Can we train the clip model to automatically expand the command content of the kontext model and improve image quality? #2162
Unanswered
CaiNiaoCYY
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Changing the background of kontext requires a very detailed description. This requires language model expansion. Can the clip model be trained to understand the relationship between simple and complex backgrounds, and automatically supplement background descriptions?
Beta Was this translation helpful? Give feedback.
All reactions