Generate amazing images by learning how you can create higher Midjourney prompts.
I used to make use of Midjourney mistaken.
My prompts lacked details and styles, leading to generic and inaccurate images. I also never added parameters to customize the default behavior of Midjourney.
In the event you’re a Midjourney user, probably you’re also making these and other mistakes, but today I’ll show you some techniques that can assist you to produce higher images and make Midjourney understand what’s in your mind.
Note: In case you’re latest to Midjourney, you’ll be able to read this guide to learn how you can create an account and start with basic Midjourney commands.
First things first — Change the default settings
Midjourney by default is nice, but you must adjust your settings if you need to benefit from it. To accomplish that, use the /settings
command.
Once the Midjourney settings pop up, activate the “MJ version 5” to make use of the newest version of Midjourney and “Remix mode” to switch the versions of the pictures you get.
Now each time you type a prompt, you’ll get the –v5 at the top and in addition you’ll have the opportunity to edit the prompts for the pictures that you simply generated with Midjourney.
The Midjourney prompt formula
A straightforward and short Midjourney prompt typically leads to images which can be taken directly from the Midjourney training data, while a more detailed prompt can create entirely latest and unique images.
Let’s see an example. Here’s a brief prompt for a blueberry pancake.
Sugar dust of blueberry pancake —
And here’s the identical prompt but with more details.
Industrial photography of sugar dust of blueberry pancake, with studio light, hyper-detailed, on black isolated plain, pro color grading, white lighting, Shot on 70mm lens, Canon camera, 8k
You see the difference?
The extent of detail in your prompt directly impacts the distinctiveness of the generated image. For this reason we must always be specific in describing what we would like, including details equivalent to the background, lighting, camera lens, format, and other relevant elements to make sure the specified consequence.
You need to use the formula below in your Midjourney prompts, but note that you simply won’t at all times need each element of the formula.
In case you don’t have a lot creativity to give you all the main points for the prompt, you’ll be able to make ChatGPT write prompts with a lot of details and even different styles as I show on this guide.
Now let’s deal with an important parameters that can assist you to create higher images than most Midjourney users.
1. Prompt Weights
While you’re working with a sophisticated prompt that has different objects, you’ll be able to give more weight to a selected object by utilizing ::
followed by a number. The upper the number, the more weight it has in the ultimate output.
Let’s see some examples.
Forest::2 Lake::1 Airplaine::3
I attempted using the identical words but with different weights, and listed here are the outcomes.
Forest::2 Lake::3 Airplaine::1
As you’ll be able to see, the upper the number, the more visible the item is in the ultimate image.
2. Negative prompting
We add the --no
parameter after we don’t want a selected object in our final image.
Say we would like a bowl of fruit without apples in it.
bowl of fruit –no apples
3. S
Stylize determines how artistic a Midjourney image will likely be.
Midjourney models are trained to create art forms, color schemes, and compositions. We will control this using --stylize
or --s
followed by a number: --s [0-1000]
.
Higher numbers will make your image look more artistic however the image is likely to be less connected to the prompt, while lower numbers will create a picture that closely matches your prompt but could also be less artistic.
By default, the common level of stylization is ready to --s 100
.
Let’s see some examples.
A beautigul girl with brown hair and green eyes –s 1000
It looks quite artistic, and may even be confused with an actual photo.
Let’s decrease the worth of stylize.
A beautigul girl with brown hair and green eyes –s 500
In these examples,500
performed just in addition to 1000
. Now I’m going to set the parameter to the default --s 100
.
A beautigul girl with brown hair and green eyes –s 100
Now we are able to already see the difference. Only one among the 4 images turned out to be good, nevertheless it’s still not nearly as good because the previous images.
4. Chaos
Chaos determines the extent of variation in the outcomes displayed within the grid. Higher values of this parameter will yield more odd and unexpected results, while lower values have more reliable, repeatable results. The default value is 0: --c [0-100]
Let’s see some examples.
dog under the water the camera –c 0
When the chaos was 0, we got reliable results. Let’s see what happens after we set the chaos to 100.
dog under the water the camera –c 100
As you’ll be able to see, most of the pictures we got with chaos 100 weren’t what we wanted.
5. Quality
Quality determines the extent of image processing by Midjourney (or how much time is spent generating a picture). Higher values will lead to images with more details, but it’s going to also use more of your subscription’s GPU minutes.
The default value for quality is 1, but you’ll be able to select from different options equivalent to 0.25, 0.5, 1, 2, or 5.
Let’s see some examples.
Flowers –q 0.25
With --q 0.25
we got images 4 times faster than the usual option, more cost effective, and simplistic.
Now let’s try 0.5.
Flowers –q 0.5
With --q 0.5
we got images twice as fast as the usual option, more cost effective, and with a reduced level of detail.
Finally, let’s add rather more detail with 1, 2, and 5.
Flowers –q 1
Flowers –q 2
Flowers –q 5
With --q2
and --q5
, I noticed a superior level of detail. Nevertheless, I didn’t see a big difference between --q2
and --q5
.
6. Ratio
By default, Midjourney generates all images in a square format, with a 1:1 aspect ratio. Nevertheless, in the event you need a special format, you’ll be able to specify it using the aspect ratio parameter: --ar[ratio]
For a horizontal image, you’ll be able to add --ar 3:2
at the top of your prompt, while for a vertical image, you’ll be able to add --ar 2:3
.
a cat within the forest, — ar 3:2
a cat within the forest, — ar 2:3
There are other aspect ratios you should utilize like 16:9
, which is used for YouTube thumbnails, and 9:16
, which replicates a selfie picture from a smartphone.
Extra resources
On this website, you will discover an inventory of styles in your Midjourney prompts from fashion designers to photographers and painters, while on this GitHub repo, you’ll find more styles and keywords reference.
jazz work coffee