Comments (4)
thanks for report,
your last error is not the same as before,
"face not detect..." that mean there is an image in the video sequence where face is poor quality or bad angle, or ...
you can find the bad image in :
"c:\Users\user\stable-diffusion-webui\extensions\sd-wav2lip-uhq\scripts\wav2lip\temp\faulty_frame.jpg"
to avoid this , you can try to :
- open your video in a video editor
- remove the frame
- save the video
- retry
I know it's not the perfect process but i'll try to make video analyser before send the entire process that could allow to correct this kind of issue
Video can have audio, it's not an issue ;)
from sd-wav2lip-uhq.
Hi,
This error seems to indicate that face could be diffcult to detected in one of the images. Does that sound possible in your situation?
from sd-wav2lip-uhq.
Hello
I think not cause the vidie is good quality and all clear seen there.
Ill try to with other video ald reply here a bit later.
from sd-wav2lip-uhq.
Same story. the soft starts workin but at some point it just give an error.
The video was clear.
Also just to make it clear. Any video can be added? video shoul be without audio? I meen as the audio shoul be added separately does it means that the video shhoul be without audio?
Also coul it be because of ffmpeg? I installed it but not sure is it there I mean how to check it? How ever the errors are not about the ffmpeg so it means that the problem is not about ffmpeg
Any way errors are still there.
from sd-wav2lip-uhq.
Related Issues (20)
- conda Conflict HOT 7
- wav2lip_gan model error
- timers just continue, never processes. HOT 3
- RuntimeError: Detected that PyTorch and TorchAudio were compiled with different CUDA versions. PyTorch has CUDA version 11.8 whereas TorchAudio has CUDA version 11.7. HOT 1
- ImportError: numpy.core.multiarray failed to import
- ValueError: max() arg is an empty sequence HOT 3
- What is the required CUDA version to run this repo reliably? HOT 1
- What does this do?
- 现在可以命令行运行吗?
- No module named 'scripts.wav2lip_uhq_extend_paths' HOT 1
- this extension killed my A1111 i have to install it again (maybe) HOT 1
- Torch not compiled with CUDA enabled HOT 3
- Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check HOT 5
- TypeError: unsupported operand type(s) for -: 'NoneType' and 'int'
- Automatic1111 Ext not work HOT 3
- The mouth does not match on the X-axis. How can I fix this?
- 是缺少模型吗?下载链接有吗
- moov atom not found / float division by zero HOT 2
- Stable Diffusion WEBUI stop working after installing "sd-wav2lip-uhq". CUDA TorchAudio issue. On clean- new virtual env. HOT 7
- Number of frames available for inference: 936 then no run HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sd-wav2lip-uhq.