Table Of Contents
- Discord Commands → Prompting, settings, and more.
└ Beginner Commands, GPU Hours, Prompting (/imagine, /shorten, /describe), Privacy
- Discord Interface → How to navigate the main interface.
└ Initial Options (re-rolls, variations, and upscales)
└ Vary and Zoom (vary, zoom)
└ External Upscaling (upscale using other software)
- Special Features
└ Vary Region (inpainting, selective changes)
└ Remix (edit prompts or switch models)
└ Remaster (convert V1/2/3 into Test Creative)
└ Upscaling Choices (options and quality)
└ Emoji Reactions (delete images, get seed numbers, and star images)
Below are some of the main commands that you enter into Discord. There are others that can be found in the main MidJourney guide, but I think these are the only ones you really need.
/help → Have no clue what the hell you are doing? Help might help! Entering this command displays a bunch of helpful information to get you started: Links to the GitBook, tips, and more.
/subscribe → Trial over and you still have the taste for more? This command sends you a link to bring you to the MidJourney subscriptions page. Click select a membership option. As mentioned in my Beginner Tips, I highly suggest the $30/mo Standard Membership and then using /relax mode to get unlimited images!
/daily_theme → If you do not want to participate in the Daily Themes but get annoyed by those Discord notifications (I sometimes have issues with uncleared notifications), you can use this to turn those on or off. This does not work in a private chat or server, so just click one of the Newbies channels in the MidJourney Discord and type /daily_theme then No and it’ll turn off notifications. You can do the same with Yes to rejoin again… I think you might need to do this over again when the team makes big changes. I think.
GPU Hour Commands
/info → Shows user info, images made (aka you have an addiction problem), if relax or fast mode is active, GPU hours remaining, in progress items, and such.
/fast → Fast mode, quick results but they count against your hours, so be careful!
/relax → Slow mode, slower processing but doesn’t count against hours, basically infinite.
NOTE: With a Standard plan, stay in relax mode all the time, unless you need to make a max upscale or you are incredibly impatient, that way you get thousands of images “free”.
/imagine → Main command to submit a prompt, then you click “prompt:” and type in your ideas after that. You are going to use this a few thousand times (unless you use Prompter, which automatically adds this so all you have to do is copy and paste!).
/shorten → Command that inspects a prompt and attempts to remove unneeded clutter. Simply type /shorten then enter your prompt, and it will show you what tokens are important, not needed, and even give you 4 short prompts which you can run by clicking the number buttons below.
Note: Shorten will strip parameters from the prompt (like –ar 3:2) so when you click a button to run a shortened prompt, be sure to add the aspect ratio back in, or any other parameter settings you need.
/describe → Command to do convert an image into text. Click “image” and upload a picture then you will get four different prompts in return, with corresponding numbers. If you like prompt number 3, click the 3 button and a dialoge box will pop up. Here you can edit the prompt, or Submit to run it. It even creates links to artists so you can check out their work and learn more as you work.
Note: This is a super fun feature, and you can use anything from a photograph you took, to a graphic, or even toss a MidJourney image back in. That said, be weary. It’s bascially another AI, and AI is far from perfect. Many times you will get prompts with a camera, lens, f/stop, and so on – which don’t really do much of anything. I once put an image in and got “pop-culture-infused” in a prompt like ten times. So utilize the computer, don’t let it do the work for you!
/settings → Adjust default settings like version, style, quality, relax mode. Careful because when you make a change it “sticks” until you go back into settings and change it. I prefer to use parameters in prompts like –version or –quality, because then they only apply for that single prompt, not all as default, but settings is still a super useful tool.
/show → This is super useful if you want to bring up an old image to run upscales or variations, or to bring an image into a new channel you are working in, you just add the job ID to this code. There are two ways to get a job ID:
(1) Discord – You can hit an image with an envelope ✉️ emoji, and the MidJourney bot will send you a message with the seed and job ID.
(2) MidJourney – You can click the three dots to open options, then click Copy Job ID.
Now back in Discord you type /show then paste the job ID (like this: /show dfd1d656-d5c5-4e3e-a1b6-420c1b52ad81) and hit enter. It will bring up the old image so you can keep working!
