Wan 3.0 4–30s or Wan 2.7 2–15s

Wan is Alibaba’s Tongyi Wanxiang video family — not a 60/120 minute dub desk, and not a 25–90 minute cartoon studio. This site runs Wan 3.0 and Wan 2.7: text-to-video, image-to-video, first and last frame, plus reference on 3.0 and continue-from-clip on 2.7. Wan 3.0 opens 4–30 seconds in one-second steps, 480p / 720p / 1080p (default 720p), with a generate-audio switch default on. Wan 2.7 opens 2–15 seconds at 720P or 1080P and takes an optional audio file instead of inventing a soundtrack. The numbers below are the ones this site opens. Vozo’s dubbed hour and Vyond’s Studio cap stay on those products.

01 — Capabilities

A 4–30s T2V family this site runs, not a dubber or a cartoon LMS

This page opens Wan 3.0 or Wan 2.7 in Create. It does not open Vozo’s 60/120 min dub, or Vyond’s 25–90 min cartoon studio.

01
Wan 3.0: 4 to 30 seconds, 480p–1080p, audio switch default on
Text-to-video ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Image and reference also offer adaptive.
02
Wan 3.0 reference: up to 10 images, 5 videos and an audio file
Output plus input duration is capped at 30 seconds.
03
Wan 2.7: 2 to 15 seconds, then continue a clip you already have
720P or 1080P. Continue is an edit of a source, not a blank 30-second generate.
04
Not Vozo’s 60/120 min dub, not Vyond’s 25–90 min cartoon desk
Vozo localizes existing video. Vyond is a cartoon studio. Wan is the family this site generates.

02 — Prompt to output

Prompts that match the clips above

Each prompt describes the picture on its card. “Use this prompt” sends that text to Create with Wan 3.0 as the starting series.

01 · Portrait
PromptClose-up of a young man with curly hair in a grey knit sweater, soft window light. He glances away, then smiles. Slow push-in, shallow depth of field.
02 · Product
PromptA white leather sneaker on a pale grey studio backdrop, soft diffused light. The camera orbits slowly. Stitching stays sharp, the look stays minimal.
03 · Street
PromptA slow dolly down a cobblestone lane in an old European village. Climbing roses on stone walls, café tables in morning sun, a few people walking in the distance.
04 · Character
PromptA young woman with shoulder-length brown hair in an olive t-shirt, late-afternoon gold light. She turns her head and looks off. Breeze in her hair, a handheld feel.

03 — Where it fits

Jobs that pick 3.0 or 2.7, not a dub or a cartoon hour

The family name is Wan. The request still has to name a series. These jobs are not Vozo’s dubbed file or Vyond’s Studio cut.

A clip that needs 4–30 seconds and a soundtrack
That is Wan 3.0 on this site. Wan 2.7 stops at 15 seconds.
Keep a face or a product with the 3.0 reference stack
Stills, clips and a voice file. That stack is why you open 3.0.
A 60-min dub of existing footage, or a 25–90 min cartoon studio cut
That is Vozo or Vyond. Wan is the T2V family this site runs.
Continue a clip you already like
Wan 2.7 video-to-video takes a source and a prompt. It is a continue, not a blank 30-second generate.

04 — Verdict

What this site actually runs

Strengths

Wan 3.0: 4–30 seconds, 480p–1080p, audio switch default on
Wan 3.0 reference: up to 10 images, 5 videos and audio
Wan 2.7: 2–15 seconds, 720P or 1080P, plus continue
First and last frame on both series

Trade-offs

The family is not one spec; duration and inputs change by series
Wan 2.7 does not generate audio from nothing — it takes an audio file
Wan 3.0 tops out at 1080p on this site, not 4K
Public Wan 2.5 / 2.2 docs exist; this page opens 3.0 and 2.7

05 — Side by side

Wan, Veo 3.1 and Kling 4.0

Wan’s column is this site’s Wan 3.0 / Wan 2.7 pair. A 4–30 second Wan 3.0 clip here is a generate row on ImgToVid. Veo 3.1 and Kling 4.0 numbers below are from those vendors’ public docs.

	Wan	Veo 3.1	Kling 4.0
Developer	Alibaba	Google DeepMind	Kuaishou
Single clip	4–30s on 3.0; 2–15s on 2.7	4, 6 or 8 seconds	3–30 seconds
Picture	480p–1080p on 3.0; 720P/1080P on 2.7	720p, 1080p, 4K at 24 fps	720p, 1080p and 4K listed
Sound	Switch on 3.0; file in on 2.7	Native, with the picture	Stereo, with lip sync
Start from	Text, still, frames; refs on 3.0; continue on 2.7	Prompt, still, first and last frame	Keyframes or 15 references
On ImgToVid	Available now	Coming soon	Coming soon

06 — How it works

Three steps to a Wan clip

Step 1
Pick 3.0 or 2.7
Wan 3.0 for length, audio and references. Wan 2.7 for a shorter pass or to continue a clip.
Step 2
Write the shot
Subject, action, camera. Add a first frame, a last frame or references when you need them locked.
Step 3
Generate in Create
Ratio, length and resolution go with the prompt. Membership and credits are checked in Create.

07 — Versions

Explore the Wan family

Both series run in Create with the same prompt box — switch any time.

08 — FAQ

Wan, in plain terms

What is Wan?

Wan is Alibaba’s Tongyi Wanxiang video family. This site runs Wan 3.0 and Wan 2.7. Public Wan 2.5 and Wan 2.2 docs exist; they are not the generator on this page.

Which Wan version should I use?

Wan 3.0 for clips up to 30 seconds, native audio and references. Wan 2.7 for 2–15 seconds, or to continue a clip you already have.

How long is a Wan clip on this site?

Wan 3.0: 4 to 30 seconds. Wan 2.7: 2 to 15 seconds. Official Wan 3.0 docs mention 2–30; this site opens 4–30.

Does Wan generate audio?

Wan 3.0 has a generate-audio switch, default on. Wan 2.7 takes an optional audio file. Do not assume every older Wan row does the same.

Can I use Wan on ImgToVid?

Yes. The generator on this page starts on Wan 3.0. You can switch to Wan 2.7 in Create. This is not Vozo’s dubber or Vyond’s cartoon studio.

Can I use the results commercially?

Commercial use of anything you generate on ImgToVid depends on your plan. Check Pricing and our Terms before you publish, and make sure prompts and uploads do not infringe someone else’s rights.