Inventing art styles with no artistic training data
This work addresses the ethical use of generative AI in art by enabling style invention without infringing on human originality, though it appears incremental as it builds on existing methods for style generation.
The paper tackles the problem of creating new painting styles without using artistic training data, achieving this through two procedures that leverage natural images and inductive biases to generate novel styles, thereby providing objective proof against plagiarism of human art.
We propose two procedures to create painting styles using models trained only on natural images, providing objective proof that the model is not plagiarizing human art styles. In the first procedure we use the inductive bias from the artistic medium to achieve creative expression. Abstraction is achieved by using a reconstruction loss. The second procedure uses an additional natural image as inspiration to create a new style. These two procedures make it possible to invent new painting styles with no artistic training data. We believe that our approach can help pave the way for the ethical employment of generative AI in art, without infringing upon the originality of human creators.