your start frame.

Can I use reference files and a start and end frame at the same time?

Yes. On OpenArt you can set the picture your video starts on, the picture it ends on, and still add reference files alongside them. Label each one in the prompt so Wan 3.0 knows which picture opens the video, which one closes it, and which references carry your character, product, or voice.

How is Wan 3.0 different from Wan 2.7?

Wan 3.0 adds 30-second videos, sound made with the picture, and video and audio clips as references. Wan 2.7 takes picture references and start and end frames, and it works well for shorter clips.