Minghao Chen
Thanks for your reply. I have some others questions about the details used in the finetuing on ImageNet 1K. In addition to hyperparameters such as learning rate, batch size, LR...
Hi, thanks for your interest in our work. Can you share the settings for the experiment? Then, I could give more detailed helps.
Hi all, thanks for your interests in our paper. In figure 2, we accutally give all the search spaces include the intial one and the final search space. In specific,...
Hi, thanks for your interests in our work. Yes, we have a plan to release a tutorial about real image editing later.
Please see the response to #15
Hi, thanks for your interest in our work. I plan to release the real image editing part within this month. Hope it can inspire you somehow.
Sorry for the late update. I was kind of busy last month. I will try to clean up the code and release it soon.
Hi all, sorry for the late release. I just cleaned the real image editing code and pushed it to the repo. I also updated the dependent library because the CLIPFeatureExtractor...
It will cost ~28GB memory for text inversion and ~31GB for Dreambooth. To reduce the GPU memory usage in text inversion, you can try to reduce the batch size for...
Hi, thanks for your interest in our paper. It is possible to add negative prompts. Typically, you should replace the unconditional token with the negative token. To be specifically, you...