Describe

The /describe command allows you to upload an image and

generate four possible prompts based on that image. Use the
/describe command to explore new vocabulary and aesthetic
movements.

/describe generates prompts that are inspirational and suggestive, it

cannot be used to recreate an uploaded image exactly.

/describe returns the aspect ratio for uploaded images.

Previous
←
Prompts

Next
→
No

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Image Prompts
You can use images as part of a prompt to inuence a Job's
composition, style, and colors. Images prompts can be used alone
or with text prompts—experiment with combining images with
different styles for the most exciting results.

To add images to a prompt, type or paste the web address where the image is
stored online. The address must end in an extension like .png, .gif, or .jpg. After
adding image addresses, add any additional text and parameters to complete
the prompt.

Prompts must have multiple image prompts or a single image prompt and a
text prompt to work.
An image URL must be a direct link to an online image.

Your file should end in .png, .gif, .webp, .jpg, or .jpeg.

In most browsers, right-click or long-press an image and select Copy Image

Address to get the URL.

The /blend command is a simplified image prompting process optimized for

mobile users.

Privacy Notes
Upload images in your direct messages with the Midjourney Bot to prevent
other server users from seeing an image.
Image prompts are visible on the Midjourney website unless a user has
Stealth Mode.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 How to Use an Image in Your Promp
1. Upload an image to Discord
Follow these instructions to upload your image to Discord.

2. Copy your image's URL

*Discord Desktop App: Right-click on the image and select Copy Link (NOT
"Copy Message Link").

Discord Web App: Click to expand the image, then right-click and choose
"Copy image address."
Discord Mobile App: Tap and hold on the image, then select "Copy Media
Link."

If none of these methods work, you can click to expand the image, and at the
bottom, select "Open in Browser" so you can copy and paste the image's URL.

To incorporate an image into your prompt, you need a direct image link that
ends with .png, .gif, .webp, .jpg, or .jpeg. If the image is on your computer or
phone, you can send it as a message to the Midjourney Bot first to generate a
link.

How To Upload Your Image

Add an Image URL to Your Prompt

To add an image to a prompt, begin typing/imagine as usual. After the prompt
box appears, drag the image file into the prompt box to add the image's URL, or
right-click and paste the link within the prompt box.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Examples
Starting Images

Greecian style statue Vintage Flower Illustration Ernst Haeckel's Jellyfish

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Ernst Haeckel's Lichen Hokusai's The Great Wave

Midjourney Model Version 5

Statue + Flowers Statue + Jellyfish

+ +

Statue + Lichen Statue + Wave

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 + +

Statue + Lichen + Flowers

+ +

Aspect Ratio Tip

Crop images to the same aspect ratio as your final image for the best

results.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Image Weight Parameter
Use the image weight parameter--iw to adjust the importance of the image vs.
text portion of a prompt. The default value is used when no--iw is specified.
Higher --iw values mean the image prompt will have more impact on the
finished job.

See the Multi Prompts page for more information about the relative importance
between parts of a prompt.

Different Midjourney Version Models have different image weight ranges.

Version Version Version

niji 6 niji 5
6 5 4

Image Weight
1 1 NA 1 1
Default
Image Weight
0–3 0–2 NA 0–3 0–2
Range

prompt example: /imagine prompt flowers.jpg birthday cake --iw .5

Image Prompt --iw .25 --iw .5

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --iw .75 --iw 1 --iw 1.25

--iw 1.5 --iw 1.75 --iw 2

--iw 3

Technical Details
Prompts that only use images and no text are not compatible with the --stylize,
or --weird parameters.

Previous
←
No

Next
→
Multi Prompts

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Multi Prompts
The Midjourney Bot can blend multiple concepts using :: as a
separator. Using a multi-prompt allows you to assign relative
importance to the concept in the prompt, helping you control how
they are blended together.

Multi-Prompt Basics
Adding a double colon :: to a prompt indicates to the Midjourney Bot that it
should consider each part of the prompt individually. For the promptspace
ship both words are considered together, and the Midjourney Bot produces
images of sci-fi spaceships. If the prompt is separated into two parts,space::
ship , both concepts are considered separately, then blended together creating
a sailing ship traveling through space.

There is no space between the double colons::

Multi-prompts work with Model Versions

1 , 2 , 3 , 4 , '5 , niji , and niji 5

Any parameters are still added to the very end of the prompt.

space ship space:: ship

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 space ship is considered as a single space and ship are considered
thought. separate thoughts

cheese cake painting cheese:: cake painting

cheese cake painting is considered cheese is considered separately from

together, producing a painted image cake painting, producing images of
of a cheesecake. painted cakes made of cheeses.

cheese:: cake:: painting

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 cheese, cake, and painting are
considered separately, producing
tiered cakes, made of cheeses with
common classical painting
compositions and elements.

Prompt Weights
When a double colon :: is used to separate a prompt into different parts, you
can add a number immediately after the double colon to assign the relative
importance to that part of the prompt.

In the example below, the promptspace:: ship produced a sailing ship

traveling through space. Changing the prompt tospace::2 ship makes the
word space twice as important as the word ship, producing images of space
that have ships as a supporting element.

[Model Versions] 1 , 2 , 3 only accept whole numbers as weights

[Model Versions] 4 , niji 4 , niji 5 , 5 , 5.1 , and 5.2 and can accept

decimal places for weights

Non-specified weights default to 1.

space:: ship space::2 ship

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 space and ship are considered as space is twice as important as ship
separate thoughts

Weights are normalized:

space:: ship is the same as space::1 ship , space:: ship::1 , space::2
ship::2 , space::100 ship::100 , etc.
cheese::2 cake is the same as cheese::4 cake::2 , cheese::100 cake::50
etc.
cheese:: cake:: painting is the same as cheese::1 cake::1 painting::1 ,
cheese::1 cake:: painting:: , cheese::2 cake::2 painting::2 etc.

Negative Prompt Weights

Negative weights can be added to parts of a multi-prompt to help remove
unwanted elements.
The sum of all weights must be a positive number.

still life gouache painting still life gouache painting::

fruit::-.5

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 a range of objects appear in the still The still life has fewer fruits
life

The --no Parameter

The --no parameter is the same as weighing part of a multi prompt to "-.5"
vibrant tulip fields:: red::-.5 is the same as vibrant tulip fields --no
red .

Previous
←
Image Prompts

Next
→
Remix

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 No
The No parameter tells the Midjourney Bot what not to include in
your image.

--no accepts multiple words separated with commas:--no item1, item2,

item3, item4

--No Comparison

still life gouache painting still life gouache painting --no

fruit

a range of objects appear in the still

life The still life has fewer fruits

--no vs. Don't

The Midjourney Bot considers every word in the prompt as a potential element
for the image. Prompting still life gouache painting without any fruit or
still life gouache painting, please dont add fruit! are more likely to
produce pictures that include fruits because the relationship between "without"
or "don't" and the "fruit" is not interpreted by the Midjourney Bot in the same

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 way a human reader would understand it. To improve your results, focus your
prompt on what you do want to see in the image and use the "--no" parameter to
specify concepts you don't want to include.

still life gouache painting still life gouache painting,

please don't add fruit!

A range of objects appear in the still

life. More fruit is present in the final
image.

Multi Prompting
The --no parameter is the same as weighing part of a multi prompt to "-.5"
still life gouache painting:: fruit::-.5 is the same as still life
gouache painting --no fruit .

How to Use the No Paramter

Add --no item1, item2, item3 to the end of your prompt.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Previous
←
Describe

Next
→
Image Prompts

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompts
A Prompt is a short text phrase that the Midjourney Bot interprets
to produce an image. The Midjourney Bot breaks down the words
and phrases in a prompt into smaller pieces, called tokens, that
are compared to its training data and then used to generate an
image. A well-crafted prompt can help make unique and exciting
images.

Basic Prompts
A basic prompt can be as simple as a single word, phrase or emoji �.

