Wan 3.0 on zzo.ai costs 100 credits ($1.00) for a 5-second 720p clip with audio. No subscription: buy credits once and they never expire.
Wan 3.0 is Alibaba’s video model, in public beta since 6 August 2026 and generally available since 24 August. It makes clips of up to 30 seconds at up to 1080p with sound, from text, a photo or reference images. It is not open source: Alibaba offers it only as a hosted model.
5–30 s clips
Up to 1080p
Sound on or off
Prompt from this video. Edit it or write your own.
Made with Wan 3.0
Each one shows the prompt, model and what it costs here. Pick one to start from it.
“One unbroken thirty-second Steadicam move through a working film studio backlot at two in the morning. No cuts anywhere in the take. 0 to 6s: the camera walks out of a scene dock past stacked flats and a rail of period costume, catching a grip taping down a cable run, then pushes through hanging plastic sheeting into open air. 6 to 14s: it crosses a New York street standing set with the rain machines at full pressure, water sheeting off fire escapes and pooling in the gutters, a stunt performer in a soaked overcoat waiting on her mark while a focus puller measures to her face. 14 to 22s: it turns left down a service alley between two sound stages, past a catering truck with its shutter half down and an electrician asleep in a folding chair, the rain noise falling away behind the wall. 22 to 30s: it comes out onto the lot road, cranes up over a parked camera truck and holds on the whole backlot under sodium light, rain still falling on one street and nowhere else. Anamorphic, sodium and mercury practicals, deep blacks, fine film grain. Sound: rain machines roaring then dropping off, a radio crackle, boots on wet asphalt, a generator running under everything, no music.”Wan 3.0, 30 s, sound, 1,200 credits, made on Wan
“Medium close-up, 50mm. A night-market noodle vendor in a white apron stands behind a steaming wok under bare hanging bulbs. He looks into the camera and says: "Thirty years. Same pan, same recipe." Then he tosses the noodles high and flames jump up from the wok. Camera: gentle living handheld that barely breathes, slight push-in. Audio: his voice, sizzling oil, crowd chatter, distant scooters. Photorealistic, warm practical light.”Wan 3.0, 8 s, sound, 160 credits, made on Wan
“A 20-second ultra-widescreen plush universe adventure clip, featuring ultra-fine plush textures throughout, cinematic space scale, a contrast between cute appearances and intense action, exaggerated FPV camera movements, and realistic soft-body physics. A spaceship made of plush fabric, buttons, zippers, and stuffing cotton carries three small plush animals — a rabbit, a fox, and a crow — fleeing at high speed through a universe composed of giant yarn planets, fluffy nebulae, and puppet giant beasts. A massive interstellar whale beast covered in deep blue long fur with eyes like two glass buttons chases the ship from within the nebula. The dynamics include the zipper ship launching via catapult, high-speed orbiting around a yarn planet, the giant whale bursting out from behind, navigating through a button asteroid belt, being swallowed by the whale beast, escaping through a golden zipper on its back, the whale slowly deflating as if losing its stuffing cotton, and finally flying through a pink-purple fluffy nebula toward a colorful button sun.”Wan 3.0, 20 s, sound, 400 credits, made on Wan
“Slow dolly-in on a matte terracotta vase standing on a travertine plinth in a sunlit plaster room. Late-afternoon light slides slowly across the wall as dust drifts through the beam. Calm, premium product film, shallow depth of field. Audio: soft room tone and a faint breeze.”Wan 3.0, 5 s, sound, 100 credits, made on Wan
“A ten-second vertical spot for an unbranded titanium dive watch, no dialogue. The watch lies face up on wet black slate in a dark room, a single hard key raking across it from the left so the brushed case and the polished lugs read as two different metals. The dial is plain matte slate-grey with luminous dot markers only. A hand in a rolled navy sleeve enters from the bottom of frame and, without lifting the watch, turns the bezel one full rotation so every detent is visible against the lume. The camera pushes from a wide macro into a tight macro on the dial as the rotation finishes, then holds. Water beads slide off the crystal and off the edge of the slate. Sound: the bezel clicking through its detents, water running off stone, a low room tone, no music. No logos, no brand names, no text or numbers anywhere on the watch.”Wan 3.0, 10 s, sound, 400 credits, made on Wan
