Wednesday, 16 April 2025

EXQUISITE STEAMROLLER TESSELLATION Prints

Ethan laser cut some large "hat" linoleum shapes for me -- 20 inches across at the widest -- on April 16, 2025.  We will hand out these big linocuts for artists to carve in Tucson, El Paso and New Mexico -- then piece them together to make big steamroller prints during the Southwest Print Fiesta on October 11th, 2025 in Silver City:





I cut off a half inch to make 35x36 inch sheets of linoleum
so that they would fit in Ethan's laser cutter






70% power, 15 mm/sec speed




We laser cut each 35x36 inch piece of linoleum
into four "hat" shapes
in about ten minutes


Video of the laser cutter in action


Four 20 inch wide "hats"
out of a 35x35 inch square of linoleum








Thank you Ethan!!!!

 And a big Thank You to Brian too, for designing the tessellation pattern than we used to laser cut.


Ethan also laser cut small images into stamp rubber, and even pink pearl erasers, to make stamps:






Tuesday, 15 April 2025

April 15, 2025

Drawn at Art Buddies in Albuquerque:




Xnview>Image>Swap> RBG>GRB




Xnview>Image>Swap> RBG>BRG

Xnview>Image>Swap> RBG>GRB


The Shape of AI to Come -- catching up with AI ART

AI ART is a big blur now, evolving so fast that I can barely keep up with all the new approaches and wrinkles -- and to think, I declared that AI ART was slowing down last November

WAN 2.1 VIDEO


Adam and I generated the AI videos above after "pulling" a Docker Image (28 GIGs) with an AI video generation program -- WAN 2.1 -- on April 12, 2025. More significantly, we generated the videos LOCALLY, on the supercomputer at Quelab, with 10 GIGs of GPU.  

I also uploaded an AI version of a portrait that I drew into the WAN 2.1 Docker Image, and generated the AI video below:

Realistic video on the right,
generated in WAN 2.1 from the image on the left

I had previously generated AI videos ONLINE in KREA-- using WAN 2.1 -- and added them to my YouTube videos:
MCP
The Shape of AI to Come

Recently I have been merely chatting with Blender, to generate 3D scenes using MCP:




Tim set up the Quelab computer so that Claude Desktop would talk to Blender directly, using MCP protocol, following the instructions from the YouTube below:

I even imported a GLB scene I had previously constructed from 3D objects -- that I generated in Google AI Studio -- and added trees and other elements to the 3D Blender scene, by merely having a conversation with Claude Desktop using MCP:

 
The original scene (top) --
I uploaded it to Blender and added the trees (bottom)
by merely chatting with Claude Desktop


NOTE: Generating 3D OpenSCAD code (to make 3D objects after uploading 2D images) is no longer free in Google AI Studio.  April 14, 2025 the free "Gemini 2.5 Pro Experimental 03-25" switched to the paid "Gemini 2.5 Pro Preview 03-25."  

MCP (Model Context Protocol) is a new standard for AI programs to talk to each other and other software, making it easier for us users to use several programs to create a single video or other project.


KREA

KREA let us train 5 free AI models for a week, after they revamped their website on March 31, 2025.  So I trained 6 AI models (one on the paid plan) on my drawings, and altered my drawings with those AI models, and was pleased with the result.  I also subscribed to the BASIC plan for a year:

My figure drawing from an ink pen,
transformed by a KREA AI model based on my drawings

KREA Blog Posts:
Download: Standing__A.SVG  (108.19 KB)

Download: Standing__B.SVG  (116.49 KB)

Colored with AI


Download: Standing__C.SVG  (133.32 KB)

Download "221129__B.SVG"  (30.50 KB)
The original pen drawing


My abstract figure drawing with an ink pen,
transformed into a recognizable figure with KREA AI

Download: Sitting_A.SVG  (207.28 KB)


When I do a reverse search on my AI images in Google Lens, I do not really find anything similar to them.  Am I generating ORIGINAL AI ART?  After all, I'm uploading my own figure drawings, and altering them with an AI model trained on my figure drawings.

However my AI results look a lot like the drawings generated in Doodly.

 

Friday, 11 April 2025

April 11, 2025 -- Portrait

The portrait session on Friday nights is free -- FRIDAY NIGHT FACES -- but the artists had to give their drawings to the sitter. This session was at Art Buddies in Albuquerque:












Holly sent us a 28 gig Docker Image for the WAN 2.1 program, and I uploaded the above image and generated the video below, on April 12, 2025:

Video generated from above image,
using WAN 2.1 inside a docker container

April 10, 2025

We drew at the Edith Bunker in Albuquerque, with Monty Singer and Brian Gonzales.  This was the last session as they were giving up the studio:

Animation of painting progress
















AI VARIATIONS



I uploaded the finished painting
and STABLE DIFFUSION generated this AI variation





In the infinite game of AI Telephone using WHISK -- I uploaded the first STABLE DIFFUSION AI variation above as SUBJECT; and the first image in the Pieces of AI ART blog post as SCENE; and an AI rope image from the Abstract into AI FIGURES blog post as STYLE -- to get the composition below:

Blending AI images in WHISK


COLLABORATION

Brian Gonzales collaborated with me by painting on my drawing from May 4, 2024:




Brian's painting of the model
on April 10, 2025

Brian collaborated with me
by painting on my drawing of May 4, 2024

My original drawing


DRAWING, CARVING, PRINTING

I also drew the same pose, as above and in Brian's collaboration, into a "hat" shaped linoleum tile, carved it, and made EXQUISITE TESSELLATION prints with it:







It's kind of poetic that the last painting session at the EDITH BUNKER dovetails with our next and current big project -- The EXQUISITE TESSELLATIONS.

This was our last painting session
at the Edith Bunker Art Studio