glunty

AI tool cheat sheets / Midjourney

Midjourney parameter cheat sheet

A searchable reference for Midjourney parameters and prompt syntax, so you stop scrolling chat history for the flag you need. Click any parameter to copy it. Midjourney changes often, so check the official docs for the newest, version-specific features.

Last verified: 2026-07-06. Free tiers and features change, so check the official site.

Omni Reference and character (V7)

--oref URL

Omni Reference (V7): put a specific person or object from a reference image into the scene. A text prompt is still required, and it costs about 2x the usual GPU time.

Example: a knight in a throne room --oref https://example.com/face.png

--ow 100

Omni weight, 1 to 1000 (default 100). Higher forces a closer match. Keep it under about 400 unless you also raise --stylize.

Example: the same man, now smiling --oref URL --ow 200

Aspect and framing

--ar 16:9

Aspect ratio as width:height. Common values are 1:1, 3:2, 16:9, and 9:16.

Example: a city skyline at dusk --ar 16:9

--ar 9:16

Tall/portrait framing, good for phone wallpapers and vertical video.

Example: a waterfall in a forest --ar 9:16

Style and variation

--stylize 100

How strongly the default aesthetic is applied. Range 0 to 1000; higher is more stylized, lower is more literal.

Example: product photo of a watch --stylize 50

--chaos 30

How varied the four results are. Range 0 to 100; higher gives more different, surprising options.

Example: abstract poster --chaos 40

--weird 250

Pushes toward unusual, offbeat aesthetics. Range 0 to 3000; use in small amounts.

Example: a teapot creature --weird 250

--style raw

Reduces the default beautification for more literal, photographic results.

Example: street photo, overcast --style raw

References (style and character)

--sref URL

Style reference: match the look of the image at that URL without copying its content.

Example: a fox --sref https://example.com/style.png

--sw 100

Style weight for --sref. Higher follows the reference style more closely.

Example: a fox --sref URL --sw 300

--cref URL

Character reference: keep the same character across images.

Example: the same girl reading --cref https://example.com/char.png

--cw 100

Character weight for --cref. Lower keeps the face but changes clothing/hair more freely.

Example: the same girl --cref URL --cw 30

Control and output

--no text

Negative prompt: exclude something. The reliable way to remove an element.

Example: a busy market --no people

--seed 12345

Sets the starting noise so a result is reproducible. Reuse a seed for consistent variations.

Example: a red car --seed 12345

--tile

Makes a seamless, repeating pattern (good for textures and backgrounds).

Example: floral pattern --tile

--q 1

Quality / render time. Lower (0.25, 0.5) is faster and cheaper; 1 is the default.

Example: quick concept sketch --q 0.5

--stop 80

Stop the job early at a percent (10 to 100) for a softer, less finished look.

Example: watercolor bird --stop 85

--repeat 4

Run the same prompt several times at once to get more options.

Example: logo ideas --repeat 4

Prompt syntax

word::2 word

Multi-prompt weighting. The number after :: sets how much a part matters.

Example: space::2 station::1

image URL first

Put an image URL at the START of the prompt to use it as an image prompt.

Example: https://example.com/ref.png a knight

/describe

Upload an image and Midjourney suggests prompts that would produce something similar.

Example: /describe (then upload an image)

/blend

Blend two to five uploaded images into one, no text prompt needed.

Example: /blend (then upload images)

Tips

Match the platform with --ar

Use 9:16 for reels and stories, 16:9 for slides and thumbnails, and 1:1 for a feed post. Setting the aspect ratio up front beats cropping later.

Use --no instead of writing "without"

Saying "no text" or "without a hat" inside the prompt often adds the thing you did not want. Put it after --no instead: --no text, --no hat.

Hold a look with --sref

Paste one --sref image URL across a whole set to keep a consistent style, then dial it with --sw. Great for a themed batch of posts.

Reproduce and iterate with --seed

Grab the seed from a result you liked, then reuse --seed with small prompt tweaks to get controlled variations instead of random ones.

Reverse-engineer a look with /describe

Not sure how to describe a style you found? Upload the image to /describe and Midjourney hands you prompt language to start from.

This is reference content. The prompts and settings run in your own AI tool, not on glunty, so reading this page makes zero requests to those services. Details change often, so verify current pricing and limits on the official site.

Official reference: Midjourney docs. Details change, so verify version-specific features there.

More AI tool guides

Suno AI tips and prompt cheat sheet

A searchable Suno cheat sheet: section tags, vocal delivery cues, the 5-part style formula, and hacks to stop wasting your daily credits. Free, copy-paste.

Leonardo.Ai token costs and cheat sheet

Learn how Leonardo.Ai tokens are spent per generation and stretch your free daily tokens with this cheat sheet.

Kling AI prompt syntax and cheat sheet

Master Kling AI prompt syntax, storyboard shots, and elements to make consistent AI video within your free daily credits.

ElevenLabs tips and voice settings cheat sheet

Tune ElevenLabs voice settings for narration or character work with a cheat sheet of stability, similarity, and Voice Design.

Ideogram tips and text-in-image cheat sheet

Get reliable in-image text from Ideogram with a cheat sheet on quoting words, Magic Prompt, fonts, and JSON prompting.

Cursor rules tips and cheat sheet

Steer Cursor with rule files and @ mentions: a cheat sheet for .mdc rules, AGENTS.md, globs, and rule precedence.

NotebookLM tips and Audio Overview guide

Get better NotebookLM answers and podcasts: a cheat sheet for source filters, the Customize Audio Overview brief, and Gemini.

ChatGPT hacks for power users

Master ChatGPT with Custom Instructions, Projects, custom GPTs, and Deep Research for faster results.

Claude hacks for power users

Master Claude with Projects, Styles, and Artifacts for nuanced writing and long-document work.

Runway prompts and tips

Camera moves, Act-One, and Motion Brush prompts to control Runway Gen-4 AI video generations.

Perplexity tips and focus modes

Focus modes, Collections, and Pro Search tips to get sourced answers from Perplexity AI search.

Imagine.art tips and credit hacks

Model picker, credit hacks, and suite workflow tips for Imagine.art image, video, and voice.

Also useful: the AI prompt library and the developer cheat sheets.

Embedded tool from glunty.com