Vidu Q3

Vidu Q3

Vidu Q3 on MachGen focuses on reference-to-video: supply one or more reference stills plus a motion prompt to guide subject appearance, motion, and scene direction.

Unlike plain image-to-video (where a still is always frame zero), reference-to-video uses references as appearance anchors - ideal for character-consistent storytelling and product continuity.

Why choose Vidu Q3

Key strengths

• Reference-first generation designed to preserve a subject or visual identity while changing the scene and action.
• Multiple references can separate identity, styling, and environment instead of forcing one image to carry the full brief.
• Optional audio supports reference-led narrative and character work.

Good fit for

• Recurring characters, mascots, products, or wardrobe across new scenes.
• Look development anchored by existing campaign or concept imagery.
• Reference-driven clips where continuity matters more than unconstrained exploration.

Inputs and output settings

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

Using Vidu Q3

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

• Give each reference a clear role in the prompt, using the names inserted by the Playground.
• When audio is enabled, include any dialogue, ambience, or sound cues that matter to the scene.

Modes

• Reference to video - one or more reference images constrain appearance; the prompt drives motion, camera, and story beats.
• Optional audio - enable native sound when dialogue, effects, or ambience should ship with the picture.
• Resolution ladder - practical outputs up to 1080p depending on the request settings in Generate.

Prompting notes

• Use clean, well-lit references that clearly show the subject you want to preserve.
• Write motion and camera in the prompt - do not restate the whole appearance already in the references.
• Keep one primary action per clip for stabler continuity.

How to get better Vidu Q3 results

• Use clean references that show the subject clearly; conflicting identities or styles weaken consistency.
• Tell the prompt what each reference controls, such as face, outfit, product shape, or environment.
• Describe the new action and camera direction without repeatedly redescribing fixed reference details.
• Test a short clip first to confirm identity retention before increasing duration or resolution.

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 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

Learn more

For model background, technical details, and architecture, see the official Vidu reference-to-video documentation.

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.

Vidu Q3 pricing

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

Vidu Q3 on MachGen

Deployment: Pass-through. Vidu Q3 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

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