The article discusses a new approach in Generative Artificial Intelligence, specifically large text-to-image models. It introduces a prompting-free generative approach that enables users to create personalized painterly content that reflects their aesthetic preferences. This approach uses semantic injection to customize an artist model in a specific artistic style and a genetic algorithm to optimize the prompt generation process through real-time iterative human feedback. It aims to provide a more user-friendly and intuitive experience in creating digital art.
Publication date: 12 Feb 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2402.06389
