-
My environment is:
GPU : RTX 3090
cudatoolkit : 11.0.221
pytorch : 1.8.0.dev20201005
torchvision : 0.8.0.dev20201007
any one has solution?
`
C:\Users\pc006\.conda\envs\face2\lib\site…
-
Downloading the detection model to C:\Users\unis\.ifnude/detector.onnx
*** Error loading script: ui.py
Traceback (most recent call last):
File "urllib\request.py", line 1348, in do_open
…
-
Even if deepfakes have gained lot of attention in the wrong reasons, it is known also to be used for movie faking. If you find interesting use case, please post them here
[Edited for content]
Clorr updated
5 years ago
-
I use faceswap gui to train, but meet an error is that 'IndexError: list index out of range'
**To Reproduce**
Steps to reproduce the behavior:
1. Go to swap GUI
2. choose extracted dirctory
…
-
Is it possible to take a face from a photo and put it on a video?
-
Hi really nice work what you are doing here. However, i'm facing a few issues
what clip model are you using? in the json file, its said its model.safetensors
I also got this error when trying to run…
-
经常训练到1200步左右的时候就报错：
Traceback (most recent call last):
File "synthesizer_train.py", line 37, in
train(**vars(args))
File "E:\MockingBird-main\synthesizer\train.py", line 180, in train
…
-
**Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network**
Hai X. Pham, Yuting Wang, Vladimir Pavlovic
https://arxiv.org/pdf/1803.07716.pdf
> Re…
-
I'm just playing with these tools, and it looks like the gfpgan and codeformer chains are realllly slow (like 20 minutes for 300 frames or 10 sec of video). I am on 4x A100's, and bumped threads up t…
-
对于FaceShifter，应该是保留source的id，和target的att，生成同时具有上述特征的新的人脸。观察你的结果，生成人脸的expression基本与source一致，而不是与target一致，猜测可能是idloss中解耦不完全，混入了expression特征。
当然如果故意保留source的expression也是一个很好的方向，类似同时faceswap+face reenact…