🤯 Any other AI art addicts here? 🤯

So, I’ve been doing a different ai thing. Specifically Nokemon because I discovered the Fakemon community on YouTube by chance.

I got this:
image

Drew this based on that

But I could not, for the life of me, get midjourney to give me any of the epic stuff other people were generating in the discord server. I just could not figure it out. Some people were giving really specific detailed prompts. Is that the trick?

2 Likes

Not Zach, but I can see why you’d think that. I think it helps me that the actor is a brunette and I’m changing his hair color in addition to making him a lot younger than what majority of his photos are.

2 Likes

It’s not a very strong likeness. Just enough for am impression.

1 Like

So here’s what I’ve learned so far:

  1. The beginning words matter the most.
  2. Don’t try to add too many things to the image. So describe one thing in detail, give AI something concrete to latch onto. Imagine Google search results when you don’t want to get a variety of images but a ton of images that are very similar.
  3. Experiment with keywords. For example, for Seri’s images above, I wanted to give him dark blond or light brown hair but AI doesn’t get that concept. It will give me either blond or brown so I had to compromise to make him blonder than what I imagined. Similarly for Lamassu images, keyword “black panther” kept giving me superheroes but black lioness gave me big cats. Words matter.
  4. Once you pick a focal thing for AI to create, add style. I’ll admit shamelessly that I’m using a real artist, Josephine Wall, because I love the results it gives me. Her artwork is colorful and imaginative and AI responds to it well. As comparison, Greg Rutkowski gives me much simpler but also nice images. But you can also use genre or art style to help guide AI.
    I do recommend playing with a free one like Dream first because then you can experiment with keywords until you land on good ones and then you can try those on Midjourney or the like.
  5. When you land on something good, keep milking it. Regenerate that prompt, maybe change a word or two and if it starts coming out too abstract, get back to the good point, put the good words back.

Okay, let’s run an experiment. I’m going to play with a few prompts and get back with results.

3 Likes

Btw, I was feeling down last night, felt a bit triggered and wanted to make myself feel better so I started generating cats. And I love all of them but here is my fave.
Actually, you know what, let me change my avatar because this is me. I’m a cat.

2 Likes

And here’s the great prompt experiment.
I want to create a vehicle from my story. How close will AI get to how I imagine it? Let’s find out.

I’m using Dream by Wombo (web, not phone app).

  1. Hoverpod floating over road in a city magically powered science fantasy magitech
    HDR setting

    Just ok.

Comic


That’s kinda cool. Let’s tweak.

  1. oval Hover pod floating over road in a city magically powered science fantasy magitech
    Comic setting

Getting there.

  1. Clear glass oval Hover pod floating over road in a city magically powered science fantasy magitech
    Comic


    It looks like a train. I think it’s starting to get confused.

    The ground pod looks interesting but the air one is not it.
    Let’s tweak.

  2. Clear glass egg shaped Hover pod floating over road in a city magic science fantasy arcane magitech
    Comic


    Hmmm. This gives me an idea.

  3. Clear glass capsule floating over road in a city magic science fantasy arcane magitech
    Comic


    Hehe. Took it literally.

  4. Clear glass space capsule floating over road in a city magic science fantasy arcane magitech
    Comic



    It’s confused.

Let’s start from scratch.

  1. Glass hoverpod hovering over road city at night science fantasy tron
    Comic


    Eh, no. Earlier was better.

  2. Glass hoverpod floating over road city at night science fantasy magitech
    Comic


    Flying saucer. :joy:

Anyway, you can see the process. Give it an object (hoverpod) a setting (city) and style (genre).

Okay. One more try, let’s see what happens when I ask it for more.

  1. Two people in Glass hoverpod floating over road city at night science fantasy magitech
    Comic

Nice saucers but not what I asked for.
Comic has a tendency to create panels so let’s try HDR again.


That’s not bad actually. Let’s cut the people.

  1. Glass hoverpod floating over road city at night science fantasy magitech
    HDR


    Kinda cool though too sci Fi.
    I stopped saving each but ran through a lot more until I arrived at this beauty.

  2. Oval Glass hoverpod hovering over road city at night urban fantasy magitech transport
    HDR


    This one is as close as I’ll ever get. It’s now official.

3 Likes

It’s a lot of trial and error.

That’s supposed to be a “stained glass galaxy” with a clear rocket as a base pic.

I don’t know if I’m looking at a lava light or something far more adult…

3 Likes

I tried seeing if I can get Night Cafe to create my fictional city. Not exactly what I had in mind, but good for inspiration at least.


I think I do prefer a commission. It’s expensive, but at least you can work closely with someone, give them examples of styles/things you like, specify how characters look/act etc. And if the artist is good, you’ll get what you’re expecting or even better. Rather than trying to figure out the jackpot magic keywords that’ll generate something even remotely close to what’s in your imagination. :thinking: I tried Art Breeder and the user experience was so confusing for me, I gave up lol

4 Likes

I spent 2 hours messing with dream doing the exact thing of your process and just…trying it over and over and getting annoyed with ads towards the end :stuck_out_tongue: It’s pretty cool if you specifically know what you are looking for.

1 Like

I did generate some good ones and I would show you, but my iPad is at 1% so maybe tomorrow :stuck_out_tongue:

3 Likes

The ads is why I prefer the web version. No ads on the web.

2 Likes

The web version severely glitches for me. I can’t see all the options of styles. What are you using it on? I’m using Chrome.

1 Like

Chrome on both my phone and my laptop.

There was a couple of glitchy days that I stepped away from it. I think they were testing new presets maybe. I don’t know. It’s not the most reliable one but free…

2 Likes

OMG. Both, Shutterstock and Adobe Stock accepted my images!

I have 3 images officially up - the same ones on both.

(yes, that’s my real name)

I don’t know how long the window for selling AI generated images is going to last. This space is very unregulated at the time and no one knows what will happen in the future. So for now, I will add a few more while they’re accepting.

1 Like

Well, that’s a temptation for me, lol. Especially as I do a ton of editing. Just got to figure out their guidelines.

2 Likes

So, edited that first “not nude” today:

Had to:
Recolor the clothing, clone an eye, add whites/hilights to the eyes, restructure nose, lips, fingertip, copy hair stretch arm and reshade, adjust one boob a hair, fix a line in the cloth that looked like aborted lettering (and messed up the look of the cloth).

Essentially, this is the same portrait, as there’s not any major edits, except for the little sparkle/stars.

2 Likes

As promised, here are the attempts with Dream. You can tell how hard I tried the prompts.

Keyword symmetric gave such a cool effect.

2 Likes

It’s actually kinda cool how it tells a story already, isn’t it? I’m tempted to present my story in pictures.

2 Likes

Yeah it is! And it also makes for good cover inspiration :wink:

2 Likes

Just because I’ve got a bit of an obsession about location…uh …

Bern Switzerland is what I’m looking up next:

Screenshot:

Anything on Wiki is free to use, generally speaking, that’s why I pulled it up this way, right now.

It goes everywhere, including a ton of edits:

Some programs, I consider that too much instruction for them to reproduce. Lol

3 Likes