“One continuous shot. A 15-second vertical lip swatch video for the lip gloss in Image 1. A young woman with natural makeup and dark hair tied back faces the camera, framed from the shoulders up, in soft window daylight against a plain warm-beige wall. 0-5s: she holds the lip gloss from Image 1 up beside her face. 5-10s: she takes off the cap and glides the applicator across her lips once, leaving a glossy rose-pink colour. 10-15s: the camera slowly pushes in to a close-up of her lips as she smiles slightly and the gloss catches the light. Keep the lip gloss exactly as in Image 1: clear tube, rose-pink gloss, plain silver cap, no text. Sound: soft room tone, the faint click of the cap. No dialogue, no BGM. No subtitles, no logos, no text.”Wan 3.0, 15 s, sound, 300 credits, made on Wan, input image made with GPT Image 2.5
“Handheld shot on a rainy night market street. The woman with the bicycle turns her head to the camera and says: ‘I know a better place for noodles.’ Rain keeps falling, people with umbrellas walk past behind her, and neon signs reflect on the wet road. Audio: steady rain, distant street chatter, and her voice.”Wan 3.0, photo to video, 5 s, sound, 100 credits, made on Wan, input image made with GPT Image 2.5
“The harbour fish market mid-morning, in one continuous walking take past the stalls: crushed ice heaped with silver fish, a monger's gloved hands sliding a whole fish onto paper, a customer pointing, the camera moving through steam and shouted orders without a cut. Documentary handheld 35mm, natural and practical light only, shallow depth of field, fine 35mm film grain, muted teal and amber grade, no on-screen text. Sound: overlapping shouted prices, ice being shovelled, paper tearing, wet slap of fish on the counter, gulls in the rafters.”Wan 3.0, 5 s, sound, 100 credits, made on Wan
“I2V: A time-lapse of a mountain landscape transitioning from a vast, starry night to a vibrant dawn. Voiceover: A deep, serene male voice says: 'In the vast silence of the cosmos, our world is but a fleeting moment. Yet, within it, life defiantly thrives.'”Wan 3.0, photo to video, 10 s, sound, 200 credits, input image made with GPT Image 2.5
What you can make with Wan 3.0
Each one comes with the settings and the prompt we would start from, and what it costs. Use it as is or edit it.
made on Wan
One 30-second take
A Steadicam walk through a film backlot at night, one take for the full 30 seconds, ending on the crane-up the prompt asks for. The prompt is from a published Wan 3 guide, where it ran on the faster Prime version; this is the standard model. One beat came out differently: the sleeping electrician appears on a phone screen instead of in the scene.
Text to video
1080p
30 s
sound
16:9
“One unbroken thirty-second Steadicam move through a working film studio backlot at two in the morning. No cuts anywhere in the take. 0 to 6s: the camera walks out of a scene dock past stacked flats and a rail of period costume, catching a grip taping down a cable run, then pushes through hanging plastic sheeting into open air. 6 to 14s: it crosses a New York street standing set with the rain machines at full pressure, water sheeting off fire escapes and pooling in the gutters, a stunt performer in a soaked overcoat waiting on her mark while a focus puller measures to her face. 14 to 22s: it turns left down a service alley between two sound stages, past a catering truck with its shutter half down and an electrician asleep in a folding chair, the rain noise falling away behind the wall. 22 to 30s: it comes out onto the lot road, cranes up over a parked camera truck and holds on the whole backlot under sodium light, rain still falling on one street and nowhere else. Anamorphic, sodium and mercury practicals, deep blacks, fine film grain. Sound: rain machines roaring then dropping off, a radio crackle, boots on wet asphalt, a generator running under everything, no music.”
Tip: Say “No cuts anywhere in the take” and give each part of the walk its own time range.
1,200 credits
made on Wan
A spoken line, then flames
He says the line as written, then the wok flares up in big flames. The prompt is from Krea’s Seedance 2.5 vs Wan 3.0 test, where Wan 3.0 also got the flames and Seedance didn’t. The signs behind him are made-up script. The MiniMax H3 page shows the same prompt.
Text to video
720p
8 s
sound
16:9
“Medium close-up, 50mm. A night-market noodle vendor in a white apron stands behind a steaming wok under bare hanging bulbs. He looks into the camera and says: "Thirty years. Same pan, same recipe." Then he tosses the noodles high and flames jump up from the wok. Camera: gentle living handheld that barely breathes, slight push-in. Audio: his voice, sizzling oil, crowd chatter, distant scooters. Photorealistic, warm practical light.”