/stealth or /private → If you pay for a Pro Subscription, entering this command will make all of your work on the MidJourney website private, only visible to you. Keep in mind, if you are in a public channel of Discord, even with Stealth Mode turned on, people can see your work, so if you are a true paranoid – message with the MidJourney Bot or work on your own server. Since I test things a lot, my feed is full of boring clutter, so I got Stealth Mode and decided to “hide” most of it and just showcase a few images to the public.
/public → If you are in Stealth Mode you can turn it off with this command, making your work visible to everyone. With /public turned on (or if you don’t pay extra for private) others can see your work, even if you are in a private server or chatting with the MidJourney Bot, because it will all show publicly on your MidJourney profile.
Once you enter a prompt, completed images are sent back as a message in a grid, and read like a book, with numbers 1 and 2 on top, and 3 and 4 on the bottom. Then you can use various buttons to make variations or upscale.
↻ → Re-rolls the same prompt, new seed is used so all images will be different.
V1 → Make variations for the first image (V3 for third and so on), will make 4 more images based on the chosen one, so they will look similar but different.
U1 → Upscale the first image (U3 for third and so on), will upscale and might change some of the appearance, for better or worse, but that is where the next upscale options come into play.
(click the prompt to copy it!)
/imagine prompt: a long hallway inside a futuristic space station --ar 3:2 --v 4
Vary and Zoom
Vary → After you make an upscale you have many options. The top row lets you create new grids by making a variation of the upscaled image, either Subtle to keep more to the image, or Strong to have more variation added.
Vary Region → See BELOW for more on this new feature. Vary Region, or as I like to call it, simply “inpainting” allows you to alter selective parts of the image, and with Remix Mode turned on – you can change the prompt for each change!
Zoom → A super-fun feature that let’s you zoom out from the image and add more details. You can even use the custom zoom and alter the prompt when you zoom to try to affect the newly added imagery.
(click the prompt to copy it!)
/imagine prompt: optical illusions --ar 3:2 --v 5
You can also download an image and use external software to upscale them yourself. The benefit to this is that it will not change the style, just the size, whereas some MidJourney upscaling alters the look slightly.
Furthermore, you can use external software to upscale an image from the grid if you wish to keep it closer to the original, since sometimes MidJourney upscaling can alter details like faces. To do this, hit the original grid with an envelope ✉ emoji and the bot will DM you 4 cropped images. Now simply download one and upscale it in other software.
I use Visions Of Chaos (which is an amazing program if you have a killer computer) which also let’s you run all kinds of AI right on your GPU, is constantly updated, and worth donating to the developer. That said, there are tons of options, both paid and free. HERE is a great link for other programs for AI upscaling, and I will add more in time.
AI Upscale with Visions Of Chaos
(MidJourney on the left / Visions Of Chaos upscale on the right)
Vary Region (aka inpainting)
This is likely the most asked for feature, and it’s here, and it’s powerful. You can now make an image, upscale it, then click Vary Region to alter parts of the image. Be sure to turn on Remix Mode so you have the option to alter the prompt before submitting.
When Vary Region is clicked, a window will pop up with your current image and a rectangle selection tool, or a lasso selection tool (I prefer the lasso tool because you can draw any kind of shape, or multiple). Draw onto the image where you want to make a change. Now in the text prompt below, alter the prompt to fit what you need. You can completely remove the old prompt and write something new. In the example below, I added a person to the scene – but you can keep doing this over and over until you change your entire image with new additions!
An exciting new feature that allows you to alter your prompt while making variations. To turn this feature on or off just enter /prefer remix or /settings then select Remix Mode. After you get your initial grid of images, the variation buttons (V1, V2) will allow you to edit your prompt. A box will pop up with your prompt, and here you can add or remove things, change parameters, or even move to the –testp algorithm, for example. Have a portrait of a man but with it was a woman? Now you can change it!
1. You can either alter a prompt or delete it all and add new terms. For example, change “a magical forest” to “a magical forest at night” or remove the whole thing and just write “night” (which is usually a more drastic change). If you don’t see a nighttime scene show up, make a few re-rolls and see if it comes in (or use weights). Your last prompt will still have an effect on the new images, so if you say “fall” and then change to “winter” you might still get some fall foliage colors in the snow.
2. Changing the aspect ratio tends to “stretch” the image as it recreates it, especially something like a landscape or drastic shifts in size. That said, I have done some cool stuff going from really tall to really wide, and it will change where people are and add to the background.
