PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention

actions into those occurring in the foreground and the background areas. The effect of the former is estimated through intrinsic image decomposition, and the region of the latter is predicted in an additional background effect control branch. Moreover, we propose an effect attention module to disentangle the learning processes of interaction and subject, alleviating confusion between them. Additionally, we introduce a synthesized dataset, Replace-5K, consisting of 5,000 image pairs with invariant subject and contextual interactions via 3D rendering. Extensive quantitative and qualitative experiments on our dataset and two real-world datasets demonstrate that our method achieves state-of-theart performance. The code is available in the https: //github.com/wei-cheng777/PS-Diffusion.