Thursday, 30 September 2021

September 28, 2021

The Tuesday Night drawing group of Santa Fe drew together online using Zoom, because of the Covid 19 quarantine.  The model was from the Washington DC area.




Evolution of the process --
scanned pencil line drawing,
Petalica Paint coloring,
style transfer in Deep Dream Generator





The VQGAN programs all started with this first image,
but none produced anything I liked after that


HOLOGRAM

UPDATE: (October 6):  Adric brought a hologram display unit to Quelab makerspace last night -- the LOOKING GLASS FACTORY Portrait HOLOGRAM display -- and we tried to upload some of my artwork to it, to see my art in holographic 3D.  The company said that this unit would accept 3D GLB files;  however it looks like one needs to convert those files using the Looking Glass Factory software, and that did not work for us (yet).

We did manage to upload my portrait drawing as a JPG, and view it in holographic 3D.  The face broke up into 3D pieces -- that is, the hologram display did not show the face as a coherent unit -- however this fragmented artifact effect is more interesting, and more what I aim to express.


My portrait drawing viewed in 
this photo does not show the effect
of the individual pieces in 3D


The treatment in Photoshop Elements 2021 (Enhance/Moving Photos.../Counterclockwise) gives the more coherent 3D effect which I expected to see in the hologram display:  
 

A more coherent 3D effect
created in Photoshop Elements 2021


Again, the exploded 3D pieces in the face are more interesting, and more in sync with how I created the portrait.  I explicitly applied the "style" of a 3D fragmented figure (below) in Deep Dream Generator, to give volume to my line drawing.  I created the "style" figure image in Paint 3D:

I applied the 3D "style" of this January drawing
created in Paint 3D,
to my portrait line drawing,
in Deep Dream Generator


I mentioned the Looking Glass Factory hologram display back in February, back when Adric told me that he had ordered it on Kickstarter.  I think it cost him a bit less than the $299 that they are asking for now



UPDATE (Oct 27):  I converted the portrait into a 3d file on 3D This.


More CLOUD People


Evolution of the process








Evolution of the process








Evolution of the process








John Tollett's drawings from the same session



Southwest Print Fiesta
Print Exchange

I finished my edition of 45 prints on the tortilla press, for the Southwest Print Fiesta Print Exchange 2021.  The image was from a figure drawing I did on August 31st, 2021. While I did "overnight" it late, it did not make it right away, and barely got to Silver City on time.





The collaborative print from Tres Gatos Press from Guadalajara in the Southwest Print Fiesta Print Exchange 2021.


OTHER

Santiago Perez has a great show at the Tortuga Gallery in Albuquerque -- Santiago's Flying Circus presents the Big Head show.  The opening was on Friday, October 1st, 2021.

at his opening in the Tortuga Gallery


This year the balloons all flew over my house at about 8 AM, Monday morning, October 4th.  This is part of the annual Albuquerque International Balloon Fiesta.

The red white and blue balloon
would fly directly over my house


Wallkanda  -- street art website


Artist Jens Haaning delivered two blank canvases instead of his commission, after the Kunsten Museum of Modern Art in Denmark fronted him $84,000.  He entitled the new work "Take the Money and Run."

Maybe this is the NFT version of "Take the Money and Run," as it is zero pixels.



September 21, 2021

The Tuesday Night drawing group of Santa Fe drew together online using Zoom, because of the Covid 19 quarantine.





Style transferred from a drawing
previously converted into the style of an Aubrey Beardsley 


The above figure was converted into the watercolor-like image below using the VQGAN+CLIP text-to-image program, entering "Sitting woman figure."  Of course the result looks nothing like my drawing.











Style twice removed from Aubrey Beardsley






























Me and Mondrian

This drawing below is rather vague and sketchy, but I can still feel the weight and attitude of the model.  As an afterthought I felt it was blocky, and reminiscent of Mondrian.  So I used two text-to-image programs to add some Mondrian:

This blocky sketch
reminded me of Piet Mondrian


A)  In AI Art Machine I entered "In the style of Mondrian" and used the URL of the above image as the "style_URL."  Then I took the last image result and applied that fake Mondrian style to the original drawing using Deep Dream Generator.

p:  "In the style of Mondrian" -- middle image;
then I applied the Mondrian style to my original drawing


The final result after the two step process:



B)  I wondered how another text-to-image program would handle the input "In the style of Mondrian," and VQGAN+CLIP created something entirely different:



C)  So I decided to combine the results by applying the style of "B" to the first image "A," in Deep Dream Generator, and got the best Mondrian result:


I applied the style of the middle image
to the first image
and the resulting last image
was the best Mondrian expression


Best Mondrian result


RELIEF PRINT

I am trying to carve a relief print of the last pose of the session:




Before I finished carving I ran the above image through a VQGAN+CLIP text-to-image program, using the text "Print in the style of Mexican printmakers."






