Human Aesthetic Preference-Based Large Text-to-Image Model Personalization: Kandinsky Generation as an Example
This addresses the problem for artists and users in the art community who struggle with achieving desired aesthetic outcomes in generative AI, offering a more user-friendly and personalized method, though it is incremental as it builds on existing text-to-image models.
The paper tackles the challenge of non-deterministic and tedious prompt engineering in large text-to-image models by introducing a prompting-free approach that automatically generates personalized painterly content based on user aesthetic preferences and a customized artistic style, using semantic injection and a genetic algorithm with real-time human feedback.
With the advancement of neural generative capabilities, the art community has actively embraced GenAI (generative artificial intelligence) for creating painterly content. Large text-to-image models can quickly generate aesthetically pleasing outcomes. However, the process can be non-deterministic and often involves tedious trial-and-error, as users struggle with formulating effective prompts to achieve their desired results. This paper introduces a prompting-free generative approach that empowers users to automatically generate personalized painterly content that incorporates their aesthetic preferences in a customized artistic style. This approach involves utilizing ``semantic injection'' to customize an artist model in a specific artistic style, and further leveraging a genetic algorithm to optimize the prompt generation process through real-time iterative human feedback. By solely relying on the user's aesthetic evaluation and preference for the artist model-generated images, this approach creates the user a personalized model that encompasses their aesthetic preferences and the customized artistic style.