xuzhang
xuzhang
The paper mentions the use of Non-uniform time step sampling during training, but no relevant parameters are found in the training code. How can this strategy be applied?
Unable to reproduce the results of the question generation task in the paper. - The results of the question generation task in the paper are as follows: - We use...
https://github.com/jinxixiang/color_controlnet/blob/main/assets/color_edit.png
 It seems that the 32G GPU is not enough. How large memory a GPU is needed for normal operation?
### PR types Bug fixes ### PR changes ### Description 修复不支持subfolder download的bug, 如下: