A.I. and ArtRage

[alkratzer]

Portrait generated with Artificial Intelligence, layered style transfers and ArtRage chalk embellishments.

99615

[sabena]

Wow very good work congratulation alkratzer

[eighty+]

Hi alkratzer great painting. Have you just come back ? As I seem to remember Your name from THE PAST OK. CIAO. EIghty +

[Enug]

This is such an interesting painting. Tell us more about AI.

[ENCHANTER]

Amazing stuff here!

[D Akey]

The final effect of the painting is stunning. The word that comes to mind is 'Esoteric' in part because of the your alchemical shorthand in the description, and partly because the painting shows a more sweeping glide into the arching rainbow world revealing a point where sonic and visual vibration cross paths.

It strikes me as if the arc of a rainbow was the prismatic groove of a hidden song, like the sun burst through revealing an Aquarian palette and you set up an easel for some not so plein aire painting.

Nice to see you again. Your paintings are like a rainbow in the desert. Nice one, Al.

[Alexandra]

Beautiful work, good to see you Al!

[alkratzer]

This landscape and the portrait posted earlier were created using a number of steps that start with generating an image using machine learning. Basically, computers are trained on 1,000s of images of faces or landscapes and "learn" the key elements of each to be able to generate new unique "photos" of faces or landscapes that never existed in the real world.

The technical term for this type of Artificial Intelligence is called "Generative Adversarial Networks" (GANs in acronym speak) The "generative" part is obvious, but the "adversarial" part is in reference to part of the training process. Two computers are given the same set of images and then the first creates "new" images and the second one looks at the results and accepts or rejects it based on if it was a successful rendition of a face, landscape or whatever. over many passes, Accepted and rejected images "teach" the first computer to get better at generating believable images. Once you have an initial image, it can be adjusted and tweaked on a number of parameters -- "more trees, less trees" or "smile, no smile" and the like -- until you are satisfied with the result.

The second step to the process involves a different Artificial Intelligence method call "Neural Networks" which are attempting to teach computers to "see" as humans do. It is sometimes called "Texture Mapping" because computers don't see depth, just pixel patterns on a flat surface. If you have ever used one of those apps that make your selfie look like Van Gogh painted it, you are using that technology. The computer has mapped numerous examples of an artist's work and then can "transfer" that style onto any other image. You can do this process using many images or even just one. By taking the generated image from step one you can use step 2 to transform its look. By creating custom collages of example textures you can create personal styles. Some of you might notice that the face posted earlier still looked like some of my earlier work. That is because I choose transformation styles that appeal to my sense of color, brush stroke and the like.

Step three involves creating multiple style versions of the same image using step 2 -- one that looks like oil paint, one that looks like pen and ink, one that introduces a random abstract shapes, etc. and then layering them and blending them in a program like Photoshop. In the face example I also added Art Rage pastel embellishments.

Want to play with this stuff yourself? Create your own images, series of steps, textures and the like?

Step 1 ArtBreeder here:
https://www.artbreeder.com

Step 2 Deep Dream Generator here:
https://deepdreamgenerator.com/

I have a one-man show of this work coming up in September. There is a Step Four that uses A.I. to upscale the images to a high resolution for printing on canvas or metal. AI Gigapixel is my software of choice for that. Pictorem in Montreal is the printing house I use -- they are one of the few that offer a high gloss epoxy glazing on canvases as well as a newer dye sublimation print on metal that is fantastic!

99800

[alkratzer]

This shows multiple layers being blended together to get the final image. By varying the blending modes (darker, multiply, overlay, pin light, hue, etc.) you can come up with all manner of subtle combinations that enhances the color variations and adds a textural depth that has one foot in a transparent ink vibe.

99801

[D Akey]

Thank you Al, for this news flash!

It's a deeply fascinating leap so far beyond what I was aware of prior, that I find that I am more into processing the ramifications more than being fascinated at the technology of it and the Art that can be made by fiddling with sliders.

Al, I can see you taking it further than what pops out from the processor. You're using that image that was generated as a starting point and that's great. And you used your catalog of paintings as the style seed making it far more personal. That's a brilliant segue for you.

My hat's off to you for wanting to continue deeper into the journey where most would probably call it done with exploiting the mix-and-match of whatever is in the database. But you're keeping the Artistry in it.

I guess regular painting will become more rarefied like practicing the Zen of calligraphy. The oweness will be on the voluntary intention or consciousness of the one making the images more than on the technique, especially since most of the casual users will likely just stop when the computer stops processing and call it finished.

Will be interesting to see where this goes with a few more clicks of the evolutionary wheel.

Thanks for the connection to the techno-world. I would probably have missed it. My head is still spinning.

I generated these variations of the one default AI character in almost absurdly short order. It's nearly like made to order clip art when I did it like that with no personal input of my own art. Such a trip and brave new world and all that. Wow.

[DaltonMoss]

You may have seen the word brilliant used in movie reviews. I hate that! But I will use it here because this is literally brilliant!

[DaltonMoss]

Earlier this year I came across a challenge. It was a picture someone posted on FB that looked like something, yet nothing in the frame was identifiable. (And caused a big argument with my friend and I.) It was like looking at something alien, not of this world. Looking at the Artbreeder page I see that it was the generator for that image. It is a fascinating system indeed.

[alkratzer]

If you get a chance, try playing with Deep Dream -- this is where you get a chance to transform things into your own style/look.

One sub-branch of this that I came up with is to make A.I. assisted animations. Basically, generate a landscape image using Art Breeder and then create hundreds of variations that alter each preceding image ever so slightly. Convert them to a standard HD video pixel size and then apply artistic styles to the images. String them together in a video editor and you get this:


https://youtu.be/Y4T3Gdj4a5g

Side note: The sound track is also A.I. generated using Musenet

https://openai.com/blog/musenet/

In this case Musenet was trained on the first 6 bars of Body and Soul.

BTW, I've also been doing this project during the lockdown:

http://www.head2head.studio

Cheers!

[Alexandra]

Very inspiring, just love them al, Al!!!!

[D Akey]

Looks really intriguing Al!

Before this AI hit the scenes, I seem to recall some early Van Gogh paintings adapting themselves to this kind of treatment. It's almost like a given owing to his geometry and such.

Your stuff really lends itself to this kind of movement as well. Must be really satisfying to see new dimensions in your art where it comes alive.

[kenmo]

Love it...

[Dany51]

Is very new for me this kind of music, thanks !

[Murano]

I've also been playing a lot with AI tools in creating graphics lately. I am not publishing it yet. Good luck with your further AI experimentation :)