Why we need two tokenizer in the train_dreambooth_lora_sdxl #7281
Unanswered
daiyixiang666
asked this question in
Q&A
Replies: 2 comments
-
|
We want to get the pooled embedding, I got this |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
SDXL uses two different text encoders. That's why. |
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
-
I am a starter and I have a question that why we need two tokenizer to trian the lora in train_dreambooth_lora_sdxl, I am some of confused
Beta Was this translation helpful? Give feedback.
All reactions