Tucson Sculpture Festival 2012

▼

Wednesday, 28 February 2024

FEBRUARY 2024 -- SUMMARY


Virgil, Ellie and Henry are making great progress on their large collaboration woodblock, and will easily have it ready by April 13th when BIG INK comes to town:

The big woodblock collaboration
by Virgil, Ellie and Henry,
for the BIG INK project


PRINT EVENTS

I got very confused and had to write about all the upcoming print projects on the BUCKET EXHIBITIONS blog:


They started making silk screen prints at Quelab:

Clara and Aaron
 making silk screen prints at Quelab


We started the month printing when Brian brought his LEGO Press to Quelab:

LEGO Printmaking
Brian constructed this LEGO press
to print bookmarks


Remarque Print Workshop is moving next year in 2025, from their current location on Central Avenue to the old Tortuga Gallery  On February 4th they had a work party to spruce up the Tortuga Gallery location:

February 3, 2024
Remarque work party
painting the front room at the Tortuga Gallery


3D Prints

Someone brought in ceramic 3D prints to the 3D Printer Meet Up at Quelab on February 18, 2024:

3D Print Meet at Quelab
Ceramic 3D prints
plus the homemade ceramic 3D extruder



State of AI ART

AI ART shifted into some odd territory in February.  Most blatantly Google's AI refused to generate images of white people with it's new GEMINI AI program.


MIDJOURNEY

My issues were more personal as MIDJOURNEY refused my payment again (I think this is a "Stripe" issue). I like Midjourney because it allows me to "BLEND" two images to generate something entirely different. At least I got to try out Midjourney's new Style Reference feature, which they released about February 1st.

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. I noticed this agenda long before Google refused to generate images of white people.
Most excellent AI version of Taylor Swift at Super Bowl LVIII
throwing the winning touchdown pass this month
(no team would sack her)


IMAGE MIXER

I found another program that will "blend" images -- Hugging Face: IMAGE MIXER.  Moreover this program will accept my figure drawings (whereas Midjourney often rejects them for being NSFW).  However the Image Mixer results are not very good when I "blend" two of my raw figure drawings together:

My drawings don't "blend" well in AI


IMAGE MIXER "blends" better with more robust images (but still not as well at with Midjourney), but does much better with text-to-image prompts:

Two robust images "blended" in Image Mixer


Two robust images "blended" in Image Mixer


LEONARDO.AI

I like LEONARDO.AI best for translating images into my drawing style, when I use the model "KrrrlLong" based on my long drawings.

The best results come after I upload a photo or sculptural image into Leonardo.AI, and it transforms that image into my drawing style:

Leonardo.AI Tinkering
Leonardo.AI
PIKA LABS
EzGif


However Leonardo.AI doesn't seem to work as well when I upload one of my drawings, and try to alter that with "KrrrlLong" (the Leonardo.AI model based on my long drawings).  I can generate something interesting, but it used to be a lot easier in the past, before they started charging for the more powerful features:

Leonardo.AI Tinkering
November 1, 2017
Leonardo.AI
It took a lot of extra generations in Leonardo.AI
to transform the drawing on the left
into the AI figure on the right


With "Alchemy" (a more robust Leonardo.AI model) I can transform my drawing into a Bernini sculpture.  Then when I "refry" or upload the robust sculptural Bernini results, I generate better figures from the model based on my drawing style:

January 27, 2024 -- BERNINI
Top:  My drawing converted into a Bernini sculpture
Bottom: The top image uploaded and "refried"
with a model based on my drawing style


GOOGLE  SEARCH Generates Images
(with SGE turned on)

I generated images in Google after turning on SGE:

February 21, 2024
The images that Google generated
were not as good or accurate
as those generated in other AI programs


GROQ Fail

GROQ is a new kind of AI program using an LPU chip, to compete with ChatGPT4 and Gemini using GPU chips.  However when I asked what kind of my drawing was -- it partly answered with "features vibrant, gradient-style colors and subtle shading"  -- but there are NO COLORS and shading in my drawings:

February 23, 2024 -- Portrait
GROQ gave the wrong answer,
at least in part

  • After I used GROQ on February 24th, they now make you sign in to ask questions of their AI.

PERPLEXITY Win

Perplexity gives a better answer



VAPORWARES

Also the AI Art YouTubers -- like Matt Wolfe, Curious Refuge, and Theoretically Media -- are coming out with more and more content, but with less and less programs that I can use.  A lot of the new developments are behind paywalls now, but the content is leaning more and more towards speculation -- such as about the SORA AI video generator, which we do not have access to yet.


🎵IN FIVE YEARS🎵

Yes, in other news, AI is primted to eliminate programmers in 5 years.  In this perfect world, everyone will be able to program using everyday English.  Maybe I'll be able to refine my bad drawings using ChatGPT∞, simply by articulating what I want to happen.  But then what will happen to all those wealthy programmers keeping prices high for the rest of us?


SOFTWARE

Most Used Programs:
3D:
Holograms (on the Looking Glass Portrait display):
***

Quelab was served with a 90 day notice to vacate the premises on February 24th; however arrangements were made to remain in the building.  We are still renovating and recovering after the 2nd flood last December.

It seems that I did a lot more stuff in February, when I thought I was just trying to keep up...
at

No comments:

Post a Comment

Note: only a member of this blog may post a comment.