Closed Olimoyo closed 1 year ago
Hi,
I noticed that the text conditioning is done using classifier-free guidance while in the original paper, they use FiLM layers.
Was there a particular reason for this decision?
Thank you, Oliver
yea, because i know cross attention on fine-grained tokens is better. this part i'm quite confident about
I see, thanks!
Hi,
I noticed that the text conditioning is done using classifier-free guidance while in the original paper, they use FiLM layers.
Was there a particular reason for this decision?
Thank you, Oliver