Tip: Put the line early in the clip and the big action after it (“first …, only then …”).
160 credits
made on Wan
A stylised 3D story in 20 seconds
Every beat of Alibaba’s own sample prompt is there, in a plush-toy look. The prompt asks for ultra-widescreen; Wan 3.0 doesn’t offer 21:9, so this is 16:9. The motion turns fast for a moment at about 3.5 to 4 seconds.
Text to video
720p
20 s
sound
16:9
“A 20-second ultra-widescreen plush universe adventure clip, featuring ultra-fine plush textures throughout, cinematic space scale, a contrast between cute appearances and intense action, exaggerated FPV camera movements, and realistic soft-body physics. A spaceship made of plush fabric, buttons, zippers, and stuffing cotton carries three small plush animals — a rabbit, a fox, and a crow — fleeing at high speed through a universe composed of giant yarn planets, fluffy nebulae, and puppet giant beasts. A massive interstellar whale beast covered in deep blue long fur with eyes like two glass buttons chases the ship from within the nebula. The dynamics include the zipper ship launching via catapult, high-speed orbiting around a yarn planet, the giant whale bursting out from behind, navigating through a button asteroid belt, being swallowed by the whale beast, escaping through a golden zipper on its back, the whale slowly deflating as if losing its stuffing cotton, and finally flying through a pink-purple fluffy nebula toward a colorful button sun.”
Tip: For long stylised clips, name the material (“ultra-fine plush textures”) once at the start; it holds for the whole length.
400 credits
made on Wan
A product dolly-in
A slow push in on a vase in a sunlit room, in one shot. The prompt is from Fuser’s Wan 3.0 vs Seedance 2.5 test, which ran it at 6 seconds; it runs at 5 here.
Text to video
720p
5 s
sound
16:9
“Slow dolly-in on a matte terracotta vase standing on a travertine plinth in a sunlit plaster room. Late-afternoon light slides slowly across the wall as dust drifts through the beam. Calm, premium product film, shallow depth of field. Audio: soft room tone and a faint breeze.”
Tip: One camera move per clip, with its speed: “slow dolly-in”.
100 credits
made on Wan
A vertical product ad (rewritten prompt)
This prompt is our rewrite of one from a published Wan 3 guide. As published, it gave us a real watch brand on the dial on the first take, and on the second the fingers passed through the watch as the hand lifted it. We changed four things: “unbranded”, a plain dial, a hand that turns the bezel without lifting the watch, and a last line asking for no logos or text. This take has a plain grey dial and no glitch, but the bezel still carries numbers, which the prompt asked it to leave out.
Text to video
1080p
10 s
sound
9:16
“A ten-second vertical spot for an unbranded titanium dive watch, no dialogue. The watch lies face up on wet black slate in a dark room, a single hard key raking across it from the left so the brushed case and the polished lugs read as two different metals. The dial is plain matte slate-grey with luminous dot markers only. A hand in a rolled navy sleeve enters from the bottom of frame and, without lifting the watch, turns the bezel one full rotation so every detent is visible against the lume. The camera pushes from a wide macro into a tight macro on the dial as the rotation finishes, then holds. Water beads slide off the crystal and off the edge of the slate. Sound: the bezel clicking through its detents, water running off stone, a low room tone, no music. No logos, no brand names, no text or numbers anywhere on the watch.”
Tip: Keep hands from picking up small products: turning, tapping or pointing hides the contact the model gets wrong.
400 credits
made on Wan, input image made with GPT Image 2.5
A model swatch from one product shot (rewritten prompt)
Reference to video from a single packshot (made with GPT Image 2.5): a model holds up the gloss, applies it and the camera pushes in to her lips, with the tube matching the image. Alibaba’s one-line example prompt gave us no model and an extra scene, twice, so we rewrote it with the formula from Alibaba’s Wan 3.0 prompt guide: one continuous shot, timed beats, the image by number, sound, and what to leave out. After the close-up the camera pulls back out, and she ends holding the capped tube.
Reference to video
720p
15 s
sound
9:16
“One continuous shot. A 15-second vertical lip swatch video for the lip gloss in Image 1. A young woman with natural makeup and dark hair tied back faces the camera, framed from the shoulders up, in soft window daylight against a plain warm-beige wall. 0-5s: she holds the lip gloss from Image 1 up beside her face. 5-10s: she takes off the cap and glides the applicator across her lips once, leaving a glossy rose-pink colour. 10-15s: the camera slowly pushes in to a close-up of her lips as she smiles slightly and the gloss catches the light. Keep the lip gloss exactly as in Image 1: clear tube, rose-pink gloss, plain silver cap, no text. Sound: soft room tone, the faint click of the cap. No dialogue, no BGM. No subtitles, no logos, no text.”
Tip: Refer to your product as “the lip gloss in Image 1” and say what must not change: colour, cap, no text.
300 credits
made on Wan, input image made with GPT Image 2.5
A photo of a person, speaking
Image to video: she turns her head to the camera and says her line, in the frame of the start image, while people with umbrellas pass behind her. The prompt is from Fuser’s Wan 3.0 vs Seedance 2.5 test, where Seedance 2.5 refused the photo as a possible real person. The start image is our own, made with GPT Image 2.5.
Image to video
720p
5 s
sound
16:9
“Handheld shot on a rainy night market street. The woman with the bicycle turns her head to the camera and says: ‘I know a better place for noodles.’ Rain keeps falling, people with umbrellas walk past behind her, and neon signs reflect on the wet road. Audio: steady rain, distant street chatter, and her voice.”
Tip: Describe the motion and the line; the photo already sets the person, the street and the light.
100 credits
made on Wan
A documentary walk
A handheld walk past the fish stalls in one take, with the market sounds in the same pass. The prompt is a published Wan 3 showcase prompt.
Text to video
720p
5 s
sound
16:9
“The harbour fish market mid-morning, in one continuous walking take past the stalls: crushed ice heaped with silver fish, a monger's gloved hands sliding a whole fish onto paper, a customer pointing, the camera moving through steam and shouted orders without a cut. Documentary handheld 35mm, natural and practical light only, shallow depth of field, fine 35mm film grain, muted teal and amber grade, no on-screen text. Sound: overlapping shouted prices, ice being shovelled, paper tearing, wet slap of fish on the counter, gulls in the rafters.”
Tip: For a documentary feel, name the camera (“handheld walking take”) and two or three things it passes, in order.
100 credits
What sets Wan 3.0 apart
A whole scene in one generation
Up to 30 seconds in a single pass; Alibaba notes that mainstream video generators, Wan 2.7 included, stop at 15. Characters and sets hold across the length; the thing to watch is an uninvited cut.
How to use it: Write “One continuous shot” on the first line if you want one take. For a sequence, give each shot its own time range, 2 to 5 seconds each, joined end to end: “Shot 1 (0-4s): …”.
Give it images of a person, product or place and it keeps them in a new scene. Alibaba says faces, hair, clothing and accessories stay consistent at fine granularity, and props keep their logos and materials shot to shot.
How to use it: Choose Reference to video, upload the images and refer to them by number in the order you uploaded them: “The child in Image 1 stands in the entryway of the modern apartment in Image 2”. In Fuser’s test the setting followed the background of the person’s photo, so give the location its own image if it matters.
Sound with the picture
Dialogue, effects and music are generated in the same pass. Alibaba: describe the action, the material and the weather clearly, and the model fills in the matching sound effects.
How to use it: Write speech as “she says: “…””, early in its shot so it isn’t cut off. Say “No dialogue” or “No BGM, generate only ambient and action sounds” when you don’t want them; otherwise the model decides.
Same price: 100 credits (720p, 5 s)
What Wan 3.0 is good at, and where it struggles
Good at
Up to 30 seconds in one generation. In Atlas Cloud’s 49-run review, “across all nine 30-second runs, no character swapped face, outfit or set.”
Follows the prompt literally: in Krea’s and Fuser’s same-prompt tests against Seedance 2.5 it caught details the other missed, such as flames jumping from a wok, dust in a light beam and hands kept in view while a potter spoke.
Timed shots land on time: Fuser asked for cuts at 3 and 6 seconds and got them within a frame.
Animates photos of people: in Fuser’s test it animated a photoreal start frame that Seedance 2.5 refused.
It ranked first for text to video and for video editing on Artificial Analysis’s leaderboards with audio in October 2026.
Limits
It can cut to another angle or dissolve when you didn’t ask, mostly in long clips; Krea got a hard cut at 13.6 seconds despite “no cuts”. Start the prompt with “One continuous shot” and check the take.
