Hyoungwon Cho

@yiyixuxu Thank you, I removed the white space in the code for code quality check.

@asomoza Thank you for your interest in our work! Thanks to [multimodalart](https://github.com/multimodalart), users can try PAG on SDXL on Hugging Face Spaces. For more information, please visit our [github page](https://github.com/KU-CVLAB/Perturbed-Attention-Guidance).

I am struggling with build error. If this is resolved, I will open a new pull request.

@yiyixuxu @asomoza Hello, I was impressed by the various experiments you conducted using PAG! We are also discussing the use of PAG in various tasks, as well as layer/scale selection....

@yiyixuxu Hello, The implementation of PAG seems flawless! Aside from the ```noise_pred_uncond``` part mentioned by sunovivid, it looks perfectly implemented. Thank you very much for implementing and merging our paper...