Replies: 3 comments 3 replies
-
Masking. For videos either use xseg or clip2seg, images can be done with manual masking or even combined with xseg. |
Beta Was this translation helpful? Give feedback.
3 replies
-
I think best result is "with 0.25 bottom" because the mouth extends far and the effect is better. Not whether with XSEG, appropriately trained, he can be able to "extend the face" |
Beta Was this translation helpful? Give feedback.
0 replies
-
i have same question, but with glasses. How i can keep glasses from input image |
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've tried with 0.25 face bottom offset but it's not realistic enough
Does anyone have any suggestions or tips?
Beta Was this translation helpful? Give feedback.
All reactions