Touching base ... with apologies to J.R.R. ...

Just a ditty to keep contact with this blog while there isn't much to talk about. Yeees, the art started its life in Bing, but I promptly cut it up, rearranged it, repainted it, did a lot of things to it. And yes, I would have painted from scratch, if I had the whole day to spend on this (I don't). And yes, I would have rendered it in CG, if I had a spare hundred bucks to spend on the props (I don't). So we'll embrace the concept of compromise: AI + digital painting.  In this instance, AI is saving me a lot of time and money, and it is being used as a tool, with reason. Argh.

Life has been interesting in the last month. I had intended to invest a tonne of time in art and writing ... nope. Not going to happen. I have done a whale of a lot of editing, yes. (I'm working with the well-known Sherlock Holmes novelist, Mike Adamson). And my romance with my new camera continues unabated. I've entered the wonderful world of Canon EOS technology, and it's amazing. Loving it. I've actually written (yes, written. Don't faint) an invitation guest post for the ANALOG blog (because Firegrounds is in the latest issue, which is out about now). But aside from this, Real Life has been biting so hard, so deep, that any creative juices that might have been flowing in June were quite literally turned off at the taps. Okay ... let's start yet again, right? Right. Never say die, and all that.

So, let's see if I can't get the reins back between my hands -- and possibly the bit between my teeth, while we're dabbling in metaphors. 

And now the aforesaid ditty --

With Apologies to J.R.R. ...

I sit beside the fire and knit
And all the sweaters that don't fit --
All the scarves that fall in mud --
Are made right here, although I could
Be off and roaming 'round the Shire!
But I'm afraid that something dire
Will happen if I leave this hill,
So here I am, and I'll be still:
Comfy by my hearth I'll sit...
And dream adventures. While I knit.

 

For a week that's been so quiet, it's also been "eventful" -- if that's a word you'd choose for "social media hijinks." This was the week when my Facebook account was cloned, and people I've known for years have received anything up to FIVE friend requests from me. Naturally, they've been reporting the nonsense left and right, and what does FB do? Assigns an AI to check whatever criteria it uses to make up its dense cybernetic mind, and then calmly tells me, via email, that the cloned about is me. That, in fact, it's me out there, pestering my friends and then complaining about myself to admin, with requests to have myself deleted. Oh ... suuuuure. Sounds plausible, doesn't it? Meh.

So the week turned into a puddle of anxiety which in no way endears me to the whole rat circus of social media. I'm a hair away from dropping the whole thing and walking away. I have a bunch of blogs (which precious few people look at), but Facebook isn't doing much for me lately: it's more of an aggravation than a pleasure. Harrumph.

Anyway -- I did get some painting done. The big project was The Dragon and His Boy, in comic art style. Plus a nice landscape or two, plus a portrait of an elven warrior woman, which derives from AI but was massively painted. Hey, I do that much painting on an image, I sign it. I wouldn't sign something that was right of the AI engine, but the one I use mostly -- Playground -- doesn't often produce images that are good enough to fly solo without a lot of painting. So I get lots of images, but the AI hands me a whale of a lot of work...

Mind you, there's a new AI just debuting at the moment: Imagine.art ... and this one has potential. It's producing images that are not too bad at all, without any work from the prompter. Now, these, below, I would not sign off on, because all I did was dodge and burn, balance, resize and crop...

... those were just too easy to generate. They're simply not my work. So... 

I might look at using Imagine in the future, when/if I have a cash flow. I do need to generate AI elements to be recomposited into complex paintings, and Imagine is certainly doing a decent job of providing them. Right now, 80% of the icons on the site flash up a "coming soon" message when clicked, so ... not yet. I'm not laying down cash before they have it fully functional!

That's all from me, for this post. More soon.

A barbarian, and more ... painting happily

 

As always, not much to say ... just images to share. Trying out new styles of art, flexing the  artistic muscles, seeing what can be done, and how. These are painted half in Photoshop, half in Krita ... the girl and cat is a a fixed-up version of an AI disaster ... I'm really only signing it because I worked long and hard to save it. The mushroom on the forest floor is from a photograph, again ... the barbarian is a first attempt at comic style art. I like it -- I must explore this at some length! 

Next projects ... a cat, for sure; maybe some dragons; perhaps a study of a couple of cute Tawny Frogmouths, if I can work out how to paint feathers, lol. I've "finished" the painting once ... nope. I didn't get feathers, I got fur! I need to go back and have a look at how artists like Natalie Jane Parker, or at least Jody Bergsma, paint feathers, and do it again. I have several rainy days coming up, in which I have nothing much to do but paint, and knit, and do Qigong, so fingers crossed that I can get this worked out!

Sooo, how much is AI, and how much is painting? Okay. I'll show you the kind of "visual noise," the mutated rubbish, AI is likely to hand me. This is what I'm getting ... sure, some people know how to get great images, but I don't seem to be able to make it work, LOL. Overall, I get trash like this -- I posted it at full size; you'll have to view it full size to see what's going on: visual noise. 

