Tuesday, 5 March 2024

March 5, 2024

We drew and printed at Sir Henry Morales' studio in Albuquerque:










PRINTS

Cassandra made a single celebrity cut on the BIG INK print:


Cassandra making a celebrity cut















STAMPING FOAM

We transferred a linocut image into Stamping Foam again, like we did on June 22, 2023:

Linocut transferred into Stamping Foam


Virgil first heated up the Stamping Foam with the highest setting on our heat gun:

Virgil heating the stamping foam
with a heat gun


Then we pressed the linocut into the Stamping Foam until it cooled.  We got the best transfer when we actually stepped onto the "Linocut and Stamping Foam" sandwich (after putting a piece of wood on top):

This transferred worked well,
though the image was not clear to begin with


Then one just has to pat the Stamping Foam into some ink, and then press the inked Stamping Foam onto paper:



Henry inked the stamping foam with a roller, but that was probably too much ink:



Print and inked Stamping Foam


The first print

Thin sticky ink seems to work best.  I left the ink out for a day the last time we tried Stamping Foam, and that worked really well.

Also we need to think about the image.  Like linocuts, the best images probably have a fairly even distribution of black and white throughout the composition (unlike with the figure image above on our first try).  

Plus the linocut has to be a "negative" image, as that will transfer into a "positive" into the Stamping Foam.  The linocut image also has to be "flipped horizontally."

If done properly, the Stamping Foam will accept and print very fine textures from the linocut...and might even print better than using a press.


Monday, 4 March 2024

March 4, 2024

Drawn at Art Buddies in Albuquerque:






























AI ART Grousing

I was complaining how the AI ART programs are generating the mundane:

February 2024: "The irony is that I get less and less satisfaction as the AI Art programs get more and more powerful. It seems that they are all pushing more and more for the same archetype -- an anime version of Taylor Swift -- and away from my drawing style..."


It's like AI is pushing us harder and harder into bland GroupThink.


Last year I wondered if Midjourney was "training" on the images that we were generating -- which is known as "training on synthetic data."  

December 13, 2023: "Does Midjourney "train" on the images I generate in their Discord? The next step of AI is to "train on synthetic" data, generated by AI...but will that mess up the results?"

Wouldn't that eventually lead to very inbreed results -- Habsburg AI? Sabine Hossenfelder thinks so:


I played on this groupthink/inbreeding idea in August 2022: When I made an AI version of "America's Most Popular Painting," playing off Komar & Melamid's project -- "The Most Wanted Paintings on the Web."


That's why I think "training your own AI model" (like I did in Leonardo.AI, and later with the long poses) is the way to get ahead with AI ART generations.  However perhaps I also need to write my own Art programs, like I did with GPT 3.5.

***
Sigh..was AI ART more exciting in 2022?


***

And now Claude 3 just came out from Anthropic, boasting that it it better than GPT 4.