#‘but what if Van Gogh used ai to make the starry night’ followed by ‘it’s a stupid hypothetical on purpose!’

[radioactivecowgirl]

youtubers I liked bending over backwards to support generative ai lmao maybe video essay YouTube is a plague

[charlesmoffat]

WHAT DOES A CHARLES MOFFAT PAINTING LOOK LIKE???

Well, if you Google "Charles Moffat painting" you will get the following:

As you can see I have a very particular style of painting. Bold colours. Usually women, but not always. Lots of grey, blacks, high contrast, lots of chiaroscuro...

So...

Can AI copy my painting style???

Well, let's find out...

I asked a popular AI art program to create 4 different versions of a Charles Moffat painting.

Here are the results:

Okay, so some observations...

The top left one is similar to my style, but obviously not my style. The choice of colours doesn't match my style.

Two of them are landscapes, and I rarely paint landscapes. Stylistically they're just wrong.

And then there's the bottom left. Her head is cut off (something I would never do), the colour scheme is all wrong, and it's definitely not my style.

Well... What about a different AI program? Maybe it could do a better job.

Nope, nope, nope.

Not remotely similar to my style.

Well, let's try again with a 3rd AI program...

Well, damn... That is just horrible.

At least it understood that I mostly draw women, but it didn't even remotely copy my style.

...

And that's the funny thing about AI. If you ask it to copy an artist who is still alive it probably isn't going to be that good at it.

But... If you ask it to copy the style of a dead artist like Van Gogh, what happens?

The Eiffel Tower in the style of Van Gogh's Starry Night.

Hmm.

And it did it so easily. Effortlessly. First try.

So what does this tell us?

Well, it tells me that all this scaremongering about AI stealing/copying the artwork of contemporary artists (who are still alive) is just nonsense.

From what I can tell AI can copy dead artists pretty well, but if you ask it copy the style of a living artist it kind of sucks at it.

Example, Yayoi Kusama is one of the most famous living artists currently around. Here's what her style looks like:

And when I asked an AI program to make a Yayoi Kusama painting here is what it made:

Well... It got the dots right.

But stylistically speaking, it isn't remotely like her style. It looks cartoonic. Amateurish.

In short, it is hardly a good copy of her work. Not even a decent copy. Poor. That's the word we need to use. It is a poor imitation.

So to anyone who is a living artist who is worried about AI copying your work... Yeah... Maybe stop worrying about it. Unless you are as famous as Yayoi Kusama then the AI probably doesn't know what your style looks like, and even if it does anything it produces will likely be a poor imitation of it.

It is the dead artists who should be upset...

But artists have been copying each other for thousands of years. This isn't actually something new. The French were dealing with this issue of "artistic theft" hundreds of years ago. They even created a word for it: Pastiche, which means "to borrow".

It isn't theft, it is pastiche. And the real threat isn't artists copying other artists or AI copying artists. The real threat is what happens when people lose interest in painting with their own two hands and start relying upon AI to paint everything for them.

[hysteriamodes]

So, four of my favorite artists are disabled. (I would include Frida Kahlo, but she's already been mentioned.)

Mary Vincent survived a horrific rape and having her arms severed by her attacker. The crazy part is she never drew and was into art until after her ordeal. I first heard about her when I was younger and I still think she's one of the coolest people.

Jessica Jewett is an artist I follow on Instagram who is also disabled and she is AMAZING. She does a lot of traditional media. I highly recommend checking her out.

She draws with her mouth. And plus, she's an author! If you have Instagram, please follower her.

And of course, Louis Wain, a schizophrenic artist. here's a variety of pieces he did and you can see his art fluctuate.

Vincent Van Gogh, another honorary mention. He was bipolar and his painting "Starry Night" in an asylum. Like Louis Wain, you can see the progression of his art and the decline when his mental health took a nose dive.

I am neurodivergent and mentally ill artist, myself, so these people mean a lot to me and I look up to them when I struggled to do art when my mental illness was awful.

