It only took Matt Laming, a 19-year-old from the United Kingdom, about a month to hit a million followers on Twitter. And all it required was sharing a steady stream of the most outlandish computer-generated images that he and a bunch of internet strangers could think up. In recent weeks, the digital marketing apprentice, better known online as @weirddalle, has shared images depicting things like people vacuuming in the forest, the Demogorgon from Netflix's "Stranger Things" holding a basketball, and a Beanie Baby that looks a lot like Danny DeVito. These and other pictures, which range from ridiculous to disturbing, were created with a freely available artificial intelligence system called Craiyon. To use it, you just type what you'd like it to envision -- "A rainbow lion eating a slice of pizza" -- and it will spit out pictures in response.

In only a few years, the variety of artworks produced by self-described AI artists has dramatically elevated. A few of these works have been offered by giant public sale homes for dizzying costs and have discovered their manner into prestigious curated collections. Initially spearheaded by a couple of technologically educated artists who adopted pc programming as a part of their artistic course of, AI artwork has just lately been embraced by the lots, as picture technology expertise has grow to be each simpler and simpler to make use of with out coding abilities. The AI artwork motion rides on the coattails of technical progress in pc imaginative and prescient, a analysis space devoted to designing algorithms that may course of significant visible info. A subclass of pc imaginative and prescient algorithms, known as generative fashions, occupies heart stage on this story.

According to ancient Nine Inch Nails (NIN) lore, we're living in Year Zero, which began on February 10th, 2022. It's a period of extreme dystopia, where a fundamentalist religious government oversees an omniscient Bureau of Morality and a strange phenomenon known as "The Presence" -- two massive spectral arms reaching from the sky -- is spotted across the country. Year Zero was an alternate reality game (ARG) that accompanied the NIN album of the same name, and it included events that immersed fans in a theocratic police state. It was designed by 42 Entertainment, which also made Halo 2's I Love Bees ARG and Last Call Poker for Activision's Gun. The game began in February 2007 at the tail end of a "golden age" for commercial ARGs, which included an Audi campaign, ARG companions to major TV shows, and an "interactive clothing" company.

This newsletter is all about deep learning, data science, machine learning, natural language processing (NLP) -- our core contents. We are taking one newsletter break from blockchain and interviews. Don't worry, they will be out again later this month. There are some cool new AI kids on the block: DALL-E 2 (openAI) and Imagen (Google). First, read our warning below.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. It's free, we don't spam, and we never share your email address.

You've all seen amazing-looking images like these, entirely generated by an artificial intelligence model. I covered multiple approaches on my channel, like Craiyon, Imagen, and the most well-known, Dall-e 2. Most people want to try them and generate images from random prompts, but the majority of these models aren't open-source, which means we, regular people like us, cannot use them freely. This is what we will dive into in this article. I said most of them were not open-source. Well, Craiyon is, and people have generated amazing memes using it.

Dall-E 2 is the successor to Open AI's Dall-E model. The name Dall-E is the portmanteau of Wall-E (a sci-fi film by Pixar) and Salvador Dalí (a Spanish artist renowned for his surrealistic style in his paintings). The model is used to generate photorealistic images from a given text description. The model is not made available to the public yet but the Open AI team has made a nice demo on their website. As you can see, these images are what an artist/graphical designer will take hours if not days to produce but DALL-E2 does it in a matter of minutes and the images it produces are so impressive.

Meta Platforms Inc. today unveiled an advanced "generative artificial intelligence system" that's designed to help artists better showcase their creativity. The system, called "Make-A-Scene," is meant to demonstrate how AI has the potential to empower anyone to bring their imagination to life. The user can simply describe and illustrate their vision through a combination of text descriptions and freeform sketches, and the AI will come up with a stunning representation of it. As the company explains in a blog post, generative AI is already used by a number of artists to augment their creativity. Examples include expressive avatars, animating children's drawings, creating virtual worlds in the metaverse and producing digital artworks using only text-based descriptions.

Large neural networks are at the core of many recent advances in AI, but training them is a difficult engineering and research challenge which requires orchestrating a cluster of GPUs to perform a single synchronized calculation. As cluster and model sizes have grown, machine learning practitioners have developed an increasing variety of techniques to parallelize model training over many GPUs. At first glance, understanding these parallelism techniques may seem daunting, but with only a few assumptions about the structure of the computation these techniques become much more clear--at that point, you're just shuttling around opaque bits from A to B like a network switch shuttles around packets. Each color refers to one layer and dashed lines separate different GPUs. Training a neural network is an iterative process.

It's incredible that a picture can be generated from a single text phrase and while many are satisfied to stop there, other creators want more control over the images. Even in these early days, there are already multiple ways to shape the AI's results: While neither a separate feature nor an integrated part of the interfaces, there are many independent guides and image tests that aim to provide style names and other key words that yield desired results. Midjourney also published some helpful prompting tips. When dealing with images, there are inevitable trade-offs between size, quality, and speed. Built on cloud-based systems, we're able to use hardware we wouldn't ordinarily have access to, enabling significantly faster image generation.