Alibaba video model with sound built in
WAN 3.0 AI Video Generator
WAN 3.0 turns one prompt into a cinematic scene with sound built in, from a single flowing shot to a multi-shot sequence up to 30 seconds long.
Make dance films, product commercials, claymation, talking characters and surreal VFX shots with WAN 3.0 on Pixel Dojo. It generates clips from 2 to 30 seconds with sound in the same pass, at 480p, 720p, 1080p, 2K or 4K, and it can follow your own reference images, videos and audio. Every WAN 3.0 clip on this page is one we made, and each shows the exact prompt so you can start from it.
10 credits ($0.63) per 5 s clip at 720p with audio. Included in every plan, from $10/month.
Already a member? Sign in
By Brian Lovett · Updated
What you can create with WAN 3.0
We made these six clips with WAN 3.0 on Pixel Dojo: a dance film, a 20 s multi-shot food scene, a perfume commercial, a claymation short, a talking character and a surreal VFX shot. Every one has its own soundtrack. Tap Use this prompt on any tile to start from it.
Dance and fashion at 1080p: crimson silk, a ring of flying water and one hard top light, held in a slow push-in for the full 10 s.
Symmetrical wide shot with a slow push-in, one continuous take. A dancer with a sleek black bun and a flowing crimson silk gown spins on a flooded concrete floor under a single hard white top light, her skirt fanning out and flinging a ring of water droplets that sparkle in the beam, a dark empty hall behind her. High contrast, deep blacks, 50mm lens, subtle film grain. Audio: splashing water, rustling silk, echoing footsteps, one low sustained cello note.
A 20 s scene in three shots from one prompt: the stall in the rain, a slow-motion wok close-up in the flames, then the same cook serving the plate with a smile.
A 20 second cinematic sequence in three shots about a night market cook. Shot 1 [0-6s]: wide shot, a street food stall glows under red paper lanterns in light rain as a cook in a white headscarf tosses noodles in a wok and a burst of flame leaps up. Shot 2 [7-13s]: hard cut to a close-up of the wok, noodles and vegetables flipping through the flames in slow motion, sparks and steam rising. Shot 3 [14-20s]: hard cut to a medium shot, the cook slides a steaming plate across the counter toward camera and smiles. Keep the cook, the stall and the rain consistent across shots. Audio: sizzling wok, roaring flame, rain on the canvas awning, lively market chatter.
A perfume commercial in macro: a water drop bursts into a crown splash beside the bottle, the amber glass stays crisp and a glint of light hits the gold cap.
Macro product shot with a slow dolly in, one continuous take, the whole bottle in frame. An unlabeled faceted glass perfume bottle with a brushed gold cap, filled with amber liquid, stands on wet black slate as a single water drop falls beside it and bursts into a crown splash, while a thin band of light sweeps across the glass and makes the liquid glow. Black studio background, glossy reflections, shallow depth of field, 100mm macro lens. Audio: one crisp water drip, a soft rising synth tone.
Claymation with charm: a one-eyed clay robot waters an orange flower on a floating moss island, with thumbprint texture in the clay and a clear stream of water that pools on the moss.
Stop-motion claymation, locked-off medium shot. A small round clay robot with a teal body and one big glowing eye tips a tiny watering can over a single orange flower on a floating island of moss, and the flower opens its petals as the water lands. Fingerprints visible in the clay, soft miniature set lighting, pastel sky backdrop, charming stop-motion stutter. Audio: tiny mechanical whirs, a gentle water trickle, a cheerful plucked ukulele melody.
A talking character close-up: he looks up from the brass lamp and delivers his line, warm lamp glow on his face and rain on the glass behind him.
Medium close-up with a slow push-in, one continuous take. A weathered lighthouse keeper in his sixties with a white beard and a navy wool cap looks up from polishing a brass lamp and says quietly: "Forty years, and the light never went out." Warm tungsten lamplight on his face against blue dusk windows, rain streaking the glass, 50mm lens, fine film grain. Audio: his low gravelly voice, wind against the glass, a distant foghorn.
Surreal VFX: a storm-cloud whale crackling with lightning trails rain over a red rock canyon at dusk, with a lone hiker on a rock pillar for scale.
Epic wide aerial shot, slow drone push forward, one continuous take. A colossal whale whose entire body is made of billowing grey storm clouds, with no skin, only swirling vapor in the shape of a whale, glides over a red sandstone canyon at dusk, lightning flickering inside the cloud body and rain trailing from its belly onto the rocks, a tiny lone hiker on a ridge in the foreground for scale. Gold and violet sky, volumetric light rays, large format clarity. Audio: deep rolling thunder, a low distant whale song, desert wind.
What WAN 3.0 does best, and how to get it
WAN 3.0 gives you multi-shot scenes from one prompt, sound in the same pass, and every resolution from 480p to 4K. These three clips show the range: a quick 480p loop, fast mode at 720p and a full 4K frame.
The dance prompt at 480p: the spin, the silk and the ring of spray all read clearly, ready for quick social loops.
Symmetrical wide shot with a slow push-in, one continuous take. A dancer with a sleek black bun and a flowing crimson silk gown spins on a flooded concrete floor under a single hard white top light, her skirt fanning out and flinging a ring of water droplets that sparkle in the beam, a dark empty hall behind her. High contrast, deep blacks, 50mm lens, subtle film grain. Audio: splashing water, rustling silk, echoing footsteps, one low sustained cello note.
Fast mode at 720p: the chef pours, lays the chashu, then pulls the soft egg apart over the bowl.
Overhead close-up, then a slow tilt down to eye level, one continuous take. A chef in a black apron ladles steaming golden broth over noodles in a dark ceramic bowl, then lays down chashu slices and a soft egg split open with a glossy orange yolk, steam curling through a warm spotlight in a dim wooden noodle bar. 85mm lens, rich warm grade, shallow depth of field. Audio: broth pouring, the clink of a ladle, low bar chatter.
The storm whale in 4K: crisp canyon detail, lightning inside the cloud and rain curtains falling below.
Epic wide aerial shot, slow drone push forward, one continuous take. A colossal whale whose entire body is made of billowing grey storm clouds, with no skin, only swirling vapor in the shape of a whale, glides over a red sandstone canyon at dusk, lightning flickering inside the cloud body and rain trailing from its belly onto the rocks, a tiny lone hiker on a ridge in the foreground for scale. Gold and violet sky, volumetric light rays, large format clarity. Audio: deep rolling thunder, a low distant whale song, desert wind.
- Multi-shot scenes from one prompt. Label each shot with a time range and WAN 3.0 plays them in order, up to 30 s. Our 20 s night market scene keeps the same cook from the wide shot to the serve.
- Sound comes built in. Every clip on this page has audio generated with the picture, and the man at the lighthouse lamp speaks his line on cue.
- Actions in sequence. Write the steps in order and WAN 3.0 performs them: our chef pours the broth, lays the chashu, then adds the egg.
- Pick the resolution for the job: 480p for quick social loops, 720p for everyday work, 1080p for hero shots, and 2K or 4K for big screens.
- Fast mode gives you a quicker turnaround at 720p for 3 credits per second.
- Describe surreal ideas in plain physical terms. For the storm whale we named the material, the light and a small hiker for scale.
- Bring your own references: up to 10 images, 5 videos or 5 audio clips to lock a character, copy a camera move or set a voice.
WAN 3.0 vs WAN 2.7: the same ramen prompt on both models
We gave WAN 3.0 and WAN 2.7 the same ramen prompt at 5 s and 720p. WAN 3.0 plays the whole sequence we wrote: it pours the broth, lays the chashu by hand, then sets down the halved egg. WAN 2.7 opens on a finished bowl and pours the broth over it, a warm hero shot of the dish. When your prompt describes several actions in a row, WAN 3.0 performs each one.
Same prompt: Overhead close-up, then a slow tilt down to eye level, one continuous take. A chef in a black apron ladles steaming golden broth over noodles in a dark ceramic bowl, then lays down chashu slices and a soft egg split open with a glossy orange yolk, steam curling through a warm spotlight in a dim wooden noodle bar. 85mm lens, rich warm grade, shallow depth of field. Audio: broth pouring, the clink of a ladle, low bar chatter.
WAN 3.0: pour, chashu, then the halved egg, each placed by hand.
Overhead close-up, then a slow tilt down to eye level, one continuous take. A chef in a black apron ladles steaming golden broth over noodles in a dark ceramic bowl, then lays down chashu slices and a soft egg split open with a glossy orange yolk, steam curling through a warm spotlight in a dim wooden noodle bar. 85mm lens, rich warm grade, shallow depth of field. Audio: broth pouring, the clink of a ladle, low bar chatter.
WAN 2.7: a finished bowl with a slow broth pour.
Overhead close-up, then a slow tilt down to eye level, one continuous take. A chef in a black apron ladles steaming golden broth over noodles in a dark ceramic bowl, then lays down chashu slices and a soft egg split open with a glossy orange yolk, steam curling through a warm spotlight in a dim wooden noodle bar. 85mm lens, rich warm grade, shallow depth of field. Audio: broth pouring, the clink of a ladle, low bar chatter.
| WAN 3.0 | WAN 2.7 | |
|---|---|---|
| Actions in the prompt | Pour, chashu, egg, in order | Broth poured over a finished bowl |
| Credits for 5 s at 720p | 10 | 10 |
| Longest clip | 30 s | 15 s |
| Top resolution | 4K | 1080p |
| Sound | Generated with the picture | Generated with the picture |
WAN 3.0 pricing: credits per clip, on every plan
WAN 3.0 is included in every Pixel Dojo plan, from $10/month. Clips use credits per second of video, and the tool shows the exact price for your settings before you generate.
List rates are 1.5 credits per second at 480p, 2 at 720p, 5 at 1080p or 2K and 6 at 4K, with fast mode at 3 per second at 720p. Sound is included in every rate. Reference images and reference audio are included too, and reference video seconds count at the output rate.
A 5 s clip at 720p is 10 credits. We made the examples on this page during a 10% sale, so their tiles show the sale price.
How to use WAN 3.0 on Pixel Dojo
- 1
Write it like a shot note
Lead with shot size and camera move, then one subject, one action, the light, the lens and the sound you want. Add "one continuous take" for a single unbroken shot.
- 2
Script your shots for longer scenes
For a sequence, name each shot, give it a time range and say what should stay the same across shots, as in our night market prompt. Tap Use this prompt on that tile to start from it.
- 3
Choose length, resolution and references
Pick 2 to 30 seconds, 480p up to 4K, and fast mode for a quicker turnaround. Add reference images, videos or audio to lock a look, a camera move or a voice, then generate.
WAN 3.0 questions
What is WAN 3.0?
WAN 3.0 is Alibaba's AI video model. It turns a text prompt, or your own images, video and audio, into clips from 2 to 30 seconds with sound, from 480p up to 4K. You can use it in the browser on Pixel Dojo or through the Pixel Dojo API.
What is WAN 3.0 best at?
Cinematic scenes with several shots and sound from a single prompt. Our 20 s night market scene plays three shots in the order we wrote them, with the same cook throughout. The examples on this page also cover dance, a perfume commercial, claymation, a talking character and surreal VFX.
How long can a WAN 3.0 video be?
From 2 to 30 seconds in one generation, or you can let the model choose the length. Longer clips can hold several shots when you write a shot list with time ranges.
What resolution does WAN 3.0 support?
480p, 720p, 1080p, 2K and 4K. Use 480p or 720p for social clips, 1080p for hero shots, and 2K or 4K for big-screen detail like our storm whale above.
Does WAN 3.0 generate audio?
Yes. Sound is generated with the picture, so every clip comes with its own soundtrack, including a spoken line when your prompt writes one. Sound is included in the price.
Can WAN 3.0 do image to video, or use my own clips and voice?
Yes. Add up to 10 reference images, up to 5 reference videos to copy motion or camera moves, or up to 5 reference audio clips to set a voice, with 15 s combined for the videos and 15 s combined for the audio. Or start from a first frame, with an optional last frame to land on. Each clip uses either references or first and last frames.
How much does WAN 3.0 cost on Pixel Dojo?
WAN 3.0 is included in every Pixel Dojo plan, from $10/month, and uses credits per second of video. A 5 s clip at 720p is 10 credits at list price, and the tool shows the price for your settings before you generate.
Make your first WAN 3.0 clip
Write a prompt above or start from any example on this page. One subscription covers every model on Pixel Dojo.
Start with WAN 3.0