This tag is intended for specific questions about replacing likeness in a video stream.
Questions tagged [deep-fake]
11 questions
3
votes
0 answers
Wave2Lip usage and performance
The actual Question:
Currently opencv is used to write video frames in a single file. Can you append the audio as well directly or is there some other way so you can create small video snippets which can than be broadcastet via rtp protocoll or…
A.J
- 41
- 2
1
vote
0 answers
transformer training loss not decreasing - Val. Acc/cy stuck at 0.58
I am training a multi-branch pytorch based pipeline for deepfake detection. I am trying to implement the following model as presented in the paper:
A Transformer-Based DeepFake-Detection Method
for Facial Organs
(Ziyu Xue, et. al,Electronics 2022 ,1…
Manuel Gk
- 11
- 3
0
votes
0 answers
Can anyone suggest a suitable VDS/VPS service to run deepfacelive?
I have a rather weak video card and despite this I would like to try to run the above program. But I don't know which site is suitable for this
I hope someone has experience in a similar topic, because until I can buy myself a more expensive video…
0
votes
1 answer
vall-e model throws 'NoneType' object has no attribute 'optimizer_name' error while training, how to fix it?
I'm trying to use the vall-e model available on this github repo: https://github.com/enhuiz/vall-e
I clone the repo with the command
git clone --recurse-submodules https://github.com/enhuiz/vall-e.git
I create a virtual environment with the…
Léandre
- 45
- 6
0
votes
0 answers
Tensorflow error running a training model in apple silicon M2
I am using Deepfakelab for macos .
The model runs well on CPU but when i choose GPU , this is the error it throws.
Whats the problem and how can I solve it?
systemMemory: 16.00 GB
maxCacheSize: 5.33 GB
device config
Prashant Pandey
- 9
- 1
0
votes
1 answer
Is it possible to run tensorflow v1.x now on google colab
I have been working on voice deepfake, but every program i used (for example mekatron, tacotron etc) needed tensorflow v1.x which is now unsupported on google colab, is there any way to use it? I am a begginer.
I tried use automatic update program…
0
votes
0 answers
Training the XSeg model for Deepfacelabs fails due to memory error
I'm new to deepfakes and I'm trying to do the 5XSeg) train.bat and everytime it finishes the filtering I get the following error. I use wf, and tried batch sizes from 1-8, always the same result. I have a Ryzen 5 3600, a 3080 Ti and 16 GB of…
user13236845
- 13
- 3
0
votes
1 answer
Can you disable AVX in deepfacelab?
A few month ago I discovered "Deepfacelab", a software with which you can create deepfakes. It is an folder-structure, so open source I guess.
Recently I tried switching from my home pc to a server which can hold multiple graphics-cards to speed up…
Bioheater
- 21
- 2
0
votes
1 answer
CUDA_OUT_OF_MEMORY in PyTorch head2head model
I am executing the head2head model presented in the Github repo here.
When I am running the code using the following command:
./scripts/train/train_on_target.sh Obama head2headDataset
with contents of the train_on_target.sh file…
Mayank Tiwari
- 2,974
- 5
- 30
- 52
0
votes
0 answers
Image stretching from points
I have an image of a face, facial landmark positions of it:
And another image with the landmarks at other positions:
I need to stretch the first image by "dragging" the landmarks to the new positions which are in the second image, in Python (I'm…
Yuval.R
- 1,182
- 4
- 15