zy-charon
zy-charon
> 请查看我们的 imaginaire 仓库。我们有一个链接可以在那里下载预处理的动物面部数据集。只需要按照那里的 FUNIT 的自述文件。 > > https://github.com/NVlabs/imaginaire May I ask where is the download link of animal faces? I clicked on this link and still couldn’t find it.
Hello, I also have the same problem. Can you share how to fix it? Thank you.
Hello, I would like to ask which file should be modified if only images are used as conditional input?
Hello, if images are used as condition input for LDM, where should I modify the training settings?
> 感谢您的有趣工作 我有一个关于如何在多个 GPU 中运行 image_train.py 的问题 May I ask if you figured it out，I have the same problem.
Sorry to bother you again. I read the source code and it seems that this is indeed a scalar. I would like to ask why a frequency loss is calculated...
@wileewang May I ask how to use unet to directly predict the image?