Shengshu: Vidu Q2

Vidu Q2 creates short scenes from text and subject references. It is useful for keeping a recognizable subject involved in a new shot, with control over framing and optional audio in the video workflow.

Compare models

viduq2

AvailableShengshuVideoAsync

Price: From $0.075
Modalities: Video

About Vidu Q2

Vidu Q2 is Shengshu's second-generation video model in its base tier, listed for text-to-video and reference-to-video. You describe a scene in text, or supply subject references so a recognizable character or object appears in a new shot. It is the entry point of the Q2 line; the Pro and Turbo variants add image and frame-pair inputs, and it returns video without the synchronized audio that Q3 introduced.

Where it works well

Reference-to-video lets a recognizable subject move into a new shot instead of being re-imagined from text each time.
Text-only prompts are supported, so no input image is required to start.
Output goes up to 1080p, with 540p and 720p for cheaper drafts.
Aspect ratios include square, 4:3, 3:4, 9:16, and 16:9, covering feeds and widescreen.

When to choose another model

Image-to-video and first/last frame inputs belong to Q2 Pro and Turbo, not this base variant.
The Vidu model map does not list synchronized audio for the Q2 series; Q3 models do.
For longer clips with scene cuts, the Q3 generation fits better.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Reference to videoText to videoTokenLab endpoint

POST/v1/videos/generations

curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "aspect_ratio": "16:9",
  "duration": 5,
  "operation": "text-to-video",
  "resolution": "720p",
  "model": "viduq2",
  "prompt": "Cinematic sunrise over a calm lake with gentle camera motion."
}'

Parameters

Reference to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	16:9, 9:16, 1:1, 4:3, 3:4	Not provided	Not provided
`audio`	Not provided	Not provided	Not provided
`bgm`	Not provided	Not provided	Not provided
`duration`	Not provided	Not provided	1-10s. The omitted-field default is not verified.
`images`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	Not provided
`subjects`	Not provided	Not provided	Not provided
`videos`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.

Text to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	16:9, 9:16, 1:1, 4:3, 3:4	Not provided	Not provided
`audio`	false	Not provided	Not provided
`bgm`	Not provided	Not provided	Not provided
`duration`	Not provided	Not provided	1-10s. The omitted-field default is not verified.
`images`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	Not provided
`subjects`	Not provided	Not provided	Not provided
`videos`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.

Text-to-video does not expose native audio generation. Its BGM control is distinct from direct audio-video generation.

Use TokenLab create endpoint and follow returned poll_url; if you need a fixed status path, use `/v1/tasks/{id}`.

Text-to-video does not expose native audio generation. Its BGM control is distinct from direct audio-video generation.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Pricing

per request

Verified price: —
Official price: How pricing works

	Official priceper request	Verified priceper request	Discount
Price	How pricing works	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 8:35 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Vidu Q2 in Console with a prompt ready to edit or send.

Help me create with viduq2 using text-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Best for

Text to Video

Character in new scenes
Supply a reference of a mascot or product and describe where it goes next, keeping it recognizable shot to shot.
Text-led short clips
Generate quick atmosphere shots from a paragraph of description for social posts.
Vertical social video
Use 9:16 output to produce clips sized for phone feeds without cropping.
Draft before upgrading
Test a concept at lower resolution on Q2 and rerun on a higher tier if it works.

Prompt examples

The mascot from the reference walks across a rooftop at dusk, camera tracks alongside, warm city lights behind.

A paper lantern drifts up through a misty bamboo forest, slow upward tilt, soft morning light.

The red scooter from the reference image rides along a seaside road, wide tracking shot, 16:9.

FAQ

What is Vidu Q2?

It is Shengshu's second-generation Vidu video model in its base tier. Per Vidu's model map it supports text-to-video and reference-to-video, with 540p, 720p, and 1080p output.

How does Q2 differ from Q2 Pro and Turbo?

The base Q2 works from text and subject references. Q2 Pro adds image-to-video and first/last-frame control, and Q2 Turbo targets fast image animation and frame pairs. Pick by which input you have.

Does Vidu Q2 generate audio?

The Vidu model map notes simultaneous audio and video output for Q3 models only, not for Q2. Treat Q2 output as picture only and add sound separately.

Can I use my own character?

Yes, through reference-to-video: supply reference images of the subject and a prompt describing the new scene. Quality of the result depends on clear, well-lit references.

Should I use Q2 or Q3?

Q3 adds synchronized audio and longer clip lengths in Vidu's docs. If you need sound or longer shots, choose Q3; if a simple silent reference or text clip is enough, Q2 works.

How much does Vidu Q2 cost?

Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Vidu Q2 use?

Use https://api.tokenlab.sh/v1/videos/generations for Vidu Q2. The request example below shows the matching code shape.

Which operations does Vidu Q2 support?

Vidu Q2 supports Reference to video, Text to video. Select an operation above to see its endpoint and request example.