Question about ISM loss in code

[jimmychuang95]

Thanks for the brilliant work!

I have a question regarding the implementation of the loss function. Based on the code provided, should the target be the unet_output at timestep t? If so, would the loss function be expressed as:

[ \epsilon(x_t, t, y) - \epsilon(x_t, t, ∅) ]

instead of:

[ \epsilon(x_t, t, y) - \epsilon(x_s, s, ∅) ]

as mentioned in the paper? I want to ensure I haven't overlooked anything in my understanding.

Thank you in advance for your time and assistance.

LucidDreamer/guidance/sd_utils.py

Lines 278 to 279 in 2ecf093

	pred_scores = pred_scores_xt + pred_scores_xs
	target = pred_scores[0][1]

[innocentARJOS]

same question
should it be like this: target = pred_scores[1][1] ,according to the paper?