Skip to main content

Sunday Morning Coffee with AI. . .

 

 

Armed with a second cup of fresh, strong coffee, I messed around a bit this morning with artlist.io using its image to image function in an attempt to convert my hand-drawn map from September 2006 to something that more resembles an old map from the mid-18th century.  And just like my experiments with Ninja AI in June, the results are mixed.  

The above map is pretty good, but Artlist keeps fouling up the place names and has trouble putting a faint overlay of hexes across the entire area.  Hexes, admittedly, are not likely to be found on any genuine maps from the era in question, but there we are.  Frankly, I prefer the appearance of the Ninja map, but there were problems getting it to correct its errors.  Grrrr. 

As is the case with so much having to do with the various AI's out there now, the output generated is a direct result of the prompts entered.  For text alone, and when you develop a lengthy, highly detailed prompt, it is possible to get a reasonably good rough draft  to further revise yourself.  I've used Gemini, Claude, and Copilot to help with podcast scripts and things like lesson plans, refinement of student assignment prompts, grading rubrics for those same assignments, and the like.  But, when you spend that much time developing a two- or three-page prompt for the AI in question to (hopefully) get something useful back, you might as well just develop the document yourself.  Agreed?

For working with images, I am sure there must be a way to get the results I am after, but for now I find artificial intelligence to be kind of like a slightly dim child.  Eager to please, but hitting the mark only about 70% of the time.  Come to think of it, that rather stark assessment is probably true for most of us.  We get it right about two thirds of the time and skin our knees or drop the ball the rest of the time.  That's certainly the case for me.

Sadly, I have some real work to do now for an upcoming departmental fall kick-off in a little under three weeks on the 22nd.  Sigh.  So, further map experiments will have to wait until another time.

-- Stokes 

Comments

pancerni said…
Two of three in baseball is pretty much unobtainable.
2:53 PM
caveadsum1471 said…
Sometimes you find it's easier to get a result yourself without relying on technology, but then I'm clearly something of a luddite as the only one still on a drawing board in the office while everyone else is draughting on a computer, it does feel a bit like the song where the chap with the hammer is trying to keep up with a steam hammer but just keeping up at the moment!
Best Iain
5:16 AM
Rittmeister_Krefeld said…
Hi, have you had a look at Azgaar? Not AI, but very easy to use and draw your own maps and hexes are a breeze:
https://azgaar.github.io/Fantasy-Map-Generator/

7:35 AM
Post a Comment

Popular posts from this blog

And We're Off!!!

  Arrrgh!  Gotta go back into camera settings on my iPhone to bring all of the frame into focus.  Blast! Painting is underway on the 60 or so Minden Austrians, which are slated to become my version of the Anhalt-Zerbst Regiment of AWI renown.  More or less indistinguishable from Austrians of the era really, right down to the red facings and turnbacks, but the eventual flags (already in my files) will set them apart.   I went ahead and based-coated all of them over a couple of days lthe last week of August, using a mix of light gray and white acrylic gesso, before next applying my usual basic alkyd oil flesh tone to the faces and hands.  In a day or two, I'll hit that with Army Painter Flesh Wash to tone things down a bit and bring some definition to the faces and hands.   As usual, the plan is to focus on about 20 figures at a time, splitting the regiment roughly into thirds along with the color party and regimental staff.  Depending on ...
6 comments
Read more

The 18th century? What's the Fascination?

Hessian musketeers by All the King's Men Toy Soldiers of Snellville, Georgia, U.S.A. Just a quick post post today, but I thought the above question might be interesting food for thought. Obviously, there is an array of possible periods, theaters, and conflicts that might catch our eyes. But what is it about the era 1700-1799 -- either real, or imagined? Is it the commanders and politics? The fairly straightforward tactics? The myriad of uniforms and flags? The variety and scope of the conflicts? The patchwork of various and sundry petty states, (at least in Central Europe)? I'm very interested to learn your thoughts. Don't be a lurker! Please leave a comment -- or even two or three. Have a nice day everyone!
35 comments
Read more