Prompting Tip!
The Midjourney Bot works best with simple, short sentences that describe

what you want to see. Avoid long lists of requests and instructions. Instead
of: Show me a picture of lots of blooming California poppies, make them
bright, vibrant orange, and draw them in an illustrated style with colored

pencils Try: Bright orange California poppies drawn with colored pencils

Advanced Prompts

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 More advanced prompts can include one or more image URLs, multiple text
phrases, and one or more parameters

Image Prompts Text Prompt

Image URLs can be added to a prompt The text description of what image
to influence the style and content of you want to generate. See below for
the finished result. Image URLs prompting information and tips. Well-
always go at the front of a prompt. written prompts help generate
amazing images.
Read more about Image Prompts

Parameters

Parameters change how an image

generates. Parameters can change
aspect ratios, models, upscalers, and
lots more. Parameters go at the end
of the prompt.

Read more about Parameters

Prompting Notes
Word Choice
Word choice matters. More specific synonyms work better in many
circumstances. Instead of big, try tiny, huge, gigantic, enormous, or immense.

Plural words and Collective Nouns

Plural words leave a lot to chance. Try specific numbers. "Three cats" is more
specific than "cats." Collective nouns also work, “flock of birds” instead of

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 "birds.”

Focus on What you Want

It is better to describe what you want instead of what you don’t want. If you ask
for a party with “no cake,” your image will probably include a cake. To ensure an
object is not in the final image, try advanced prompting using thee
--no
parameter.

Prompt Length and Details

Prompts can be simple. A single word or emoji will work. However, short
prompts rely on Midjourney’s default style, allowing it to fill in any unspecified
details creatively. Include any element that is important to you in your prompt.
Fewer details means more variety but less control.

Try to be clear about any context or details that are important to you. Think
about:

Subject: person, animal, character, location, object

Medium: photo, painting, illustration, sculpture, doodle, tapestry

Environment: indoors, outdoors, on the moon, underwater, in the city
Lighting: soft, ambient, overcast, neon, studio lights
Color: vibrant, muted, bright, monochromatic, colorful, black and white, pastel
Mood: sedate, calm, raucous, energetic

Composition: portrait, headshot, closeup, birds-eye view

Previous
←
Writing Prompts

Next
→
Describe

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Remix
Use Remix Mode to change prompts, parameters, model versions,
or aspect ratios between variations. Remix will take the general
composition of your starting image and use it as part of the new
Job. Remixing can help change the setting or lighting of an image,
evolve a subject, or achieve tricky compositions.

Remix is an experimental feature that may change or be removed at any

time.

Using Remix
Activate Remix mode with the/prefer remix command or by using the
/settings command and toggling the 🎛 Remix Modebutton. Remix changes
the behavior of the variation buttons (V1, V2, V3, V4) under image grids. When
Remix is enabled, it allows you to edit your prompt during each variation. To
Remix an upscale select .
Make Variations

When Remix is enabled, Variation buttons turn green when used instead of

blue.
You can switch Model Versions when using Remix.
When you are done with Remix use the/settings or /prefer remix

command to turn it off.

Create a standard image variation when Remix is active by not modifying the
prompt in the pop-up window.

Step 1 Step 2
line-art stack of pumpkins Remix

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Turn on Remix mode. Select "Make Variations."

Select an image grid or upscaled Modify or enter a new prompt in the

image to Remix. pop-up.

Results
pile of cartoon owls

The Midjourney Bot generates an

image using the new prompt with
influence from the original image.

Starting Image Model Change

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 line-art stack of pumpkins line-art stack of pumpkins --test

Subject Change Medium Change

balloon-animal shaped stack of vibrant illustrated stack of fruit

pumpkins"

Using Parameters with Remix

You can add or remove Parameters while using Remix mode, but you must use
valid parameter combinations. Changing/imagine prompt illustrated stack
of pumpkins --version 3 --stylize 10000 to illustrated stack of pumpkins
--version 4 --stylize 10000 will return an error because Midjourney Model
Version 4 is incompatible with the Stylize parameter.

Only parameters that normally influence variations will work while using Remix:

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Affects Initial Affects Variations
Generation and Remix

Aspect Ratio* ✓ ✓

Chaos ✓

Image Weight ✓

No ✓ ✓

Quality ✓

Seed ✓

Same Seed ✓

Stop ✓ ✓

Stylize ✓

Tile ✓ ✓

Video ✓ ✓

Changing aspect ratios with Remix will stretch an image. It will not extend
the canvas, add missing details, or fix a bad crop.

How to Activate Remix

Use the Settings Command
Type /settings and select Remix from the pop-up.
🎛 Remix

Use the Prefer Remix Command

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Type /prefer remix to toggle Remix mode on and off.

Previous
←
Multi Prompts

Next
→
Shorten

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Shorten
The /shorten command analyzes your prompt, highlights some
of your prompt's most inuential words, and suggests
unnecessary words you could remove. With this command, you
can optimize your prompt by focusing on essential terms.

/shorten is not compatible with multi prompts or the

--no parameter

Analyze a Prompt with

/Shorten
The Midjourney bot analyzes your prompt by breaking it down into smaller units
known as tokens. These tokens can be phrases, words, or even syllables. The
Midjourney bot converts these tokens into a format it can understand. It uses
them with the associations and patterns learned during its training to guide how
your image is generated. Think of tokens as the building blocks that help the
Midjourney bot make sense of the input and create the desired visual output.

Long prompts with unnecessary words, lengthy descriptions, poetic phrases, or

direct addressing of the bot ("Please make me an image," "Thank you for your
help, Midjourney Bot!") can lead to unexpected elements being added to your
images.

The /shorten command can help you discover the most important words in
your prompt and what words you can omit.

Shorten Command Example

If you want to create a pile of sprinkle covered donuts you might try the prompt:
Please create a whimsical majestic tower of donuts, intricately crafted
and adorned with a mesmerizing array of colorful sprinkles. Bring this
sugary masterpiece to life, ensuring every detail is rendered in
stunning magical realism. Thank you!

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 If you use /shorten command with the above prompt the Midjourney Bot will
return the following information:

IMPORTANT TOKENS
Please create a whimsical majestic tower of donuts, intricately crafted
and adorned with a mesmerizing array of colorful sprinkles. Bring this
sugary masterpiece to life, ensuring every detail is rendered in stunning
magical realism. Thank you!

SHORTENED PROMPTS
1 Please, majestic tower of donuts, crafted, array of colorful sprinkles,
sugary masterpiece, rendered, magical realism

2 Please, majestic tower of donuts, colorful sprinkles, sugary masterpiece,

rendered, magical realism

3 majestic tower of donuts, colorful sprinkles, sugary, magical realism

4 majestic tower of donuts, colorful sprinkles, magical

5 tower of donuts, sprinkles

The most Important tokens in your prompt are highlighted in bold, the least
important are stikethroughed. You will also be given 5 possible shorter prompts
based on this information.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Shortened Option 1 Shortened Option 2

Please, majestic tower of donuts, Please, majestic tower of donuts,

crafted, array of colorful sprinkles, colorful sprinkles, sugary
sugary masterpiece, rendered, masterpiece, rendered, magical
magical realism realism

Shortened Option 3

majestic tower of donuts, colorful

sprinkles, sugary, magical realism

Shortened Option 4 Shortened Option 5

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 majestic tower of donuts, colorful tower of donuts, sprinkles
sprinkles, magical

Analyzing the Results

The shortest prompt, Option 5 : tower of donuts, sprinkles produced an
image closest to the original goal. Many of the filler words like "whimsical,"
"mesmerizing," and "masterpiece" could be omitted. Learning that "tower" and
"magical" were considered important tokens helps explain why some images
were generated with fairytale castle elements. Learning this provided a clue
that "magical" should be removed from the prompt if the goal was to create a
stack of delicious donuts.

The /shorten command is a tool to help you explore how the Midjourney Bot

interprets tokens and experiment with words, but it may not work for all
subjects and styles of prompting.

How to Use Shorten

Use the /shorten <your prompt> command in any Bot Channel to get
information on your prompt

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Previous
←
Remix

Next
→
Working with Your Own Images

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Pan
The Pan option allows you to expand the canvas of an image in a
chosen direction without changing the content of the original
image. The newly expanded canvas will be lled in using guidance
from the prompt and the original image.