Implying that disabled artists can't do art on their own and need to rely on AI is absolutely ableist and infantalizes us. Just because we're not able bodied or mentally ill doesn't mean we can't do art.

What a genuinely shitty thing to say.

If these people can do art, especially Mary and Jessica, you have no excuse not to learn how to draw and stop relying on a computer to make an image. It's not art, the people above made art.

That is art.

"ai is making it so everyone can make art" Everyone can make art dipshit it came free with your fucking humanity

[vinmiral]

Save separate layers photo image editor pixelstyle

SAVE SEPARATE LAYERS PHOTO IMAGE EDITOR PIXELSTYLE HOW TO

SAVE SEPARATE LAYERS PHOTO IMAGE EDITOR PIXELSTYLE GENERATOR

The original image and the target image are input to the discriminator, and it must determine if the target is a plausible transformation of the original image. The Pix2Pix model is a type of conditional GAN where the creation of the output image depends on the input, in this case, the original image. Possible approachesĪs you may already guess, there are several approaches to do what we want:ġ.Pix2Pix model.

SAVE SEPARATE LAYERS PHOTO IMAGE EDITOR PIXELSTYLE GENERATOR

As such, the two models are trained simultaneously in an adversarial process where the generator seeks to better fool the discriminator and the discriminator seeks to better identify the counterfeit images. The discriminator model is updated directly, whereas the generator model is updated via the discriminator model. The GAN architecture consists of a generator model for outputting new plausible synthetic images, and a discriminator model that classifies images as real (from the dataset) or fake (generated). Since we have to generate a new picture in a certain way, we will use GAN (Generative Adversarial Network). If we use machine learning models or neural networks to solve Image-to-image translation tasks, then this approach is called “ Neural Style Transfer”.įor example, when you want to transform horses into zebras, or pears into light bulbs using machine learning - you become a magician with the “Style Transfer” wand! General concepts Image-to-image translation is a class of vision and graphics tasks where the goal is to learn the mapping between an input image and an output image. Such tasks are called Image-to-image translation. After that, you can generate a new image by combining the content from your photo with the style from the second image. In other words, you need to extract the content from your pet photo and extract the style from the second image. So, what you want to get is a new image of your pet but in Van Gogh style. Imagine that the first picture is a photo of your favorite pet and the second one is a painting by Van Gogh “Starry night”. Let’s give a simple example to better understand what exactly we have to do. Our task is to create a model that will take a usual picture, photo, meme, whatever you want, and convert it to pixel art style. Now that we have defined what a pixel art style is, we can move on to the practical side of this article.

SAVE SEPARATE LAYERS PHOTO IMAGE EDITOR PIXELSTYLE HOW TO

Pixelate your favorite meme and and enjoy How to transform images The task definition Make individual pixels clearly visible, but not necessarily in low-resolution images.A certain color scheme:It is considered good practice to use the minimum number of colors ideally - the standard 16 colors available on the vast majority of video subsystems, even the earliest ones: in them, three bits encode signals R, G, B and the fourth bit encodes brightness.Thus, we can formulate the following features of the pixel style: A certain color gamut is used, and also in each case, its own pixel size is used to make the image look more harmonious. Some might think that the pixel style is just poor quality images with oversized pixels, but I want to explain how this is just untrue. Therefore, the idea of creating AI that will automatically apply the pixel style to any photo or picture seemed very appealing! General Pixel Art rules Usually, it takes a lot of time for the artist to create such pictures, since you need to keep in mind the limitations in resolution and color palettes. Some pictures in the pixel style can be surprising, with their elaboration and idea. Memories. Pixel art brings back great, nostalgic feelings for gamers who grew up playing Nintendo, Super Nintendo, or Genesis.

[caveartfair]

This Artist’s Quest to Counter Art World Elitism Culminated in a 10-Foot-Tall Picasso

Elliott Arkin, The Spanish Gardener, 2018, in a storage warehouse prior to installation.

Artist Elliott Arkin, 58, has made a living pursuing his own esoteric interests, costs be damned. He’s worked as a sculptor for animated films like Horton Hears a Who, earned his real estate license, collaborated with Vito Acconci on a roving art-education initiative, and served (for a very short time) as the official sculptor for opera superstars Three Tenors, all while pursuing a variety of idiosyncratic projects.

He’s also just spent roughly $120,000 of his own money producing a 10-foot-tall sculpture of Pablo Picasso pushing a lawn mower. Titled The Spanish Gardener (2018), it will be on view tomorrow through July 15th on the corner of Degraw Street and Columbia Street in Brooklyn (a neighborhood dubbed the Columbia Street Waterfront District) as part of the Brooklyn Greenway Initiative.

On a recent Friday afternoon, I met up with Arkin to visit his Picasso, which, at the time, was being stored in a large commercial warehouse, surrounded by boxes of speaker equipment. The mixed-media sculpture includes a fiberglass head, a body of urethane and foam, and a mower partially composed of a chunk of repurposed telephone pole. A CNC routing machine assisted with some of the work, but Arkin stresses that he didn’t totally outsource the production to technology.

Elliott Arkin, The Spanish Gardener, 2018, in progress. Courtesy of the artist.

Seedbed (Picasso Mowing), . Elliott Arkin Contemporary Art and Editions

“There was a lot of surface work—it was important to me that it retains a more classically sculpted quality, with tool marks,” he says. “Things that are carved by the computer have a colder, more manufactured look. I want to see the hand of the maker.” Arkin’s Picasso is indeed expressive; his oversized dome, smooth and bald, resembles some mix of a bobblehead and an Occupy Wall Street protest puppet. He does not look too happy, gazing off into the middle distance at some unseen irritant.

It’s been a journey to get to this point. Arkin, originally from Miami, moved to New York City in 1983. He made a name for himself with realistic figurative sculptures—occasionally comic, occasionally grotesque—made of colored polymer clay. He also moonlighted on the commercial side. Arkin fell in with a crowd of artists surrounding Broadcast Arts, a production company that made commercials, among other things. He contributed animation work for the first season of Pee-wee’s Playhouse, and rented a studio from the company in Lower Manhattan where he could pursue his own creative work.

“People were always hanging around,” Arkin says of the firm’s freelance stable: artists like Gary Panter, Wayne White, and Laurie Anderson, as well as Mo Willems, who would go on to write the classic cautionary tale for children, Don’t Let the Pigeon Drive the Bus!

After success with galleries in the 1980s, Arkin’s career faltered following the art market crash in 1991, yet he kept plugging away. Often, he would tell himself: “It’s time for you to give up art and get a real job, please, you’re in a ridiculous world. Nothing is ever going to work.” Future successes were modest and sporadic, but enough to keep Arkin inspired and afloat. He dabbled in real estate and, for a short time, produced art history-related jewelry (tiny renditions of Gustav Klimt’s Kiss, snippets of Vincent van Gogh’s Starry Night).

Fountain ( Warhol Watering Pool Boy ), 2012. Elliott Arkin Contemporary Art and Editions

Bourgeois Having Tea With Spider, 2013. Elliott Arkin Contemporary Art and Editions

He also began contributing satirical cartoons to Artnet’s online magazine in 2000; one of the first ones depicted the critic Charlie Finch violently eating Jeffrey Deitch. By 2009, those drawings would inspire a new series of sculptures presenting famous artists in the style of common garden gnomes.

Arkin started with a tiny version of Picasso mowing a lawn—the basis for the newer, scaled-up piece about to go on view in Brooklyn. He initially titled it Seedbed, a semi-lewd reference to Acconci’s famous onanistic performance from 1972. Mini-Picasso’s first home was at Belvoir Terrace in Massachusetts, where Arkin was teaching at the time.

This pint-sized Picasso was then included in the 2010 Brucennial, a sprawling, ramshackle show organized by the Bruce High Quality Foundation. That exposure led, unexpectedly, to the offer of an exhibition at the Museum of Modern and Contemporary Art (MAMAC) in Nice, France.

For the French museum’s roof garden, Arkin conceived an expanded suite of five sculptures. Picasso was joined by van Gogh, Andy Warhol, Georgia O’Keeffe, and Louise Bourgeois. He named the entire set “A Peaceable Kingdom,” after an 1834 painting by Edward Hicks. (“Everyone’s working together,” he explains.) Arkin chose his quintet of artists based on their indirect relationship to gardens or gardening: “Bourgeois with spiders, O’Keeffe planting flowers,” he says. “Someone like Rembrandt wouldn’t make sense.” The artist has rough plans for a Frida Kahlo addition to his kingdom, “holding a thatched basket with help from a monkey,” Arkin explains. “It can act as a bird-bath outdoors.”

Older works by Elliott Arkin in his Brooklyn apartment.

The public—and collectors—responded well to the irreverent, impish figures in “A Peaceable Kingdom.” Hotelier Ian Schrager bought one; so did the writer James Frey. Another collector snapped up an edition of the entire group and installed them outdoors in Martha’s Vineyard. It’s important to Arkin that his sculptures, modeled on garden gnomes, can actually be installed in a garden. He’s not a fan of the “religiousness” that many people have when it comes to artists and art objects, the “preciousness and pomposity” that can often prevail. Case in point, he says: a tiny sculpture he made of Ai Weiwei, giving the viewer the middle finger. It’s meant to serve as a ring holder.

Arkin identifies as a populist; his art is meant to be enjoyed, not puzzled over. In that sense, he has something in common with the late Seward Johnson, known for doing things like blowing up the protagonists of Grant Wood’s American Gothic into a 25-foot-tall, three-dimensional sculpture. It’s an accessible sensibility that spills over into yet another side project, Mister ArtSee, which Arkin views as a way to give the art world “a character that’s meant to be a Smokey Bear for art and art education.” He also has future plans to develop an operable, conceptual slot machine as a sculpture. It’s not hard to imagine Arkin’s vision exploding out into other territories; I’d love to see what sort of mini-golf course he might conjure with unlimited funds.

Yet there’s a sly, sinister edge to Arkin’s work that prevents it from always being too family-friendly. In his Brooklyn apartment, there’s a chockablock rack of older works, with editioned pieces next to shockingly adept sculptures made when the artist was a teenager.

Catalan Cattelan Caganer, 2016. Elliott Arkin Contemporary Art and Editions

Elliott Arkin, Shrunk, 2014.

Among the more recent works is a small-scale riff on Jeff Koons’s sculpture of Michael Jackson and his pet monkey Bubbles—in Arkin’s version, a grotesque Ronald Reagan takes the place of M.J.—and a figurative rendering of a woman with comically enormous breasts, meant to be a light parody of John Currin’s nudes. Nearby, a petite sculptural version of Maurizio Cattelan is crouching, pants around ankles, in order to deposit some solid-gold excrement.

A small wine fridge is helping keep certain fragile pieces cool. One is a clay study for a sculpture of Marcel Duchamp playing chess (the final version, Arkin says, will be interactive). The other work, around 3 inches long, is a hyper-detailed self-portrait of the artist lying on a psychologist’s couch, made from a material called Castilene. He spent eight months perfecting its details using needles; you need a magnifying glass to view it properly.

I asked Arkin what his ultimate ambitions are. “Throughout my career I’ve made intimate sculptural works in the art world, and worked in broader fields—film, or designing windows at Tiffany’s,” he says. “The Spanish Gardener is the first time I’m combining the two areas.” One dream he has is to finally produce a massive, 25-by-25-foot version of an older work, Le Cadre: a gold-colored, frame-shaped sculpture that mashes up key moments in art history, from Sandro Botticelli’s Birth of Venus to Edvard Munch’s Scream. “Other ideas?” he muses, clearly enamored of the chance to finally supersize his ambitions. “Fountains? Piazzas? That would be great!”

from Artsy News