Open DDXDB opened 4 months ago
It has been confirmed that the problem is caused by multiple buckets with different resolutions. I adjusted the picture to 512512 and 5121024, and the current utilization rate is 80%+
Please raise this with kohya directly on his sd-scripts repo. Perhaps he can do something about it.
It will do JIT compile for each resolution which takes time. It should run at 80%-100% usage after JIT compile for each resolution in the dataset is complete.
I followed the steps below to install iPEX-based kohya_ss
The following computer configurations have been tested:
It appears to run without problems or errors. but Regardless of the computer, GPU usage has been fluctuating between 5-30%, can not be maintained at 100%. The A770 is only about 7s/it.I was able to achieve 100% utilization in March using the same configuration and very fast I use the following Settings for training: LoRA_BasicSettings_ipex (1).json