- Home
- AI Video Models
- WAN AI
WAN 3.0, live on Pixel Dojo
WAN AI: make WAN 3.0 videos with sound on Pixel Dojo
WAN is made by Alibaba. You can run it here on Pixel Dojo: WAN 3.0 for video with sound, WAN 2.7 and WAN 2.6 Flash for the earlier looks, and WAN 2.7 Image for stills. Our 5 second 720p WAN 3.0 clip cost 10 credits.
This is one of our own WAN 3.0 runs: a bamboo raft on a misty river, a flock of egrets lifting off the water, and the sound of the river in the file. Below we explain the WAN family, run one prompt on three WAN versions and show WAN 3.0 working from a reference picture.
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 WAN AI is
WAN is a family of video and image models made by Alibaba. You can run it here on Pixel Dojo. People search for it as WAN AI, Wan or Wan video, and they usually mean the newest version, WAN 3.0.
WAN 3.0 makes clips with sound from a text prompt, from a first and last frame, or from reference pictures, video and audio. It goes up to 4K and offers 16:9, 9:16, 1:1, 4:3 and 3:4 frames. WAN 2.7 and WAN 2.6 are the versions before it, and WAN 2.7 Image makes stills.
On Pixel Dojo the whole WAN family runs on one plan next to Kling 4.0, Seedance 2.5, Veo 3.1 and MiniMax H3, so you can try one prompt on two engines and keep the take you like.
More from WAN 3.0 and WAN 2.7 Image
Two more WAN 3.0 clips with sound and two WAN 2.7 Image stills. Prompts, settings and credits are on every tile.
WAN 3.0 in vertical 9:16 with a fisheye look, wheels and cheers in the sound track.
Fisheye tracking shot of a skateboarder in his twenties carving around a concrete bowl at sunset, he launches over the coping, grabs the board and lands back into the bowl, long shadows on the concrete. Sound: wheels roaring on concrete, the clack of the tail, friends whooping.
WAN 3.0 at 720p: the burner flame lights the envelope as the basket leaves the grass, with the roar in the sound track.
Low angle shot from a frosty meadow at dawn: a balloon pilot in his forties in a sheepskin jacket pulls the burner handle and a roaring flame lights the inside of a striped red and gold envelope as the basket lifts off the grass, breath steaming in the cold air, mist over the fields behind. Sound: the deep roar of the burner, creaking wicker, a distant rooster.

WAN 2.7 Image at 1.5 credits: deep color and sun shafts through the market roof.
Wide photograph of a covered spice market at midday, pyramids of saffron, paprika and turmeric in brass bowls, a spice seller in his sixties in a striped robe weighing cardamom on a hanging scale, shafts of sun through a lattice roof, dust in the air.

WAN 2.7 Image at 1.5 credits: a grid of colored pools and a bright line of salt.
Aerial photograph of salt pans at sunset, a grid of shallow pools glowing pink, copper and violet, a salt worker in his fifties in a straw hat raking a long white ridge of salt along one dyke, his long shadow across the water, crisp detail.
One prompt on WAN 3.0, WAN 2.7 and WAN 2.6 Flash
We gave three WAN versions the same brief: a bamboo raft drifting between karst peaks at sunrise, a raftsman poling, a woman with a bicycle and egrets lifting off the water. All three ran at 720p for 5 seconds.
WAN 3.0, 720p, 5 s, with sound, 10 credits.
Wide shot of a bamboo raft drifting down a misty river between towering green karst peaks at sunrise. A raftsman in his sixties steers with a long pole while a woman in her late twenties in a yellow raincoat sits on the raft holding a bicycle, and white egrets lift off the water around them. Sound: water lapping the bamboo, birdsong, the pole knocking the riverbed.
WAN 2.7, 720p, 5 s, 10 credits.
Wide shot of a bamboo raft drifting down a misty river between towering green karst peaks at sunrise. A raftsman in his sixties steers with a long pole while a woman in her late twenties in a yellow raincoat sits on the raft holding a bicycle, and white egrets lift off the water around them. Sound: water lapping the bamboo, birdsong, the pole knocking the riverbed.
WAN 2.6 Flash, 720p, 5 s, 7.5 credits.
Wide shot of a bamboo raft drifting down a misty river between towering green karst peaks at sunrise. A raftsman in his sixties steers with a long pole while a woman in her late twenties in a yellow raincoat sits on the raft holding a bicycle, and white egrets lift off the water around them. Sound: water lapping the bamboo, birdsong, the pole knocking the riverbed.
- All three kept the raft, the yellow raincoat, the bicycle and the karst peaks in every frame.
- WAN 3.0 gave the most life: a whole flock of egrets taking off around the raft with the sun breaking through.
- WAN 2.7 brought the raft toward the camera under a soft pink sky, the most painterly of the three.
- WAN 2.6 Flash told the same scene in a clean side view at 7.5 credits, the lowest price in the test.
WAN 3.0 from a reference picture
WAN 3.0 can take pictures as references and keep the person and place from them. We made a ceramicist in her studio on WAN 2.7 Image, then asked WAN 3.0 to have her throw a tall vase.