Pan allows you to increase the image resolution beyond the maximum
1024px x 1024px dimensions in one direction.

Pan is compatible with Midjourney Model Version 5, 5.1, 5.2, and niji 5

Panning an Image
The Pan buttons ⬅ ➡ ⬆ ⬇ will appear after upscaling an image. When

panning, only the closest 512 pixels to the side of the image, along with the
prompt, are used to determine the new section.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompt: A vibrant fantasy landscape

Starting Image Pan ⬆

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Pan ⬇

Pan ⬅ Pan ➡

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 After panning an image once, you can only pan that image again in the same
direction (horizontal/vertical). You may continue to pan in that direction as
often as you like. After panning several times, the image may become too large
to send on Discord. When this happens, you will be sent a link to the image
instead.

Pan ⬅ and ➡ several times

Pan with Remix Mode

Panning supports Remix Mode. This allows you to change your prompt when
panning.

Starting Image Pan ➡ + Remixed Prompt

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Pan ➡ + Remix prompt: A vibrant
fantasy city

Starting prompt: A vibrant fantasy

landscape

Previous
←
Style Tuner

Next
→
Zoom Out

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Style Tuner
Personalize the appearance of your Midjourney images using the
Style Tuner. Use the /tune command to generate a range of
sample images showing different visual styles based on your
prompt. Choose your favorite images, and you'll receive a unique
code you can use to customize the look of future Jobs.

Share your Style Tuner and Codes with others to share, explore, and experiment
with different aesthetics.

/tune and codes are only compatible with Midjourney Model Version 5.2

/tune is not compatible with the current default Midjourney Model Version

6
/tune is only available while in Fast Mode.

--style parameters created with the Style Tuner are compatible with
--

stylize values between 20–1000.

How to Use the Style Tuner

1. Generate Your Custom Style Tuner
Create a Style Tuner page using the/tune command.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 2. Select Your Preferred Options
Style Directions: Choose the number of image pairs you want to see in your
Style Tuner (16, 32, 64, or 128 pairs).
Default Mode: Select the style mode for your sample images (Default or
Raw). If you typically do not use the --style raw parameter with your prompts,
choose "default."

Use an Exisiting Style Tuner

If another user has previously generated a Style Tuner with your prompt, you
will receive a link to that Tuner. Click the link to access the existing Style

Tuner. Using a previously generated Style Tuner does not use your
subscription's GPU minutes.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 3. Submit your Job
Click the Submit button.

Confirm your submission.

Your Style Tuner generates a pair of images for each Style Direction. A Style
Tuner with 16 directions will generate 32 images. A Style Tuner with 128
directions will generate 256 images. Generating these images uses your
subscription's Fast GPU time.

4. Open Your Custom Style Tuner

When your Style Tuner is ready, the Midjourney Bot will send you a direct
message with a link to your Tuner.

Click the link to open your Style Tuner in your web browser.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Try this Style Tuner: https://tuner.midjourney.com/ejYLCOY

5. Select images
Your Style Tuner will show rows of image pairs, each representing a distinct
visual direction for your prompt. Click on the image you prefer in each pair. If
you don't feel strongly about either image, leave the empty middle box selected.

6. Copy Your Code

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 The Style Tuner generates a code you can add to your prompts with the
--style
<code> Parameter. Learn more about parameters.

To copy your prompt and Parameter

Find your customized code at the bottom of the page.

Click the Copy button to copy your original prompt and newly generated
--
style <code> parameter.

You can share your Style Tuner page with friends and generate new codes
without using any additional GPU minutes!

7. Generate an Image
Return to Discord
Use the /imagine command and paste your copied prompt and--style
<code> parameter into the prompt field.

Generate your image

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 8. Use Additional Midjourney Tools
Take your image further by using other Midjourney tools like Upscale, Pan,
Zoom-Out, Remix, or Vary-Region.

9. Experiment and Explore

Use your style code with a new prompt:

The Style Tuner you create uses your initial prompt to create sample
images and help you visualize the impact of your choices. However, the

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 generated codes can be used with any prompt. Remember that styles and
prompts always work together to generate an image, so a style code may
not transfer as intended to other prompts.

Experiment: Style codes and prompts interact in complex ways. A code may
have a strong effect on one prompt and a subtle effect on a similar prompt.
The images you choose in your Style Tuner can combine in unexpected and
creative ways. Use style codes as a tool to explore new looks and visuals.

Generate more codes: You can return to your Style Tuner page at any time to
change your selections and create new codes.
Share style codes: You can share or use style codes created by friends.
Check out the Midjourney style-tuner channel to share your codes and
discover new styles!
Find a Style Tuner page: Find the Style Tuner page for any style code by
adding it to this URL: https://tuner.midjourney.com/code/StyleCodeHere.

10. Save and Reuse Your Codes

Use the /settings command and turn on 🎛Sticky Style. Sticky Style will
save the last --style parameter used in your personal suffix, so you don't
have to repeat the code on future prompts. Change codes by using a new
--

style or unselecting 🎛Sticky Style.

Use custom options to store your favorite codes.

Or, create your own Discord server to organize your images, prompts, image
references, and Style Tuner codes.

Style Tune Examples

prompt vibrant california poppies
All images were made by style created using this Style Tuner

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Random Codes
Use the --style random parameter to apply a random 32 base styles Style
Tuner code to your prompt. You can also use --style random-16 , --style
random-64 or --style random-128 to use random results from other lengths of
tuners.

--random simulates Style Tuner code with random selections chosen for 75% of
the image pairs. You can adjust this percentage by adding a number to the end
of the --random parameter. For example,--style random-32-15 simulates a
32-pair tuner with 15% of the image pairs selected,
--style random-128-80
simulates a 128-pair tuner with 80% of the image pairs selected.

Combine Codes
Combine multiple codes in one parameter with a hyphen,
--style code1-code2 .
Combine multiple codes and style raw:--style raw-code1-code2

Style Tuner and --stylize

The --stylize parameter adjusts the influence of the --style parameter on your
generated images. If you're not seeing the desired effect from your code,
consider combining it with higher stylization values, like--stylize 250 , or --
stylize 500 .

Comparison
prompt vibrant California poppies --style fdeQ4zOX5jd --stylize 250

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --stylize 20 --stylize 100 (default)

--stylize 250 --stylize 750

Style Raw
Combine your custom style code with Midjourney Style Raw by using
--style
raw-<code> .
Example: To use Style Raw and --style fjo5S8BgMoV use --style raw-
fjo5S8BgMoV .

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Style Tuner and Niji Model Version
Style Tuner codes created with the Midjourney Bot are not compatible with the
Niji Model version accessed through the Midjourney Bot. To create a Style Tuner
or Code for Niji Model version, join the Niji Discord community and interact with
the Niji Bot in the same way you interact with the Midjourney Bot. Your
Midjourney subscription gives you access to the Niji community and Bot.

Technical Details
/tune is compatible with prompts that include the following:
--aspect
--chaos
--tile
multi prompts

/tune and style codes are not compatible with image prompts that do not
include a text prompt.

If your /tune command does not return a clickable link, check that Embeds and
Link Previews is enabled in your Discord App Settings

Previous
←
Upscalers

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Upscalers
The current Midjourney and Niji Model Versions produce grids of
1024 x 1024 pixel images. Use U1
the U2 U3 U4 buttons under
each image grid to separate your selected image from its grid. You
can then use theUpscale (Creative) or Upscale
(Subtle) tools to increase the size of your image.

The Upscale (Subtle)option doubles the size of your image and keeps details

very similar to the original. Upscale (Creative)

also doubles the size of your
image and adds new details to the image. Experiment with each upscaler option
to find the one most suitable for the style of your image.

Upscale tools use your subscription's GPU minutes. Upscaling can take up

to twice as many GPU minutes as generating an initial image grid.

Upscale tools are not compatible with the tile parameter.

How to Use the Upscale Tools

1. Generate an Image
Create an image using the/imagine command.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 2. Select an Image
Use a U button to separate your selected image from the grid.

