Midjourney AI Imagery: Getting Started

Jul 25, 2022 at 03:30 pm by Warlord720

With AI-powered image creation tool Midjourney going into open beta there is now an opportunity for everyone to give it a try. In the past few weeks, we’ve been seeing some really great, cool, and at times downright creepy (the good kind) of Midjourney-generated images and they have not disappointed.

Now it seems that digital art in some forms will come down to whoever can come up with the most creative input that the ai can understand. For those of you new to this concept all it takes is a few words or more of creative input to get started generating an ai image with Midjourney.

In fact, the process is so simple at this point that it is run on Discord with paid plans giving you direct access to the Midjourney bot without all the clutter of other users. Not that the clutter is bad, in fact, it can be inspiring and full of great input words and phrases to add to your own library of inputs. Even using the same phrase, you will get a somewhat different outcome from the original.

I’m no expert in Midjourney at this point but you don’t have to be to use it so let’s look at how to get started.

Go over to midjourney.com and select Join the Beta which as I stated earlier is run on Discord so you will have to download and learn to use Discord if you want to use Midjourney. It’s not that hard but can a bit confusing for the first time or the first few minutes depending on how fast you pick things up. A lot of Renderosity Mag readers use Discord but there are those that never have so that small learning curve will have to be included for them.

When you finish jumping through some simple hoops to get an account you can go right over to the Discord server, pick a Newbie thread, and start generating your 25 free images. They will go fast because you get four initial “takes” in differing variations on the first image, then you use their extremely simple interface to either upscale or get variations on one, any or all of the four initial images.

There are commands that can be used at the end of the input string like:   - - width 1920      - - height 1024      or   - -ar 16:9. The double hyphens are essential to each command.



Tip: If you are not fond of the default aspect ratio you can use:   --ar 16:9
Example:    cosmic star cloud with aliens --ar 16:9


An input starts with the /imagine command:

Midjourney AI Discord Prompt

Now you just sit back and wait for the magic to happen as it generates the image.

A prompt such as this:

Midjourney Prompt

…produced the image below:

Midjourney Variations

From here you make your choice, mine being image #3 as they are numbered 1-2 on top and 3-4 on bottom. Ignore the pointing hand cursor as that is there only to point out for this article the image I used. The blue U3 button below the image is how you choose it for upscaling. U equals upscaling, V is for more variations. If I wanted to see 4 more variations of image one, I would select the V1 button for those variations.

Midjourney generated image.

Not exactly rocket science and that is the cool part. It’s so simple almost anyone with computer skills can create images and these images can be the building block of a larger project like the background in a scene as shown below:

Midjourney generated Xeno Cave

In iClone it can be used to save polycount overhead as a scene background as shown below:

Used in iClone 8

In summary, Midjourney does not require technical skills and opens up image generation to anyone that wants to try it during the open beta. As stated before, you do get 25 free images before you have to choose a plan at $10 per month for 200 images per month or $30 per month for unlimited images.

As for myself I went through the free images very quickly and signed up for the $10 tier until I can see what my usage might be as we are able to change plans within the user interface with changes effective at the end of the current billing cycle.

So… if this intrigues you or you have a use for generated images then I’d suggest jumping over to midjourney.com and getting started. And get your credit card out as you are probably going to need it eventually.


M.D. McCallum, aka WarLord, is an international award-winning commercial graphics artist, 3D animator, published author, project director, and webmaster with a freelance career that spans over 20 years.  Now retired, M.D. is currently working part-time on writing and select character development projects. You can learn more about MD on his website


Top Stories

This website uses cookies to ensure you get the best experience possible More Info
Got it!