Closed matpalm closed 1 year ago
noticed in get_x_prev_and_pred_x0 that sigma_t is always set to 0. which means the later noise calculation will always be zero at
get_x_prev_and_pred_x0
sigma_t
noise
https://github.com/divamgupta/stable-diffusion-tensorflow/blob/master/stable_diffusion_tf/stable_diffusion.py#L124
furthermore noise is never used ? ( which means that the temperature is not used either )
temperature
i notice in the DDIMSampler (and PLMS) that noise is usually added to x_prev e.g.
x_prev
https://github.com/CompVis/stable-diffusion/blob/main/ldm/models/diffusion/ddim.py#L203
not sure if this is a bug (in which case it should be added) or if it's not required for inference? (in which case the noise and sigma can just be removed from code)
sigma
Hi @matpalm - did you ever get a clear explanation as to by sigma_t = 0? It doesn't seems to be denoising diffusion if this is zero.
noticed in
get_x_prev_and_pred_x0
thatsigma_t
is always set to 0. which means the laternoise
calculation will always be zero athttps://github.com/divamgupta/stable-diffusion-tensorflow/blob/master/stable_diffusion_tf/stable_diffusion.py#L124
furthermore
noise
is never used ? ( which means that thetemperature
is not used either )i notice in the DDIMSampler (and PLMS) that noise is usually added to
x_prev
e.g.https://github.com/CompVis/stable-diffusion/blob/main/ldm/models/diffusion/ddim.py#L203
not sure if this is a bug (in which case it should be added) or if it's not required for inference? (in which case the
noise
andsigma
can just be removed from code)