train several resolutions at same time.

Thank you for your hard work.

Currently, Bucket systems are coded to fix only one resolution.
If possible, I would like to train images of different resolutions at the same time.
For example, 512 x 512, 576 x 1024, 1024 x 1024, 760 x 1280

Unfortunately, even if you turn off the enable_bucket option, it is being forced to resize.

I want to train a particular area further with a small image, but it is trained in large sizes due to forced resizing, and as a result, the learning quality of everything deteriorates on average.

I would like to be able to completely turn off bucket and force resize.

Start by tracing the training entry points that handle enable_bucket, bucket selection, and forced resizing. Compare the requested mixed-resolution behavior with the current single-resolution flow; done means bucket resizing can be completely disabled while images at the listed resolutions train without forced resizing, with relevant training checks updated.

Written by the indexing model from the issue text.