August 24, 2021 -- VQGAN+CLIP -- Abraham AI

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

Krrrl Drawings Playlist

Krrrl Drawings from August 21, 2021

witih VQGAN+CLIP

SEATED LEANING FIGURE

Note that the first three images have been enlarged for printing, and are found on the "Enlarged Images" page.

YANDEX and Google visually similar images

Enlarged (5041 x 6142, 9.83 MB):  GIGAPIXEL__002.jpg

I altered my pencil drawings using AI (artificial intelligence) in the VQGAN+CLIP programs (using the then default database "imagenet_16384" I believe). The 14 images that follow are based on my seated leaning figure drawing above:

AI variations of my drawing

YANDEX and Google visually similar images

Enlarged (3176 x 3144, 11.38 MB):  GIGAPIXEL__003.png

Fake EGON SCHIELE

text:  "portrait of crypto degen | Egon Schiele"

YANDEX and Google visually similar images

Enlarged (1400 x 1400, 3.55 MB):  Hollyupscale.png

Enlarged (3128 x 3167, 11.95 MB):  GIGAPIXEL__001.png

Fake MOEBIUS

text:  "portrait of crypto degen | Moebius"

YANDEX and Google visually similar images

Fake EGON SCHIELE AND MOEBIUS

text: "Human figure in the style of Egon Schiele and Moebius"

YANDEX and Google visually similar images

Fake AUBREY BEARDSLEY

text:  "Thicken lines in the style of Beardsley"

YANDEX and Google visually similar images

Fake AUBREY BEARDSLEY

text:  "portrait of crypto degen | Thicken lines in the style of Beardsley"

YANDEX and Google visually similar images

Fake ART NOUVEAU

text:  "In the style of art nouveau"

YANDEX and Google visually similar images

Fake ART DECO

text:  "In the style of art deco"

YANDEX and Google visually similar images

Fake TAMARA de LEMPICKA

text:  "In the style of Tamara de Lempicka"

YANDEX and Google visually similar images

Fake DIEGO RIVERA

text:  "In the style of Diego Rivera"

YANDEX and Google visually similar images

Fake OTTO DIX

text:  "In the style of Otto Dix"

YANDEX and Google visually similar images

Fake ROBERT WILLIAMS

text:  "In the style of Robert Williams"

YANDEX and Google visually similar images

DEEP DREAM

text:  "Deep dream"

YANDEX and Google visually similar images

MOST UNUSUAL DRAWINGS STYLE

text:  "Most unusual drawing style"

YANDEX and Google visually similar images

IN THE STYLE OF PRINTMAKING

text:  "In the style of printmaking"

SITTING FIGURE

The sitting figure drawing below lead to three variations in AI (the first shown at two different levels of development):

I first converted this figure into a square image so that the AI program does not distort the proportions.  The program first converts the image into a square before it continues with the AI treatments.

First converted into a square image

text:  "In the style of Sir John Everett Millais"

YANDEX and Google visually similar images

Fake SIR JOHN EVERETT MILLAIS

text:  "In the style of Sir John Everett Millais"

(first generation)

YANDEX and Google visually similar images

Fake SIR JOHN EVERETT MILLAIS

text:  "In the style of Sir John Everett Millais"

(second generation)

YANDEX and Google visually similar images

Fake ROGER DEAN

text:  "In the style of Roger Dean"

YANDEX and Google visually similar images

ARCHITECTURE

text:  "In the style of architecture"

text:  "In the style of architecture"

RECLINING FIGURE

The reclining figure drawing below was also altered in the VQGAN+CLIP AI program, and in Infinite Patterns and Deep Dream Generator:

Photoshop Element 2021

This drawing was distorted first

in Photoshop Element 2021

Filter/Distort/Liquify...

YANDEX and Google visually similar images

BAD ART

text: "bad art"

INFINITE PATTERNS

I also altered the high resolution version of the reclining figure using a Google AI experiment -- Infinite Patterns Colab notebook -- by the guy who designed Deep Dream Generator, Alexander Mordvintsev:

This infinite pattern

seeded with my reclining figure drawing

Then I applied the style  of that pattern to the reclining figure drawing in Deep Dream Generator, and further altered it in XnView:

Deep Dream Generator

XnView

Still needs work,

after using two AI processes on my drawing

Pen Drawings

colored by Petalica Paint

ABRAHAM.AI

I created the following images in Abraham.ai using only text-to-image:

YANDEX and Google visually similar images

 text: "Cafe scene in the style of Tamara de Lempicka"

(second try)

YANDEX and Google visually similar images

 text: "Cafe scene in the style of Tamara de Lempicka"

(first try)

I entered the same text twice (because I thought the system didn't work the first time), and was surprised to get the two different images above.

The first image I created in Abraham.ai was horrible:

text:  "Drawing the human figure on Tuesday Night"

Abraham.ai is a strange collective approach to creating text-to-image art, created by Gene Kogan:

 

Abraham is an open project to make an autonomous artificial artist, a crowd-sourced AI that generates art.

