DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models Zhengyang Yu1 Zhaoyuan Yang

However, such a solution often shows unsatisfactory editability on the source image. To address this, we propose DreamSteerer, a plug-in method for augmenting existing T2I personalization methods. Specifically, we enhance the source image conditioned editability of a personalized diffusion model via a novel Editability Driven Score Distillation (EDSD) objective.