So you go and go and go, with AI, and you manage to salvage an element from this, an element from that, and stash them, to be used as part of a painting. In all honesty, 3D is soooo much easier! If I had a tonne of money, I'd just buy a wagonload of props and git renderin'! AI is starting to annoy me ... a lot. I've been mucking about with this for two months or so, and its entertainment value has pretty much palled for me, because (and I'm the first to confess this!) I can't make it work. Now and then I get a good image accidentally; 97% of the time, it's just what you see here: unpredictable, uncontrollable, surrealistic, often nightmarish or monstrous mutation. It's actually pretty disappointing, so you might not hear much more from me about AI art, unless something happens and I miraculously start to get pleasing results. Results that are worth the subscription fees these guys are charging. I'm still using the free sample services, and I'm not exactly inspired to pay bucks for this!

Signing off now, and call it a day. Goodnight to all...

Tarzan in Caprona ... or Fangorn Forest, if you prefer!

 

Have I mentioned that I love my Huion pen tablet? Well, let me mention it again. I looooove my Huion pen tablet! Now, this is the kind of work I've wanted to do got a long, long time, and here we are! The first thing I painted was the background, a few days ago --

Fangorn Forest, as painted mostly in Krita, and a little bit in Photoshop. I was looking at this and thinking, "That reminds me of the Mario Larnaga concept art for the original King Kong" (the one that's coming up to its 90th birthday), which in turn made me think of the art that was done for the Tarzan comics and films, waaaay back when, and this popped into my mind. Noice!

In fact, it's so pretty, I did several different crops:

...that's the full screen version of the art, which I would call "Tarzan's Dark Domain." And in turn, this version made me think how this could make a great wallpaper! So -- here you go, guys, help yourselves and enjoy: this one is 1600x900, which suits my own monitor, and if it doesn't suit yours, I'm sure you have some kind of imaging program that will change the size to something that does. Feel free.

Wallpaper version -- 1600x900 ... help yourself!

While we're in fantasy land ...

I won't lie: this is 75% Lexica, and 25% me (whereas the Tarzan is 100% me, wholly digitally painted, right down to the last blade of grass in the background. I'm still mucking about with AI, but I'll be candid: it's highly frustrating, on so many levels. If I get into that here, I'll be grumbling in an hour's time, and it has as much to do with sexual politics as with the vagaries of AI technology, or even the highly dubious copyright status of pictures generated by a machine. So --

Dangitall, let's just paint:

...and here we are, right back in a world of digital doodling. That's all from me for now. Time to go and organise some dinner. 

Fantasy, guy candy, fun in Photoshop, and a little fiction...

This batch was a real, genuine adventure. To begin with, the portrait of an elf ... Legolas, if you like ... was rescued from a pretty awful Lexica image: parts of a helmet growing out of his head??? Lines and wrinkles on a young, immortal elf??? A beard line, on an elf??!! Noooo way. So -- it looks like, if we want Legolas, we're going to paint! So be it.

The fantasy woman is an amalgam of five different haphazard attempts by Stable Diffusion to get into the ballpark. Armour segments floating in midair, armour pieces growing out of her skin, hands that looked like demented octopi with waving, backward-jointed extra fingers ... argh. Horrrrrible. So again we painted, and then painted some more more: the best face I could get, the best attempt at the costume, the best hair option ... slap it all together, fix the eyes (one iris waaay bigger then the other one, and the wrong shape, to boot!!), remove the crop lines, from where the machine took bits and pieces of various images and stuck them together not quite at random; paint for a couple of hours; put in a new background... end of the day, you bet I'm going to sign off in the image. I work four hours on something, I danged-well sign it. 

The faerie warrior and the fly agaric is an amalgam of a Genesis 8 render I did over a year ago, and a photograph I got with my phone last week. This one was a lot of fun, and also a major challenge, to get the colours and resolutions of the two images to agree. One is a render, the other a phone pic. Even at this late stage, I can honestly say I learned something new in Photoshop. Want the original phone pic, for comparison? Here you go: 

The last image is a painting from a photograph at Carrick Hill. There's this one doorway, or gateway...

 ...and how could you resist! It's just begging to become a painting, and a fantasy at that. Delicious. The trick was to get just the right image for the "beyond" part of this. If this is the doorway to adventure, then it had better be a landscape you can't say no to. So I wrote a little drabble to go with it: 

Edgar had heard many times about the gateway -- and according to the locals who lived around Eltenham Forest, several opened into the earth, or into faraway places. He'd always dreamed of finding one, and last summer holiday he spent most of the time investigating old trees and misty dells, with no luck at all. This year, when he'd given up and wasn't even looking anymore, here it was! Maybe the magic worked this way he thought as he ventured closer, and closer ... the harder you looked, the less you were likely to find yourself a gateway to adventure.

Very close now, he could smell the clean, sharp scents of mountain air and hear the calls of strange birds, unlike any that lived anywhere near Eltenham. A chill breeze wafted from the gate, and tendrils of mist crept cautiously through at his feet. Here at Cricklewood Hall, it was a hot afternoon full of droning beetles and the heavy scent of flowers, but far on the other side of that gate, dawn light cascaded down the east side of a range of dragon-fang mountains, and the smell of pine trees prickled his nose.

He was almost to the gate, dying to step through, when he saw the man on the other side -- and the man has seen him!

So there you have it ... this was my fantasy fix in the last couple of days! I might do SF next, or possibly glam, or perhaps SF glam. I'm sure that's a thing ... and if it isn't, it ought to be. 

Elven hunk or Marvel super-villain? Golly, let me think...

 

This one is a digital painting based on an AI image that was, frankly, alarming -- and there's a story behind this, so stay with me! I've been trying out an engine called Lexica, which is a lot easier to work with than the other three I've tried so far (Wombo, Dreamlike and Playground). Lexica will at least get into the ballpark, even if its people do tend to have fourteen fingers and three legs (rolls eye). But...

I gave it a pretty simple prompt. I asked it for an elf warrior maiden ... and I pretty much got what I asked for, right off the bat. Cool, right? What could possibly go wrong, then, if we decided we wanted Legolas as well? 

Change the prompt to say YOUNG MAN, and MALE, rather than maiden, and surely it ought to just click over into the masculine filters and give me the beautiful young male version??? Harrumph.

No, I haven't signed off on these: I haven't done anything to them, they're just as Lexica handed them to me. On the left, "elf warrior maiden." Okay: good one. On the right -- oh yeah, here we go. Change the parameter from female to male, and it changes from a beautiful young woman to a malevolent old coot with a scowl and a horned helmet! The tropes are alive and well at Lexica, I see. Soooo...

Yep, this was always going to be a painting, although it started with Lexica's closest attempt to Legolas: he still looks like a Marvel Super Villain crossed with Grand Moff Tarkin, with bits of a helmet growing right out of his skull!!!??? But it gave me a place to start painting --

So, three hours of painting later ... Legolas. Gone are the vacuum-sucked Moff Tarkin cheekbones and the scowl, the scarred cheek, and the trenches of lines and wrinkles in his face, and the dumb hairline, and the even dumber helmet horns that somehow sprouted right out of his cranium. Gone is the long, thin face that looks like a 1930s movie villain ... Fu Manchu, anyone? Grrrr. Three hours of painting. You bet your life I'm going to sign this one.

Anyway ... I wanted Legolas, I got Legolas, and AI gave me a good place to start, but ... I give up. I've been looking at the most amazing things that people can get these AI engines to do, but after six weeks I still can't make it work for love or money, LOL. So tomorrow, I'm going back into Krita. If we're going to paint, let's paint and enjoy it, right? Right.

The Festival of Fire - story illustrations

 

Just finished the suite of illustrations to accompany a story ... nice! The Festival of Fire is a "deep outline" of a fantasy tale ... dragons and cats, a magical city, a many-layered backstory ... at around two thousand words. And I might work this up full-length; it speaks to me. 

The art started life as AI rubbish. And I do mean rubbish. Cats with three tails, one growing out of his chest? Dragons with wings sprouting from their heads? Three-legged humans?! Rooftops floating in mid-air??? Lanterns not attached to anything, floating around by themselves?!! Cars buried in the road surface?!! 

Suffice to say, I took each AI generated disaster to pieces and put it back together. That's over ten hours of painting, so -- you bet your dang boots I'm signing off on these images! They're mine now, no matter where they started life. 

If you like fabulous cats and dragons, and fancy a short read about a boy called Tomas and a felix called Tyree, I've posted it to my writing blog ...thanks for looking!

Adventures in digital painting, at any rate ... and a bit of "hybrid" SF...

Progress report of sorts... digital painting progresses nicely: suffice to say, I'm learning a lot. It's fantastic that this version of Krita passes files cleanly back and forth between its own file format and Photoshop -- means I can paint in both, at whim. 

And the experiment to see if we can use AI to generate picture elements for recompositing works, at least up to a point. The SF piece, here is a digital painting till you get to the robot. Duh. The robot was generated as an element by "Dream by Wombo," which is Ma Google's freebie engine. I was able to get a usable robot to use as a picture element, and didn't have to pay forty bucks for a prop! Because, with the best will in the world, I own two robot props, and you've seen them so often, in so many settings and combinations ... meh. So ... okay. AI has its uses in the short term; namely, to save me beaucoup bucks when I need to get an image without a prop. Argh.

Knowing that I need to do this, I am therefore looking at just about every option out there, before I tell my hubby which one I'd like the year's subscription to, for my birthday. So far, I've looked at Lexica, Wombo, Dreamlike Art, and Playground ... Lexica is the best; Wombo is terrifically hit and miss, but it beats the others hands down. Dreamlike should be called Nightmarelike, because it distorts everything and everybody into grotesqueness. I asked it for "a beautiful young Irish girl with long red hair," and it gave me a picture that looked like a still from a horror movie --

Nope. Let's go back to painting! So I, uh, did. These are a blend of Krita and Photoshop, with bits and bobs generated by some computer to save me bucks. 

We're about to pack up for a few days' trip to the Limestone Coast, and when I get back ... I'm going to start up DAZ again, for the first time in over a year. What's more, I'm going back to raytracing for a while, to get canvases on which to paint. Let's see what we can do here! 

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.