You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for sharing your cool work!
I have a question about the learning rate of your null-text inversion. According to a notebook, the learning rate is set blow. However, in your paper, the learning rate is set to 0.01.
optimizer = Adam([uncond_embeddings], lr=1e-2 * (1. - i / 100.))
where $i$ represents an index of a for-loop for i in range(NUM_DDIM_STEPS):.
If we set NUM_DDIM_STEPS over 101, the learning rate gets negative.
My question is that can we modify lr=1e-2 instead of 1e-2 * (1. - i / 100.)?
The text was updated successfully, but these errors were encountered:
HI, @amirhertz !
Thank you for sharing your cool work!
I have a question about the learning rate of your null-text inversion. According to a notebook, the learning rate is set blow. However, in your paper, the learning rate is set to 0.01.
where$i$ represents an index of a for-loop
for i in range(NUM_DDIM_STEPS):
.If we set NUM_DDIM_STEPS over 101, the learning rate gets negative.
My question is that can we modify
lr=1e-2
instead of1e-2 * (1. - i / 100.)
?The text was updated successfully, but these errors were encountered: