A blog related to original AI artworks. I make AI artworks using coined words and emoji as prompts.
At Design Festa vol.60, held at Tokyo Big Sight, we selected a few dozen works from over 130,000 images to exhibit and sell on the spot. Other works, excluding the latest ones, can be viewed on our official site, and posters are available for purchase on Rakuten. The exhibition, titled "Free Creations by AI Art", was displayed at booth C-151. This marks our second poster exhibition of AI art.
Stable Diffusion XL, an AI, created a variety of artworks. For this event, the artistʼs real name or the pen name *Kanabstracd* was provided as a prompt to the AI, occasionally supplemented with 1–2 additional words. From the many images generated by varying the random seed, we selected works that showcased the AIʼs “artistic talent” for display and sale. Many AI art creators focus on realistic images such as photos or anime-style visuals. However, since image-generating AIs lack structural knowledge about real-world entities like the human body, they are not well-suited for creating realistic images. At Dasyn, we instead focus on producing painterly, particularly abstract, images. By instructing the AI to create works different from those of specific ukiyo-e artists or famous painters (using those as negative prompts), we enable the AI to demonstrate diverse “artistic talents.”
This update comes a bit late, but I plan to write a separate article about the results, as I did last year.