Prompt Design Resources for MidJourney AI

by Shane McGeehan

Visual Notebook

Chapter 4

Parameter Notes

Table Of Contents

Chapter 1: Beginner Notes

Chapter 2: Discord Notes

Chapter 3: Prompting Notes

Chapter 4: Parameter Notes

Parameters

Parameters are little codes you can add to a prompt to change various things from the size to the algorithm version used. It is best practice to put all parameters (the terms below) at the end of a prompt. If you are using my Prompter tool, you can simply check boxes and enter numbers, so no need to really know all of them by heart.

Algorithms

--version 1 → Uses the first OG algorithm, good for macro and textures. (can also use --v 1)
Limitations: Not compatible with Stylize or HD.

--version 2 → Uses old algorithm from version 2, more abstract. (can also use --v 2)
Limitations: Not compatible with Stylize. HD is not compatible with Quality values above 2.

--version 3 → Artistic and creative. (can also use --v 3)
Limitations: HD is not compatible with Quality values above 2.

--version 4 → New model, powerfully smart and complex, and incredibly with image prompts. (can also use --v 4)
Limitations: (Version 4 is not compatible with HD, Tile, Video, or SameSeed. Quality must be between 0.25 and 2, but currently isn’t working and will default to 1. Style can be set to 4a or 4b (--style 4a) or cursed. Stylize goes from 0 to 1000 (default 100). Not compatible with separate image weights. Single image prompts are not allowed (need 2 or one with text also).

(click the prompt to copy it!)

/imagine prompt: a waterfall --v 1

/imagine prompt: a portrait of an explorer --v 1

Version 1

(waterfall / explorer)

Version 2

(waterfall / explorer)

Version 3

(waterfall / explorer)

Version 4

(waterfall / explorer)

Test And Testp

Test and Testp (for photo-like looks) were introduced as a short trial, but they ended up sticking around for a while. I suspect they will be removed at some point. These algorithms are a combination of the opensource code from Stable Diffusion and some secret sauce from the MidJourney team. At the time of release, it was impressive and fun for its realistic qualities, but it’s a more simplistic and less creative model.

--test → (temporary beta testing) New algorithm, general artistic mode, more coherence. (there are many limitations, but since this will change by the hour I am not adding details here)
--testp → (temporary beta testing) New algorithm, photo-realism mode, more coherence. (there are many limitations, but since this will change by the hour I am not adding details here)
--creative → (temporary beta testing) Use with --test or --testp to make the image more creative and chaotic.
Limitations: (TESTand TESTP have many limitations but I am not going to list everything here. Personally I feel like TEST might be gone eventually, and Version 4 is where it’s at. Anyway, aspect ratio is limited to 1:1, 2:3, and 3:2. You wont get a warning but it’ll limit to those sizes. Also --stylize can only go from 1250 and 5000.)

(click the prompt to copy it!)

/imagine prompt: a waterfall --test

/imagine prompt: a portrait of an explorer --test

/imagine prompt: a waterfall --test --creative

/imagine prompt: a portrait of an explorer --test --creative

Test

(waterfall / explorer)

Testp

(waterfall / explorer)

Test Creative

(waterfall / explorer)

Testp Creative

(waterfall / explorer)

NijiJourney

--niji → NijiJourney, a model trained on anime and illustrative styles, is now on MidJourney as an add-on algorithm. Simply add --niji to the end of a prompt to get a really cool cartoonish look. Great with characters and action scenes. The Niji only version can be found on NijiJourney.com however now it’s a part of MidJourney too!
Limitations: (Also --sameseed, --stylize, --tile, --hd, and --video are not compatible yet. Quality works and can go from 0.25 to 5, similar to V3. Weights work, but not image weights.)

(click the prompt to copy it!)

/imagine prompt: a waterfall --niji

/imagine prompt: a portrait of an explorer --niji

NijiJourney

(waterfall / explorer)

Output Parameters

At the end of our prompt is where all the parameters go, and they can do a lot to change your output. You can now only change the algorithm version, that we talked about above, but you can also use my GPU time to increase quality, add artistic stylization, weird chaos, specify a starting seed, or change the frame size. Below are a list of all the parameters and examples of what they might do.

Quality

--quality → Spends more time on details (--quality 2) (0.25 faster, 1 default, 5 super high). Please note that for V4 quality only goes from 0.25 to 2, and currently Quality 2 is broken, so just skip this parameter in V4 for now.