3. Select Upscale
Click on the Upscale (Subtle)or Upscale (Creative)
button to upscale your
image. The upscalers will double the size of your image to 2048 x 2048 pixels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Upscale Comparison
Prompt: chiaroscuro rooster portrait
Original 1024 by 1024 pixel image.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Detail from original image
Original image After Upscale (2x) to 2048 x 2048 px

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Upscale Comparison
Prompt: 1960s pop-art acrylic painting of a stream running through a
redwood forest

Original image Subtle upscale

Creative upscale

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Detail from original image Detail from subtle upscale

Detail from creative upscale

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Upscale Tips
Upscale older Jobs by refreshing them with the /show command.

Legacy Upscalers
Earlier Midjourney model versions generated grids of lower-resolution images.
You can use a legacy Midjourney upscaler on these images to increase the size
and add additional details. There are multiple legacy upscale models available
for upscaling images made with earlier Midjourney models. Using a legacy
upscaler uses your subscription's GPU minutes.

Previous
←
Vary Region + Remix

Next
→
Style Tuner

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Vary Region
Use the Midjourney Vary Region editor to select and regenerate
specic parts of an upscaled image.

The Vary (Region) button appears after a Midjourney image has been

upscaled.
Regional variations are guided by the content in your original image and the
area you select.

Vary (Region) is compatible with Midjourney Model Versions

V5.0 , V5.1 ,

V5.2 , V6 and niji 5

How to Use Vary Region

1. Generate an Image
Create an image using the/imagine command.

2. Upscale the Image

Use the U buttons to upscale your selected image.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 3. Select Vary Region
Click on the 🎛 Vary (Region)button to open the editing interface.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 4. Select Areas to Regenerate
Choose the freehand or rectangular selection tools in the lower left of the
Editor.
Select the areas of your image that you want to regenerate.
The size of your selection will affect your results. Larger selections give
the Midjourney Bot more room to generate new creative details. Smaller
selections will result in smaller, more subtle changes.
Note: You cannot edit an existing selection but can undo multiple steps
using the undo button in the upper right corner.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 5. Submit Your Job
Click the Submit→ button to send your request to Midjourney Bot. The Vary
Region editor can now be closed, and you can return to Discord while your Job
is processed.

Note You can use the 🎛 Vary (Region)button underneath an upscaled image
multiple times to experiment with different selections. Your previous selection
will be preserved. You can continue to add to this existing selection or use the
undo button to clear your selection.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 6. View Your Results
The Midjourney Bot will process your Job and generate a new image grid of
variations within the area you selected.

Vary Region Examples

Upscaled Image Selection

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompt: colorful candy brooches

Result

Upscaled Image Selection

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompt: architectural drawing of a
house

Result

Vary Region + Remix Mode

You can use Remix mode with the Vary Region editor to update your prompt
while regenerating specific parts of your image. Read about using Remix Mode
with the Vary Region editor.

Original Image Selection

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompt: gouache alligator in Updated Prompt: gouache alligator
sunglasses in green sunglasses

Result

Updated Prompt: gouache alligator

in green sunglasses

Technical Details
Jobs generated using Vary (Region) will honor the following parameters:
--chaos
--fast

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --iw
--no
--stylize
--relax
--style
--version
--video
--weird

Previous
←
Weird

Next
→
Vary Region + Remix

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Vary Region + Remix
Combine Remix Mode and the Midjourney Vary Region editor to
select and regenerate specic parts of an upscaled image using a
new or modied prompt.

The Vary (Region) button appears after a Midjourney image has been

upscaled.
Regional variations results are guided by the content in your original image,

the area you select, and the modified prompt used.

Vary (Region) is compatible with Midjourney Model Versions
V5 V6 niji

5 and niji 6

How to Use Remix Mode with Vary

(Region)
1. Enable Remix Mode
Use the /settings command and select 🎛 Remix from the pop-up.

2. Generate an Image
Create an image using the/imagine command.

3. Upscale the Image

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Use the U buttons to upscale your selected image.

4. Select Vary Region

Click the 🎛 Vary (Region)button to open the editing interface.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 5. Select Areas to Regenerate
Choose the freehand or rectangular selection tools in the lower left of the
Editor.
Select the areas of your image that you want to regenerate.
The size of your selection will affect your results. Larger selections give
the Midjourney Bot more room to generate new creative details. Smaller
selections will result in smaller, more subtle changes.
Note: You cannot edit an existing selection but can undo multiple steps
using the undo button in the upper right corner.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 6. Modify Your Prompt
Describe what you want to generate in the selected areas with an updated
prompt. Your revised prompt should focus on the details you want to introduce
or change.

7. Submit Your Job

Click the Submit→ button to send your request to Midjourney Bot. The Vary
Region editor can now be closed, and you can return to Discord while your Job
is processed.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Note You can use the Editor Button underneath an upscaled image multiple
times to experiment with different selections and prompts.

8. View Your Results

The Midjourney Bot will process your Job and generate a new image grid using
the information from your original image and the guidance of your new prompt.

New Image Grid Original vs. Varied Comparison

8. Upscale and Vary Region again

You can upscale one of your new images and use the Vary Region Editor again
to continue refining your image.

Selection Result

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Updated Prompt: hot air balloon
lithograph

Result

Updated Prompt: castle in the

meadow lithograph

Vary Region + Remix Prompting Tip

Selections The size of your selection affects the outcome. Larger selections
provide the Midjourney Bot with more contextual information, which can
improve the scaling and context of new additions. But selecting too much

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 may lead to the newly generated elements blending or replacing parts of the
original image you wished to preserve.

Prompts Experiment with how you modify your prompt when Using Vary
Region + Remix Mode. Prompts should focus on what you want to happen in
the selected area. The Midjourney Bot also considers the existing image
when generating a selected area, so shorter focused prompts often are more
effective. Midjourney Prompts should not be conversational. Instead of
"Please change the meadow trail into a beautiful stream," be direct and
prompt "meadow stream."

Work in Small Steps If you want to change many parts of an image, work on
one part at a time. This way, you can create a focused prompt for each part.

Vary Region + Remix Examples

Original Image Selection

Prompt: gouache alligator in Updated Prompt: gouache alligator

sunglasses in green sunglasses

Result

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Updated Prompt: gouache alligator
in green sunglasses

Original Image Selection

Prompt: scratchboard apple tree Updated Prompt: rainbow

branch scratchboard apple tree branch

Result

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Updated Prompt: rainbow
scratchboard apple tree branch

Technical Details
Jobs generated using Vary (Region) + Remix Mode will honor the following
parameters:
--chaos
--fast
--iw
--no
--stylize
--relax
--style
--version
--video
--weird

Previous
←
Vary Region

Next
→
Upscalers

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Zoom Out
The Zoom Out option allows you to extend the canvas of an
upscaled image beyond its original boundaries without changing
the content of the original image. The newly expanded canvas will
be lled-in using guidance from the prompt and the original image.

Zoom Out does not increase the maximum 1024px x 1024 px size of an

image.

Zoom Out
🎛 Zoom Out 2X 🎛 Zoom Out 1.5Xbuttons will appear after upscaling an

image.

Prompt: vibrant California poppies

Starting Image Zoom Out 1.5X

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Zoom Out 2X

Make Square
With Make Square you can adjust the aspect ratio of a non-square image to
make it square. If the original aspect ratio is wide (landscape), it will be
expanded vertically. If it is tall (portrait), it will be expanded horizontally. The
emoji ↔ ↕ next to the ↔ Make Squarebutton also indicates which way the

image will be expanded. The ↔ Make Squarebutton will appear underneath

non-square upscaled images.

Prompt: vibrant California poppies

Starting Image ↕ Make Square

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Starting Image ↔ Make Square

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Custom Zoom
The 🎛 Custom Zoom button lets you choose how much to zoom out on an

image. 🎛 Custom Zoom button under an upscaled image will pop up a dialogue
box where you enter a custom value for--zoom . --zoom accepts values
between 1-2.

