Skip to content

Conversation

@bananaman1983
Copy link

@bananaman1983 bananaman1983 commented Nov 24, 2023

image

Very basic implementation of gradio interface

Properly working installation of 3DDFA_V2 is required

  1. contents of the 3DDFA_V2_cropping/ should be copied to the 3DDFA_V2 root. shape_predictor_68_face_landmarks.dat should be ready too
  2. line 15 of gradiodemo.py should be properly modified to reference the 3DDFA_V2 root folder( path_3DDFA = "E:/3DDFA_V2-master/")
  3. post.mp4 and post.ply outputs are stored separately under the 'out/' folder with 6-digit random numeric serials(no duplicate checks, files may get overwritten if crammed)

Implemented fixes from the camenduru and the hack-mans repo

gradio demo for the ease of use
shell script for no segment no loop .ply .mp4 generation from imgage
from the camenduru fork
from the hack-mans repository
added KMP_DUPLICATE_LIB_OK env.
os.isdir===> os.path.isdir
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant