Prompt Design Resources for MidJourney AI

by Shane McGeehan

Blog: Recent Entries

Newest Posts

Publication: AI, Machines Rising

I was recently interviewed by Rob Wilson to offer some of my thoughts about AI and photography for an article in the digital publication of FRAMES Magazine… I also created the example images from the author’s photographs using 3 techniques and 3 different AIs - the attached is

It’s a worthwhile read if you are interested in new technology and how it might change the ways we work as image-makers. I was very honest and positive about how I foresee the two tools converging, as they already are and have been in the past… That said, I can’t help but laugh a little at how any time people talk about AI they act like the world is coming to an end. Of course it is, but chill, yo. (and don’t even get me started on Beno Saradzic’s out-of-context line about David Holz using images without consent, or how AI is breaking copyright law - that’s not true and not how it works)

Read the Article here:
LOOK CLOSER: “AI – Machines Rising ” – by Rob Wilson

(click to view)

Melting AI

I am a photo artist. Much of my work begins with a camera, but it isn’t your typical photography. I developed a process in Adobe Photoshop to “melt” my photos, and decided to try the effect on some MidJourney V4 images.

I won’t give away my magic trick secrets, but basically I create an Action that makes a bunch of little changes to an image, then I create another Action that runs the first Action hundreds and hundreds of times, using a Script to save out a frame with each step. Then when I compile the frames together in Adobe Premiere, you get this weird melting/dripping/trippiness effect… Just testing some ideas for a possible bigger project.

(click to view)

Christmas Cards

I decided to make my own Christmas cards with MidJoureny AI this year. To be honest, I rarely ever buy cards, so I don’t feel bad about “taking away” from the market by using AI. In fact, I am known in small circles for making really well-crafted (or also sloppy and childlike) designs with prints, paper, and glue.

Anyway, I prompted and re-rolled a ton of ideas then printed a few dozen, more than I needed. You know, just your typical wholesome holiday content, like… a snowman with a flamethrower, a pissed-off Santa breaking toys, and of course one of the famous reindeer taking a break to smoke a joint. Why not?!

(click the prompt to copy it!)

/imagine prompt: a snowman holding a flamethrower in a snow-covered field with snowflakes in the air and a giant forest fire in the background --ar 2:3 --v 4

/imagine prompt: a wide shot of santa claus standing in a toy shop angery and smashing toys all over the floor --ar 2:3 --v 4

/imagine prompt: rudolph the Red-Nosed Reindeer smoking a cigarette standing in the middle of a wintry Forest --ar 2:3 --v 4

(click to view)

Are Computers Artists?

I define art as something an artist calls art. Simple, right? Therefore, a person can make an amazing painting and call it art, or someone could scream at a rock and call it art. Critics might say “hey, yelling at a rock isn’t art” but they are wrong. It’s art because the artist said it’s art. The critic is always welcome to say “I don’t like this art” but they can’t say it isn’t art… Art is ideas, concepts, self-expression, and a form of communication.

Let’s try to take away the human element as best we can so it’s all computer. I used the text-to-text AI (ChatGPT) to ask for 10 highly descriptive sentences, then copy those into MidJourney. Some results, as you see below, are quite beautiful, and could be hanging in a gallery for others to ponder over - but they are not art. They are just random results of two smart algorithms. The computer didn’t think about what it wanted to communicate, make the viewer feel, or where the work was going next - it just ran code until completion… This is why I strongly believe (and this is my opinion based on my definitions) that if someone thinks of themselves as an artist and uses AI to create images and calls them art - they are.

(click the prompt to copy it!)

The deep blue of the ocean stretched out as far as the eye could see, with whitecaps on the waves caused by the gusty winds --v 4

The desert was a barren wasteland, with rolling sand dunes and sparse vegetation as far as the eye could see --v 4

The sunset painted the sky with a canvas of oranges, pinks, and purples, casting a warm glow over the city below --v 4

(click to view)

Mooooon

I just completed a really important study so you all don’t have to… I was wondering what would happen as I kept adding O’s to the word MOON as a prompt. I began and got a moon, then another mooon, then another moooon, but then… yep… it only took 5 O’s, but we got there. 🐄

(click the prompt to copy it!)

/imagine prompt: mooooon --v 4 --style 4a --stylize 0 --chaos 0 --ar 3:2 --seed 420

(click to view)

Sketch To Image

I’m not very good at drawing, but when I went to grad school and class was boring, I would make lots of random doodles in my notebooks. Since V4 is so good with image prompts, I have been photographing them and seeing how AI can evolve the silly little sketches.

