
A method is proposed to enable pre-trained latent diffusion models to achieve state-of-the-art results on the image harmonization task by addressing the image distortion issue caused by the VAE compression.


coremsg

enhancing-image-harmonization-with-latent-diffusion-models


Enhancing Image Harmonization with Latent Diffusion Models


title_rewrite


Patch-based normalization network for portrait harmonization achieves state-of-the-art results.


phnet-patch-based-normalization-for-portrait-harmonization


PHNet: Patch-based Normalization for Portrait Harmonization



The authors propose PHNet, a patch-based normalization network, to address the challenges of harmonizing portraits by focusing on local visual coherence. Their approach showcases state-of-the-art results on the iHarmony4 dataset.
