Echoxvf

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (CUDABFloat16Type) should be the same

5

During the beginning of training, I encountered an issue where the data type was inconsistent with the convolutional kernel type. How should this be resolved? File "/data/scripts/train.py", line 254, in...

May I ask if the pre-trained model for open-sora1-1 stage 1 STDiT2-XL/2 is also PixArt-XL-2-512x512.pth, or is it trained from scratch?