Midjourney is the premiere AI image generator. It functions on Discord, a communications platform, and allows users to create any image you can imagine. It generates images off of user prompts sent in through the Midjourney Discord server. This page is a guide to perfecting your Midjourney AI prompts to get the most out of your words.
Join the Midjourney discord server and follow the instructions on the official Midjourney website. After that, find any of the designated prompting channels such as Newbies-### (with some string of numbers). Now you’re in! Use the chat bar to start prompting image generation based on the syntax below.
Tip: look at how other people are prompting their images. Learn from their prompting styles/format and draw inspiration from their imagination!
The Midjourney AI is a bot that you can interact with on Discord. It uses commands to perform various tasks such as creating images, changing default settings, monitoring user info, and more. Here are some of the commands you can use:
/ask: Get an answer to a question.
/blend: Easily blend two images together.
/daily_theme: Toggle notification pings for the #daily-theme channel update.
/docs: Use in the official Midjourney Discord server to quickly generate a link to topics covered in this user guide.
/describe: Writes four example prompts based on an image you upload.
/faq: Use in the official Midjourney Discord server to quickly generate a link to popular prompt craft channel FAQs.
/fast: Switch to Fast mode.
/help: Shows helpful basic information and tips about the Midjourney Bot.
/imagine: Generate an image using a prompt.
/info: View information about your account and any queued or running jobs.
/stealth: For Pro Plan Subscribers: switch to Stealth Mode.
/public: For Pro Plan Subscribers: switch to Public Mode.
/subscribe: Generate a personal link for a user’s account page.
/settings: View and adjust the Midjourney Bot’s settings.
/prefer option: Create or manage a custom option.
/prefer option list: View your current custom options.
/prefer suffix: Specify a suffix to add to the end of every prompt.
/show: Use an images Job ID to regenerate the Job within Discord.
/relax: Switch to Relax mode.
/remix: Toggle Remix mode.
Please note that some commands are deprecated, such as /private (replaced with /stealth), /pixels, and /idea.
You can use these commands in any Bot Channel, on private Discord servers where the Midjourney Bot has been permitted to operate, or in a direct message with the Midjourney Bot. Bot Channels are Discord channels where the Midjourney Bot has been permitted to process Slash Commands. On the official Midjourney Discord, all channels in the Newcomer Rooms, Thread Channels, Themed Image Gen, and General Image Gen categories are Bot Channels.
A prompt in Midjourney AI is a short text phrase that the bot interprets to produce an image. The bot breaks down the words and phrases in a prompt into smaller pieces, called tokens, that can be compared to its training data and then used to generate an image. A well-crafted prompt can help make unique and exciting images.
Here are some tips for creating effective prompts:
Basic Prompts
A basic prompt can be as simple as a single word, phrase, or emoji. The Midjourney Bot works best with simple, short sentences that describe what you want to see. For example, instead of saying “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”, you could say “Bright orange California poppies drawn with colored pencils”.
Advanced Prompts
More advanced prompts can include one or more image URLs, multiple text phrases, and one or more parameters. Image URLs can be added to a prompt to influence the style and content of the finished result. Parameters can change how an image generates, such as aspect ratios, models, upscalers, and more.
Prompting Notes
Prompt Length: Very short prompts will rely heavily on Midjourney’s default style, so a more descriptive prompt is better for a unique look. However, super-long prompts aren’t always better. Concentrate on the main concepts you want to create.
Grammar: The Midjourney Bot does not understand grammar, sentence structure, or words like humans. Word choice also matters. More specific synonyms work better in many circumstances. Instead of big, try gigantic, enormous, or immense. Remove words when possible. Fewer words mean each word has a more powerful influence.
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. If you want to ensure an object is not in the final image, try advance prompting using the –no parameter.
Think About What Details Matter: Be as specific or vague as you want, but anything you leave out will be randomized. Being vague is a great way to get variety, but you may not get the specific details you want. Try to be clear about any context or details that are important to you.
Use 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 “birds.”
For more detailed information about each aspect of prompting, you can visit the Midjourney Prompts page.
Used to modify your prompt and follow your initial prompt text
Aspect Ratios: This parameter (–aspect-ratio or -a) allows you to specify the aspect ratio of the generated image. You can use values like 1:1, 16:9, 4:3, 2:1, 3:2, 9:16, 3:4, 1:2, and 2:3.
Chaos: The –chaos parameter introduces randomness into the image generation process. Higher values result in more chaotic and unpredictable images.
Fast: The –fast parameter speeds up the image generation process but may result in lower quality images.
Image Weight: This parameter (–image-weight or -iw) between 0-2 controls the balance between the text prompt and the image prompt when both are provided. Higher values give more weight to the image prompt.
Model Versions: Midjourney AI has multiple model versions, each excelling at producing different types of images. You can specify the model version using the –version or –v parameter. The current default model is 5.2.
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.
Seed: The –seed parameter allows you to specify a seed number that influences the initial image generation. Using the same seed number and prompt will result in similar final images.
Stylize: The –stylize or –s parameter influences how strongly the default aesthetic is applied. Low stylization values produce images that closely match the prompt but are less artistic.
Style Raw: The –style raw parameter reduces the influence of the default Midjourney aesthetic and works well for advanced users who want more control over their images or more photographic images.
Tile: The –tile function converts your image into a repeatable tile. This is useful when creating textures or backgrounds you’d like to duplicate over large areas. Imagine using this when generating a foliage or leaf texture you can implement over large 3d models seamlessly.
“King of LA”
Sometimes a simple prompt can work wonders!
“historic traffic, millions of cars cluttering the dense city streets, people forced to the side, cars driving very fast, bumper to bumper, Los Angeles”
This drawing got the spirit of the prompt. But notice how too many factors can dimmish each one’s influence. For example, you don’t see many cars moving fast in this image despite that being included in the prompt
