HomeAI News
[Advanced Tutorial] User Guide for Midjourney Command Suffix Parameters

[Advanced Tutorial] User Guide for Midjourney Command Suffix Parameters

March 16th, 2023
View OriginalTranslated by Google

command list

You can interact with the Midjourney bot on Discord by entering commands. Commands are used to create images, change default settings, monitor user information, and perform other useful tasks. Midjourney commands can be used in any bot channel, run Midjourney Bot on a licensed private Discord server, or in direct messages with Midjourney Bot. /ask Get answers to your questions. /blend Easily blend two images. /daily_theme Toggle notification alerts for #daily-theme channel updates /fast Switch to express mode. /help Displays useful basic information and tips about Midjourney Bot. /imagine Generate images using hints. /info View information about your account and any queued or running jobs. /stealth For Pro plan subscribers: switch to incognito mode /public For Pro plan subscribers: switch to public mode /subscribe Generate a personal link for the user account page. /settings View and adjust Midjourney Bot's settings /prefer option Create or manage custom options. /prefer option list View current customization options. /prefer suffix Specifies a suffix to add to the end of each prompt. /show Regenerate the job in Discord using the image job ID. /relax Switch to relaxation mode. /remix Toggle Remix mode.

parameter list

Parameters are options added to the prompt to change how the image is generated. Parameters can change the aspect ratio of the image, switch the Midjourney model version, change the Upscaler used, and more. Parameters are always added to the end of the prompt. You can add multiple parameters to each prompt. Basic parameters aspect ratio --aspect or --ar change the generated aspect ratio. confusion --chaos <number between 0–100> Change the chaos of the result. Higher values produce more unusual and unexpected spawns. negative --no Negative hints, e.g. --no plants will try to remove plants from the image. quality --quality <.25, .5, 1 or 2> or --q <.25, .5, 1 or 2> How much time you want to spend rendering quality. The default value is 1. Higher values cost more, lower values cost less. seed --seed <integer between 0–4294967295> Midjourney bot uses a seed number to create a field of visual noise, such as TV static, as a starting point for generating an initial image grid. The seed number is randomly generated for each image, but can be specified with the --seed or --sameseed arguments. Using the same seed number and hint will produce a similar final image. stop --stop <integer between 10–100> Use the --stop parameter to complete a job mid-process. Stopping the job at an earlier percentage may produce blurrier, less detailed results. style --style <4a, 4b or 4c> Switch between versions of Midjourney Model Version 4 modeling The --stylize <number> or --s <number> parameter affects how Midjourney's default aesthetic style is applied to the job. "Light" booster --uplight Use an alternate "light" enhancer when the U button is selected. The result is closer to the original grid image. The enlarged image is less detailed and smoother. Beta Enhancer --upbeta Use an alternate beta enhancer when the U button is selected. The result is closer to the original grid image. Zoomed-in images add significantly less detail.


Model version and parameter compatibility

Default (model version 4)

model version

Midjourney regularly releases new model versions to improve efficiency, consistency and quality. Different models are good at different types of images. Niji --niji Alternative model for anime style images. hd --hd Use an earlier alternative model that produces larger, inconsistent images. This algorithm may work on abstract and landscape images. test --test Use Midjourney special test mode. test photo --testp Use Midjourney's special photography test mode. Version --version <1, 2, or 3> or --v <1, 2, or 3> Use an earlier version of the Midjourney algorithm. The current algorithm (V4) is the default.

Image Prompts

You can use images as part of your cues to influence the composition, style and color of your work. Image cues can be used alone or combined with text cues - try combining images of different styles for the most exciting results. To add an image to a prompt, type or paste the URL where the image is stored online. The URL must end with an extension like .png, .gif, or .jpg. After adding the image address, add any other text and parameters to complete the prompt. The image prompt is placed in front of the prompt. A hint must have two images or an image and other text to work properly. Image URLs must be direct links to online images. In most browsers, right-click or long-press on the image and select "Copy Image Address" to get the URL. The /blend command is a simplified image hinting process, optimized for mobile users.

Upload images to Discord

To use a personal image as part of a prompt, upload it to Discord. To upload an image, click the plus sign next to where the message is entered. Select Upload File, choose an image, and send the message. To add this image to your prompt, start typing /imagine as usual. When the popup appears, drag the image file into the popup to add the image's URL. Alternatively, right-click on the image, select Copy Link, and paste the link into the prompt box.

Image Prompts in V3

The image cues in earlier versions of the Midjourney model were more of an abstract inspiration than the initial input images in the current model. Image cues are used as visual inspiration, not a starting point. image weights, --iw Earlier versions of the Midjourney model could use the image weight parameter --iw to adjust the importance of image URLs versus text. --iw 0.25 is the default, used when no --iw is specified. Higher --iw values mean that image cues will have a greater impact on the final composition. See the Multiple Prompts page for more information on the relative importance of the various parts of the prompt. --iw accepts integers -10,000–10,000. Example 2: The text prompt "Vibrant California Flower" combined with the image prompt of Van Gogh's sunflowers. Hint: http://sunflowers.png vibrant California poppies --v 3 --iw <value>


Use the Remix mode to change hints, parameters, model versions, or between different scales. Remix will take the general composition of your starting image as part of a new job. Remixing can help change an image's environment or lighting, develop a theme, or achieve tricky compositions. Remixing is an experimental feature and may be changed or removed at any time. use remix Remix mode is activated via the /prefer remix command or using the /settings command and toggling the 🎛️Remix button. Reblending will change the behavior of the morph buttons (V1, V2, V3, V4) under the image grid. When remix is enabled, it allows you to edit hints in each morph. To remix to expand the selection 🪄 to make variations. When Remix is enabled, the morph button turns green instead of blue when in use. You can change model versions when using Remix. When you're done remixing, use the /settings or /prefer remix command to turn it off. Creates a standard image variation when Remix is active without modifying the prompt in the popup.

Using parameters and remixing

You can add or remove parameters when using remix mode, but only with valid parameter combinations. Changing the /imagine prompt from 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 not compatible with the Stylize parameter. Only parameters that normally affect changes will work when using remix:

How to activate Remix

Use the Settings command Type /settings and select Remix from the popup. 🎛️Remix Using the Prefer Remix command Type /prefer remix to toggle remix mode on and off.

Multiple prompts

Using :: as a separator allows Midjourney Bot to consider two or more different concepts in isolation. Separating prompts allows you to assign relative importance to different parts of the prompt. Multi-prompt basics Adding a double colon :: to the prompt will make Midjourney Bot automatically consider each part separately. In the example below, all the words in the prompt hot dog are considered as a whole and an image of a delicious hot dog is created. If the cue is split into two parts, hot::dog, the two concepts are considered separately, creating a picture of a warm dog.

prompt weight

When using a double-colon :: to separate a prompt into different parts, a number can be added immediately after the double-colon to assign relative importance to that part of the prompt. In the example below, the hint hot::dog will generate a hot dog. Changing the cue to hot::2 dog doubles the importance of the word hot to the word dog, producing an image of a very hot dog!

Negative Prompt Weight

Negative weights can be added to hints to remove unwanted elements. The sum of all weights must be a positive number.

--no parameter

The --no parameter is equivalent to assigning the weight of a certain part of the multi-tip to "-.5", for example, vibrant tulip fields::red::-.5 is the same as vibrant tulip fields --no red.


no dataCoffee time! Feel free to comment