I’ve been messing round with totally different generative AI apps, identical to a lot of you. I’m making an attempt to determine how I can use them in my job and likewise get actually good at utilizing the varied AI instruments. As a result of I create on-line programs, I’ve been engaged on making my very own illustrations that work properly.
In a earlier publish, I shared some suggestions based mostly on issues I’ve studying utilizing AI. I’m utilizing Midjourney for my examples, however there are a whole lot of instruments on the market on your preliminary experimentation.
Listed below are some suggestions I’ve picked up and the way I make these free illustrated characters that I share on LinkedIn.
It Begins with Prompts
The key to getting the appropriate pictures relies on the prompting. The problem with AI is that you just by no means know what you’ll get and once you get one thing that you just actually like, you could not get it once more.
- I begin easy and don’t attempt to overstate or be too descriptive initially. After which I work from there.
- I additionally have a look at what pictures folks share within the AI group and after I discover one thing I like, I attempt their prompts to see what I get.
- For prompts, I largely use a personality, an motion, after which the model. Relying on what I would like, I’ll add a location or one thing to supply extra visible context.
There’s a whole lot of bias constructed into the AI language fashions. For instance, if I kind in businessman, 99% of the time it will likely be a white businessman in a go well with. Why white? Why a go well with? That’s one thing that you must account for as you create characters.
Whatever the bias, I begin with one thing generic like businessman. That often provides me a white man in a go well with. However that’s OK to begin. As soon as I get the appropriate look, I modify the descriptor. Some tricks to get higher preliminary characters:
- As an alternative of simply “businessman,” use an age to see what you get. I discover 40-year-old is an efficient addition.
- It doesn’t matter what you get, the primary level is to see in case you can give you one thing constant.
- There are a whole lot of good movies now on how you can write prompts. The extra you apply and mess around, the higher you get.
- Sooner or later, I name it good and transfer on. My objective is to discover a easy strategy to get a ok picture. Enjoying round in AI for hours (or days…which is able to occur) is enjoyable, however not one thing I can afford to do for lengthy.
As you may see within the pictures under, you get some fairly respectable preliminary pictures to begin. I can work with these.
Describing the motion is the place you get the pose you need and may use. I hold it easy.
- I prefer to insert “gesturing” as a part of the immediate. It provides me extra diversified arm positions.
- Add an emotion or state-of-being equivalent to “confused” or “offended.”
- I additionally change the pose and should use “arms crossed” or “fingers on hips.”
- Mess around and see what you get.
You’ll discover how the pictures change based mostly on a number of easy phrases.
As you evaluation the pictures above, you’ll discover that the types change fairly a bit. You’ll additionally discover that you could be not get the pose you count on. For instance, “fingers on hips” contains arms crossed. “Arms crossed” aren’t full physique poses. That’s one thing you must stay with.
As you apply and get to know how you can write prompts it is possible for you to to design extra constant types.
As talked about above, getting a constant model may be robust. A whole lot of it’s going to come all the way down to the way you write prompts and the texture you get for them as you apply.
- For illustrated characters, I desire a comparable model and no background so it’s simple to scrub up.
- My default immediate model is “flat vector illustration” as a result of that works properly for lots of e-learning course design.
- It additionally works persistently more often than not. And even when the illustrated characters aren’t the identical, they usually are shut sufficient to make use of collectively.
- I do mess around with distinctive model descriptions. For instance, I’ll state “within the model of [add descriptor].”
As you evaluation the pictures above, you’ll discover that including a method description to the “flat vector illustration” begins to supply a extra particular model that will get nearer to consistency.
Bonus Fashion Tip: Getting Rid of the Background
The AI picture is simply the place to begin. Typically you might have to do some edits to fingers, faces, and so on. One of many essential issues is getting a clear background in order that I can place the picture the place I need it.
To get as clear a background as doable, I add the immediate: “white background.” That works 90% of the time. The picture under is similar “fingers on hips” immediate as above with the addition of “white background” within the immediate.
Overcoming Bias with AI
As I famous above, there’s built-in bias which might embrace issues like gender and race, but in addition model of garments. You’ll be able to mitigate a few of that by altering the descriptor. As soon as I get a picture model I like, I’ll begin to add extra descriptions to get extra various characters. Very quickly in any respect, I’ve a various set of characters from which to construct.
One factor to think about is your personal bias. For instance, I’ll search for a selected picture after which assume that it really works due to how “I see” that character and what it ought to symbolize.
These are among the fundamental tricks to get began creating your personal characters with AI. In a comply with up publish, I’ll share my secret sauce and what I do to hurry issues up and the way I edit the characters.
Don’t neglect to obtain the characters I’ve already added. I’ll be including extra, so hold your eyes peeled.