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.
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 timestept
? 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.
https://github.com/EnVision-Research/LucidDreamer/blob/2ecf0936617103107e4b20c34e94d204196f7a44/guidance/sd_utils.py#L278-L279