This PR needs some testing before merging, so I'm creating it as a draft.

Based on my previous contribution to AliaksandrSiarohin/first-order-model#55.

Building

docker build -t avatarify .

Running

docker run -it --rm --gpus=all -p 5557:5557 -p 5558:5558 avatarify

ffmpeg version 4.1.4-1build2 Copyright (c) 2000-2019 the FFmpeg developers
  built with gcc 9 (Ubuntu 9.2.1-4ubuntu1)
  configuration: --prefix=/usr --extra-version=1build2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
  libavutil      56. 22.100 / 56. 22.100
  libavcodec     58. 35.100 / 58. 35.100
  libavformat    58. 20.100 / 58. 20.100
  libavdevice    58.  5.100 / 58.  5.100
  libavfilter     7. 40.101 /  7. 40.101
  libavresample   4.  0.  0 /  4.  0.  0
  libswscale      5.  3.100 /  5.  3.100
  libswresample   3.  3.100 /  3.  3.100
  libpostproc    55.  3.100 / 55.  3.100
0: ./avatars/mona.jpg
cam_fomm.py:26: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
  config = yaml.load(f)
[mjpeg @ 0x561a4d0f8a00] Format mjpeg detected only with low score of 25, misdetection possible!
Input #0, mjpeg, from 'pipe:0':                                                                                                                           
  Duration: N/A, bitrate: N/A
    Stream #0:0: Video: mjpeg, yuvj420p(pc, bt470bg/unknown/unknown), 640x480 [SAR 1:1 DAR 4:3], 25 tbr, 1200k tbn, 25 tbc
Stream mapping:
  Stream #0:0 -> #0:0 (mjpeg (native) -> rawvideo (native))
[swscaler @ 0x561a4d153040] deprecated pixel format used, make sure you did set range correctly
[video4linux2,v4l2 @ 0x561a4d0fe680] ioctl(VIDIOC_G_FMT): Invalid argument                                                                                
Could not write header for output file #0 (incorrect codec parameters ?): Invalid argument                                                                
Error initializing output stream 0:0 --                                                                                                                   
Conversion failed!                                                                                                                                        
Traceback (most recent call last):
  File "cam_fomm.py", line 173, in <module>
    sys.stdout.buffer.write(buf)
BrokenPipeError: [Errno 32] Broken pipe
Exception ignored in: <_io.TextIOWrapper name='<stdout>' mode='w' encoding='utf-8'>
BrokenPipeError: [Errno 32] Broken pipe

Hi,

I pull the last commit, executed again the install.sh and tryed run:

bash run.sh

But this error occours:

(avatarify) eltonnunes@eltonnunes-home:~/Repository/others/avatarify$ bash run.sh 0: ./avatars/einstein.jpg 1: ./avatars/eminem.jpg 2: ./avatars/jobs.jpg 3: ./avatars/mona.jpg 4: ./avatars/obama.jpg 5: ./avatars/potter.jpg 6: ./avatars/ronaldo.png 7: ./avatars/schwarzenegger.png load checkpoints.. cam_fomm.py:34: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. config = yaml.load(f) Traceback (most recent call last): File "cam_fomm.py", line 231, in stream = pyfakewebcam.FakeWebcam(f'/dev/video{opt.virt_cam}', frame.shape[1], frame.shape[0]) File "/home/eltonnunes/.conda/envs/avatarify/lib/python3.8/site-packages/pyfakewebcam/pyfakewebcam.py", line 54, in init fcntl.ioctl(self._video_device, _v4l2.VIDIOC_S_FMT, self._settings) OSError: [Errno 22] Invalid argument

Anyone can help ?

My OS: Linux Mint 19.3 Cinnamon

Describe the bug

To Reproduce

Info (please complete the following information):

• OS (e.g., Linux):
• GPU model:

• Any other relevant information:

Screenshots

Logs

I am on latest Ubuntu I have installed correctly and updated everything but when I run bash run.sh then it didn't. Run so I run with sudo bash run.sh but so it sometime shows me avatar list to select and sometimes it open webcam and when I press X and configure my face than multiple cam windows start opening and I can't understand what's the issue and how to fix it please help me out

RuntimeError: CUDA error: no kernel image is available for execution on the device

I have a Windows 10 machine with Nvidia GTX Titan card. Nvidia says it supports CUDA 3.5 which I think is the minimum required?

Also I read in the notes that it should fall to the CPU if the GPU isn't supported? How would I configure that if the card is the problem?

Windows 10 system.

Traceback (most recent call last): File "cam_fomm.py", line 13, in from sync_batchnorm import DataParallelWithCallback ModuleNotFoundError: No module named 'sync_batchnorm'

Seeing the landmarks of both the current frame and the avatar can make it easier to get a good pose. I also thought it was interesting to expose a little of the underlying techniques

Hi, I want to run avatarify on macOS, but I need to use google colab... How do I find the IP address of the notebook so I can connect to the server? I tried to put the !curl ipecho.net/plain command in the notebook and I received an IP, but when I use this IP, the terminal is stuck on Receiving from.

This is the google colab command:

and this is what I see in the terminal:

Error when running run_windows.bat

File "cam_fomm.py", line 11, in import cv2 ImportError: DLL load failed: The specified module could not be found.

Tried to install different opencv libraries to no avail. Any ideas how to solve this?

(base) E:\avatarify>run_windows.bat --is-client --in-addr tcp://2.tcp.eu.ngrok.io:10176 --out-addr tcp://0.tcp.eu.ngrok.io:12257 Traceback (most recent call last): File "afy/cam_fomm.py", line 4, in import yaml ModuleNotFoundError: No module named 'yaml'

Describe the bug

initially the tar file has a 3 textbook icon but whenever I download it now it shows a regular file icon and that is the problem. Even if you move it into the right directory it’s still gonna show file not found

Info (please complete the following information):

• OS (windows 10 home):
• GPU model: GeForce 1660 ti,windows 10 home, 6gb graphics

• Any other relevant information:

Screenshots

Logs

Hello guys, I really need a bit of help running Avatarify on the Google Colab server since I use a Mac. I already have Miniconda and unpacked the repositories in the Avatarify Folder. I was following the steps for running on google collab, everything was going just about right until the "start the worker" section of the code. Can anyone advise on what to do. I have a screenshot of th result attached to this

Laptop shutdown due to overheating, now I open avatarify.... it’s working fine but I can’t find the avatar folder to add new model or remove existing ones. I’ve search every where but nothing. Pls help.

I have a problem, after I give the git clone command and equip it using the cd avatarify python command, I try to compile with the other command and this error returns me "avatarify python failed solving environment",what i do?

option --use-feature: invalid choice: '2020-resolver' (choose from "fast-deps', 'truststor che')

I tried installing from scratch as I always does that work fine but now when I try ruining the scripts.windows.bat it gives me this at the end process