Textual Inversion
#1059
Replies: 3 comments
-
|
TI wont allow you to train a real model: It's just a compliment and a way to "trick it" into what you want from a 5 image baseline... You still need to cherrypick from 1000 generations to get really good results. But yeah, +1 for the suggestion. |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
I would love to see that too! |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
Dreambooth is Far far superior |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Will this ever be added to the GUI, please! This would be cool to personalize images!
More specifically to upload your own images and train off of those. Maybe there is a way to already do it that I am not aware of.
Beta Was this translation helpful? Give feedback.
All reactions