Video generation

Vidu Q3-mix

Name: Vidu Q3-mix
Author: Shengshu Technology (Vidu)

Vidu Q3-mix is the reference-to-video-only Q3 variant that Shengshu describes as the strongest overall balance of visual quality, dynamics and intelligent scene transitions, with audio-video joint output.

A video generation model by Shengshu Technology (Vidu) · read 2026-08-14 · sourcing high

Up to: 16 seconds
Resolution: 1080p
Aspect ratios: 16:9, 9:16, 3:4, 4:3
Weights: Not released
API: Yes
Commercial use: Not established

It generates 1 to 16 second clips at 720p or 1080p from 1 to 7 reference images. Unlike the other Q3 variants it has no off-peak discount.

Commercial use — Not established

Vidu's Terms of Use (https://platform.vidu.com/docs/terms-of-use) were not reviewed, so commercial-use rights are left unverified.

The licence notes recorded during research were read for a commercial-use position and did not state one. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Shengshu Technology (Vidu)'s own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in: text, image
What it makes: video, audio
Maximum duration: 16 seconds
Maximum resolution: 1080p
Aspect ratios: 16:9, 9:16, 3:4, 4:3, 1:1
Controls: reference-character-consistency
Weights: Not released
API: Yes
Pricing: Credits at $0.005 each, per second: 720p 24 credits/s ($0.12), 1080p 29 credits/s ($0.145). Off-peak mode is not supported for this model.
Released or updated: 2026-04-13

Strengths

Positioned as Vidu's best-balanced reference model
Intelligent scene transitions plus joint audio
1 to 16 second range

Weaknesses

Most expensive Vidu tier at $0.145/s
No off-peak discount
Reference-to-video only; no plain text-to-video or start-end mode
No 540p tier

Best for

Hero shots where subject consistency and transition quality matter more than unit cost.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

Character and set consistency: the weakest link names “consistency”
Temporal consistency: flicker, drift and morphing names “consistency”

MCP servers that front Shengshu Technology (Vidu)

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

Shortgenius Video generation
Generate AI short-form videos and auto-publish them to TikTok, YouTube, Instagram, Facebook and X.
Vivideo Video generation
AI video generation via the Vivideo API: auto or manual mode, avatars, voices, brand kits.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Vidu Q1

Vidu Q1 is the legacy model kept for existing integrations. It produces exactly 5 second clips at 1080p only, across text-to-video, image-to-video, st

Video generation

Vidu Q2

Vidu Q2 is the previous generation and the model that established Vidu's reference-to-video positioning: up to seven reference images covering faces,

Video generation

Vidu Q3-pro

Vidu Q3-pro is Shengshu's top-quality Q3 variant for text-to-video, image-to-video and start-end-to-video, producing 1 to 16 second clips at 540p, 720

Video generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.