Vidu AI Video Generator

Vidu is Shengshu Technology’s video model family. Q3 is the general series with synchronized audio. Q4 Preview, launched October 7, 2026, is the flagship: image-to-video and reference-to-video, up to 16 seconds and 4K. The map below is from Vidu’s model table.

01 — Capabilities

Pick the Vidu id, then the duration follows

Vidu is not one clip length. Q1 is 5 seconds. Q2 is 1–10. Q3 and Q4 Preview reach 16. What you can start from also changes by id.

01
Q3 still takes text; Q4 Preview does not
The model map marks text-to-video on Vidu Q3 and Vidu Q1. Q4 Preview is image-to-video and reference-to-video only. A blank prompt is the wrong door for Q4.
02
Audio from Q3 onward
Q3 Pro, Mix, Drama, Ad and Turbo list synchronized audio-video output. Q4 Preview generates dialogue and effects with the picture. Image-to-video on Q4 defaults audio on.
03
References get serious on Q4
Q4 Preview takes 1–15 images and up to 3 voice references. That pack is the reason to open Q4 instead of Q3. Q3 is the generalist; Q4 is the reference stack.
04
4K is a Q4 Preview listing
Q3 tops out at 1080p in the table. Q4 Preview lists 540p, 720p, 1080p, 2K and 4K, default 720p, 24 fps. Do not read 4K back onto Q3.

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. The generator on this page runs Seedance 2.5, not Vidu.

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 Q3 or Q4, not “Vidu” in the abstract

The family name is Vidu. The request still has to name an id. Q3 for a text start. Q4 Preview when you have stills and voices to lock.

You only have a prompt
That is a Q3 (or Q1) job on Vidu’s own map. Q4 Preview will not take it. Do not plan a text-only pipeline on the flagship id.
A character has to stay the same person
Q4 Preview’s page is explicit: up to 15 stills and 3 voice clips. Series, ads, one take. Q3 does not list that stack.
A short ad with audio already in
Q3 Ad is listed for 5–8 second clips with shot changes. Q3 Drama is the storytelling variant. Both include synchronized audio in the table.
Finish at 4K
Only Q4 Preview lists 2K and 4K. Default there is still 720p. Treat 4K as a Q4 setting, not a family-wide promise.

04 — Verdict

What Vidu’s model map actually lists

Strengths

Q3: text and image routes, synchronized audio, up to 16 seconds, 1080p
Q4 Preview: image and reference, up to 16 seconds, 2K/4K, 15 images + 3 voices
24 fps across Q3 and Q4 Preview
Specialized Q3 ids for drama and ads

Trade-offs

The family is not one spec; duration and inputs change by id
Q4 Preview has no text-to-video
4K is Q4 Preview only, and Q4 is still labeled Preview
Vidu is not available on ImgToVid

05 — Side by side

Vidu, Veo 3.1 and Kling 4.0

Vidu’s column is the family as of Q4 Preview in October 2026. Individual ids are narrower than this table.

	Vidu	Veo 3.1	Kling 4.0
Developer	Shengshu	Google DeepMind	Kuaishou
Single clip	Up to 16s on Q3/Q4; 5s on Q1	4, 6 or 8 seconds	3–30 seconds
Picture	1080p on Q3; 4K on Q4 Preview	720p, 1080p, 4K at 24 fps	720p, 1080p and 4K listed
Sound	Native from Q3 onward	Native, with the picture	Stereo, with lip sync
Start from	Text on Q3; image/refs on Q4	Prompt, still, first and last frame	Keyframes or 15 references
On ImgToVid	Coming soon	Coming soon	Coming soon

06 — How it works

Start a clip on ImgToVid

Step 1
Describe one shot
Subject, action, camera. If you wanted Vidu’s Q3 text route or Q4’s 15-image stack, say that in the prompt. Vidu will not be the model that runs it.
Step 2
Use the generator on this page
It runs Seedance 2.5, because Vidu is not offered here. The prompt and the settings carry into Create.
Step 3
Generate in Create
Membership and credits are checked there. Coming back to this page does not switch the model over to Vidu.

07 — FAQ

Vidu, in plain terms

What is Vidu?

Vidu is Shengshu Technology’s video model family. The current general series is Vidu Q3. The flagship is Vidu Q4 Preview, launched on October 7, 2026. Older ids include Vidu Q2, Vidu Q1 and Vidu 2.0.

How long is a Vidu clip?

It depends on the id. Q1 is 5 seconds. Q2 is 1–10 seconds. Q3 and Q4 Preview go up to 16 seconds. Image-to-video on Q4 is 3–16 seconds, default 5.

Does Vidu generate audio?

Q3 and Q4 Preview list synchronized audio-video output. Q4 image-to-video defaults audio to on. Do not assume every older id does the same; Q1 and Q2 are specified more as picture models on the map.

Q3 or Q4 Preview?

Q3 if you need text-to-video or a general 1080p clip with audio. Q4 Preview if you have stills and voices to lock, or you need 2K/4K. Q4 Preview does not take text only.

Can I generate Vidu videos on ImgToVid?

No. The generator on this page runs Seedance 2.5 so you can draft a shot. Vidu itself is marked coming soon.

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.