Skip to content

Instantly share code, notes, and snippets.

@whs2k

whs2k/Running DeepFaceLab

Last active April 12, 2020 20:46
Show Gist options
  • Save whs2k/b3fa252a041504e0b6dbed31bc6da264 to your computer and use it in GitHub Desktop.
Save whs2k/b3fa252a041504e0b6dbed31bc6da264 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
Running DeepFaceLab
https://github.com/iperov/DeepFaceLab
#Utils:
#For downloading youtube videos: https://www.y2mate.com/en19
#For spliting videos into images: https://www.online-convert.com/result/74a551a3-0134-4119-90d9-fb7361028642
#For Trimming Videos (WIndows): Right click image and "Open with Photos"
#1. Find Source Video/Images
#2. Find Destination Video/Images
# Extract Images from dst .mp4
chdir Documents\GitHub\DeepFaceLab-DF.wf.288res.384.92.72.22\DeepFaceLab-DF.wf.288res.384.92.72.22
python main.py extract --input-dir workspace\data_dst\Ellen_images --output-dir workspace\data_dst
#Train Model
python main.py train --training-data-src-dir workspace\data_src\aligned_Mr.Bean_Rowan_Atkinson --training-data-dst-dir workspace\data_dst\alinged_Ellen --model-dir models --model SAEHD
#Merge Results
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment