DON’T RECOMMEND DOWNLOADING THIS. IT IS NOT FINISHED AND IT WILL NOT BE IN THE NEAR FUTURE. I DON’T HAVE TIME FOR THIS. YOU CAN DO WHATEVER YOU WANT WITH MY CODE. SORRY!
This application can change faces in videos. Please don’t use it to make porn if you do not have permission from the person you want to see to do some nasty stuff.
This article is about my version of FakeApp from DeepFakes. FakeApp v1 or v2 didn’t work for me so I implemented my own User Interface.
I am reading all the comments. So if you want to improve something write it here.
Known issues (needed improvements):
- configurable temporary directory
- running “Extract frames” and “Extract faces” on GPU
- CNN takes a long time to recognize a face (also this)
- build Tensorflow with avx, sse
- save a copy of merged files to your data folder
- way to merge the images without using a video
Backend of my application is downloaded from FaceSwap repository. It is running on standalone version of Python (WinPython).
The rest is implemented in C# using WPF application. This app should be standalone and the only thing you need to install is CUDA 9.0 and cuDNN 7.0 if you want to use GPU instead of CPU. Note that if you want to use GPU, you have to have graphic card with CUDA capability at least 3.0.
You can download installer of MyFakeApp here (only x64 for Windows):
You can also modify this application by downloading my repository (Visual Studio solution):
Note: The first build will take a long time, because it is extracting FaceSwap application from zip.
ScreenShots:
How do I use this on a laptop with Intel hd3000 graphics? I don’t have the money or room for a bulky archaic PC
LikeLike
> Buys new inferior laptop
> complains it’s not as good as “archaic” technology
LikeLike
What I mean is, the architecture of a PC is archaic. And no one is complaining here sir.
LikeLike
Guys if anyone had successfully conversion with an AMD cpu or gpu. i would appreciate it if u could reply because i am drowning in errors .
LikeLike
It need instruction. IDK what all these buttons do. Extract frames? huh? Faces, train… Idk what to do
LikeLike
You shouldn’t be here if you don’t know the definitions of those words.
LikeLike
….
LikeLike
Hope to develop OpenCL
LikeLike
“dont make porn videos without the permission of the person” haha this is the internet, if it exists there is porn of it xD
LikeLike
When i export the Video its only black, but the file is a little bit bigger then the processed video. Anyone knows what i am doing wrong?
LikeLiked by 1 person
Hi, is there any way to make this work with newer versions of Cuda? Older versions of Cuda are no longer available, I have Cuda 10.1 but when I try to train with GPU it just says it can’t find Cuda 9 & won’t recognise Cuda 10.1 so I’m forced to try traing using my CPU.
LikeLike
Hi, I got an error.
AttributeError: module ‘keras.utils.conv_utils’ has no attribute ‘normalize_data_format’
How can I fix this problem?
LikeLike
How to use
LikeLike
Hi I want to make a video but I don’t know anything about your app kindly help if you can
LikeLike
这是AMD最后的救星。
LikeLike
Help please:
LikeLike
Help please: https://prnt.sc/oyx42z
LikeLike
a gray colored mask is coming on the edited video ? whats the issue
LikeLike
i am not able to convert video
LikeLiked by 1 person
This blog about MyFakeApp – FakeApp alternative has helped me a lot,
is very well written. I used this fat burner product:
https://s96.me/fit and I reached the ideal weight. Kiss you All!
LikeLike
When i try to create a video it says not able to create frames
LikeLike
When i try to create a video it says not able to create frames
LikeLike
点击训练后闪退
LikeLike