(click the prompt to copy it!)

/imagine prompt: a photograph of a circus tent at night with street lights --quality 0.25 --sameseed 420 --v 3

--quality 0.25

(V3, less detail, brighter)

--quality 1

(V3, default quality)

--quality 5

(V3, detailed, darker)

0.25 / 1 / 2

(on V4, sometimes minimal)

Stylize

--stylize → How artistically stylized images are (--stylize 800) (650 off, 2500 default, 60000 crazy)

(click the prompt to copy it!)

/imagine prompt: a stone pathway winding through the woods --stylize 650 --v 3

/imagine prompt: a field of tall flowers with storm clouds above --stylize 0 --v 4

--v 3 --stylize 650

(V3 lowest, off)

--v 3 --stylize 60000

(V3 max, crazy color ‘n stuff)

--v 4 --stylize 0

(V4 lowest, off)

--v 4 --stylize 1000

(V4 max, more creative)

Style

--style → When using the Version 4 model, you can switch between the old 4a style and the newer 4b style settings. (--style 4a) (4a or 4b currently available). Sometimes it’s nice to test out an idea with both to see how they look.

(click the prompt to copy it!)

/imagine prompt: a watercolor painting of a man in a hat standing in a rainforest at sunset --style 4a --v 4

/imagine prompt: art nouveau style of a jellyfish floating in an industrial tank --style 4a --v 4

--style 4a

(original styling)

--style 4b

(new release styling)

--style 4a

(original styling)

--style 4b

(new release styling)

There was a hidden “easter egg” in the last update with a hidden style called CURSED. Since the secret is out, I might as well share it here as well (added 2023-01-02). Add this parameter to any prompt (--style cursed) and you get some weird pixelated, textured, gritty, glitched, dark, and twisted images. images. The lacking quality may not be for everyone, but it’s super fun to play around with! 💀

(click the prompt to copy it!)

/imagine prompt: a watercolor painting of a man in a hat standing in a rainforest at sunset --style cursed --v 4

/imagine prompt: art nouveau style of a jellyfish floating in an industrial tank --style cursed --v 4

--style cursed

(prompt 1 cursed)

Upscale

(prompt 1 upscale)

--style 4a

(prompt 2 cursed)

--style 4b

(prompt 2 upscale)

Chaos

--chaos → How random and abstract the output is (--chaos 85) (0 to 100, higher is chaotic)

(click the prompt to copy it!)

/imagine prompt: a skyscraper with snow-capped mountains in the background --chaos 100 --v 4

--chaos 0

(no chaos)

--chaos 25

(slight chaos)

--chaos 50

(things get strange)

--chaos 100

(super weird)

Stop

--stop → Used to stop image generation at a percent (--stop 50 to end 50% through). This is great if you want to quickly test some ideas, and maybe see the colors or compositions. Be aware that when you upscale an image that is all blurry, it will no longer be “stopped” in the process.

(click the prompt to copy it!)

/imagine prompt: an old turntable next to a lamp with vintage wallpaper in the background --stop 10 --v 4

--stop 10

(blurry)

--stop 25

(slight detail)

--stop 50

(a bit more)

--stop 75

(almost there)

Tile

--tile → Creates a seamless texture that you can tile as a pattern (works best with TEST).

(click the prompt to copy it!)

/imagine prompt: old colonial style buildings, city streets, palmetto trees, rivers, and beach drone view ultra detail cartographic map, fantasy game, final fantasy style, 2d, icons and symbols, anime studio trigger style, cartoon style, illustration --tile --testp

/imagine prompt: a city --tile --testp

--tile

(image from MidJourney)

Patterned

(repeating 4 times)

--tile

(image from MidJourney)

Patterned

(repeating 4 times)

HD

--hd → Algorithm “add-on” (compatible with V2 or V3) that’s better for large images, with a less consistent composition, but good for abstracts.

(click the prompt to copy it!)

/imagine prompt: a photograph of a ship in the ocean --v 3 --hd

/imagine prompt: a painting of the surface of the moon --v 3 --hd

Not HD

(original V3 for comparison)

--hd

(V3 with HD added)

Not HD

(original V3 for comparison)

--hd

(V3 with HD added)

No

--no → Do not include something, same as using a weight of -0.5 (--no trees would avoid trees or --no blue would avoid blue, but you can also use weights like blue::-0.5). Be sure to put this at the end with the other parameters, and only include one - if you use more than one no command things get weird or you get an error because of too much negative weight.

