Model & Version

Model version (--v)

--v

Selects which Midjourney model version renders the image. Newer versions generally improve coherence, prompt-following, and detail; the default is the current latest.

Syntax
--v <version number>
Default
Current latest version

What it does

The --v parameter chooses the underlying Midjourney model version. Each version is a distinct model with its own strengths — newer releases have generally improved coherence, text handling, prompt-following, and fine detail, while some earlier versions retain a particular aesthetic people still prefer.

Because versions are different models, the same prompt and seed can look meaningfully different across them, and some parameters are version-specific. If you omit --v, Midjourney uses the current default version.

Examples

a watercolour landscape --v 6

Renders on version 6’s model.

a watercolour landscape --v 7

Renders on the newer model, typically more coherent.

Common mistakes

  • Expecting a seed to reproduce across versions — different models differ.
  • Using version-specific parameters on a version that does not support them.
  • Combining --v with --niji; they select different models.

Model version is part of what makes a result reproducible. Recording which version produced an image means a look is repeatable even after Midjourney moves its default on.

Frequently asked questions

Frequently Asked Questions

Quick answers to the most common questions.

Related parameters

Keep the parameters behind every Midjourney image

Numonic pulls your Midjourney exports into a searchable catalog with the prompt, parameters, and Job ID intact — so the exact settings behind a look you loved are one search away, not lost in a folder.