Midjourney AI is a powerful tool for creating unique and beautiful images, but it can be tricky to master.
In this blog post, we’ll go over some pro tips and tricks for getting the most out of Midjourney AI, including how to use keywords and advanced settings to achieve the style and results you’re looking for.
Whether you’re a professional artist or a hobbyist, these tips will help you take your paintings to the next level.
2d logo, minimal, mechanized ape --s 4
2d logo, minimal, mechanized ape --chaos 60 --s 4
Even though all words have a default weight of 1, words that are closer to the start of the prompt have a greater effect on the result. The things that your desired image can’t do without must be as early in the prompt as possible. Proper grammar is less important in most cases.
Commas are soft breaks, :: are hard breaks. This affects how hard MJ tries to blend two concepts together for the image.
Adding weights to words with ::n can significantly affect the result. Same with –iw n for images. A value of 0.5 will result in taking some small elements, a few shapes and colors, into the resulting image. But the words will take precedence. A value of 10 is almost like telling MJ to give you a new version of the image prompt while disregarding any words.
Aspect ratios can also have a significant impact on the result. E.g. portraits on images with ratios that have room to fit more than one face have a tendency to develop unwanted extra faces or facial features. It’s important to choose the best aspect ratio for the things you want to fit in the frame.
If you want a particular thing, it can help to reference an artist that had done many such works. E.g. if you want a good portrait, include a good portrait artist in the prompt. The more you narrow MJ’s frame of reference to images of the thing you’re trying to generate, the more consistent it gets in generating said thing. Adding artists is one way to do that.
Being very long and descriptive can produce amazing results or total nonsense. There is definitely a limit where prompts get too complex for MJ to reliably figure out what you want in your image. But at the same time, some images can only be generated by tweaking long prompts and doing many, many iterations until you get what you want. Sometimes, you can develop a long prompt that produces great results but it’s really only a few words that are going the heavy lifting. You kinda have to guess which ones they are by examining your images.
Image + text prompt describing the thing in the image is a decent way of ensuring that some key elements of the image prompt transfer to the generated image.
If a style you want to replicate isn’t in MJ’s reference archive, you can use an image or multiple images in that style to help MJ get you what you need. E.g. if a painter’s name is not recognized, you could still potentially copy elements of their style by using their works in an image prompt.
Sometimes you need to tell MJ things that we take for granted. E.g. prompting for a “beautiful face” does not always mean MJ will give you a symmetrical face, tho symmetry is very closely related to our perception of beauty in humans. So something like “symmetrical beautiful face” tends to produce better results, or even just adding the word “symmetry” in the prompt, possibly with a higher weight, can have an effect.
Negative weights are an underused feature but can be very helpful for particular prompts that confuse MJ. If I’m getting too much ice in my “ice cream” prompt, a simple –no ice can go a long way.
Here are some of the ways you can generate variations in images and some of the advanced settings for the same:
In a nutshell, your style is affected by the keywords of your choice — and you can specify what kind of styles you choose to go for. Each of the above settings can be tweaked and modified to suit your needs and preferences, giving you complete control over the final image.
So there you have it, our top pro tips for painting with Midjourney AI. With these tips and tricks, you’ll be able to achieve the results you want and create truly unique and beautiful images. Happy painting!
You can be as specific or as vague as you want, but anything you leave out will be randomized. Being vague is a great way to get variety, but you may not get what you’re looking for. Try to be clear about any context or details that are important to you.
Try using objects that have a lot of photos available on the internet. Examples include wizard, priest, angel, emperor, necromancer, rockstar, city, queen, Zeus, house, temple, farm, car, landscape, mountain, river.
Try using strong feelings or mystical-sounding themes in your prompts. Examples include “a sense of awe” “the will to endure” “cognitive resonance” “the shores of infinity” “the birth of time” “a desire for knowledge” “the notion of self”.
Try describing a style in your prompt. Examples include “a cyberpunk wizard”, “a surreal landscape” “a psychedelic astronaut”. Other styles to try include cyberpunk, psychedelic, surreal, vaporwave, alien, solarpunk, modern, ancient, futuristic, retro, realistic, dreamlike, funk art, abstract, pop art, impressionism, minimalism.
You can also try invoking unique artists to get a unique style in your image. Examples include “Temple by James Gurney” or “Father by MC Escher”. Other artists to try include Hiroshi Yoshida, Max Ernst, Paul Signac, Salvador Dali, James Gurney, M.C. Escher, Thomas Kinkade, Ivan Aivazovsky, Italo Calvino, Norman Rockwell, Albert Bierstadt, Giorgio de Chirico, Rene Magritte, Ross Tran, Marc Simonetti, John Harris, Hilma af Klint, George Inness, Pablo Picasso, William Blake, Wassily Kandinsky, Peter Mohrbacher, Greg Rutkowski, Paul Signac, Steven Belledin and Studio Ghibli. You can even combine names for new styles, such as “A temple by Greg Rutkowski and Ross Tran”.
Try specifying a particular medium in your prompt. Examples include “a watercolor painting of a landscape” or “a child’s drawing of a home”. Other mediums to try include painting, drawing, sketch, pencil drawing, woodblock print, matte painting, child’s drawing, charcoal drawing, ink drawing, oil on canvas, graffiti, watercolor painting, fresco, stone tablet, cave painting, sculpture, work on paper, and needlepoint. If the style is unspecified, it will lean towards photorealism.
Language models often ignore negative words, so it’s best to speak in positives. Avoid phrases like “a hat that’s not red” and instead try “a blue hat”. Avoid phrases like “a person but half robot” and instead try “half person half robot”.
Be specific and clear about what you want in your prompt. Avoid phrases like “monkeys doing business” and instead try “three monkeys in business suits”.
If you have a specific composition in mind for your image, be sure to specify it in your prompt. Examples include “a portrait of a queen” or “an ultrawide shot of a queen”. Other compositions to try include portrait, headshot, ultrawide shot, extreme closeup, macro shot, and an expansive view of.
Avoid overwhelming the system with too many small details in your prompt. Avoid phrases like “a monkey on roller skates juggling razor blades in a hurricane” and instead try “a monkey that’s a hurricane of chaos”.
Are you the victim of a car accident? If so, you know how difficult it…
Qatar is a small peninsula with over 560 km of coastline in the Arabian Gulf,…
Have a bored dog that you hate leaving at home? Leaving your dog at home…
Even if you're over the moon excited about exploring the wonderful world of sugar dating…
When planning a vacation trip to Michigan, you have to rack your brains seriously. The…
Introducing the reMarkable 2: The Next-Generation Paper Tablet Are you tired of lugging around a…