“Art-Free Generative Models: Art Creation Without Graphic Art Knowledge”, 2024-11-29 (; similar):
We explore the question: “How much prior art knowledge is needed to create art?” [little to none, as already known from GAN & scaling & transfer research]
To investigate this, we propose a text-to-image generation model trained without access to art-related content. We then introduce a simple yet effective method to learn an art adapter using only a few examples of selected artistic styles.
Our experiments show that art generated using our method is perceived by users as comparable to art produced by models trained on large, art-rich datasets.
Finally, through data attribution techniques, we illustrate how examples from both artistic and non-artistic datasets contributed to the creation of new artistic styles.