I needed a Metamask Ethereum wallet to participate in Abraham.ai:

• 0xB06614BD2B97F14a47112D0673f7FCE35A998AB8

• Abraham Discord

• Gene Kogan also authored this Google Experiment -- What Neural Networks See

• The VQGAN+CLIP programs seem to download images from ImageNet.  That is probably why the AI program works best when referencing better known artists.  Perhaps downloading the WikiArt database would tap into more diverse artistic styles. 

• Screen Saver World

• Deep Dream Generator tutorial video

Animated Figure GIFs

This is a 3 minute movie of the GIF files I made of my figure drawings over the past year:

Krrrl Drawings Playlist

KRRRL GIFs

Nice soundtracks to this video would be:

• Tim Hecker -- Sleep Mix
• Boards of Canada -- Sundown
• Eno -- Music for Installations

I was very pleased to discover that Windows Media Player would make videos from animated GIFs.

August 17, 2021

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

Petalica Paint

Petalica Paint

Petalica Paint

Petalica Paint

Petalica Paint

 VQGAN+CLIP: "In the style of Giger"

I altered the drawing on the left

with the VGAN+CLIP program

Petalica Paint

VQGAN+CLIP: "In the style of Moebius"

I altered the drawing on the left

with the VGAN+CLIP program

Photoshop Elements 2021

Deep Dream Generator

I appropriated the style 

from a faux Egon Schiele image I generated in VQGAN+CLIP,

to transfer to the red/brown drawing on the left,

using Deep Dream Generator,

to create the image on the right

Deep Dream Generator

Deep Dream Generator

• Drawings from the same session by John Tollett

KOMASUKI

Knife

I drew and cut into Expanded PVC Foam again.  I hated the drawing and the outcome -- however for the first time I loved using the cutting tools. High quality knives make a big difference (need oil)!

Failed relief print,

but making progress  --

the Japanese Komasuki knife (upper right)

is a real pleasure to cut with

Different AI Programs

Faces

Artbreeder -- I used this AI program to create fake women that don't exist.  This program also creates fake landscapes, buildings, albums covers, etc..

Artbreeder

Created in Artbreeder

(without any input of my drawings)

In Deep Dream Generator, another online AI program, I transferred a different style to the faces above:

Deep Dream Generator

Nvidia's Inpainting Demo -- I further altered the image above using this AI program:

Nvidia Inpainting Demo

But is it ART?

• Erica Marin was promoted to the Director of the El Paso Museum of History

• Random Creature Generator for Blender

• I was remembering when I met the Polish poster artist Mieczysław Górowski in Austin

• Masks are being mandated indoors again in New Mexico on Friday, August 20th, due to the rise in Delta Covid infections

More fun with VQGAN+CLIP -- Sculptural

Inspired by Matteo Rattini and his Sculptures that don't Exist, I ran some of my Paint 3D drawings through VQGAN+CLIP, aiming to get a more sculptural effect:

Krrrl Drawings Playlist

Krrrl Drawings pushed towards sculpture

with VQGAN+CLIP

Similar images from: Google and YANDEX 

texts: In the style of Henry Moore

Similar images from: Google and YANDEX

Further altered by Deep Dream Generator

March 23, 2021

3D source drawing

 for the two images above

Similar images from: Google and YANDEX

texts: In the style of Henry Moore |V-Ray |Unreal Engine |Hyper-realistic

June 1, 2021

3D source drawing

 for the image above

Similar images from: Google and YANDEX

texts: In the style of Henry Moore |V-Ray |Unreal Engine |Hyper-realistic

March 16, 2021

3D source drawing

 for the image above

Similar images from: Google and YANDEX

texts: In the style of Henry Moore |V-Ray |Unreal Engine |Hyper-realistic

Further altered by Deep Dream Generator

May 4, 2021

3D source drawing

 for the image above

Similar images from: Google and YANDEX

texts: more complex

Similar images from: Google and YANDEX

texts: loops

Further massaged in

 Photoshop Elements 2021, edited in Layers

March 9, 2021

3D source drawing

 for the two images above

Similar images from: Google and YANDEX

texts: more complex

April 13, 2021

3D source drawing

 for the image above

Artbreeder

The first image in this blog post was uploaded and altered in another AI program -- ARTBREEDER -- where now everyone can tweak it and download different variations, like the one below:

The first image in this blog post

uploaded and altered in Artbreeder  --

Click THIS LINK to alter it some more

• YANDEX is the Russian search engine, and it usually gives me the best selection of "similar images."  The YANDEX links above each image in this blog post, are specific "reverse image searches" to that image.

• The previous blog post shows off how VQGAN+CLIP altered some of my other drawings.

• Idea: I could enlarge a few images in the AI program waifu2x, and then print a few of these images out large on the big printer at Quelab and have an interesting pop-up exhibition of FAKE ART.  I did that for the "Our Existential Space" exhibition.

• This sculptural AI reminds me of the animations of Esteban Diacono and Extraweg

• Nvidia Art Gallery

• Nvidia AI demos

• Links to a few of my other sculpture projects

There is a way to blend VQGAN+CLIP with the Visions of Chaos software (instructions here).