AutoEdit: Automatic Hyperparameter Tuning for Image Editing

Dimitris Metaxas (Rutgers University) · Yunjie Tian (University at Buffalo, SUNY) · DAVID DOERMANN (University at Buffalo) · Chau Pham (State University of New York at Buffalo) · Quan Dao (Rutgers University) · Mahesh Bhosale (State University of New York at Buffalo)

computational costs computational overhead diffusion modelsediting objectiveshyperparameter identificationhyperparameter search spacemarkov decision processoptimal hyperparameter configurationspractical deployment proximal policy optimization reinforcement learning framework reward function sequential decision-making text-guided image editingtime efficiency

Recent advances in diffusion models have revolutionized text-guided image editing, yet existing editing methods face critical challenges in hyperparameter identification. To get the reasonable editing performance, these methods often require the user to brute-force tune multiple interdependent hyperparameters, such as inversion timesteps and attention modification, \textit{etc.} This process incurs high computational costs due to the huge hyperparameter search space. We consider searching optimal editing's hyperparameters as a sequential decision-making task within the diffusion denoising process. Specifically, we propose a reinforcement learning framework, which establishes a Markov Decision Process that dynamically adjusts hyperparameters across denoising steps, integrating editing objectives into a reward function. The method achieves time efficiency through proximal policy optimization while maintaining optimal hyperparameter configurations. Experiments demonstrate significant reduction in search time and computational overhead compared to existing brute-force approaches, advancing the practical deployment of a diffusion-based image editing framework in the real world.