Fine-Tuning a Generative Model on My Art: an Experiment with DreamBooth

As an AI Developer and Artist, I’m always thrilled to find new ways of combining and mixing these two realms. Lately, with the introduction of text-to-image models and the exponential growth of the generative AI sector, the possibilities to experiment are almost endless. <h1>Integrating AI in the creative process</h1> Personally, I often use generative AI during my creative process and not as the end result of it. I think text-to-image models are great tools to make the whole artistic process smoother and faster. In fact, they’re really useful for testing different color combinations, for finding inspiration, for creating reference images and prototypes that play with patterns and concepts in unexpected ways. I wanted to take this one step further and an idea struck me: what if, instead of utilising general models in my process, I fine-tuned a generative neural network on my own art and then used it instead? I was also curious about which features about my creations the network would pick up and reproduce in its outputs. This would mean identifying some key characteristics that remain constant across my whole body of work and that are distinctive of my own personal style. The ultimate goal was not only gaining a tool for generating references but also better understanding my artistic persona. <a href="https://medium.com/@sarasisti.mi/fine-tuning-a-generative-model-on-my-art-an-experiment-with-dreambooth-814947a5e3fb">Learn More</a>