Generate
Back to Models
Models/vidu/video · text-to-video · image-to-video · reference-to-video · first-last-frameMixed deployment

Vidu Q3 Turbo

Vidu Q3 Turbo balances generation speed and visual quality for rapid anime, advertising, and concept-video iteration. On MachGen it supports text-to-video, image-to-video, reference-to-video, and first-to-last-frame generation at 540p or 720p; the first three modes use managed inference, while frame-pair generation can include upstream-generated audio.

Current MachGen support
Text to VideoImage to VideoReference to VideoFrame to Frame1-16s540p / 720pPer type: 7 imageOptional audioPrompt enhancementSeed control
Starting at $0.015 / output s
540p · 1-5s$0.015/s
540p · 6-10s$0.018/s
540p · 11-16s$0.02/s
720p · 1-5s$0.03/s
720p · 6-10s$0.04/s
720p · 11-16s$0.045/s
+3 more price tiers in the full pricebookLive public pricebookSee full pricebook

Overview

Vidu Q3 Turbo is the faster Q3 tier. MachGen exposes text-to-video, image-to-video, reference-to-video, and first-to-last-frame generation at 540p or 720p.

Text, image, and reference modes run on MachGen-managed inference and include generated audio. First-to-last-frame uses the upstream Vidu integration and exposes its own audio setting.

Model guide

Why choose Vidu Q3 Turbo

Key strengths

  • A faster Q3 option for iterating across text, image, reference, and first-to-last-frame workflows.
  • Broad input coverage makes it useful when the creative direction changes during exploration.
  • Reference and frame-pair modes give more control than a text-only prompt.

Good fit for

  • Rapid concept testing, social drafts, anime motion, and advertising variations.
  • Trying several motions for the same starting image.
  • Reference-led subject tests before moving to a higher-cost final.
Supported on MachGen

Inputs and output settings

This table reflects the model routes and controls currently exposed by MachGen.

ModeRequired inputAvailable settings
Text to VideoText promptResolution: 540p, 720p
Aspect ratio: 16:9, 9:16, 1:1, 4:3
Duration: 1-16s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt enhancement
Prompt limit: 5,000 characters
Image to VideoText prompt and source image; optional end frameResolution: 540p, 720p
Duration: 1-16s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt enhancement
Prompt limit: 5,000 characters
Reference to VideoPer-type limits: up to 7 images, plus a text promptResolution: 540p, 720p
Aspect ratio: 16:9, 9:16, 1:1, 4:3
Duration: 1-16s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt enhancement
Prompt limit: 5,000 characters
First & Last FrameText prompt, start frame, and end frameResolution: 540p, 720p
Duration: 1-16s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt limit: 5,000 characters
Workflow

Using Vidu Q3 Turbo

  1. Choose a supported generation mode in Playground.
  2. Add the required prompt and source or reference assets.
  3. Select output settings from the controls shown for that mode.
  4. Generate, then inspect the returned asset before reusing the settings through the API.

Practical guidance

  • Describe the subject, action or composition, environment, and visual direction in a clear order.
  • For image animation, describe the intended motion and camera behavior instead of repeating what is already visible.
  • Give each reference a clear role in the prompt, using the names inserted by the Playground.
  • Use compatible start and end frames, then describe the transition between them.
  • When audio is enabled, include any dialogue, ambience, or sound cues that matter to the scene.

Modes available on MachGen

  • Text to video - prompt plus aspect ratio and output controls.
  • Image to video - animate one starting image with prompt-directed motion.
  • Reference to video - use one or more appearance references while the prompt defines motion and scene direction.
  • First and last frame - pin opening and closing compositions and let the model generate the transition.
Best results

How to get better Vidu Q3 Turbo results

  • Use Turbo to settle the action, framing, and duration before refining a final in a quality-focused model.
  • For references, explain what must be borrowed from each image instead of asking the model to copy everything.
  • Use first and last frames when the ending composition is more important than open-ended motion.
  • Change one variable per iteration so speed produces useful comparisons rather than unrelated samples.
Limits

Limits and availability

  • MachGen admits only the modes and settings listed above for this catalog model.
  • Source assets must finish uploading before a request can be submitted.
  • Generated results can vary between requests, including when the same prompt and settings are reused.
  • Vidu Q3 Turbo uses a mixed deployment. Hosted for T2V, I2V, R2V; pass-through for F2F. The selected task determines the execution route.
Learn more

Learn more

For model background, technical details, and architecture, see the official Vidu Q3 model map.

Try this model in the MachGen Playground.

Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.

Pricing

Vidu Q3 Turbo pricing

See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.

On MachGen

Vidu Q3 Turbo on MachGen

Deployment: Mixed deployment. Vidu Q3 Turbo uses a mixed deployment. Hosted for T2V, I2V, R2V; pass-through for F2F. The selected task determines the execution route.

The Playground and API sections on this page list the inputs and output settings exposed for this model.