aibender logo aibenderAI model catalog
Video GA Proprietary

Vidu Q3

by Shengshu (Vidu) · China

Character consistency with multiple references

Open in interactive catalog Explore data analysis
Release2026-06
Context100K
Max output—
ParametersUndisclosed
Local / VRAMAPI only
LicenseProprietary

Overview

Vidu Q3 is a model in the Video category from Shengshu (Vidu). It was released in 2026-06. The vendor is based in China. Best for: Character consistency with multiple references.

Strengths

  • Reference consistency
  • Audio
  • Fast

Limits

  • Closed
  • No 4K

Specifications

VendorShengshu (Vidu)
CategoryVideo
Release2026-06
StatusGA
LicenseProprietary
Commercial useNot specified
Context window100K
Input modalitiesText, Image, Video
Output modalitiesVideo, Audio
Prompt typesText, Image, Reference
Negative promptsNo
Max outputs1 clip
Resolution720p-1080p
Duration5-16s
Frame rate24 fps
Audio generationYes
Local deploymentNo
API accessYes
Pricing$0.05-0.20 / second
ConfidenceMedium
Vendor countryChina
Vendor typeMedia lab

Pricing & hardware

$0.05-0.20 / second

API-only: local GPU memory is not applicable. API access is available.

More from Shengshu (Vidu)

No other models are listed for this vendor.