minimaxiH3 Get access
ViduText-to-videoVendor content policy applies

Vidu Q2 Reference-to-video

Vidu Q2 Reference-to-Video is an advanced AI video generation model that brings static images to life. Upload a reference image and describe the motion you want — the model generates high-quality video with smooth animation, optional audio, and cinematic quality up to 1080p.

$0.096per secondStarting price at the base resolution and quality tier.
$0.77Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “The character rides a horse across the grassland”

What it does

Vidu Q2 Reference-to-video, in practice.

Vidu Q2 Reference-to-Video is a capable AI video generation model that generates video featuring specific subjects. Provide subject images alongside a motion prompt, and the model produces smooth, natural video that faithfully preserves each subject's appearance and identity — offering a strong balance of quality and cost for subject-driven workflows.

  • Balanced quality and speed Solid visual consistency and motion quality at a mid-tier price point.
  • Subject-driven generation Feature specific characters or objects with consistent appearance throughout the video.
  • High resolution output Generate videos in 540p, 720p, or 1080p quality.
  • Flexible duration Create videos from 1 to 10 seconds in length.
  • Audio generation Optional audio with configurable type: full audio, speech only, or sound effects only.
  • Prompt Enhancer Built-in tool to automatically improve your motion descriptions.

Run Vidu Q2 Reference-to-video

from $0.096/sec
resolution
audio_type
aspect_ratio
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
subjectsInformation about the subjects in the images. Supports 1–7 subjects, total 1–7 images
promptA textual description for video generation.default Santa Claus and the bear hug by the lakeside.
durationThe duration of the generated media in seconds.default 5
resolutionThe resolution of the generated media.540p 720p 1080p
audio_typeAudio type, required when audio is true, defaults to all.all speech_only sound_effect_only
aspect_ratioThe aspect ratio of the generated media.16:9 9:16 1:1 4:3 3:4
movement_amplitudeThe movement amplitude of objects in the frame.auto small medium large
generate_audioWhether to generate audio for the video.default True
seedThe random seed to use for the generation. -1 means a random seed will be used.default

Sample prompt

The prompt behind the sample.

The character rides a horse across the grassland
duration: 5resolution: 720paudio_type: allaspect_ratio: 16:9movement_amplitude: autogenerate_audio: Trueseed:

FAQ

Short answers.

How much does Vidu Q2 Reference-to-video cost?

Pricing starts at $0.096 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $0.77. Usage is billed per request from your balance — no subscription.

Does Vidu Q2 Reference-to-video run uncensored here?

No. Vidu applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Vidu Q2 Reference-to-video for everything else it does well.

What does Vidu Q2 Reference-to-video take as input?

It is a text-to-video model. Vidu Q2 Reference-to-Video is an advanced AI video generation model that brings static images to life. Upload a reference image and describe the motion you want — the model generates high-quality video with smooth animation, optional audio, and cinematic quali

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run Vidu Q2 Reference-to-video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models