Wan 3.0 AI UGC Ad Generator

A UGC ad is four things at once — a creator, a room, your actual product and the voice that sells it — and here all four come out of one generation. No roster to pick a face from, no text-to-speech bolted on afterwards, and no lip-sync pass to marry the two.
Your first clip is free. No card.

Cast it, then say the line

Drop the product. Add a face if you have one.

0 / 20 assets

10 images + 5 clips + 5 tracks. A creator still and a pack shot is two.

Nothing uploaded yet — with no references the creator is whoever the prompt describes. Load a pack to see a face, a product and a voice get numbered.

0 / 20000
Model
Aspect ratio
9:16
Duration
Resolution
Sign up free · 1 clip on Wan 3.0

Reference material runs on credits. The free clip is a prompt or a photo in, video out — reading a file, a link or footage you already have is the paid side of the same Wan 3.0 model. See what a clip costs.

1 free clip on the real wan3.0-video · an email, no card · no watermark on any tier, including the free one

Four cases from Wan's own published creator handbook, each printed with the prompt that produced it · Try this loads the prompt

Two women in gym kit standing beside treadmills, one turning to speak to the otherTWO FACES, TWO VOICES · 16:9 · 15S

Two faces, two voices, one pass

One model, one pass, no roster

What a UGC ad generator does here — and the one thing it does differently

A UGC ad is a person in an ordinary room saying something believable about a thing they are holding. Four elements, and the category builds them in three separate purchases.

A vertical frame of a woman moving to a beat in a domestic kitchen

Vertical, by default

Face, room, product and voice in the same pass

The usual stack goes: pick a face from a roster, send the script to a text-to-speech voice, then run a lip-sync pass to marry the two — and composite the product in afterwards. That is why so many of these share a particular deadness. The mouth is solving for a waveform that was recorded somewhere else, and the hand is holding something that was never in the room. Wan 3.0 samples all four together. The face, the kitchen, the bottle and the line arrive in the same render, which is also why turning the sound off does not make it cheaper — it was never a second product. The trade is real and it runs the other way too. There is no roster, so there is no face you can browse; you either describe who is on camera or hand over a photo. There is no variant button, so six hooks is six runs. And nothing carries forward between runs — two generations give you two people unless a reference image says otherwise. What a roster costs you sits on the other side of the same coin: a face you can pick is a face your competitor can pick. The four films above are Wan's own published handbook cases under CC BY 4.0, printed with their prompts verbatim so every number on this page can be checked against a file you can play.

Longest single clip, natively multi-shot
30s

Longest single clip, natively multi-shot

Vertical at the landscape rate
9:16

Vertical at the landscape rate

Reference images in one run
10

Reference images in one run

Face, room, product and voice
One pass

Face, room, product and voice

Watermarks, on every tier
0

Watermarks, on every tier

  • No ad-account connection and no ROAS scoring — download the file and run it in your own manager.
  • No avatar roster — the face comes from your reference photo, or from the sentence you write.
  • No variant button — six hooks is six runs, at 40 credits each.
  • No identity that survives between runs — put everything that has to match inside one thirty-second generation.

What you put in

Four ways to cast a UGC ad, depending on what has to stay the same

All four run the same model at the same per-second rate. What changes is how much of the result you can ask for a second time — which is the only question that matters once one hook starts working and you need nine more like it.

  • A woman dancing in a night-lit kitchen, generated from text with no reference image

    Describe the creator, run once

    No upload. Write who is on camera, what room they are in and the exact line, and the model casts somebody — consistent for the length of that clip and gone after it. The cheapest way to find out whether a hook is worth shooting at all.

    One-off hooks · text only
  • A woman wearing a blouse that was supplied as a separate reference photograph

    Hand over the product

    One clean pack shot as a reference image, named in the prompt, and the thing in frame is the thing you sell rather than something shaped roughly like it. Set the ratio to 9:16 yourself — on adaptive, the framing is read from the photo you just uploaded.

    Your SKU, in frame · up to 10 images
  • A man by a rainy window whose face was supplied as a reference image

    Cast a face and keep it

    A frontal still of the creator plus the pack shot, both named. The same person can then hold a different colourway in each run, which is the difference between an ad and an ad account: fifteen variants a viewer reads as one person.

