-
traying the demo on https://replicate.com/cjwbw/video-retalking
getting this error every time
`Traceback (most recent call last):
File "/root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/…
-
hello there,
I am trying to convert swin model to onnx and then tensorrt, but a problem which I face is that it does not support dynamic input resolution after tracing the model using torch.jit.trac…
-
We have used the following snippet to control what happens when moderngl context gets cleared or what render-programs will/can alter when being called. This used to work in 5.9:
```python
# our cu…
-
In ./recongnition/_tools/mask_render.py, II executed `CUDA_VISIBLE_DEVICES=0 python mask_renderer.py t`he utilization rate of GPU is 0, but the CPU is used to complete the data generation. How to use …
-
**Describe the bug**
When testing GroupNorm, some shapes cause stack overflow on trisc0. This is probably caused by inline not always work and. cause the function call depth to blow up.
**To Repro…
-
### Description
Right now, how identities are shown is pretty simple. If someone doesn't have a mask on, you can see their true identity. If someone has a mask on they will show up as Unknown. In /tg…
-
I created a label map with 2 segments and gave voxel value 0.4 to 1 segment and 0.6 to the other. The label map in NIfTI format was originated from the NIfTI PET imaging file using 3D Slicer, thus the…
-
The first stage (sync) uses the lower half of the face, while the second stage (wav2lip) uses the lower half of the face and mask_ Margin=8, will these two different data processing methods affect the…
-
Hi guys
I would like to know if you can give me an Idea in how can I make the `.composite` method accept `geometry` attribute?
Because I can do, via command line, this:
`convert dog-face.jpg -alpha…
-
## About
A unified library for **FaceX** to run all the FaceX algorithms using only one line of code.
## Example
### Running cartoonify using FaceX library
import facex
import cv2
…