Change the Aspect Ratio of an Upscaled Image

You can use --zoom 1 in this Custom Zoom pop-up box to change the aspect

ratio, with the--ar parameter , without zooming out.

Change Your Prompt with Custom Zoom

🎛 Custom Zoom allows you to change the prompt before you expand your

image, giving you finer control over the finished image. For example, changing
the prompt to "A framed picture on the wall" gives this result:

Starting Image Custom Zoom + Changed Prompt

prompt: vibrant California poppies

Zoom Out prompt: A framed picture

on the wall --zoom 2

Previous
←
Pan

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Next
→
Writing Prompts

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Aspect Ratios
The --aspect or --ar parameter changes the aspect ratio of
the generated image. An aspect ratio is the width-to-height ratio of
an image. It is typically expressed as two numbers separated by a
colon, such as 7:4 or 4:3.

A square image has equal width and height, described as a 1:1 aspect ratio. The
image could be 1000px × 1000px, or 1500px × 1500px, and the aspect ratio
would still be 1:1. A computer screen might have a ratio of 16:10. The width is
1.6 times longer than the height. So the image could be 1600px × 1000px,
4000px × 2000px, 320px x 200px, etc.

The default aspect ratio is 1:1.

--aspect must use whole numbers. Use 139:100 instead of 1.39:1.

The aspect ratio impacts the shape and composition of a generated image.
Some aspect ratios may be slightly changed when upscaling.
Older Midjourney Version Models may not support all aspect ratios.

Aspect Ratio Comparison

prompt example: imagine/ prompt vibrant California poppies --ar 5:4

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Aspect ratios greater than 2:1 and 1:2 are experimental and may produce
unpredictable results.

Common Midjourney Aspect Ratios

--aspect 1:1 Default aspect ratio.
--aspect 5:4 Common frame and print ratio.
--aspect 3:2 Common in print photography.
--aspect 7:4 Close to HD TV screens and smartphone screens.

Changing the Aspect Ratio of an

Image
Do you love an image you have generated but wish it was taller or wider? You
can use the 🎛 Zoom Out buttons on any upscaled image to change the aspect
ratio of your image. The Midjourney Bot will fill in the new space with additional
content informed by your prompt and the original image.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 How to Set the Aspect Ratio
Use Aspect Ratio Parameters
Add --aspect <value>:<value> , or --ar <value>:<value> to the end of your
prompt.

Previous
←
Parameter List

Next
→
Chaos

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Chaos
The --chaos or --c parameter inuences how varied the initial
image grids are. High
--chaos values will produce more unusual
and unexpected results and compositions. Lower
--chaos
values have more reliable, repeatable results.

--chaos accepts values 0–100.

The default --chaos value is 0.

The Influence of Chaos on Jobs

No --chaos value
Using a very low --chaos value, or not specifying a value, will produce initial
image grids that are similar.

prompt example: /imagine prompt: a silver seashell inlaid with pink and
green accents --c 0

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Low --chaos values
Using a low --chaos value will produce initial image grids that are slightly
varied.

prompt example: /imagine prompt: a silver seashell inlaid with pink and
green accents --c 10

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Moderate--chaos values
Using a moderate --chaos value will produce initial image grids that are varied.

prompt example: /imagine prompt: a silver seashell inlaid with pink and
green accents --c 25

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 High--chaos Values
Using a higher --chaos value will produce initial image grids that are more
varied and unexpected.

prompt example: /imagine prompt: a silver seashell inlaid with pink and
green accents --c 50

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Very High--chaos Values
Using extremely high --chaos values will produce initial image grids that are
varied and have unexpected compositions or elements.

prompt example: /imagine prompt: a silver seashell inlaid with pink and
green accents --c 80

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 How to Change the Chaos Value
Use the--chaos or --c Parameter
Add --chaos <value> or --c <value> to the end of your prompt.

Previous
←
Aspect Ratios

Next
→
No

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Version
Midjourney regularly introduces new model versions to improve
coherency, eciency, quality, and style. You can switch model
versions using the --version or --v parameter or using the /settings
command and selecting your preferred model version. Different
models excel at producing different types of images.

--version accepts the values 1, 2, 3, 4, 5, 5.0, 5.1, 5.2, and 6.

--version can be abbreviated --v .

--v 6 is the current default model.

Model Version 6
Midjourney Model Version 6 has enhanced prompt accuracy for longer inputs,
improved coherence and knowledge, and advanced image prompting and
remixing capabilities.

Midjourney Model Version 6 was released on December 20, 2023, and became
the default model on February 14, 2024.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompt: vibrant California poppies - Prompt: high contrast surreal
-v 6 collage --v 6

Model Version 6 + Style Raw Parameter

Midjourney Model Version 6 can be fine-tuned with the--style raw parameter
to help achieve more photographic or more literal results.

Read more about the Midjourney--style parameter.

default --v 6 --v 6 --style raw

vibrant California poppies --v 6 vibrant California poppies --v 6 -

-style raw

default --v 6 --v 6 --style raw

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 fruit salad tree --v 6 fruit salad tree --v 6 --style
raw

Model Version 5.2

The Midjourney V5.2 model was released in June 2023. To use this model, add
the --v 5.2 parameter to the end of a prompt, or use the
/settings command
and select 5 MJ Version 5.2

Default Model 06/22/23–02/14/2024

This model produces more detailed, sharper results with better colors, contrast,
and compositions. It also has a slightly better understanding of prompts than
earlier models and is more responsive to the full range of the
--stylize
parameter.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompt: vibrant California poppies - Prompt: high contrast surreal
-v 5.2 collage --v 5.2

Model Version 5.2 + Style Raw Parameter

Midjourney Model Versions 5.1 and 5.2 can be fine-tuned with the--style raw
parameter to reduce the Midjourney default aesthetic.

Read more about the Midjourney--style parameter.

default --v 5.2 --v 5.2 --style raw

vibrant California poppies vibrant California poppies --style

raw

default --v 5.2 --v 5.2 --style raw

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 high contrast surreal collage high contrast surreal collage --
style raw

Niji Model 6
The Niji model is a collaboration between Midjourney and Spellbrush tuned to
produce anime and illustrative styles with vastly more knowledge of anime,
anime styles, and anime aesthetics. It's excellent at dynamic and action shots
and character-focused compositions.

To use this model, add the --niji 6 parameter to the end of a prompt, or use
the /settings command and select 🎛 Niji version 6

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Prompt: vibrant California poppies - Prompt: high contrast surreal
-niji 6 collage --niji 6

Niji 6 vs. Midjourney Version 6

--v 6 --niji 6

vibrant California poppies --v 6 vibrant California poppies --niji

6

--v 6 --niji 6

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 fruit salad tree --v 6 fruit salad tree --v 6 --style
raw

How to Switch Models

Use the Version Parameter
Add --v 6 --v 6 --style raw --v 5.2 --v 5.2 --style raw --niji 6 or --
niji 6 style raw to the end of your prompt.

Use the Settings Command

Type /settings and select your preferred version from the menu.

6 MJ Version 6 5 MJ Version 5.2 🎛 Niji Version 6

Legacy Models

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 You can experiment with early Midjourney models using the--version
parameter Read more about Midjourney Legacy Models.

Previous
←
Tile

Next
→
Video

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 No
The No parameter tells the Midjourney Bot what not to include in
your image.

--no accepts multiple words separated with commas:--no item1, item2,

item3, item4

--No Comparison

still life gouache painting still life gouache painting --no

fruit

a range of objects appear in the still

life The still life has fewer fruits

--no vs. Don't

The Midjourney Bot considers every word in the prompt as a potential element
for the image. Prompting still life gouache painting without any fruit or
still life gouache painting, please dont add fruit! are more likely to
produce pictures that include fruits because the relationship between "without"
or "don't" and the "fruit" is not interpreted by the Midjourney Bot in the same

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 way a human reader would understand it. To improve your results, focus your
prompt on what you do want to see in the image and use the "--no" parameter to
specify concepts you don't want to include.

still life gouache painting still life gouache painting,

please don't add fruit!

A range of objects appear in the still

life. More fruit is present in the final
image.

