Global repeat is useful, but when training multiple concepts it's a lot better to have the ability to repeat certain concepts to increase their representation in the overall dataset.
This PR adds two new concept options:
1: Repeat concept:
Global repeat is useful, but when training multiple concepts it's a lot better to have the ability to repeat certain concepts to increase their representation in the overall dataset.
2: Separate buckets:
Places the selected concepts in their own separate buckets, so they do not get mixed in with the rest of the images of the same resolution when training with higher batch sizes. This might help prevent some bleeding between styles/subjects.
Global repeat is useful, but when training multiple concepts it's a lot better to have the ability to repeat certain concepts to increase their representation in the overall dataset.
This PR adds two new concept options: 1: Repeat concept: Global repeat is useful, but when training multiple concepts it's a lot better to have the ability to repeat certain concepts to increase their representation in the overall dataset.
2: Separate buckets: Places the selected concepts in their own separate buckets, so they do not get mixed in with the rest of the images of the same resolution when training with higher batch sizes. This might help prevent some bleeding between styles/subjects.