1.11.10

make sure batch size is set correctly, if only inpainting images are …

1.11.9

add an extra assert to make sure researcher / user cannot sample with…

1.11.8

1.11.8

1.11.7

1.11.7

1.11.6

fix ddp and self conditioning in elucidated ddpm

1.11.5

make sure self conditining works in distributed training, cleanup lat…

1.11.4

fix a bug with inpainting for non-elucidated ddpm

1.11.2

allow for one to pass in a tuple to use_linear_attn kwargs in unet, t…

1.11.1

an extra assert to make sure images are not integer type

1.11.0

update with the best type of downsample