(click the prompt to copy it!)

/imagine prompt: a forest --no green --v4

/imagine prompt: a forest:: green::-0.5 --v4

V4 with --no

(--no doesn’t work well in V4)

V4 with ::-0.5

(negative weight works)

V3 with --no

(--no works)

V3 with ::-0.5

(negative weight works)

Seeds

--seed → Variations use the same style, number from 0 to 4294967295 (--seed 1234). This feature spreads the same noise patterns across all 4 images in the grid. This means that if you run a prompt with a specified seed a few times, image 1 should match image 1 on each grid (same with image 2 and 2, 3 and 3, and so on).

--sameseed → All images will use the same seed, to look similar (--sameseed 1234). This feature spreads the same noise pattern across all 4 images in the grid separately, meaning they will all have similar traits. This can be useful if you like a certain composition and want to have many variations of it.

NOTE: A few things: Keep in mind that in V3 and below, seed images are similar but still different, so you can never get an exact match. In V4, however, a seed is precise, meaning you can run a prompt with a seed many times and the images will be 100% identical (SameSeed is not compatible with V4). That said, if you use the envelope emoji to get a seed from a V4 upscale and then run it, the result will not match. You need to go back to the original grid, get that seed, then run the prompt to return a result like the upscale. Lastly, if you run a prompt with seed 555, for example, then make a variation, the seed will change, meaning you can’t give someone “instructions” to re-make an image with a variation in the history. I hope that makes sense. Geek stuff right there.

(click the prompt to copy it!)

/imagine prompt: a rainbow over a waterfall in the rainforest --seed 420 --v 3

/imagine prompt: a glass sphere with a desert inside, a tall saguaro cactus --seed 420 --v 4

/imagine prompt: a colorful glowing mushroom in the forest --sameseed 420 --v 3

V3 with Seed (first run)

(compare grid to the next example)

V3 with Seed (second run)

(similar grid, but different images)

V4 with Seed

(every run will be identical)

V3 with Sameseed

(all 4 in the grid are similar)

Upscaling

This was a Version 3 thing, so be aware that using these with Version 4 could degrade the quality and make things look strange. That said, on V3 and below, if you know you want a specific type of upscaler, you can skip a step (saving GPU hours) by specifying the upscaler in your prompt. So if you add --uplight to a prompt and click U4, for example, the upscale will be UpLight instead of the default Detailed Upscale.

--uplight → Upscale light, results are closer to the original, smaller file though.
--upbeta → New algorithm for upscaling, smooth, more details, and larger final resolution.

(click the prompt to copy it!)

/imagine prompt: a glass vase full of colorful flowers in the sand on a beach with ocean waves in the background --v 3

/imagine prompt: a glass vase full of colorful flowers in the sand on a beach with ocean waves in the background --v 3 --uplight

/imagine prompt: a glass vase full of colorful flowers in the sand on a beach with ocean waves in the background --v 3 --upbeta

Original Grid

(example with selected image)

Detailed Upscale

(default if no upscale specified)

--uplight

(upscale will be UpLight)

--upbeta

(upscale will be UpBeta)

Video

The video command only works for the first 4-up. Once the image is finished give it a ✉️ emoji and the Bot will DM you the images and video to download. If you do a regular quality image, the video is short and fast (7 seconds), however, if you include --quality 5 or something, you get a really long video (like 34 seconds). Just make sure to stay in /relax mode otherwise higher-quality settings will eat up a lot of GPU hours.

--video → Saves a progress video in DM, need to react with a ✉️ emoji too!

(click the prompt to copy it!)

/imagine prompt: a city street --v 3 --video

Quality 1 with Video

(version 3 grid)

Quality 5 with Video

(version 3 grid)

Frame Size

--aspect or --ar → Used to add an aspect ratio that isn’t a square (--ar 16:9 for a wide output)
--w and/or --h → Similar to aspect, you can use these to set width and height. (--w 1000) (not compatible with V4 or Niji)

(click the prompt to copy it!)

