The Viking hunk, a Chinese princess, an alien encounter, and dawn in the woods ... painting happily

If anybody tells you that AI generated art is the bee's knees ... don't you believe it. Dream Wombo handed me a lot of rubbish today, but I saw the potential in some of it and spent about seven hours painting the images you see here. AI is a very mixed bag: as a concept, it's not fair to "proper" artists, and at the same time, 90% of the results you get out of it are ... weird. My experiments are almost finished ... horses with five legs? People with seven fingers on one hand? People with two heads? A horse with two torsos? Say, what?!! 

So, I think I'm just about done experimenting. I've learned a lot ... learned what I don't like about AI generated images, as well as what I do like. Some engines are better than others; none is as hot as they're reputed to be, but the best can certainly produce the raw materials to make excellent pictures. 

The one thing I dislike the most about AI (and this is the thing that would/will stop me using it very much) is that it's totally random. You know, in your mind's eye, the image you want. The engine hands you something that's so idiotically different, you wonder what it was thinking. Example: You ask for a teacup with teapot ... it gives you (I kid you not!) a woman with thirteen fingers and flowers spilling out of the left side of her skull, holding a teacup the size of a bucket, while a teapot the size of an oil drum grows out of her left elbow. 

What?!!!!

So, experiments complete. I might play with AI occasionally when I'm totally bored, but I'd prefer to imagine my own images and create them from scratch. Like this one:

  

That was me. All me. Painted in photoshop, after being composited from a couple of my own photos, plus a royalty free image of a deer that was sourced from one of those free wallpaper sites where they make you look at 200 commercials before you get to save a picture. You could also go to Wikimedia for sources, or go to any one of dozens of free image sites. These provide the elements from which a picture is composited, and... I'll be totally candid --

In a week, I've seen enough three-armed, two-headed, fourteen-fingered people, and two-headed, five-legged horses, to last me for several years. Look at this one, on the left. Looks okay at first glance. Count the fingers. Who programmed Lexica to believe that human beings have fourteen fingers?! Soooo...

This is something I'll play with when I'm bored, but for all useful purposes, the only thing I'd use it for is to generate the occasional picture element, when I can't afford to pay a bucketful of money to buy a prop.

Fair to say, though, that AI generated art is in its infancy. Come back in five years and see what's happening in this field. The way computers and software advance, I have an intuition that five years from now you won't be able to tell something that was produced by a machine from something a human sweated blood over, for a week. And that's what worries me the most. In fact, it's worrying the entire creative community -- musicians, writers, artists, the lot of us. Many people can see their livelihoods going away. I'm lucky, I don't have to worry about that. I'm retired, and this is just a hobby...

I like to paint. Like...

The "raw" image showed enough promise for me to paint on it for about ninety minutes. But check out the original raw image ... those eyes are doll's eyes; then, as if that wasn't enough, the computer set his hair on fire!!! And the shoulder of his tunic is going right into his skin. There's no depth to the image, and nothing is "happening" in it. It's good raw material, but as a finished image... nope. Good thing I like to paint, right?! 

Same deal with the Chinese princess. The original offering from Dream Wombo was filled with flotsam and jetsam, the face had weird buttons and bits added in for no reason, and the hair went "wrong" at one side. Took me an hour and a half to rescue that one, too!

Mmmm. Experiments complete. I shall now quit bellyaching about AI, and go back to painting, which is what I like best in any case! I'll try to post more often, too ... I've been neglecting this blog terribly -- 2022 did a number on me (don't even ask), but this is 2023, and almost through to the end of Q1. Time to drive on. So -- here we go. 

More adventures in "the other thing," with a LOT of painting

My experiments in AI come under the heading of something like, "Know your enemy." Because ... I'm not going to dissemble here. AI bothers me. This stuuff you see here is only 50% my art. The rest? Generated by some computer. The first image here was generated originally by Wombo Dream, the other two by Lexica. But I feel "wrong" about claiming these as my pictures without painting, so ... I painted. A lot. Fair to say that by the time I was done painting, they looked very, very different from the AI original -- especially the space station. 

To be honest, the original AI version of the space station was a bit rubbish. Then I got a glimpse of what it could be, and I set to work. About two hours later, I had it ... with a background generated in Amberlight and a hulluva lot of painting in Photoshop. 

This, at left, is what Lexica gave me, and I wasn't exactly thrilled ... but I saw the potential. So, the AI design became one element of a different (and far better) image. I guess you could say I did it this way rather than spending a tonne of money on a prop, and rendering it in Iray! Because the truth is, I don't have the cash flow now to be able to spend a lot of money on props, and I've been wondering for ages what I was going to do about that. So, for me, it comes down to a question of ethics ... nooooo, I don't feel comfortable with AI art generation, but can I use elements from these images which I prompted, in combination with a load of work, and call the final art my own? I want to say yes, because it comes down to this: I didn't design the 3D props I would render, either, so ... yeah. You see the gist of the argument. So long as I actually work on the image, "do it over," make it my own, I think I can sign off on it. Anyway, that's theory at the moment.

The first image -- the Chinese warrior -- started life in Google's AI art engine, which is now called Dream.ai, and used to be Wombo, if I understand this correctly. Wombo's results vary dramatically from prompt to prompt. It can spit out something quite good or something really bad; occasionally, it comes up with something filled with promise. I did a range of these experiments to use as the base canvases for painting, and I'll post some of the paintings as we go.

The second image began in Lexica: not bad, but flat, "tepid," and needing work. It's early days yet; as I get to know more of what I'm doing, these elements will be combined into new and radically different forms ... basically, because I don't have the bucks to buy 3D goodies anymore. They're expensive. Too rich for my blood, when my cashflow went away. So ... 

AI? Sigh. I don't feel "comfortable" with the whole concept, but for me it has a part to play ... it just isn't the whole job. Not by a lot shot. 

And there's just no answer to this... The word is gobsmacked.

Today's adventures in AI and Photoshop. Let is be understood on Day One, I do NOT approve of AI art ... which is why each of these images is heavily painted, reworked, turned into something new. Honestly... the artist in me is just about to throw up hands and tear out hair. I did these in Lexica AI + Photoshop (80% of one, 20% of t'other) in less time than it took me to drink a cup of tea. No exaggeration. On the one hand, I'm gobsmacked, waaaay beyond amazed; on the other hand, I'm appalled, because I have this vision of people forgetting how to paint, because you basically tell the AI what you want and it gives you something you can work with ... maybe not anything like what you imagined, but something -- at a fidelity, a resolution, that you would work days or weeks to achieve with a paintbrush. Argh.

Speaking purely as an artist, frankly, I find it scary. Verrrry scary. I mean, it's fun, and hobbyists like myself will be enjoying the heck out of this, but why would a publisher hire an artist to paint for a week for hundreds (or even thousands) or bucks, when you can type in "fantasy warrior, man, long black hair, longshot, full length, Frank Frazetta, silver armor,  broadsword, full face, brooding, stormy sky, not portrait," and it hands you the base canvas for this? I shipped them all into Photoshop and added birds, smoke, clouds, fire ... changed the eye colour, added feathers in his hair, dodged this, burned that, saturated the colour ... and signed off on it. And frankly, I'm a bit sheepish about signing off on something that is really only 25% me. 

In fact, the whole concept of AI art has been bothering me for some time, which is why I find myself so bemused to be doing this stuff for the fun of it. As soon as I really learn how to do this, I plan to use AI elements and feed them into Krita etc, to be forged into new and utterly unique PAINTINGS ... by the time I'm done, the result will be my work, no one else's ... at which point the source images are no different from tracing over a photo to get a rough guide from which to paint. AI will be incorporated into my work as a replacement for the beaucoup bucks I can't spend on 3D props any longer. I ain't got the cash, and like any boot-end artist these days, I don't expect to get any more low price gigs. AI has made sure of that. Still, it's humungous fun, and it'll give me the ability to do more and better paintings, when I fully learn this. But -- honestly ... sigh.

 

Adventures in Krita, and explorations into AI. Gasp!

So ... where have I been for so long? Short version: 2022 "did a number" on me, and although I've started to make the journey back to health and strength, there's a (very) long way to go yet. For the longest time, I wasn't able to do anything much of anything. Then, on top of everything else I got Covid, and took months to throw it off -- the truth is, it's six months later, and I still haven't recovered a hundred percent...

In that time, art and writing have been next to impossible. I think I've written four short stories in the last year; and four items have been published, or are about to be (I just posted to my writing blog, bringing that up to date with scribbling and publishing) ... but writing new stuff? Painting? Rendering? That's been too much to even contemplate, till these last few weeks. Then...

Couple of things: I've gotten my feet wet with Krita. Full-on painting. Soooo much to learn, before I start doing exotic young hunks, (nudge wink) so I might as well learn on cats and owls and flutterflies, right? Krita is a LOT of fun. If you have any interest, it's open source, free forever, and looks (to me) to be just about the equal of things like Corel Paint, perhaps not quite on the same level with Rebelle ... but these progs are prohibitively expensive, while Krita is ... well, it's free. It's Krita.org, as far as I know, not dot-com.

The great news is, the Huion tablet is on and working, and is fan-flipping-tastic. It's making it possible for me to actually sketch and doodle. The squirrel pen and ink image was my first ever foray into the program, and it really is pen and ink. The owl was my first full-on true painting. I need to buy some extra brushes -- acrylic brushes, oil brushes, watercolour brushes, textures. Very soon, we'll be off to the races.

And just as I discover this, along comes the wonderful world of AI. Well, now. The truth is, since  don't have much of a cash flow, DAZ is a bit too expensive for me. All I can do is work with the existing props and sets and costumes, and one has to say, there's only so many ways you can rearrange them before you start to recognise literally every element of every picture. But with AI, it's free, incredibly fast, and amazingly vivid. 

The Chris Foss style heavy industrial spaceship image took minutes. Seriously. Argh. Urgh. You want stuff like this? Seconds, and there is is...

I do believe I have just heard the death knell for many, many forms of art. Unless DAZ can make its product more affordable AND easier to render on systems which real people (not industry pros, or companies chucking around tonnes of money) can afford, more and more people will drift away to AI. In fact, I'm heading in that direction, as well as long, slow, laborious painting in Krita. But I do want to be painting those exotic young hunks, and you do have to start somewhere, so ... here we go. Starting.