Vidu is made by the Chinese company ShengShu. It builds a clip from several references: a character, an object and a place, and the characters keep their looks.
Vidu Q4 takes 1 to 15 images, renders 3 to 16 seconds, and outputs 540p up to 4K. Sound is on by default.
Vidu Q4 resolutions
540p
1,800 tokens per second
Quick drafts.
720p and 1080p
3,800 tokens and 4,800 tokens per second
For social and ads.
2K and 4K
7,600 tokens and 15,600 tokens per second
For big screens.
What Vidu does
Up to 15 references
Set characters, clothes, objects and background as separate images.
Consistent characters
Faces stay the same from frame to frame.
Sound
An audio track is generated with the video.
Prompt examples
At least one image is required. A prompt is optional when you animate one frame. With several references a prompt is required.
Two characters
Upload two portraits: "They meet on a platform and hug, it is snowing"
Product
Upload a bag and a model: "She walks down the street with this bag, the camera follows"
Animate
Upload a landscape: "Clouds drift, ripples run across the lake"
Parameters
Duration
3 to 16 seconds
Resolution
540p, 720p, 1080p, 2K, 4K
References
1 to 15 images
Aspect ratios
16:9, 9:16, 1:1, 4:3, 3:4
Sound
on by default
How much Vidu costs
What
Tokens
USD
5 sec, 540p
9,000 tokens
≈ $0.30
5 sec, 720p
19,000 tokens
≈ $0.63
8 sec, 1080p
38,400 tokens
≈ $1.28
5 sec, 4K
78,000 tokens
≈ $2.60
USD shown at the Basic rate: $5 = 150,000 tokens. Larger plans cut the token price by up to 40%. Tokens never expire, and there is no subscription.
$5 by card gives 150,000 tokens. That covers 16 five-second clips in 540p.
How to start
Sign in
With Google, Telegram or email. Takes under a minute.
Top up
From $5 by card or from $2 in crypto. No subscription, and tokens never expire.
Generate
Open the Video tab and pick Vidu Q4. Upload a photo and add a prompt.