someaistuff.
fal-aiReleased Feb 9, 2026

Vidu

Vidu's Q3 Turbo Model.

Compare
Provider endpoints0
Benchmark results2
Measured performance

Benchmark results

All leaderboards ↗
AA-Video-T2V ↗2.1
917.54

Text-to-video · audio evaluated · all categories

95% CI 899.54–935.54 · n=3,251

Independent result
AA-Video-T2V-Silent ↗2.1
898.91

Text-to-video · silent evaluation · all categories

95% CI 880.91–916.91 · n=3,606

Independent result
Access & cost

Prices across providers

0 quotes

No listed provider price

fal ↗Artificial Analysis Video Arena ↗

Model specifications

Developer
fal-ai
Modality
Video
Context
Not reported
Maximum output
Not reported
Weights
Not reported
Released
Feb 9, 2026
Provider listed
Feb 6, 2026
First discovered
Oct 16, 2026

Provider-reported tasks

Exact identities

  • falfal-ai/vidu/q3/text-to-video/turbo
  • aa-video043f0cb2-3565-45ad-bf78-7e2de8288e94

Sources

fal ↗Artificial Analysis Video Arena ↗

Updated Oct 22, 2026

More from fal-ai

View all ↗
fal-aiListed 16 days ago

Vidu Q4 Reference to Video

Uses up to 12 image references and three voice clips for consistent subjects and voices in 3–16 second videos, up to 4K.

No reported score
No reported score
Price not listed
+Compare
fal-aiListed 16 days ago

Vidu Q4

Vidu Q4 turns a first-frame image into 3 to 16 second videos with native audio at up to 4K. Best for animating stills, product shots and character scenes with dialogue.

No reported score
No reported score
Price not listed
+Compare
fal-aiListed 16 days ago

Kandinsky 6.0 VSR

Kandinsky 6.0 VSR Lite is a fast, lightweight video super-resolution model for quick, cost-efficient upscaling.

No reported score
No reported score
Price not listed
+Compare
fal-aiListed 16 days ago

Kandinsky 6.0 Pro

Kandinsky 6.0 Pro is Kandinsky Lab's flagship text-to-video model, generating high-resolution clips with cinematic motion and precise prompt adherence.

No reported score
No reported score
Conditional pricing →
+Compare