the snr dmd loss in pixart alplha 512x512

[icelighting]

thanks for your great work. when i use the dmd distillation code, i find the snr loss is not use the mse loss, but the coeff * latents, not the grad and may be negative. Is it related to the way model learning using snr gamma?

[Feynman1999]

thanks for your great work. when i use the dmd distillation code, i find the snr loss is not use the mse loss, but the coeff * latents, not the grad and may be negative. Is it related to the way model learning using snr gamma?

The default args.snr_gamma should be none ？ I am also puzzled about the difference between these two， which one should use