Multi Prompting
The --no parameter is the same as weighing part of a multi prompt to "-.5"
still life gouache painting:: fruit::-.5 is the same as still life
gouache painting --no fruit .

How to Use the No Paramter

Add --no item1, item2, item3 to the end of your prompt.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Previous
←
Chaos

Next
→
Quality

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Quality
The --quality or --q parameter changes how much time is
spent generating an image. Higher-quality settings take longer to
process and produce more details. Higher values also mean more
GPU minutes are used per job. The quality setting does not impact
resolution.

The default --quality value is 1.

--quality only accepts the values: .25, .5, and 1 for the current model.

Larger values are rounded down to 1.

--quality only influences the initial image generation.

The Influence of Quality on Jobs

Higher --quality settings aren't always better. Sometimes a lower--quality
settings can produce better results—depending on the image you're trying to
create. Lower --quality settings might be best for a gestural abstract look.
Higher --quality values may improve the look of architectural images that
benefit from many details. Choose the setting that best matches the image
you're hoping to create.

Version Quality Compatibility

Model Version Quality .25 Quality .5 Quality 1

Version 6 ✓ ✓ ✓

Version 5.2 ✓ ✓ ✓

niji 5 ✓ ✓ ✓

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Quality Comparison
Prompt example: /imagine prompt intricate woodcut of a peony --q .25

--quality .25 --quality .5

quickest results, least detailed results less detailed results

4× faster and ¼ the GPU minutes. 2× faster and ½ the GPU minutes.

--quality 1

the default setting

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 How to Use the Quality Parameter
Use the--quality or --q Parameter
Add --quality <value> or --q <value> to the end of your prompt.

Previous
←
No

Next
→
Repeat

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Repeat
The --repeat or --r parameter runs a Job multiple times.
Combine--repeat with other parameters, like --chaos to
increase the pace of your visual exploration.

--repeat accepts values 2–4 for Basic subscribers

--repeat accepts values 2–10 for Standard subscribers

--repeat accepts values 2–40 for Pro and Mega subscribers

The --repeat parameter can only be used in Fast and Turbo GPU mode.

Using the redo (re-roll) 🎛 button on the results of a --repeat Job will only

re-run the prompt once.

Use the--repeat or --r Parameter

Add --repeat <value> or --r <value> to the end of your prompt.

Previous
←
Quality

Next
→
Seeds

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Seeds
The Midjourney bot uses a seed number to create a eld of visual
noise, like television static, as a starting point to generate the
initial image grids. Seed numbers are generated randomly for each
image but can be specied with the --seed parameter. If you
use the same seed number and prompt, you will get similar nal
images.

--seed accepts whole numbers 0–4294967295.

--seed values only influence the initial image grid.
Identical --seed values using Model Versions 1 , 2 , 3 , test , and testp
will produce images with similar composition, color, and details.
Identical --seed values using Model Versions
4 , 5 , 6 and niji will
produce nearly identical images.
Seed numbers are not static and should not be relied upon between
sessions.

Seed Parameter
If no Seed is specified, Midjourney will use a randomly generated seed number,
producing a wide variety of options each time a prompt is used.

Jobs run three times with random seeds:

prompt example: /imagine prompt celadon owl pitcher

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Jobs run three times with
--seed 12345 :
prompt example: /imagine prompt celadon owl pitcher --seed 123

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 How to Find a Job's Seed Number
Use a Discord Emoji Reaction
Find the seed number of a Job in discord by reacting with an ✉ envelope emoji
to a Job.

Use The Show Command to Bring Back Old Jobs

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 To get the seed number for a past image, copy the job ID and use the
/show
<Job ID #> command with that ID to revive the Job. You can then react to the
newly regenerated Job with an ✉ envelope emoji.

How To Change Seed Numbers

Use the--seed Parameter
Add --seed <value> to the end of your prompt.

Previous
←
Repeat

Next
→
Stop

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Style
The --style parameter replaces the default aesthetic of some
Midjourney Model Versions.

Model Versions 6, 5.2, 5.1 and Niji 6 accept --style raw .

The Effects of
--style raw
--style raw uses an alternative model that may work well for users already
comfortable with prompting who want more control over their images. Images
made with --style raw have less automatic beautification applied, which can
result in a more accurate match when prompting for specific styles.

Model Version 6
--v 6 --v 6 --style raw

black and white oak tree icon black and white oak tree icon --style
raw

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --v 6 --v 6 --style raw

child's crayon drawing of a cat child's crayon drawing of a cat --style

raw

Model Version 5.2

--v 5.2 --v 5.2 --style raw

ice cream icon ice cream icon --style raw

--v 5.2 --v 5.2 --style raw

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 child's drawing of a cat child's drawing of a cat --style raw

How to Use Styles

Use the--style Parameter
Add --style <style name> to the end of your prompt.

Use the Settings Command

Type /settings and select 🎛 Raw from the menu to append--style raw to
all prompts.

Previous
←
Stop

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Next
→
Stylize

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Stylize
The Midjourney Bot has been trained to produce images that favor
artistic color, composition, and forms. The
--stylize or --s
parameter inuences how strongly this training is applied. Low
stylization values produce images that closely match the prompt
but are less artistic. High stylization values create images that are
very artistic but less connected to the prompt.

--stylize 's default value is 100 and accepts integer values 0–1000 when

using the current models

Common Stylize Settings

Influence of Stylize on Model Version 6
prompt example: /imagine prompt child's drawing of a cat --s 100

--stylize 0 --stylize 50

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Equal to 🎛 Style Low

--stylize 100 (default)

Equal to 🎛 Style Med

--stylize 250 --stylize 500

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Equal to 🎛 Style High

--stylize 750

Equal to 🎛 Style Very High

prompt example: /imagine prompt colorful risograph of a fig --s 100

--stylize 50 --stylize 100 (default) --stylize 250

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Equal to 🎛 Style Low Equal to 🎛 Style Med Equal to 🎛 Style High

--stylize 750

Equal to
🎛 Style Very High

How to Switch Stylization Values

Use the Stylize Parameter
Add --stylize <value> or --s <value> to the end of your prompt.

Use the Settings Command

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Type /settings and select your preferred stylize value from the menu.

🎛 Style Low 🎛 Style Med 🎛 Style High 🎛 Style Very High

Previous
←
Style

Next
→
Tile

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Tile
The --tile parameter generates images that can be used as
repeating tiles to create seamless patterns for fabrics, wallpapers
and textures.

--tile works with Model Versions

1 2 3 test testp 5 5.1 5.2 and 6 .

--tile only generates a single tile. Use a pattern making tool like this

Seamless Pattern Checker to see the tile repeat.

Tile Examples
prompt a pattern of pink and blue striped river stones --tile

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 prompt a pattern of colorful watercolor fall leaves --tile

How to Use the Tile Parameter

Add --tile to the end of your prompt.

Previous
←
Stylize

Next
→
Version

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Weird
Explore unconventional aesthetics with the experimental
--
weird or --w parameter. This parameter introduces quirky and
offbeat qualities to your generated images, resulting in unique and
unexpected outcomes.

--weird accepts values: 0–3000.

The default --weird value is 0.

--weird is a highly experimental feature. What's weird may change over time

--weird is compatible with Midjourney Model Versions 5, 5.1, 5.2, 6, niji 5

and niji 6

--weird is not fully compatible with seeds

The Influence of Weird on Jobs

The optimal --weird value is dependent on the prompt and requires
experimentation. Try starting with smaller values, such as 250 or 500, and then
go up/down from there. If you want a generation to be conventionally attractive
and weird, try mixing higher--stylize values with --weird . Try starting with
similar values for both. Example /imagine prompt cyanotype cat --stylize
250 --weird 250 .

prompt example: /imagine prompt cyanotype cat --weird 250

--weird 0 --weird 250

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --weird 500 --weird 1000

prompt example: /imagine prompt lithograph potato --weird 250

--weird 0 --weird 250

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --weird 500 --weird 1000

prompt example: /imagine prompt clockwork chicken --weird 250

--weird 0 --weird 250

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --weird 500 --weird 1000

What's the difference between --

weird , --chaos , and--stylize ?
--chaos controls how diverse the initial grid images are from each other.
--stylize controls how strongly Midjourney's default aesthetic is applied.
--weird controls how unusual an image is compared to previous Midjourney
images.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 How to Use the Weird Parameter
Add --weird <value> or --w <value> to the end of your prompt.