    The same creator, again · face + product
  • Two women beside gym treadmills mid-conversation

    Cast two, and write the exchange

    Two images, two voice references, and dialogue written as dialogue. The gym clip above is exactly this — two speakers, four lines, one generation — and the voice colour of each one is taken from an audio reference rather than picked off a list.

    Duos and reaction ads · 5 audio refs

All four bill identically: 8 credits a second at 480P, 16 at 720P, 32 at 1080P. References are free — a UGC ad with ten reference images costs the same as one with none. Every limit and rate, per second.

Before you write a word

A fifteen-second UGC ad holds twenty-nine words. Your script is probably sixty.

This is the cheapest mistake to fix and the most expensive one to discover after the render. Both rates below are measured off Wan's own published cases, and they differ for a reason worth knowing: conversation has breathing in it, and a single read does not.

  • One creator, straight to camera

    Words a second
    2.5
    15 seconds
    37 words
    20 seconds
    50 words
    30 seconds
    75 words
    Where the number comes from
    The handbook's dashboard case names its own rate in the prompt — speaking speed about 2.5 words/second — and gets it

    The default shape for a hook. Write to thirty-seven and the read still sounds unhurried.

  • Reaction ads

    Two creators, back and forth

    Words a second
    1.93
    15 seconds
    29 words
    20 seconds
    38 words
    30 seconds
    58 words
    Where the number comes from
    The gym clip above runs 15.00 seconds and contains twenty-nine words across four lines — a turn of the head, a towel and a sip of water all cost time

    Slower than it looks. Two people need room to react, and the reaction is what makes it read as UGC.

  • Voiceover over product footage

    Words a second
    2.5
    15 seconds
    37 words
    20 seconds
    50 words
    30 seconds
    75 words
    Where the number comes from
    Same rate as a piece to camera — nothing is waiting for a mouth, but the pictures still have to land

    Use when the product is the hero and there is no creator to cast.

Count the words before you count the seconds. A sixty-word script in a fifteen-second slot does not get politely trimmed — the read speeds up until it stops sounding like a person, which is the exact quality a UGC ad is buying. Cut to twenty-nine and the hook has room to breathe. Prompts with the clip each one produced.

What actually costs you the render

Six ways a UGC ad stops being usable

None of these are about taste. Each one is a reason the file cannot be uploaded to an ad manager, which makes it a reason the credits are gone. Four of the six are visible in the clips above, against the prompts printed beside them.

  • Your vertical ad came back landscape

    Ratio is a parameter, and its default reads your reference image. Upload a wide pack shot on adaptive and you have asked for a wide ad. The try-on clip above is 1280×720 for exactly this reason; the kitchen clip, with nothing uploaded, honours the 9:16 in its prompt.

    Set 9:16 on the control before you press Generate. This page ships locked to vertical, so the only way to lose it is to change it.

    Locked by default
  • The last beat never happened

    Timecodes past thirty seconds are not clamped — they are discarded. The try-on prompt lays out four shots across ninety seconds and returns eight, with the beats compressed rather than the running time cut.

    Keep the whole shot list inside thirty seconds and give the call to action its own window. If the spot is sixty, board it as two generations and cut them together.

    Hard ceiling
  • The read is rushed, or a line is missing

    More words than the seconds hold — twenty-nine in fifteen for a conversation, thirty-seven for one person reading to camera.

    Count the script first, then pick the duration. Longer is cheap here: five more seconds at 480P is 40 credits.

    Arithmetic
  • Hook two is a different person from hook one

    Every generation is a fresh sample, and nothing about a face carries forward on its own.

    Attach the same frontal still to every run and name it in the prompt, or put all the beats that must match inside one generation. How far the likeness actually holds.

    Reference image
  • The label on the pack is mush

    Small type is where generative video is weakest, and a pack is mostly small type.

    Shoot the legible frames as close-ups and say what has to be readable. Anything below headline size, plan a graphic over it in the edit. What the pack shot needs to look like.

    Shot choice
  • The take you liked has vanished

    A finished clip is returned as a link that expires 24 hours after the run.

    Download it, or run it signed in — a signed-in run is kept in your library instead of behind a link with a clock on it.

    Save it

A UGC ad that errors out is refunded automatically. One that completes and is simply wrong is not — which is the whole argument for finding out at 480P, where the same model, the same cut and the same voice cost a quarter of the finished version.

The part that gets ads rejected

A face, a claim, and two separate toggles

A UGC ad is a person appearing to recommend a product, which makes it the most regulated thing you can generate. Three rules decide whether your UGC ad runs, and none of them are about the model.

  • A generated person is allowedThe FTC's Consumer Reviews and Testimonials Rule, in force since 21 October 2024, is explicit: "The rule has no blanket prohibition on the use of AI-generated avatars in marketing… Section 465.2 of the rule is drafted specifically so as to not prohibit companies from using virtual influencers."
  • A generated customer is notThe line it draws is about what that person says: "It's possible that a company's use of such an avatar might be considered a 'testimonial' under the rule. That would be prohibited under the rule only if the underlying testimonials were fake or false." In a script, the difference is one verb — she can demonstrate the product and read a claim you can already substantiate; she cannot say she bought it and loves it, because nobody did.
  • TikTok has a switchAds Manager carries a setting reading "This ad contains AI-generated content", required when an ad includes image, video or audio that is completely AI-generated or significantly modified by AI. Check it again on every duplicated campaign — duplication is how a hook test gets built.
  • That is not the branded-content switchCommercial content disclosure is separate and answers a different question — this post promotes a product — and a Branded Content post needs it regardless of how the footage was made. Two settings, two problems, and missing either one costs distribution.
  • Meta labels what it detects"Meta uses industry-standard detection methods, such as C2PA to identify when ad content has been created or edited using third-party generative AI tools." Read the current requirement on Meta's advertising standards before a launch — it is the platform's page to change.
  • What you ownClips you generate are yours to publish, sell and bill a client for, on every paid plan, under Alibaba's usage policy for the Wan 3.0 model and our terms. No watermark and no separate licence to buy. Likeness, trademarks and any claim on screen stay your clearance problem, the same as with a camera and a real creator.

Upload someone's likeness or voice only with their agreement. A creator still of a real person is a reference the model will hold for thirty seconds, which is the feature and also exactly what makes misuse easy.

Full policy: Responsible use

Pricing · per output second · vertical costs the same

Six UGC hooks cost less than one finished ad

Billing is per second of output, so length and resolution are the only two dials that move the number — the vertical cut is not a surcharge and the sound is not an add-on. A fifteen-second vertical UGC ad is 120 credits at 480P, 240 at 720P and 480 at 1080P. Six five-second hooks at 480P is 240 credits, which is half of one finished fifteen-second ad at 1080P. Test first, finish once.

What a UGC test costs, by shape

Billed by
output second
One 5s hook, 480P
40 credits
Six 5s hooks, 480P
240 credits
One 15s ad, 720P
240 credits
One 15s ad, 1080P
480 credits
One 30s ad, 720P
480 credits
Free on signup
1 clip + 24 credits

$39.90 a month on Pro is 2,240 credits — nine finished fifteen-second vertical ads at 720P, or fifty-six hook tests at 480P. Every figure above is the per-second rate times the seconds, so you can check the whole table with a calculator before you spend anything. Every plan and pack · what a failed generation costs.

Same monthly credits either way

  • Free first clipNo card

    One generation on the real wan3.0-video. See what Wan 3.0 does with your own shot — 480P, three seconds, sound in the same pass.

    $0once

    No card at any point

    Generate free clip

    An email, no card

    1 clip, once

    480P · up to 3s · with sound
    An email, no card

    The same `wan3.0-video` Alibaba runs for the paid plans — 480P is a resolution, not a lesser model

    • The real wan3.0-video, not 2.7
    • Sound generated with the picture
    • Model ID and task ID on the receipt
    • A failed run never costs you
    • 720P and 1080PPaid
    • Clips longer than 3 secondsPaid
    • Reference, document and editing modesPaid
    • More than one clip, everPaid

    One question answered: what Wan 3.0 does with your idea. 1080P, thirty seconds and every input mode start at $12.90.

    At a glance

    Clips a month
    1, once
    Takes per run
    1
    Longest clip
    3s
    Top resolution
    480P
  • StarterSave up to 20%

    A launch post a week. Enough to find out whether the Wan 3.0 AI video generator suits the way you work, without a decision about volume.

    $12.90/mo$15.90

    $154.80 billed yearly

    Cancel anytime

    640 credits / month · ≈ 16 clips

    at 5s 480P · 8 at 720P · 4 at 1080P

    Plan credits expire at the end of the month

    • 640 credits a month — about 16 finished clips
    • 2 takes of one prompt per run
    • Every resolution — 480P, 720P and 1080P
    • Every length — 2 to 30 seconds in one pass
    • Every input — text, image, reference, document, web page
    • Sound written in the same pass, no watermark
    • Commercial use included — publish it, sell it, bill for it
    • Wan 3.0 Prime, the fast tier, whenever you want it
    • A failed run never costs credits
    • 7-day refund while the credits are untouched
    • Cancel in two clicks — the price you joined at is locked

    Everything under the first two lines is on this plan at $12.90. The bigger plans buy seconds and takes — never a better model.

    At a glance

    Clips a month
    ≈ 12 at 5s 480P
    Takes per run
    2
    Credits per dollar
    Baseline
    Refund window
    7 days
  • Most people land here
    Pro

    One finished clip every working day, with three alternates each. The draft-at-480P, finish-at-1080P loop, sized for a working week.

    $39.90/mo$49.90

    $478.80 billed yearly

    Cancel anytime

    2,240 credits / month · ≈ 56 clips

    at 5s 480P · 28 at 720P · 14 at 1080P

    Plan credits expire at the end of the month

    • 2,240 credits a month — 3.5× Starter
    • ≈ 56 finished clips a month, or 14 at full 1080P
    • 4 takes of one prompt per run — pick one instead of re-rolling2× takes
    • +13% credits per dollar than StarterBetter rate
    • Room to draft at 480P and finish at 1080P in the same week
    • Every resolution — 480P, 720P and 1080P
    • Every length — 2 to 30 seconds in one pass
    • Every input — text, image, reference, document, web page
    • Sound written in the same pass, no watermark
    • Commercial use included — publish it, sell it, bill for it
    • Wan 3.0 Prime, the fast tier, whenever you want it
    • A failed run never costs credits
    • 7-day refund while the credits are untouched
    • Cancel in two clicks — the price you joined at is locked

    The jump from Starter is quantity, takes and rate. The model, the resolutions and the thirty seconds were already yours.

    At a glance

    Clips a month
    ≈ 44 at 5s 480P
    Takes per run
    4
    Credits per dollar
    +21% vs Starter
    Refund window
    7 days
  • StudioBest rate

    Client volume, and the plan where you stop rationing 1080P. Thirty-one full-resolution finished clips a month, at the lowest price per credit we sell.

    $99.90/mo$119.90

    $1,198.80 billed yearly

    Cancel anytime

    6,240 credits / month · ≈ 156 clips

    at 5s 480P · 78 at 720P · 39 at 1080P

    Plan credits expire at the end of the month

    • 6,240 credits a month — 9.75× Starter, 2.8× Pro13×
    • ≈ 156 finished clips a month, or 39 at full 1080P
    • +26% credits per dollar — the best rate we sellBest rate
    • Enough 1080P that you stop drafting at 480P first
    • 4 takes of one prompt per run
    • Sized for a client roster rather than one channel
    • Top up any month without changing plan
    • Every resolution — 480P, 720P and 1080P
    • Every length — 2 to 30 seconds in one pass
    • Every input — text, image, reference, document, web page
    • Sound written in the same pass, no watermark
    • Commercial use included — publish it, sell it, bill for it
    • Wan 3.0 Prime, the fast tier, whenever you want it
    • A failed run never costs credits
    • 7-day refund while the credits are untouched
    • Cancel in two clicks — the price you joined at is locked

    The plan for a client roster rather than one channel: four takes of every prompt, 1080P without rationing it, and room to re-shoot a scene without watching the balance drop.

    At a glance

    Clips a month
    ≈ 124 at 5s 480P
    At full 1080P
    ≈ 31 a month
    Credits per dollar
    +28% vs Starter
    Refund window
    7 days

The whole procedure

How to run a six-hook UGC ad test tonight

Five steps to a tested UGC ad. The first two cost nothing, and they are the two that decide whether the other three were worth running.

