SandBase is live — $1 in free credits on signupStart free ›
Use in agentVidu models

Vidu modelsvideo generation api

vidu/q2/reference-to-video/pro

Vidu Q2 Pro by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.

Input
Text prompt for video generation, max 2000 characters
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
Output video resolution Allowed values: 540p, 720p, 1080p.
18
Duration of the video in seconds (0 for automatic duration) Range: 1 to 8.
Random seed for reproducibility. If None, a random seed is chosen.
URLs of the reference videos for video editing or motion reference. Supports up to 2 videos.
The movement amplitude of objects in the frame Allowed values: auto, small, medium, large.
Whether to add background music to the generated video

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

URLs of the reference images for subject appearance. If videos are provided, up to 4 images are allowed; otherwise up to 7 images.
Idle

Example output — click Run to generate your own

API README

Vidu Q2 Reference to Video Pro

Vidu Q2 Reference to Video Pro concentrates on the vidu/q2/reference-to-video/pro workflow for pro work in video production. Vidu Q2 Pro by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation. Teams can place this named operation inside review, asset preparation, and publishing pipelines while keeping the original request attached to every result. The endpoint is especially useful when a project has a defined transformation goal and needs a repeatable request contract instead of an ad-hoc desktop step. Because vidu/q2/reference-to-video/pro is a separate catalog entry, evaluations should use this route’s own inputs, output expectations, and billing behavior. This is the creative remit of the exact endpoint, not a family-wide promise.

The mandatory portion is prompt. For example, the route documentation includes “@Figure 1 Character Reference@Refer to the special effects, movements, and camera work of Video 1.”. Vidu Q2 Reference to Video Pro exposes bgm, seed, prompt, duration, resolution, aspect_ratio, movement_amplitude as its documented request surface. bgm controls whether to add background music to the generated video; seed controls random seed for reproducibility. If None, a random seed is chosen; prompt controls text prompt for video generation, max 2000 characters; duration controls duration of the video in seconds (0 for automatic duration); resolution controls output video resolution; resolution accepts 540p, 720p, 1080p; aspect ratio controls the aspect ratio of the generated image; aspect ratio accepts 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16. Applications can submit that exact shape asynchronously, retain the chosen arguments in job metadata, and collect the resulting media URL for review or publishing.

Highlights

  • Coherent motion. Vidu Q2 Reference to Video Pro is built to turn the route’s text or reference media into a temporally connected sequence rather than unrelated frames.
  • Shot direction. Prompts can describe subject action, camera movement, pacing, and atmosphere so Vidu Q2 Reference to Video Pro has a concrete motion plan.
  • Reference-aware generation. When this route accepts source media, Vidu Q2 Reference to Video Pro uses it to anchor identity, composition, or the clip boundary throughout generation.
  • Production variants. Declared duration, resolution, framing, or inference controls support repeatable video options for review and selection.

Pricing

Billing optionPrice
Billing formulaparams.resolution == "1080p" ? 0.2 + params.duration * 0.1 : params.resolution == "720p" ? 0.3 : params.resolution == "520p" ? 0.2 : 0.1
duration=1 · resolution=540p$0.100000
duration=1 · resolution=720p$0.300000
duration=1 · resolution=1080p$0.300000
duration=2 · resolution=540p$0.100000
duration=2 · resolution=720p$0.300000
duration=2 · resolution=1080p$0.400000
duration=3 · resolution=540p$0.100000
duration=3 · resolution=720p$0.300000
duration=3 · resolution=1080p$0.500000
duration=4 · resolution=540p$0.100000
duration=4 · resolution=720p$0.300000
duration=4 · resolution=1080p$0.600000
duration=5 · resolution=540p$0.100000
duration=5 · resolution=720p$0.300000
duration=5 · resolution=1080p$0.700000
duration=6 · resolution=540p$0.100000
duration=6 · resolution=720p$0.300000
duration=6 · resolution=1080p$0.800000
duration=7 · resolution=540p$0.100000
duration=7 · resolution=720p$0.300000
duration=7 · resolution=1080p$0.900000
duration=8 · resolution=540p$0.100000
duration=8 · resolution=720p$0.300000
duration=8 · resolution=1080p$1.000000

When to Use

ScenarioWhy it fits
Choose Vidu Q2 Reference to Video ProUse it when the job specifically calls for pro and the route’s documented input contract matches assets already available in your workflow.
Keep the request reproducibleUse the required prompt explicitly, then record optional choices alongside the prompt for repeatable reruns.
Build controlled creative variationsChange one declared control at a time when comparing framing, format, duration, resolution, style, or other route-supported output decisions.
Integrate asynchronous deliveryUse this endpoint when an application can submit work, track completion, and collect the returned media URL instead of requiring an immediate inline artifact.
Validate before a large batchRun representative prompts and source assets first, confirm the visual or audio behavior, then lock the successful request shape for scaled production.

Prompt Guide

Lead with the subject or transformation, then add the composition, environment, style, lighting, motion, voice, or fidelity details relevant to this route. Keep every parameter inside the documented schema; the example below uses only fields declared for vidu/q2/reference-to-video/pro.

{
  "prompt": "@Figure 1 Character Reference@Refer to the special effects, movements, and camera work of Video 1.",
  "resolution": "540p",
  "aspect_ratio": "21:9",
  "movement_amplitude": "auto"
}

Technical Specs

SpecificationDetails
Model IDvidu/q2/reference-to-video/pro
Execution modeasync
Task typevideo
bgmboolean · optional
seedinteger · optional
promptstring · required
durationinteger · optional · min 1 · max 8
resolutionstring · optional · choices: 540p, 720p, 1080p
aspect_ratiostring · optional · choices: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
movement_amplitudestring · optional · choices: auto, small, medium, large
reference_image_urlsarray · optional
reference_video_urlsarray · optional

Related Models

Related Models

vidu/q2/image-to-video/proVidu Q2 Pro by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.vidu/q2/image-to-video/turboVidu Q2 Turbo by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.vidu/q2/text-to-videoVidu Q2 is Shengshu's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.vidu/q2/video-extension/proVidu Q2 Video Extension is Shengshu's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.vidu/q1/image-to-videoVidu Q1 by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.vidu/q1/reference-to-videoVidu Q1 by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.vidu/q1/start-end-to-videoVidu Q1 Start End To Video by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.vidu/q1/text-to-videoVidu Q1 is Shengshu's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.