Screen direction and the order of events can slip: Krea asked for left-to-right travel and the rider came toward the camera instead. Write the order out (“first …, only then …”).
When the image and the prompt disagree, it keeps the image.
Small on-screen text and labels can come out garbled or mirrored. Alibaba itself says text rendering and audio texture are “not yet where we want them”.
The sound mix is loud: Krea measured it 9 to 14 dB above Seedance 2.5’s, so expect to turn it down in an edit.
Up to 1080p, with no 4K. Video editing and document input exist on Alibaba’s own platform but aren’t offered on zzo.ai.
A good first result with Wan 3.0, step by step
Draft cheap, finish high. Each step shows its settings and cost.
1
Find the shot at 480p
Run the idea at the lowest resolution and a short length. Change one thing at a time.
480p
5 s
sound
16:9
3 runs × 50 = 150 credits
2
Run the full length at 720p
Write the timed shots and generate the length you need. Check long takes for cuts before you move on.
720p
15 s
sound
16:9
300 credits
3
Render the final at 1080p
For finals and large screens. Each run is a new take, so expect small differences from the draft.
1080p
15 s
sound
16:9
600 credits
About 1,050 credits ($10.50 at the standard rate) for the whole job. Failed runs are refunded, so they don’t count.
Settings, explained
What each option does and what it does to the price.
Modes
Text to video starts from your words. Image to video uses your photo as the first frame and keeps its shape; describe the motion, not the picture. Reference to video uses your images to keep a person, product or place consistent.
Same price: 100 credits (720p, 5 s)
Resolution
480p for drafts, 720p for most social posts, 1080p for finals. Each step up doubles the price per second.
480p: 50 · 720p: 100 · 1080p: 200 credits (5 s)
Clip length
From 5 to 30 seconds here. Price scales with length. Long clips are where uninvited cuts happen, so write “One continuous shot” or time each beat.
5 s: 100 · 30 s: 600 credits (720p)
Audio
On by default, at no extra cost. Switch it off if you will add your own music or voice-over.
Same price: 100 credits (720p, 5 s)
Aspect ratios
16:9 for the web and YouTube, 9:16 for Reels, TikTok and Shorts, 1:1, 4:3 and 3:4 for feeds and product shots. Image to video follows the shape of your photo.
16:9, 9:16, 1:1, 4:3, 3:4 · no price difference
Wan 3.0 specs
Updated 2026-10-28
Developer
Alibaba
Released
2026-08-06
Type
Video
Modes
Text to video, Image to video, Reference to video
Clip length
5–30s
Resolution
480p, 720p, 1080p
Audio
Optional (on/off)
Aspect ratios
16:9, 9:16, 1:1, 4:3, 3:4
Commercial use
Allowed, under our terms
Failed generations
Credits refunded automatically
Starts at
50 ($0.50)
Wan 3.0 price per generation
Credits are charged only when a generation starts, and refunded if it fails. The cheapest option is 50 credits.
Alibaba’s prompt guide for Wan 3.0 builds a prompt from parts: an overall description, the reference images by number, the shots with their times, dialogue, sound, style and a short list of what to leave out. One sentence is enough to get a video, but the more precise the description, the closer the result.
Time the shots end to end, 2 to 5 seconds each, with no gaps or overlaps: “Shot 1 (0-3s): …, Shot 2 (3-6s): …”.
Ask for one take on the first line: “One continuous shot”. For a camera that doesn’t move: “Fixed shot, camera static, position unchanged”.
Write speech as “he says: “…”” and say “No dialogue” when there should be none; otherwise the model decides.
Keep the negatives short: only what you don’t want, such as “No subtitles, No watermark, No extra brand names”. Don’t repeat what the prompt already says.
Avoid fast repeats the model can’t control, such as “shaking head 3 times per second”.
With a first-frame image, describe the motion, plot, dialogue and camera; the image already sets the subject and scene.
When a result goes wrong
The usual problems with Wan 3.0, why they happen and what to change.
The clip cuts to another angle
Why: Wan 3.0 can insert cuts or dissolves, especially in long clips.
Fix: Put “One continuous shot” on the first line, as Alibaba’s guide advises, keep the action in one place and run it again if needed.
Things happen in the wrong order or direction
Why: Testers saw events overlap and a rider travel the wrong way.