OTHER NOTES

Erin Currier had an opening at the Blue Rain Gallery on September 10, 2021:






Holly Grimm directed me to an upscale resolution Colab program online -- Real-ESRGAN Inference Demo(--face_enhance)

AI Art Machine (another text-to-image Colab online


Charles Townley came to Albuquerque to buy three Desert Triangle prints -- by Zeke Peña, Mykl Wells and Tanya Rich.

Victor and Charles Townley
at VM Coffee in Albuquerque
September 27, 2021

He also told me about a new book from Duke University -- Chicano and Chicana Art.

Wednesday, 8 September 2021

September 7, 2021 -- Spatial

The Tuesday Night drawing group of Santa Fe drew together online using Zoom, because of the Covid 19 quarantine. The model was from the Washington DC area.




I used the following programs to make the video above:

Plus I used other online art programs to generate images in this blog post:

SPATIAL

I referenced famous sculptors with AI in order to ultimately create spaces that I could imagine walking into.


Base pencil drawing "initial_image" input
to generate the shallow spaces pictured below


I altered the above drawing several time in the "text-to-image" program VQGAN+CLIP, changing the input prompts:


YANDEX and Google similar visual images


YANDEX and Google visually similar images



Different programs, very different results


I used the SAME TEXT -- "A Giacometti figure walking into infinite space" -- in Abraham.ai, a kind of crowdsourcing "text-to-image" generator, but the result came out very differently:


YANDEX and Google visually similar images
"A Giacometti figure walking into infinite space"


I continued to use the SAME TEXT in a different  "text-to-image" VQGAN program -- AI Art Machine:


YANDEX and Google visually similar images
Same prompt "p":  "A Giacometti figure walking into infinite space"


Note:  Neither of the above two different VQGAN programs allowed me to input an initial image -- both of them were completely "text-to-image."



I then combined TWO of my drawings and the final result was better (note that this source image is a square, the dimension that the VQGAN program uses):

Base "initial_image" input
to generate the spaces pictured below


YANDEX and Google visually similar images
Englarge (1792 x 1792, 4.33 MB):  Giacometti_less.png


YANDEX and Google visually similar spaces
prompts:  "People occupying a Henry Moore space"


YANDEX and Google visually similar images
prompts:  "People occupying a Piranesi space"



STYLE TRANSFER
Deep Dream Generator


I transferred the style of an image I created earlier this year in Paint 3D to some of my figure drawings using DEEP DREAM GENERATOR:


The style of this image (made in Paint 3D)
transferred well to the
six different figures below





YANDEX and Google visually similar images



I took some advice from Steve's Makerspace YouTube, and made sure that both the style image and the target image had black backgrounds.

I inverted the drawing 
to make the background dark 
before importing it into Deep Dream Generator


YANDEX and Google visually similar images



YANDEX and Google visually similar images


YANDEX and Google visually similar images







PORTRAIT ALCHEMY

I used AI (artificial intelligence) again to alter my portrait drawing:

Scanned raw pencil drawing
and base "initial_image" input
for the images below


Altered in VQGAN+CLIP:

YANDEX and Google visually similar images


Then I imported the above portrait into Artbreeder:


YANDEX and Google visually similar images


Paint by Numbers

If I simplify this result above, I might be able to make a serigraphy edition of the AI artwork.  I used three Paint by Numbers programs to reduce the AI portrait into 4 colors:

YANDEX and Google visually similar images






COMBO

YANDEX and Google visually similar images



16 colors



4 colors




CLIP Guided Diffusion HQ

There seems to be many  "text-to-image" variations on the "VQGAN approach.  The CLIP Guided Diffusion HQ is posted on Hugging Face.

I uploaded both the "initial image" and "image prompt" -- the top two images in the collage below -- to the program on Hugging Face, and typed in the text "Walking through the street aimlessly," to get the resulting ambiguous image on the bottom:



Video --




RELIEF PRINT

I drew the last post on a 7 x 7 inch square of expanded PVC, and cut and printed the plate immediately after the drawing session, on the Tortilla Press.




AI variation



PHOTO BOX

Ethan Moses brought his homemade camera/dark room to Quelab on September 8th, to take and develop photographs.  The ingenious system worked quite well, and Ethan took flattering photos of everyone.


Ethan Moses taking my photo




I'm developing the  photo
inside the box