Previous
←
Video

Next
→
Vary Region

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Parameter List
Parameters are options added to a prompt that change how an
image generates. Parameters can change an image's Aspect
Ratios, switch between Midjourney Model Versions, change which
Upscaler is used, and lots more.

Parameters are always added to the end of a prompt. You can add multiple
parameters to each prompt.

Using an Apple device?

Many Apple devices automatically change double hyphens (--) to an em-dash
(—). Midjourney accepts both!

Basic Parameters
Aspect Ratios
--aspect , or --ar Change the aspect ratio of a generation.

Chaos
--chaos <number 0–100> Change how varied the results will be. Higher values
produce more unusual and unexpected generations.

Fast
--fast override your current setting and run a single job using Fast Mode.

Image Weight
Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --iw <0–2> Sets image prompt weight relative to text weight. The default value
is 1.

No
--no Negative prompting, --no plants would try to remove plants from the
image.

Quality
--quality <.25, .5, or 1> , or --q <.25, .5, or 1> How much rendering
quality time you want to spend. The default value is 1. Higher values use more
GPU minutes; lower values use less.

Random
--style random , add a random 32 base styles Style Tuner code to your prompt.
You can also use --style random-16 , --style random-64 or --style random-
128 to use random results from other lengths of Style Tuners.

Relax
--relax override your current setting and run a single job using Relax Mode.

Repeat
--repeat <1–40> , or --r <1–40> Create multiple Jobs from a single prompt. --
repeat is useful for quickly rerunning a job multiple times.

Seed
--seed <integer between 0–4294967295> The Midjourney bot uses a seed
number to create a field of visual noise, like television static, as a starting point
to generate the initial image grids. Seed numbers are generated randomly for
each image but can be specified with the --seed or --sameseed parameter. Using
the same seed number and prompt will produce similar ending images.

Stop
--stop <integer between 10–100> Use the --stop parameter to finish a Job
partway through the process. Stopping a Job at an earlier percentage can

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 create blurrier, less detailed results.

Style
--style <raw> Switch between versions of the Midjourney Model Version 5.1
and 5.2.
--style <4a, 4b, or 4c> Switch between versions of the Midjourney Model
Version 4.
--style <cute, expressive, original, or scenic> Switch between versions
of the Niji Model Version 5.
Use the /tune command to create a Style Tuner and generate custom style
codes.

Stylize
--stylize <number> , or --s <number> parameter influences how strongly
Midjourney's default aesthetic style is applied to Jobs.

Tile
--tile parameter generates images that can be used as repeating tiles to
create seamless patterns.

Turbo
--turbo override your current setting and run a single job using Turbo Mode.

Video
--video Saves a progress video of the initial image grid being generated. Emoji
react to the completed image grid with ✉ to trigger the video being sent to your
direct messages. --video does not work when upscaling an image.

Weird
--weird <number 0–3000> , or --w <number 0–3000> Explore unusual aesthetics
with the experimental --weird parameter.

Default Values (Model Version 5.2)

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Aspect
Chaos Quality Seed Stop Stylize
Ratio

Default
1:1 0 1 Random 100 100
Value
whole
.25 .5,
Range any 0–100 numbers 0– 10–100 0–1000
or 1
4294967295

Aspect ratios greater than 2:1 are experimental and may produce
unpredictable results.

Default Values (Model Version 6)

Aspect
Chaos Quality Seed Stop Stylize
Ratio

Default
1:1 0 1 Random 100 100
Value
whole
.25 .5 or
Range 1:3–3:1 0–100 numbers 0– 10–100 0–1000
1
4294967295

Model Version Parameters

Midjourney routinely releases new model versions to improve efficiency,
coherency, and quality. Different models excel at different types of images.

Niji
--niji <4, or 5> An alternative model focused on anime-style images.

Version

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --version <1, 2, 3, 4, 5.0, 5.1, 5.2, or 6> or --v <1, 2, 3, 4, 5.0,
5.1, 5.2, or 6> Use a different version of the Midjourney algorithm.

Legacy Parameters
Some parameters only work with earlier Midjourney Models.
Read More about legacy parameters here.

Compatibility
Model Version & Parameter Compatability

Affects Affects
initial variations Ver. 6 Ver. 5.2 Niji 5
generation + remix

Max
Aspect ✓ ✓ any any any
Ratio

Chaos ✓ 0–100 0–100 0–10

Image 0–3 .5–2 .5–2

✓
Weight default=1 default=1 default

No ✓ ✓ ✓ ✓ ✓

Quality ✓ .25, .5, or 1 .25, .5, or 1 .25, .5, o

Repeat ✓ ✓ ✓ ✓

Seed ✓ ✓ ✓ ✓

Stop ✓ ✓ 10–100 10–100 10–10

cute,
express
Style raw raw
origina
and sce

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Affects Affects
initial variations Ver. 6 Ver. 5.2 Niji 5
generation + remix

0–1000 0–1000 0–100

Stylize ✓
default=100 default=100 default=

Tile ✓ ✓ ✓ ✓ ✓

Video ✓ ✓ ✓ ✓

0–3000 0–1000 0–100

Weird ✓
default=0 default=0 default

Previous
←
Shorten

Next
→
Aspect Ratios

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Blend
The /blend command allows you to upload 2–5 images quickly
and then looks at the concepts and aesthetics of each image and
merges them into a novel new image.

/blend is the same as using multiple image prompts with

/imagine , but the

interface is optimized for easy use on mobile devices.

/blend works with up to 5 images. To use more than 5 images in a prompt

use image prompts with

/imagine

/blend does not work with text prompts. To use text and image prompts

together, use image prompts and text with

/imagine

/blend Options
After typing the /blend command, you will be prompted to upload two photos.
Drag and drop images from your hard drive or add images from your photo
library when using a mobile device. To add more images, select the
optional/options field and select image3 , image4 , or image5 . The /blend
command may take longer to start than other commands because your images
must be uploaded before the Midjourney Bot can process your request.

Blended images have a default 1:1 aspect ratio, but you can use the optional
dimensions field to select between a square aspect ratio (1:1), portrait aspect
ration (2:3), or landscape aspect ratio (3:2).

Custom suffixes are added to the end of/blend prompts, like any other
/imagine prompt. Aspect ratios specified as part of the /blend command
override aspect ratios within a custom suffix.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Blending Tip
For the best results, upload images that are the same aspect ratio as your
desired result.

How to Use
/blend

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Previous
←
Working with Your Own Images

Next
→
Image Prompts

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Image Prompts
You can use images as part of a prompt to inuence a Job's
composition, style, and colors. Images prompts can be used alone
or with text prompts—experiment with combining images with
different styles for the most exciting results.

To add images to a prompt, type or paste the web address where the image is
stored online. The address must end in an extension like .png, .gif, or .jpg. After
adding image addresses, add any additional text and parameters to complete
the prompt.

Prompts must have multiple image prompts or a single image prompt and a
text prompt to work.
An image URL must be a direct link to an online image.

Your file should end in .png, .gif, .webp, .jpg, or .jpeg.

In most browsers, right-click or long-press an image and select Copy Image

Address to get the URL.

The /blend command is a simplified image prompting process optimized for

mobile users.

Privacy Notes
Upload images in your direct messages with the Midjourney Bot to prevent
other server users from seeing an image.
Image prompts are visible on the Midjourney website unless a user has
Stealth Mode.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 How to Use an Image in Your Promp
1. Upload an image to Discord
Follow these instructions to upload your image to Discord.

2. Copy your image's URL

*Discord Desktop App: Right-click on the image and select Copy Link (NOT
"Copy Message Link").

Discord Web App: Click to expand the image, then right-click and choose
"Copy image address."
Discord Mobile App: Tap and hold on the image, then select "Copy Media
Link."