Fix: Write the order (“first …, only then …”) and the direction (“moves from left to right across the frame”) in plain words.
A prop changes shape between shots
Why: Fuser saw a pot change between the close-up and the medium shot.
Fix: Describe any prop that must match as carefully as the person, and name it again in every shot.
The setting doesn’t match the one you described
Why: In reference to video, the scene can follow the background of the person’s photo instead.
Fix: Upload a separate image of the location and refer to it by number.
A spoken line is cut off
Why: A line placed late in the last shot has little room to finish.
Fix: Put dialogue early in its shot, or give the clip a few more seconds.
Small text is garbled or mirrored
Why: On-screen text is still maturing, according to Alibaba.
Fix: Keep text short and large, or add it in an editor.
The request was refused or the run failed
Why: Alibaba’s content check blocked the input or output, or the model returned an error.
Fix: Nothing is charged: the credits return to your balance. Reword the prompt or try a different image.
Wan 3.0 vs Wan 2.7
Wan 3.0 is the first Wan model with 30-second clips. Alibaba points to more lifelike, varied faces and finer consistency of characters and props. Unlike Wan 2.1 and 2.2, it has no open weights.
Up to 30 seconds in one generation; Wan 2.7 stopped at 15.
More lifelike, varied faces: “built for diverse, lifelike faces rather than the glossy, interchangeable look of typical AI characters”, according to Alibaba.
Characters and props stay consistent at finer detail across shots.
Documents and web pages as input, and video editing, on Alibaba’s own platform. zzo.ai offers text, image and reference to video.
No open weights: it is available only as a hosted model.
Wan 3.0 on zzo.ai costs 100 credits ($1.00) for a 5-second 720p clip with audio. No subscription: buy credits once and they never expire. Depending on resolution and length, a generation costs 50 to 1,200 credits ($0.50 to $12.00 at the standard rate). As low as $0.45 with the $199.99 pack. Failed generations are refunded automatically.
Do I need a subscription to use Wan 3.0?
No. zzo.ai has no subscription: buy a credit pack once and spend it on Wan 3.0 or any other model. Credits never expire.
How long can Wan 3.0 videos be, and at what resolution?
On zzo.ai, Wan 3.0 makes clips from 5 to 30 seconds at 480p, 720p, 1080p, in 16:9, 9:16, 1:1, 4:3, 3:4 aspect ratios.
How much does a 10-second Wan 3.0 video cost?
A 10-second 720p clip with sound costs 200 credits: $2.00 at the standard rate, or $1.82 with the $199.99 pack. There is no subscription.
Can I use Wan 3.0 through an API or in Claude?
Yes. Create an API key in Settings, then use Wan 3.0 from Claude, Cursor or your own code through the zzo.ai MCP server. It draws from the same balance at the same prices as the website.
What is Wan 3.0?
Wan 3.0 is Alibaba’s video generation model, in public beta since 6 August 2026 and generally available since 24 August 2026. It makes clips of up to 30 seconds at up to 1080p with sound, from text, a photo or reference images.
Is Wan 3.0 open source? Can I run it locally?
No. Alibaba offers Wan 3.0 only as a hosted model and has published no weights; the open Wan models on Hugging Face are from the 2.x generation. To use Wan 3.0 you run it online, for example here.
Wan 3.0 or Seedance 2.5: which should I use?
Pick Wan 3.0 when you want the prompt followed literally, a photo of a person animated, or a lower price per second. Pick Seedance 2.5 when one unbroken take, exact screen direction or a quieter, film-like sound mix matters most. In Fuser’s five same-input tests (2 October 2026) Wan 3.0 won three and tied one.
Does Wan 3.0 make sound?
Yes. Speech, sound effects and music are generated with the picture. You can switch sound off; the price is the same either way.
Why did my Wan 3.0 video cut to another shot?
Wan 3.0 sometimes inserts a cut or a dissolve nobody asked for, more often in long clips. Start the prompt with “One continuous shot”, give each beat a time range, and run it again if needed.
Why was my Wan 3.0 request rejected?
Alibaba’s content check blocks sexual, violent and other policy-breaking inputs and outputs, and suspected copyright infringement. When a request is refused, the credits go back to your balance automatically.
Can I use Wan 3.0 videos commercially?
Yes. Videos you generate on zzo.ai are yours to use, including in commercial work, as long as the content itself doesn’t break our terms or anyone else’s rights.