3. Stuff like quality or chaos are only set in the initial roll, so for example, you can’t start without quality and then add –quality 5, nothing will change. Also, image prompts don’t work in TEST as usual, but you can run a V3 image prompt and then Remix to TESTP. You can’t add an image prompt via Remix though.
4. Since the codebase was changed, jobs before October will not allow you to run variations or remixes, so the simple fix is to hit the image with an envelope emoji, then the Bot will send you info. Copy the Job ID then type /show and paste the Job ID. This will bring the job back and variations and remixing will work!
5. As things change with this new feature I’ll update these notes.
Below is a visual example of how you can use the Remix feature to change your prompt while working through an idea, and sometimes end up somewhere completely different. This is a little random, but I just wanted to show you how a scene feels the same while changing characters, mediums, and versions. It’s actually pretty amazing.
(click the prompt to copy it!)
/imagine prompt: a photograph of a man walking down a street --v 4
/imagine prompt: a photograph of a woman walking down a street --v 4
/imagine prompt: a painting of a woman walking down a street --v 3
(click the prompt to copy it!)
/imagine prompt: a 3d render of a woman walking down a futuristic neon street --v 3
/imagine prompt: a 3d render of a woman walking down a futuristic neon street --v 4
/imagine prompt: a tintype photograph of a woman walking down a 1930s street --v 4
Remaster is a special feature that allows you to re-roll an upscaled image V3 image into the new V5 algorithm, and adding –v to the prompt. The remaster will alter the image, and might not be what you want, but it is still super fun to play with. Find an old prompt from V3 and Remaster it to V5 – so weird! I love going through really old prompts and trying them out with a Remaster.
This section is only for older versions of MidJourney. In Version 3, for example, after you upscale an image from the grid, you have the choice to uplscale it more using different upscalers. They have their pros and cons, depending on the look you want. If you are using a newer version (like V5) ignore this section, since you don’t have these options.
Upscale to Max → A final upscale that is only allowed in /fast mode. Makes image larger, adds details, but makes things a little weird for some images (you’ll likely see what I mean), in which case you can use the below upscale options:
Light Upscale Redo → If you aren’t happy with the upscale, this will redo it with less detail changes and look more similar to the previous image, however the image is smaller in resolution.
Beta Upscale Redo → New algorithm for upscaling, smooth like the Light Upscale, but with more details, and also much larger resolution.
Detailed Upscale Redo → This is basically the standard upscale, but the button shows up if you did a Light or Beta Upscale, basically meaning to go back to the original upscaler, adding details and such.
Note: Keep in mind that grids in V5 are already upscaled to max, so when you click an upscale button it just crops and gives you the image you picked. Actually pretty amazing. They look great and you don’t need to wait for an upscale or worry about details being altered!
(click the prompt to copy it!)
/imagine prompt: a city street --ar 16:9 --v 3
/imagine prompt: a city street --ar 16:9 --v 3 --uplight
/imagine prompt: a city street --ar 16:9 --v 3 --upbeta
❌ Emoji → React to the image with the red :x: emoji to cancel and delete an image. This is great to declutter your public MidJourney gallery while you work, but be aware that any image you delete is gone for good, on Discord and MidJourney. (I rarely use it because I am a disorganized slob)
✉️ Emoji → React to the image with the :envelope: emoji and the MidJourney Bot will send you a DM with the seed, job ID, and video link (if you had –video in the prompt). This is a useful feature for a few reasons, and I’ll talk about these in more depth later, but basically:
1. If you like an image you can use -seed ### or –sameseed ### with the number given by the Bot and get (maybe) a similar output composition.
2. If you like an image in the original grid, but an upscale changes part of it, you can use the envelope emoji on the original grid and the Bot will message you all 4 images separated. That way you can download the image and upscale it yourself. Check out the External Upscaling section for more on that.
3. If you use –video in your prompt you can download a generative video showing your image go from complete noise to final form.
4. If you want to work on an old image, get the job ID from the Bot and use /show then job_id and copy and paste the job ID. The old image will enter and you can then Upscale, Remix, and so on.
⭐️ Emoji → React to the image with the :star: emoji to mark it as a favorite. Your image will be posted in the #favotires channel on Midjourney’s Discord. Then you can be a star.