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
Hello all, I have a question that maybe experienced people know the answer of:
I can train beautiful textual inversions with the base v1.5 model. However, when I try to use textual inversion embedding training with a custom model checkpoint, I get crazy nonsensical garbage as output. Why is this so?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello all, I have a question that maybe experienced people know the answer of:
I can train beautiful textual inversions with the base v1.5 model. However, when I try to use textual inversion embedding training with a custom model checkpoint, I get crazy nonsensical garbage as output. Why is this so?
Beta Was this translation helpful? Give feedback.
All reactions