  1. Write six openings, not one ad

    Same offer, same product, six different first sentences. The hook that wins is reliably not the one you would have picked, which is the entire reason to generate rather than book.

    Free
  2. Count the words

    Twenty-nine for a conversation, thirty-seven for one person talking, per fifteen seconds. A line that does not fit gets rushed rather than trimmed.

    Free
  3. Run all six at 480P, three seconds, vertical

    240 credits for the set. You are looking for which opening survives being watched with the sound on, not whether the grade is right.

    First pass
  4. Watch them on a phone, muted, then unmuted

    Muted finds the one that reads without a caption. Unmuted finds the one where the read sounds like a person. Different hooks win each test, and that is the useful part.

    The honest pass
  5. Re-run only the survivor, full length at 720P

    One 15-second ad at 720P is 240 credits — the same as the whole test that found it. Attach the same reference image so the creator is the one you already validated.

    Before you spend media budget

The order is the point. Every step above moves a decision earlier, to where changing your mind is still free.

Questions people actually ask

AI UGC ad generator questions

What it takes in, what one ad costs, and what the platforms require before it runs.

What is a Wan 3.0 AI UGC ad generator?

A place to write a creator-style ad and have Wan 3.0 render it — the person, the room, your product and the spoken line in a single pass, up to thirty seconds, vertical, with sound. There is no avatar roster to browse and no ad-account integration; what comes out is an MP4 you upload wherever you buy media.

Can I use my own product photo instead of a stock one?

Yes, and it is the main reason to use this rather than a compositing tool. Attach the pack shot as a reference image and name it in the prompt, and the thing in frame is the thing you sell. Up to ten reference images in one run, and references do not add to the cost.

Does it come with a voice, or do I add that afterwards?

The voice is generated in the same pass as the face that speaks it, so there is no separate text-to-speech step and no lip-sync pass. You can also supply an audio reference and have the delivery take its colour from that, as the phone-call case above does. Turning sound off does not reduce the price.

How long can one UGC ad be?

Thirty seconds, in a single generation, with cuts inside it — long enough for a UGC ad to run hook, demonstration and call to action without stitching. A sixty-second ad is two generations edited together.

Why did my vertical ad come out horizontal?

Because the ratio control was on adaptive and it read your reference image. A landscape pack shot produces a landscape ad. Set 9:16 explicitly; this page ships locked to it, and the try-on case above is what happens when it is not.

How many words fit in a fifteen-second ad?

About twenty-nine for two people talking and about thirty-seven for one person reading to camera — both measured off Wan's published cases, one of which names its own rate of 2.5 words a second. Past that the read speeds up rather than the ad getting longer.

Can I get the same creator across ten different UGC ads?

Only if you supply her. Nothing about a face carries between runs on its own, so attach the same frontal still to each one and name it in the prompt. Anything that absolutely must match — a face and a pack together — is safest inside one generation.

What does one UGC ad cost?

Per output second: 8 credits at 480P, 16 at 720P, 32 at 1080P. A fifteen-second vertical UGC ad is 120, 240 or 480 credits. Six five-second hooks at 480P is 240 — half of one finished ad at 1080P.

Is there a free way to try it?

One free clip per account on the real model, three seconds at 480P with sound, plus 24 credits on signup which buy exactly one more of the same. No card.

Is there a watermark?

No, on any tier, including the free clip. The watermarks visible on the example films are Alibaba's own and are left on because those are their runs, not ours.

Can I run these as TikTok or Meta ads?

Yes, with disclosure. TikTok Ads Manager has a setting for ads containing AI-generated content, and duplicating a campaign is where it gets missed — check it on every variant. Meta detects AI-made creative through C2PA metadata and labels it. Both are separate from branded-content disclosure.

Can a generated creator say she loves the product?

No — that crosses from demonstration into a testimonial, and the FTC's rule prohibits testimonials that misrepresent that the person exists or had the experience. She can show the product, demonstrate it and read a claim you can substantiate. She cannot report an experience nobody had.

Test the hook you are least sure about. It is free.

Take the UGC hook you cannot decide on, put your own product photo in it, and watch three seconds with the sound up. If it does not survive that, it will not survive a feed.

Written and maintained by the wan-3.run editorial teamPublished Last updated Tool version 2026.09.4