Authentically Human! Not Written by AI!
All Content Copyright © Michael Chesley Johnson AIS PSA MPAC

Saturday, December 31, 2022

AI and the Painter, Part 2: A Path Forward

View in browser

"Cottonwood Days" / 12x16 Oil
Based on AI-generated image

In my previous post on AI (Artificial Intelligence), I wrote about what AI image generation is and how it works.  In this post, I'll share an idea of how AI may be useful to what I call the "get your hands dirty" painter.

First, let me say that, for me, AI can never replace what I do as an artist.  Making art is all about touch—holding a brush or pastel stick, stirring a pile of paint with a knife, drawing an expressive line with a lump of charcoal.   You get none of this tactile satisfaction when you feed prompts to an AI.

Yet I have a curious mind, and recently I wanted to see if the technology could help an artist like me.  In the studio, I use reference material gathered in the field—photographs, pencil sketches, color studies—to create a work that is more "considered" and finished than a painting I can do en plein air.  Would it be possible to use an AI-generated image as another reference for painting?

I proposed a process:  Submit a few field references to the AI along with a text prompt describing the scene, and then use the generated image to paint from.

On Midjourney, the AI platform I'm experimenting with, there's a large community of artists.  Most of them, it seems, work purely digitally and using text prompts only.  (A text prompt might go something like:  "Dragon and mountain from Tolkien, intricate details, Frank Frazetta style." See below for the result.)  Others feed the AI sketches along with text prompts and then fine-tune the result through image editing software like Topaz.  After an informal poll of users, I determined that few or none are doing what I wanted to do, which is to use the generated image as a reference for painting in traditional media.

Here's the grid of four images generated by the Midjourney AI from the dragon prompt.  Interestingly, there seems to be a signature on the top left image—a telling clue, letting us know that parts of the image may have been scraped from the Internet from another artist's work.  Or did the AI add it all on its own?

Prompting with an image is easy.  Prompting with text, not so much—especially if you want to send the AI down a certain path.  You can get all kinds of wacky, nightmarish results if you don't consider carefully your choice of words.  Although there's an abundance of documentation on using Midjourney, I will say that this platform is not for the novice computer user.  Even with many years as a systems analyst, programmer and all-round computer geek (yes, I had a life before art), I found the learning curve steeper than I had hoped.  I won't get into all the technical bits here, as that's not my goal.  But I do want to share with you the process and the results of two experiments.

Experiment 1:  Image Prompt (color study, pencil sketch) + Text Prompt

Here are the two images submitted, one a color study, the other a pencil sketch:

Here is my text prompt:
impressionist oil painting of a rocky cliff with faint candy stripes situated by a calm lake, clouds bathed by sunset light 
Here is the first result, a grid of four images:

I decided not to paint any of these, as they are too different from the actual scene, which is more accurately depicted in the color study.  I also thought the trees were a little strange, if not downright frightening.

Experiment 2:  Image Prompt (color study, photo) + Text Prompt

Here are the two images submitted, one a painting, the other a photo:

Here is my text prompt:
cottonwood trees, autumn, impressionist style oil painting
Here some results, grids of four images:

I decided to take these three: 

And referred to them in creating the following painting in oil:

"Cottonwood Days"
12x16 oil

I like the painting I made, and I think the experiment was successful.  But honestly, I might have been able to do pretty much the same by just looking at fine paintings of scenery on the web or in Southwest Magazine if I truly needed the inspiration—and I wouldn't have had to learn how to write a useful text prompt.  Will I use the AI in the future?  Probably not, but if this sort of thing interests you, go for it.  Let me know how it goes.

No comments: