I used the following programs to make the video above:
Plus I used other online art programs to generate images in this blog post:
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:
prompts: "Zbrush | In the style of Henry Moore"
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:
"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:
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
prompts: "People occupying a Giacometti space"
prompts: "People occupying a Henry Moore space"
prompts: "People occupying a Piranesi space"
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
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
I used AI (artificial intelligence) again to alter my portrait drawing:
prompts: "Renaissance portrait"
Then I imported the above portrait into Artbreeder:
I used VQGAN+CLIP to generate another variation on my portrait:
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:
Github: Paint by Number Generator
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:
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.
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