Shengshu: Vidu Q2 Pro

Vidu Q2 Pro uses images, references, and start-and-end frames to direct a clip. It suits shots whose visual starting point is already planned, particularly when a transition between two compositions needs to be controlled.

Compare models

viduq2-pro

AvailableShengshuVideoAsync

Price: From $0.075
Modalities: Video

About Vidu Q2 Pro

Vidu Q2 Pro is the quality-oriented tier of Shengshu's Q2 video line. It starts from a still image, subject references, or a pair of start and end frames, which makes it the choice when the opening composition is already planned. Vidu's docs credit it with strong visual aesthetics and with editing support in reference-based generation, and it produces picture without synchronized audio.

Where it works well

Start and end frames let you fix both ends of a shot and have the model generate the transition between them.
It animates a prepared still, so an approved illustration or photo sets the look of the clip.
Vidu's docs note video editing support within reference-based generation.
Resolutions of 540p, 720p, and 1080p are offered, so drafts and finals use one model.

When to choose another model

It has no plain text-to-video operation; the base Vidu Q2 handles text-led scenes.
Synchronized audio is a Q3 feature in Vidu's model map, so Q2 Pro clips are silent.
Clips run shorter than the Q3 models, which the docs rate for longer durations.

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.

Image to videoReference to videoStart and end frames 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": "image-to-video",
  "resolution": "720p",
  "model": "viduq2-pro",
  "prompt": "Cinematic sunrise over a calm lake with gentle camera motion.",
  "image_url": "https://example.com/image.jpg"
}'

Parameters

Image to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	官方未公开独立 aspect_ratio；按输入图比例约束. The omitted-field default is not verified.
`audio`	Not provided	Not provided	Not provided
`audio_type`	Not provided	Not provided	Not provided
`duration`Required	1, 2, 3, 4, 5, 6, 7, 8	Not provided	图生视频: 1-10s；首尾帧: 1-8s；公共契约当前按 1-8s fail-closed 暴露. The omitted-field default is not verified.
`end_image`	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.
`image`	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.
`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`Required	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	图生视频: 720p / 1080p；首尾帧: 540p / 720p / 1080p. The omitted-field default is not verified.
`start_image`	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.
`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.
`voice_id`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.

Reference to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	官方未公开独立 aspect_ratio；按输入图比例约束. The omitted-field default is not verified.
`audio`	Not provided	Not provided	Not provided
`audio_type`	Not provided	Not provided	Not provided
`duration`Required	1, 2, 3, 4, 5, 6, 7, 8	Not provided	图生视频: 1-10s；首尾帧: 1-8s；公共契约当前按 1-8s fail-closed 暴露. The omitted-field default is not verified.
`end_image`	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.
`image`	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.
`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`Required	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	图生视频: 720p / 1080p；首尾帧: 540p / 720p / 1080p. The omitted-field default is not verified.
`start_image`	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.
`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.
`voice_id`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.

Start and end frames to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	官方未公开独立 aspect_ratio；按输入图比例约束. The omitted-field default is not verified.
`audio`	false	Not provided	Not provided
`audio_type`	Not provided	Not provided	Not provided
`duration`Required	1, 2, 3, 4, 5, 6, 7, 8	Not provided	图生视频: 1-10s；首尾帧: 1-8s；公共契约当前按 1-8s fail-closed 暴露. The omitted-field default is not verified.
`end_image`	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.
`image`	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.
`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`Required	Not provided	Not provided	Not provided
`resolution`Required	540p, 720p, 1080p	Not provided	图生视频: 720p / 1080p；首尾帧: 540p / 720p / 1080p. The omitted-field default is not verified.
`start_image`	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.
`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.
`voice_id`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.

Start/end-frame generation does not expose the native audio selector available to Q3; image/reference audio support is operation-specific.

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

Resolutions follow the official Vidu documentation. Durations from 1 to 8 seconds are accepted.

Start/end-frame generation does not expose the native audio selector available to Q3; image/reference audio support is operation-specific.

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, 1:04 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 Pro in Console with a prompt ready to edit or send.

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

Use cases

Controlled transitions
Supply the first and last frame of a scene change, such as day to night, and let the model create the movement between them.
Animating approved art
Bring a finished storyboard frame to life while keeping its composition, so the animation follows the picture the team already approved.
Reference-driven edits
Combine reference images with a prompt to place a known subject into a revised shot.
Product reveal clips
Start from a packshot and describe a slow camera move for an ad.

Prompt examples

From the first frame to the last frame, the sun sets over the harbor and the street lamps turn on, smooth continuous camera.

Animate this illustration: leaves fall from the tree and the girl turns to look at the camera.

Keep the product from the reference centered while the background shifts from studio white to a sunlit kitchen.

FAQ

What is Vidu Q2 Pro?

It is the Pro tier of Shengshu's Q2 video generation line. It supports image-to-video, reference-to-video, and start-to-end frame generation, with output at 540p, 720p, and 1080p.

What does start-end-to-video do?

You provide a first frame and a last frame, and the model generates the footage connecting them. It is useful when you must control exactly where a shot begins and ends.

Does Q2 Pro support text-only prompts?

No. It starts from images, references, or a frame pair, so a visual input is always required. For text-led generation use the base Vidu Q2, or one of the Q3 models.

How is it different from Q2 Turbo?

Turbo is positioned for fast generation on image and frame-pair inputs, and Pro adds reference-to-video and a quality focus. Choose Turbo for drafts and Pro for the shot you plan to keep.

Does it include sound?

No. Vidu's model map attributes simultaneous audio and video output to the Q3 models. Add music or effects in post if you use Q2 Pro.

How much does Vidu Q2 Pro 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 Pro use?

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

Which operations does Vidu Q2 Pro support?

Vidu Q2 Pro supports Image to video, Reference to video, Start and end frames to video. Select an operation above to see its endpoint and request example.