EMA: support side-by-side validations with base model network

[bghira]

when training using EMA, the validations follow upstream Diffusers, and we temporarily overwrite the unet / transformer parameters in the base model with the EMA weights, before running inference.

however, we should provide the ability to generate the validations using both sets of weights, and stitch them together into a side by side representation, similar to this, with each output labeled: