TY  - STD
AU  - Senmao Li
AU  - Joost van de Weijer
AU  - Taihang Hu
AU  - Fahad Shahbaz Khan
AU  - Qibin Hou
AU  - Yaxing Wang
AU  - Jian Yang
PY  - 2023//
TI  - StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
N2  - A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images. They either finetune the model, or invert the image in the latent space of the pretrained model. However, they suffer from two problems: (1) Unsatisfying results for selected regions, and unexpected changes in nonselected regions. (2) They require careful text prompt editing where the prompt should include all visual objects in the input image. To address this, we propose two improvements: (1) Only optimizing the input of the value linear network in the cross-attention layers, is sufficiently powerful to reconstruct a real image. (2) We propose attention regularization to preserve the object-like attention maps after editing, enabling us to obtain accurate style editing without invoking significant structural changes. We further improve the editing technique which is used for the unconditional branch of classifier-free guidance, as well as the conditional one as used by P2P. Extensive experimental prompt-editing results on a variety of images, demonstrate qualitatively and quantitatively that our method has superior editing capabilities than existing and concurrent works.
UR  - https://arxiv.org/abs/2303.15649
L1  - http://158.109.8.37/files/LWH2023.pdf
N1  - LAMP
ID  - Senmao Li2023
ER  -