- This topic has 1 reply, 2 voices, and was last updated 6 months ago by
.
Viewing 1 reply thread
-
Posts
-
-
I took a look at the “explanation” on huggingface but don’t really understand what SelfAttentionGuidance and Style Align in SDForge does. What I see when I activate it is not entirely clear to me either. SelfAttentionGuidance looks good and seems to enhance the brilliance of the image (?), but what does Style Align do?
-
I am reading the paper and the codes. It applies a blur to the latent to the elements selected by the cross attention process, which are supposed to be spatial elements that are important.
It is the latent image that the final image steers away from. I plan to write an article along with a usage guide.
-
Viewing 1 reply thread
- You must be logged in to reply to this topic.
