Ümüt Yildiz.
Grace-2020-4
"The encounter between AI and aesthetics is crucial because aesthetics is considered a quintessentially human domain. Its intractability and complexity have long appeared as insusceptible to algorithmic reduction. For some, art, aesthetics, and creativity are the pinnacle of human abilities and, therefore, represent a final bulwark against the seemingly unstoppable advances of AI. In other words, this complex field becomes the ultimate testing ground for AI’s possibilities and limitations."
Lev Manovich and Emanuele Arielli
AI video has traversed whirlwind changes in the past four years. Every time the tools changed, the narratives and themes explored changed. From pure abstraction to figuration, artists have made amends with what the tools offered to convey their ideas. These four artists started exploring AI video in 2020 and have continued to develop their practice with all the tools that came after. We felt it was important to trace back their paths to create a conceptual and thematic arc that would help the Daily Program better represent their work and open an opportunity for collectors to create personal timelines with the artists' past and present works. Each, in their artistic framework, has created portals that, though using similar tools, emanate personal preoccupations and creative ideas. These are the four sub-series that comprise this group show:
Grace-2020
Ümüt Yildiz
20 1/1 AI Videos
Grace was my initial self-trained StyleGAN model. When I delved into AI in generative art, I used BigGAN initially. Although it was an interesting model, it didn't allow me to utilize my own pictures. In 2019, StyleGAN was released, marking an incredibly captivating moment for me. Towards the end of 2019, I extensively worked on my local PC while pursuing my Bachelor of Art, aiming to complete it by early 2020. During this period, I pushed my computer to handle challenging tasks for my thesis. AI back then differed significantly from today's capabilities. It required collecting a substantial dataset, around 1000-2000 pictures, which I curated manually. Tools like Midjourney and Runway emerged around that time, but being a student with limited income, I couldn't afford virtual machines. I did my best with my local machine. StyleGAN allowed the machine to learn from the data I provided, enabling me to infuse a part of myself into it. I explored how AI perceives humans and the beauty of our species, delving into a study that fascinated me. Additionally, I was intrigued by social media as a phenomenon, collecting over 1000 smartphone pictures of various people. Over a span of more than two weeks, I collected and curated the pictures. Despite the challenges posed by my thesis and freelancing for a living, I resumed experimenting with StyleGAN in December 2019.
The training process ran continuously for about three weeks until the machine produced its first evolved picture. StyleGAN initially replicates the dataset before attempting to create new variants. The images were initially pixelated and blurry, prompting adjustments to parameters and another month of training. Unfortunately, the computer crashed during this period, coinciding with the onset of the COVID-19 pandemic. Despite social media's prominence in Germany and the support among artists, the StyleGAN results still didn't resemble the dataset. It needed more training time, but an unfortunate turn of events occurred—the computer crashed. However, the StyleGAN model persisted on the hard drive. After rescuing the model to a notebook, the rendering process began. Witnessing how AI thought and interpreted was exhilarating; the results were abstract, focusing primarily on eyes and hair. It seemed like the machine was on the brink of understanding how a human face is constructed. AI thinks and sees in patterns, so it's natural that eyes and hair, prevalent in the dataset, were learned first.
While some considered my experiment a failure in the context of beauty images, it was not so for me. Throughout the output creation process, I discovered various things, such as the initial aspects we remember about a person, like their eyes and hair. The beauty of abstract morphing shapes forming new creatures and the eyes providing a living, organic feeling to the work became evident after multiple renderings from this model. After three years of working with AI, I'm thrilled to finally present this piece, showcasing the hard work invested in its creation and the progress we've made in the AI community.
Artifacts
Milo Poelman
20 1/1 AI Videos
These were the first AI images I created back in 2021 and were part of a research project on digital reproduction and machine vision. I ran the generation on two google colab models called: “The Big Sleep: BigGANxCLIP” and “Aleph2Image (Delta): CLIP+DALL-E decoder”.
“We perceive. When what we perceive is taken for true, reality, as it appears to us, becomes for us reality itself; The form becomes the object in its totality.”
The plant is organic, it moves, grows, and breathes. It never stands still, it is not an object. The plant is alive. We, however, perceive it as a static object. We do not see the plant moving or growing or breathing. So when the plant is translated, the form is used as if it were the essence of the plant. For us, the form is the plant itself. As a direct extension of the human body, our technology converts this objective translation into information understandable to them. It creates files and images that represent an objective view but are not within our frame of reference. Therefore, we cannot translate this information into what it stands for. n these early machine dreams, the AI imagined new plants that now have become artifacts in ever growing technological advancements. They almost appear as digital fossils.
Denoising Evolution: The Portal of Evolutionary Diffusion
Domingo Pablo
8 1/1 AI Videos
"Denoising Evolution: The Portal of Evolutionary Diffusion," a project that invites us on a journey through the interconnected realms of biology, technology, and the human spirit. Each piece in this collection is a unique exploration into the wonders of evolution, transformation, and the fusion of the organic with the digital. 'The Portal of Evolutionary Diffusion' is a poetic voyage where AI and natural evolution blend. Here, the dance of diffusion models blurs lines between flesh and code, unveiling a cosmos where each discovery becomes a verse in the grand narrative of life, echoing the eternal interplay of nature and technology.
Stable Diffusion Animations 2022
Chris Royal King
13 1/1 AI Videos
These works were some of my early explorations with AI animations. They were created with deforum stable diffusion notebook.