There are lots of applications you can turn to generating images using artificial intelligence. Despite this, Midjourney remains one of the best and most popular options since it launched in beta in July 2022.
It’s not free to operate: introductory prices start at $10 per month or $96 per year, which gives you 3.3 hours of image generation per month (image rendering usually takes about a minute). However, the quality of the end result may tempt you to subscribe if you need a lot of AI graphics.
Assuming you’re ready to sign up (at least for a month), here’s how to get started with Midjourney – the commands you need to know, how to save and view images, and some of the capabilities of the generative AI tool.
Getting started
Midjourney works via Discord: You can join the midjourney channel hereand you will need to sign up for a (free) Discord account if you don’t already have one. The next steps require two administrative steps – agreeing to Midjourney’s terms of service and signing up for one of Midjourney’s subscription tiers. You’ll get a neat little table showing the differences between each level.
Midjourney does a decent job of explaining how everything works once it’s all out of the way. Unless you’re on one of the more pricey plans, you’ll be writing prompts and uploading images through a channel open to other users, so don’t be shy – it’s really good for getting inspired by what other people are doing and seeing what’s up possible thanks to the AI engine.
To get started, you’ll need to engage with one of the #newbie channels, which are clearly linked on the left side of the web interface. Click to jump to any of them and see what’s going on – take a look at how different artistic styles are described for different results, from “abstract and expressive” to “hyper-realistic” and everything in between.
Another online location you need to know about is Midjourney official website. While all image creation takes place on Discord, on this site you can find an archive of all the photos you’ve taken and browse other artwork that’s trending on the Midjourney network. You can also read about Midjourney updates here.
Writing prompts
Go to the #newbie channel, type “/imagine” followed by a space and you can start showing suggestions. If you’ve never used an AI image generator before, describe what you want to see: You can be as artistic as possible by placing any person or object in any setting and using any style of graphics.
As usual with generative AI tools, the more detailed and precise you can be, the better. However, you can be vague if you want (you’re just less likely to get something close to what you imagined). See a watercolor of an elephant in a boat or a photo of an apple on a table, the decision is yours.
After a few moments of thought, you’ll get four generated images based on the prompt – if you want Midjourney to try again, click the reroll button (blue and white circle with arrows). If you like one of the images more than the rest, you can click on one of them V1–V4 buttons to see its four variations (the images are numbered from left to right and top to bottom).
Click any of U1–U4 buttons to take a closer look. Here you have access to some editing features: you can create fresh variations of the entire image or just parts of it, shrink the image (and let the AI fill the canvas), or stretch the image in any direction using the four arrow buttons. Click on any image to view it in full-size mode, then right-click to save it elsewhere.
Going forward
You can add various parameters to the tooltip and that’s it full list here. For example, you can operate them to change the aspect ratio of an image, create tiling images, or create more varied results. So if you need a wide rather than square image, you can add “—16:9 aspect” to the end of the prompt.
It’s also worth knowing the “—cref” and “—sref” parameters, which may be followed by a URL pointing to the image. Utilize the first (character reference) to show Midjourney the character you want to operate in your images, and the second (style reference) to show Midjourney the style you want your photos to look like.
There are also a few other commands you can operate instead of “/imagine” on Discord. Utilize “/describe” to have Midjourney display a text prompt based on the image provided, or “/blend” to have Midjourney combine up to five different images into something fresh. You can point to images on the Internet or upload them from your device.
Head to on the Midjourney website to find all your photos and download them if you need to – eventually you’ll be able to generate images here too, but the feature hasn’t fully launched yet. You can operate the filters on the right to browse through the artwork you have created. It is also possible to download multiple images at once or sort them into custom folders if necessary.