If none of these methods work, you can click to expand the image, and at the
bottom, select "Open in Browser" so you can copy and paste the image's URL.

To incorporate an image into your prompt, you need a direct image link that
ends with .png, .gif, .webp, .jpg, or .jpeg. If the image is on your computer or
phone, you can send it as a message to the Midjourney Bot first to generate a
link.

How To Upload Your Image

Add an Image URL to Your Prompt

To add an image to a prompt, begin typing/imagine as usual. After the prompt
box appears, drag the image file into the prompt box to add the image's URL, or
right-click and paste the link within the prompt box.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Examples
Starting Images

Greecian style statue Vintage Flower Illustration Ernst Haeckel's Jellyfish

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Ernst Haeckel's Lichen Hokusai's The Great Wave

Midjourney Model Version 5

Statue + Flowers Statue + Jellyfish

+ +

Statue + Lichen Statue + Wave

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 + +

Statue + Lichen + Flowers

+ +

Aspect Ratio Tip

Crop images to the same aspect ratio as your final image for the best

results.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Image Weight Parameter
Use the image weight parameter--iw to adjust the importance of the image vs.
text portion of a prompt. The default value is used when no--iw is specified.
Higher --iw values mean the image prompt will have more impact on the
finished job.

See the Multi Prompts page for more information about the relative importance
between parts of a prompt.

Different Midjourney Version Models have different image weight ranges.

Version Version Version

niji 6 niji 5
6 5 4

Image Weight
1 1 NA 1 1
Default
Image Weight
0–3 0–2 NA 0–3 0–2
Range

prompt example: /imagine prompt flowers.jpg birthday cake --iw .5

Image Prompt --iw .25 --iw .5

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 --iw .75 --iw 1 --iw 1.25

--iw 1.5 --iw 1.75 --iw 2

--iw 3

Technical Details
Prompts that only use images and no text are not compatible with the --stylize,
or --weird parameters.

Previous
←
Blend

Next
→
Describe

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Permutation Prompts
Permutation Prompts allow you to quickly generate variations of a
prompt with a single/imagine command. By including lists of
options separated with commas
, within curly braces
{} in your
prompt, you can create multiple versions of a prompt with
different combinations of those options.

Basic Subscribers can create a maximum of 4 Jobs with a single Permutation

Prompt.
Standard Subscribers can create a maximum of 10 Jobs with a single
Permutation Prompt.
Pro and Mega Subscribers can create a maximum of 40 Jobs with a single
Permutation Prompt.

You can use Permutation Prompts to create combinations and permutations

involving any part of a Midjourney Prompt, including text, image prompts,

parameters, or prompt weights.
Permutation prompts are only available while using Fast mode.

Permutation Prompt Basics

Separate your list of options within curly brackets {} to quickly create and
process multiple prompt variations.

Prompt Example:
/imagine prompt a {red, green, yellow} bird creates and processes three
Jobs.

/imagine prompt a red bird

/imagine prompt a green bird
/imagine prompt a yellow bird

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 GPU Minutes
The Midjourney Bot processes each Permutation Prompt variation as an
individual Job. Each Job consumes GPU minutes.

Permutation Prompts will show a confirmation message before they begin

processing.

Permutation Prompt Examples

Prompt Text Variations
The prompt /imagine prompt a naturalist illustration of a {pineapple,
blueberry, rambutan, banana} bird will create and process four Jobs:

a naturalist illustration of a pineapple a naturalist illustration of a blueberry

bird bird

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 a naturalist illustration of a rambutan a naturalist illustration of a banana
bird bird

Prompt Parameter Variations

The prompt /imagine prompt a naturalist illustration of a fruit salad
bird --ar {3:2, 1:1, 2:3, 1:2} will create and process four Jobs with
different aspect ratios:

a naturalist illustration of a
fruit salad bird --ar 3:2

a naturalist illustration of a
fruit salad bird --ar 1:1

a naturalist illustration of a
fruit salad bird --ar 2:3

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 a naturalist illustration of a
fruit salad bird --ar 1:2

The prompt /imagine prompt a naturalist illustration of a fruit salad

bird --{v 5, niji, test} will create and process three Jobs using different
Midjourney Model Versions:

a naturalist illustration of a fruit salad a naturalist illustration of a fruit salad

bird --v 5 bird --niji

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 a naturalist illustration of a fruit salad
bird --test

Multiple and Nested Permutations

It is possible to use multiple sets of bracketed options in a single prompt.
/imagine prompt a {red, green} bird in the {jungle, desert} creates and
processes four Jobs.

/imagine prompt a red bird in the jungle

/imagine prompt a red bird in the desert
/imagine prompt a green bird in the jungle
/imagine prompt a green bird in the desert

It is also possible to nest sets of bracketed options inside other sets of

brackets within a single prompt:

Example: /imagine prompt A {sculpture, painting} of a {seagull {on a

pier, on a beach}, poodle {on a sofa, in a truck}}.

/imagine prompt A sculpture of a seagull on a pier.

/imagine prompt A sculpture of a seagull on a beach.
/imagine prompt A sculpture of a poodle on a sofa.
/imagine prompt A sculpture of a poodle in a truck.
/imagine prompt A painting of a seagull on a pier.
/imagine prompt A painting of a seagull on a beach.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 /imagine prompt A painting of a poodle on a sofa.
/imagine prompt A painting of a poodle in a truck.

Escape Character
If you want to include a , within the curly brackets that does not act as a
separator place a backslash \ directly before it.

imagine prompt {red, pastel, yellow} bird produces three Jobs

/imagine prompt a red bird
/imagine prompt a pastel bird
/imagine prompt a yellow bird

imagine prompt {red, pastel \, yellow} bird produces two Jobs

/imagine prompt a red bird
/imagine prompt a pastel, yellow bird

Previous
←
Advanced Prompting Tools

Next
→
Remaster

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Remaster

Remaster
The Remaster feature is available for upscaled images generated using earlier
Midjourney Model Versions. It creates a new grid of images using the latest
Midjourney Model, combining the original image's composition with the
coherency of the newer Midjourney Model Version v5.2.

Remaster any previously upscaled job by clicking the🎛 Remaster button

beneath the original upscale.

To Remaster very old jobs, use the/show command to refresh that job in
Discord.

prompt example: /imagine prompt Byzantine sandcastle cathedral --v 2

Original Model Version 2 Image Remastered with Model Version 5.2

Previous
←
Permutation Prompts

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Next
→
Repeat

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Stylize
The Midjourney Bot has been trained to produce images that favor
artistic color, composition, and forms. The
--stylize or --s
parameter inuences how strongly this training is applied. Low
stylization values produce images that closely match the prompt
but are less artistic. High stylization values create images that are
very artistic but less connected to the prompt.

--stylize 's default value is 100 and accepts integer values 0–1000 when

using the current models

Common Stylize Settings

Influence of Stylize on Model Version 6
prompt example: /imagine prompt child's drawing of a cat --s 100

--stylize 0 --stylize 50

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Equal to 🎛 Style Low

--stylize 100 (default)

Equal to 🎛 Style Med

--stylize 250 --stylize 500

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Equal to 🎛 Style High

--stylize 750

Equal to 🎛 Style Very High

prompt example: /imagine prompt colorful risograph of a fig --s 100

--stylize 50 --stylize 100 (default) --stylize 250

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Equal to 🎛 Style Low Equal to 🎛 Style Med Equal to 🎛 Style High

--stylize 750

Equal to
🎛 Style Very High

How to Switch Stylization Values

Use the Stylize Parameter
Add --stylize <value> or --s <value> to the end of your prompt.

Use the Settings Command

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 Type /settings and select your preferred stylize value from the menu.

🎛 Style Low 🎛 Style Med 🎛 Style High 🎛 Style Very High

Previous
←
Styles and Aesthetics

Next
→
Style

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com
 For questions or support visit the Midjourney Discord support channels.

Convert web pages and HTML files to PDF in your applications with the Pdfcrowd HTML to PDF API Printed with Pdfcrowd.com