I love how it interprets some, adding style and objects and color, but keeping the main elements. It’s cool too because it adds another layer of creative input to the fairly automated process.

I think people look at AI as being too machine-driven, and it kind of is at times, but little things like this let the user gain more control. I foresee a future of AI where we can use sketches, draw over an image to alter it, and create multiple prompts for certain areas of the image. It’s going to be a wild tool, and one that will take a lot of learning and work as well. ✏

(click the prompt to copy it!)

/imagine prompt: IMAGEURL a drawing of a man climbing a staircase that leads to the moon, 3d elements, an open book, insanely detailed with psychedelic color, hard lighting --ar 2:3 --stylize 1000 --chaos 100 --v 4

/imagine prompt: IMAGEURL a colorful painting --v 4 --ar 2:3

(click to view)

Style, Stylize, and Chaos in V4

MidJoureny just added some sweet new options for V4 today, and so I updated Prompter with new drop-down selections for 4A and 4B, as well as stylize and aspect ratios.

Ya’ll been playing around with all the new style & stylize options? It’s so fun to see the different options you can get from a single prompt idea. To experiment, I ran the same prompt using a seed (for the best comparison) with the minimum and maximum values of both Stylize and Chaos, on both Style 4a and 4b. As you can see, sometimes things get really weird in high amounts… If you want to really have fun, try some prompts with --stylize 1000 --chaos 100. 🤪

(click the prompt to copy it!)

/imagine prompt: art nouveau style of a jellyfish floating in an industrial tank intricate insanely detailed volumetric lighting --v 4 --stylize 1000 --chaos 100

(click to view)

Flicker Film Cube

You can do some really cool stuff with MidJourney images and video editing, especially if you like a good flicker film. This piece makes me think of the old Mothlight film by Stan Brakhage, where the animation isn’t about a narrative, but perception itself.

I’ve been working on a larger video project with graphical imagery of dripping cubes, but along the way, I keep making these smaller pieces while I try out new things and experiment. This image was created by running variations on a single prompt over and over and over. I then downloaded the 100+ images and edited them together in Adobe Premiere (also creating a theta wave soundtrack in Adobe Audition)… This is The Cube. ⬛

(click the prompt to copy it!)

/imagine prompt: a holograph of a cube dripping with black liquid --v 4

Mediums for (no) Thanksgiving

Happy Thanksgiving, folks! I’ve been a vegetarian for 10+ years, but you know, I honestly don’t care what you do. Have a blast and enjoy your feasts, but watch out… the birds might be a little upset! 😦Let’s have some fun with medium descriptors in Version 4. Here are a bunch of pissed-off turkeys in the kitchen holding knives… Like any? Try them out with your own prompt ideas!

(click the prompt to copy it!)

/imagine prompt: claymation of a turkey standing in a kitchen with an angry look on its face and holding knives --v 4

(click to view)

Letters from Images

AI is currently not that good at spelling, but what if we make some really cool designed letters and edited them together to spell a word? That way the resolution is WAY higher too. I had the idea of using image prompts of letters to guide the AI. First, I made simple JPGs of the letters of my name in Photoshop and uploaded them to Discord.

Next, I made an image prompt for every letter of my name (copying and pasting and changing the image URL every time) and re-rolled to find the best ones. I’m kind of a geek, so I prompted the letters of my name out of motherboards, led lights, wires, and so on. I then edited them all together to spell… my name!

(click the prompt to copy it!)

/imagine prompt: IMAGEURL 3d rendering of the letter S:: top down photography of circuit boards, wires, transistors, backlit glowing led lights, computer fans, electronics, against a black background::3 --ar 2:3 --v 4

(click to view)

Blog Search

Blog Categories

Blog Archives

Melting AI

I am a photo artist. Much of my work begins with a camera, but it isn't your typical photography....

Christmas Cards

I decided to make my own Christmas cards with MidJoureny AI this year. To be honest, I rarely ever...

Mooooon

I just completed a really important study so you all don't have to... I was wondering what would...

Flicker Film Cube

You can do some really cool stuff with MidJourney images and video editing, especially if you like...

At The Club

I mean, if AI is always good for anything, it's some weird juxtaposition laughs. Everyone...

Pin It on Pinterest

Share This