Mr DeepFakes Forums
  • New and improved dark forum theme!
  • Guests can now comment on videos on the tube.
   
Total Likes Received: 84 (0.29 per day | 25.77 percent of total 326)
(Find All Threads Liked ForFind All Posts Liked For) Total Likes Given: 66 (0.23 per day | 20.25 percent of total 326)
(Find All Liked ThreadsFind All Liked Posts)
Reputation:  34
Details

dpfks
(Administrator)
Administrator

Registration Date: 02-25-2018
Date of Birth: Not Specified
Local Time: 12-11-2018 at 12:38 PM
Status:

dpfks's Most Liked Post
Post Subject Numbers of Likes
DeepFaceLab Explained and Usage Tutorial 5
Thread Subject Forum Name
DeepFaceLab Explained and Usage Tutorial Guides
Post Message
DeepFaceLab

NOTE: Making DeepFakes require a NVIDIA GPU with 2GB+ vRAM

I have moved from Faceswap to DeepFaceLab due to ease of use, better outcomes, and a lot of time saved. This tutorial will be a mix of the creator's instructions, and how I use and understand the program. The GitHub can be found here: You are not allowed to view links. Register or Login to view.

You are not allowed to view links. Register or Login to view.

Features:
  • Available as standalone with zero dependencies, ready to be used with prebult binary for all windows versions.
  • New models (H64, H128, DF, LIAEF128, MIAEF128, AVATAR)
  • New architecture, easy to experiement with models
  • Works on 2GB old cards, such as GT730. Example of a deepfake trained on a 2GB gtx850m notebook in 18 hours: You are not allowed to view links. Register or Login to view.
  • Face data embedded in png files
  • Automatically manage GPU by choosing the best GPU(s) and also supports multi GPUs (only for identical cards) - do not use cards in SLI mode.
  • New preview window
  • Extractor in parallel
  • Converter in parallel
  • Added debug option for all stages
  • Added MTCNN extractor which reduces less jitter aligned faces complared to DLIBCNN; however this can produce more false positives in facial recognition.
[Image: You are not allowed to view links. Register or Login to view.]
Left = dlib
Right = MTCNN
  • Manual extractor allows you to fix missed faces, manually, or do full manual extract
[Image: You are not allowed to view links. Register or Login to view.]
[Image: You are not allowed to view links. Register or Login to view.]

Models Types:

H64 (2GB+): 64x64 face resolution, which is used in the original FakeApp or FaceSwap app, but this model in DeepFaceLab uses TensorFlow 1.8 DSSIM Loss function and separated mask decoder and better ConverterMasked. For 2GB and 3GB VRAM model works in reduced mode.

H64 example: Robert Downey Jr

[Image: You are not allowed to view links. Register or Login to view.]

[Image: You are not allowed to view links. Register or Login to view.]

H128 (3GB+): Same as above; however the resolution is improved 128x128 which conserves better face details, and will perform better with higher resolution videos and close-up shots. For 3GB and 4GB VRAM model works in reduced mode.

H128 example: Nicholas Cage

[Image: You are not allowed to view links. Register or Login to view.]

H128 example: Asian face on blurry target

[Image: You are not allowed to view links. Register or Login to view.]

[Image: You are not allowed to view links. Register or Login to view.]

DF (5+GB): dfaker model. Has 128x128 resolution with a full face model. When using this model, it is recommended not to mix src faces with different lighting conditions.

DF example: Nicholas Cage

[Image: You are not allowed to view links. Register or Login to view.]

LIAEF (5GB+): New model which combines DF, IAE and experiments. The model tries to morph the src face into dst while keeping the facial features of src face but less aggressive morphine. This model has problems with closed eyes recognition. 

LIAEF128 example: Nicholas Cage

[Image: You are not allowed to view links. Register or Login to view.]

[Image: You are not allowed to view links. Register or Login to view.]

LIAEF128: Trump to Nicholas Cage example video

[Video: You are not allowed to view links. Register or Login to view.]

LIAEF128YAW (5GB+): Currently testing, but useful for when your src has too many side faces against dst faces. It feeds NN by sorted samples by yaw.

MIAEF128 (5GB+): Same as the model above, but it also tries to match brightness and color features.

MIAEF128 model algorithm:

[Image: You are not allowed to view links. Register or Login to view.]

MIAEF128 success example: Harrison Ford

[Image: You are not allowed to view links. Register or Login to view.]

MIAEF128 fail example: Nicholas Cage

[Image: You are not allowed to view links. Register or Login to view.]

AVATAR (4GB+): non GAN, 256x256 face controlling model.

[Image: You are not allowed to view links. Register or Login to view.]

AVATAR video example:

[Video: You are not allowed to view links. Register or Login to view.]

dpfks's Forum Info
Joined:
02-25-2018
Last Visit:
Today, 07:42 AM
Total Posts:
421 (1.46 posts per day | 27.16 percent of total posts) Find All Posts
Total Threads:
126 (0.44 threads per day | 22.03 percent of total threads) Find All Threads
Time Spent Online:
1 Week, 1 Day, 10 Hours
Thanks/Likes:
Given: 66 | Recieved: 84
Members Referred:
2
dpfks's Contact Details
Additional Info About dpfks
Sex:
Undisclosed