dropout strategy

[ryancll]

          We adopt the same dropping strategy ("we randomly drop image only (zero image) for 5% of samples, drop text only (empty string) for 5% of samples, drop both of them for 5% of samples for dual-cross-attention.") in all training phases.

"We did not drop image conditional latent in VDG" means the concatenated frame latent with noise will not be dropped.

Originally posted by @Doubiiu in #8 (comment)

Have you ever trid randomly drop image conditional latent(concated latent) for training? I'm curious why you think this strategy is unnecessary.