Step one: WAN 2.7 Image, 1.5 credits.
Photograph of a ceramicist in her fifties with long silver braids and clay streaked forearms seated at a potter's wheel in a sunlit adobe studio, shelves of turquoise glazed bowls behind her, morning light falling through a wooden shutter, 50mm lens, warm natural color.
Step two: WAN 3.0 with the still as a reference, 720p, 5 s, 10 credits.
@Image 1 is the ceramicist. Medium shot in her sunlit adobe studio: she draws a tall vase up from the spinning clay with wet hands, the walls rising smoothly, then she lifts her hands away, smiles and lets the wheel slow. Sound: the hum of the wheel, wet clay, a soft laugh.
- WAN 3.0 kept her face, silver braids, shirt and the whole studio from the reference picture.
- The clay rose from a short bowl into a tall vase over the 5 seconds, with her wet hands guiding it.
- The clip came back with sound in the file, at 10 credits on the tile.
The WAN versions on Pixel Dojo
Every WAN model below runs on any plan. Each model page shows its credit price before you generate.
| WAN model | What it makes | Where |
|---|---|---|
| WAN 3.0 | Video with sound from text, start and end frames or reference pictures, video and audio, up to 4K | /wan-3-0-video |
| WAN 2.7 | Text to video and image to video at 720p or 1080p | /wan-2.7-video |
| WAN 2.6 | Standard and Flash video at 720p or 1080p | /wan-2.5 |
| WAN 2.7 Image | Stills in Standard and Pro | /wan-2.7-image |
| WAN Reference to Video | Builds a clip around your reference pictures | /wan-reference-to-video |
How to write a prompt for WAN 3.0
Write it like a shot list: the camera first, then who is in the frame, one clear action, the place and the light. Our raft prompt opens with "Wide shot", names two people with their ages and clothes, gives one action each and ends with three sounds.
Name the sounds you want. WAN 3.0 makes audio with the picture, and a short "Sound:" line with two or three cues steers it.
For a person you want to keep, start from a picture. Tag it as @Image 1 in the prompt and say what that picture shows, as we did with the ceramicist.
What else you get on Pixel Dojo
Unlimited on every plan
On every paid plan, Relax runs Qwen Image 2.1, FLUX 3 Image Klein and MiniMax H3 Turbo, plus every video and photo effect, unlimited with no credits spent.
Sensei, the AI director
Describe a project and Sensei plans it, prices it, waits for your approval and reviews every take.
Video Studio
Generate, edit and extend a clip in one place, on whichever top video engine suits the shot.
One click video effects
300+ one-click video effects turn a photo into a trend clip, from AI Hug to AI Inflate, with no prompt to write, and 3 are free every day.
Film Studio
An idea becomes a finished film: script, cast, storyboard, clips and an editor pass that trims every shot, with each step priced before it runs.
Start from a genre
Pick a format such as a UGC ad, a micro drama, a movie trailer or an explainer, and the matching studio opens with the settings and a sample idea filled in.
Credits that roll over
Your credits roll over while you stay subscribed, so nothing you pay for disappears at the end of the month.
Every top model, plus an API
More than 80 image and 60 video models in one account, with a public API and a hosted MCP server for your own apps and AI assistants.
What WAN costs on Pixel Dojo
Our WAN 3.0 clips cost 10 credits each for 5 seconds at 720p with sound. WAN 2.7 cost 10 credits, WAN 2.6 Flash cost 7.5 and each WAN 2.7 Image still cost 1.5.
Plans are Lite $10 a month for 160 credits, Pro $25 for 500 credits, Pro Max $50 for 1,100 credits. WAN is paid by credits. Every paid plan also includes unlimited MiniMax H3 Turbo video, clips up to 5 seconds at 720p, with no credits spent. Credits roll over while you stay subscribed.
Under our refund policy, a first purchase can be refunded within 7 days, in full if under 20% of the credits are used and pro-rated after that.
Made with WAN 3.0
All how-tosThe exact prompts and settings behind each one.
Prime Time: Mini Golf DayEight stills to a WAN 3.0 episodeNov 6 · About 188 creditsSeedream 5WAN 3.0Seed Audio
Who Wins? 3 Video Models, 1 FrameOne frame, one prompt, three modelsNov 5 · About 198 creditsSeedream 5MiniMax H3WAN 3.0
Pink Caricature: Gym DayOne saved character to a gym comedyNov 4 · About 142 creditsSeedream 5WAN 3.0Seed Audio
WAN AI questions
Who makes WAN AI?
WAN is made by Alibaba. You can run it here on Pixel Dojo, with WAN 3.0, WAN 2.7, WAN 2.6 and WAN 2.7 Image on one plan.
Is this the official WAN website?
No. Pixel Dojo is an independent studio that runs the WAN models alongside Kling, Seedance, Veo, MiniMax and many more.
Is WAN AI free on Pixel Dojo?
No. WAN is paid by credits here: our 5 second 720p WAN 3.0 clips cost 10 credits. Every paid plan includes unlimited MiniMax H3 Turbo video, and anyone with an account gets 3 free effects a day.
What is the newest WAN version?
WAN 3.0. It makes video with sound and takes reference pictures, video and audio. WAN 2.7 and WAN 2.6 are still on Pixel Dojo too.
Can I train a WAN LoRA?
Yes. Pixel Dojo has a WAN LoRA trainer alongside the FLUX, Qwen and Z-Image trainers.
Video Effects New
Your first video is free. One photo, one click.
310 ready-made effects, from AI Hug and Earth Zoom In to product spins and listing walkthroughs. Upload a photo and press Generate. No prompt to write, and a free account gets 3 a day.
Make your first WAN 3.0 clip
Write a prompt above or start from any example on this page. One plan covers every top model, six studios and Sensei, and your credits roll over.
Start with WAN 3.0