Generate
Back to Models
Models/pixverse/video · text-to-video · image-to-video · reference-to-videoPass-through

Pixverse V6

PixVerse V6 targets directed cinematic and stylized generation across text, image, and reference inputs. MachGen supports up to three reference images, 1-15 second clips from 360p through 1080p, and optional generated audio. In Models, direct camera movement through the prompt; structured camera controls are available in Storyboard.

Current MachGen support
Text to VideoImage to VideoReference to Video1-15s360p / 540p / 720p / 1080pPer type: 3 imageOptional audioSeed control
Starting at $0.025 $0.02 / output s with auto-reload
Auto-reloadRegular
360p · audio off$0.02/s$0.025/s
540p · audio off$0.028/s$0.035/s
720p · audio off$0.036/s$0.045/s
1080p · audio off$0.072/s$0.09/s
360p · audio on$0.028/s$0.035/s
540p · audio on$0.036/s$0.045/s
+2 more price tiers in the full pricebookLive public pricebookSee full pricebook

Overview

PixVerse V6 is a general-purpose video model available on MachGen for text, starting-image, and reference-guided generation. Current controls support 1-15 second outputs from 360p through 1080p, depending on the selected mode.

Optional generated audio is available where shown in the playground. Review outputs for text legibility, physics, and continuity rather than treating those qualities as guaranteed.

Model guide

Why choose Pixverse V6

Key strengths

  • A flexible general-purpose video model spanning text, image, and reference-driven generation.
  • Wide duration and resolution controls support both quick drafts and longer polished clips.
  • Camera direction and optional audio make it useful for stylized, cinematic, and social formats.

Good fit for

  • Stylized scenes, social video, music visuals, and cinematic concepts.
  • Animating stills with deliberate camera movement.
  • Reference-led subjects or environments that need a recognizable visual anchor.
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: 360p, 540p, 720p, 1080p
Aspect ratio: 16:9, 9:16, 1:1, 4:3
Duration: 1-15s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt limit: 2,048 characters
Image to VideoText prompt and source imageResolution: 360p, 540p, 720p, 1080p
Duration: 1-15s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt limit: 2,048 characters
Reference to VideoPer-type limits: up to 3 images, plus a text promptResolution: 360p, 540p, 720p, 1080p
Aspect ratio: 16:9, 9:16, 1:1, 4:3
Duration: 1-15s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt limit: 2,048 characters
Workflow

Using Pixverse V6

  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.
  • 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.
  • Image to video - use a starting image; framing follows the source image.
  • Reference to video - use reference images as appearance guides without forcing them to be the first frame.
  • Audio - enable generated audio when the selected mode offers it; pricing may differ between audio-on and silent output.
Best results

How to get better Pixverse V6 results

  • State the subject action and camera movement separately, then add style and lighting.
  • Choose one dominant visual idea; dense lists of effects often produce less coherent motion.
  • For reference mode, use images with compatible lighting and perspective when they belong in the same scene.
  • Enable audio only when the prompt includes useful sound direction; otherwise evaluate the visual result first.
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.
  • Pixverse V6 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.
Learn more

Learn more

For model background, technical details, and architecture, see the official PixVerse V6 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.

Pricing

Pixverse V6 pricing

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

On MachGen

Pixverse V6 on MachGen

Deployment: Pass-through. Pixverse V6 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.