/imagine prompt: octane 3d render of an alien landscape at sunset, volumetric lighting, green, red, purple --v 4 --ar 1:1

/imagine prompt: octane 3d render of an alien landscape at sunset, volumetric lighting, green, red, purple --v 4 --ar 3:2

/imagine prompt: octane 3d render of an alien landscape at sunset, volumetric lighting, green, red, purple --v 4 --ar 2:3

--ar 1:1

(square is default)

--ar 3:2

(landscape ratio)

--ar 2:3

(portrait ratio)

Aspect Ratios

Images in MidJourney are square by default, however, you can use parameter commands (--ar, --w, --h) to alter the aspect ratio of your images. You can match screen sizes, use 9:16 for a story on social media, or get REALLY wide or tall with them. In Prompter, I broke down the ratios into categories for Cinema, Phones, Photography, and more. For visual examples of each of these, check out the chapter on Aspect Ratios.

Cinema

4:3 → Close to early television and film (--ar 4:3)
16:9 → Modern HD standard for televisions, computer monitors, phones (--ar 16:9)
2.39:1 → Close to anamorphic widescreen, widest cinematic, landscapes (--ar 239:100)

(click the prompt to copy it!)

/imagine prompt: a city street --v 3 --ar 4:3

/imagine prompt: a city street --v 3 --ar 16:9

/imagine prompt: a city street --v 3 --ar 239:100

--ar 4:3

--ar 16:9

--ar 239:100

Phones

1:1 → Square, Instagram, default in MidJourney (--ar 1:1)
9:16 → Vertical HD, standard for most phones (--ar 9:16)
9:19.5 → Close to vertical for new iPhones (--ar 90:195)

(click the prompt to copy it!)

/imagine prompt: a city street --v 3 --ar 1:1

/imagine prompt: a city street --v 3 --ar 9:16

/imagine prompt: a city street --v 3 --ar 90:195

--ar 1:1

--ar 9:16

--ar 90:195

Photography

3:2 → Widest view - prints at 4×6, 8×12, 16×24, 20×30, 24×36, 30×40 (--ar 3:2)
2:3 → (same as above, but vertical) (--ar 2:3)

5:4 → Less wide - prints at 8×10, 16×20, 24×30 (--ar 5:4)
4:5 → (same as above, but vertical) (--ar 4:5)

(click the prompt to copy it!)

/imagine prompt: a city street --v 3 --ar 3:2

/imagine prompt: a city street --v 3 --ar 2:3

/imagine prompt: a city street --v 3 --ar 5:4

/imagine prompt: a city street --v 3 --ar 4:5

--ar 3:2

--ar 2:3

--ar 5:4

--ar 4:5

Super Wide

600px → Kinda Wide (--w 600)
800px → Wide, short (--w 800)
1000px → More Wide, short (--w 1000)
1500px → Very wide, short (--w 1500)
2000px → Super wide, short (--w 2000)
3000px → Holy shit wide, short (--w 3000)

(click the prompt to copy it!)

/imagine prompt: a city street --v 3 --w 1500

Super Tall

600px → Kinda tall (--h 600)
800px → Tall, narrow (--h 800)
1000px → More Tall, narrow (--h 1000)
1500px → Very tall, narrow (--h 1500)
2000px → Super tall, narrow (--h 2000)
3000px → Holy shit tall, narrow (--h 3000)

(click the prompt to copy it!)

/imagine prompt: a city street --v 3 --h 1500

Others

5:8 → Tall (--ar 5:8)
8:5 → Wide (same as above, but horizontal) (--ar 8:5)

2:1 → Taller (--ar 2:1)
1:2 → Wider (same as above, but horizontal) (--ar 1:2)

9:20 → Taller-er (--ar 9:20)
20:9 → Wider-er (same as above, but horizontal) (--ar 20:9)

(click the prompt to copy it!)

/imagine prompt: a city street --v 3 --ar 8:5

/imagine prompt: a city street --v 3 --ar 2:1

/imagine prompt: a city street --v 3 --ar 20:9

/imagine prompt: a city street --v 3 --ar 5:8

/imagine prompt: a city street --v 3 --ar 1:2

/imagine prompt: a city street --v 3 --ar 9:20

--ar 8:5

--ar 2:1

--ar 20:9

--ar 5:8

--ar 1:2

--ar 9:20

Pin It on Pinterest

Share This