sharkDDD

Hi, Thanks for your new dataset. The dataset is not available from the OneDrive link. Would it be possible to put your dataset on OneDrive again? Thanks in advance, Best,

Non-uniform time step sampling are not implemented in the released code ?

1

The paper proposes the non-uniform time step sampling to increase the probability of t falling in the early sampling stage but in the code of the forward method in LatentDiffusion,...

Bad results

3

I did not modify any code, I simply ran the training and inference programs directly, and the results were very poor. I'm not sure what the problem is. As the...

感谢您的工作，我在阅读源码过程中发现在inference时对图像进行了pad，然后在生成结果中再移除了pad的部分，请问这个操作是用来处理什么问题的。我测试了几个样例，即使移除了pad，结果好像也不受影响。我在其他论文的相关程序中也看到会有pad的操作，所以我想咨询一下您，这里的pad是用来避免一些可能出现的问题吗？

About the pretrained imagenet encoder:

1

Thank you very much for your work. I have a question I would like to consult: In the paper, it is mentioned that features are extracted using a backbone pre-trained...