numz / sd-wav2lip-uhq Goto Github PK
View Code? Open in Web Editor NEWWav2Lip UHQ extension for Automatic1111
License: Apache License 2.0
Wav2Lip UHQ extension for Automatic1111
License: Apache License 2.0
I installed the latest version of sd-wav2lip-uhq and kept only sd-wav2lip-uhq in the extensions folder, just to troubleshoot the problem. SD-webui 1.5.1 latest version
Here is the error message from the backend:
Using cuda for inference.
Reading video frames...
Number of frames available for inference: 459
LLVM ERROR: Symbol not found: __svml_cosf4_ha
Please press any key to continue . . .
A1111 can be started with the --api option - the docs are available on http://127.0.0.1:7860/docs
I see, for example, /sdapi/v1/txt2img to access the txt2img functionality. Is there a way to access Wav2lip Studio in a similar fashion? Thanks
*** stderr: Running command git clone --filter=blob:none --quiet https://github.com/suno-ai/bark.git /tmp/pip-req-build-922ue580
*** error: RPC failed; curl 16 Error in the HTTP2 framing layer
*** fatal: expected flush after ref listing
*** error: subprocess-exited-with-error
*** × git clone --filter=blob:none --quiet https://github.com/suno-ai/bark.git /tmp/pip-req-build-922ue580 did not run successfully.
*** │ exit code: 128
*** ╰─> See above for output.
*** note: This error originates from a subprocess, and is likely not a problem with pip.
*** error: subprocess-exited-with-error
*** × git clone --filter=blob:none --quiet https://github.com/suno-ai/bark.git /tmp/pip-req-build-922ue580 did not run successfully.
*** │ exit code: 128
*** ╰─> See above for output.
*** note: This error originates from a subprocess, and is likely not a problem with pip.
*** [notice] A new release of pip is available: 23.0.1 -> 23.2.1
*** [notice] To update, run: python -m pip install --upgrade pip
Launching Web UI with arguments: --no-download-sd-model --xformers --share --listen --enable-insecure-extension-access
Hi, I'm a content creator on YouTube and I was really excited to try out your new extension so I could make a video about it. . . Well in short, I can't get it to work so it would not be a very good video. . . Seriously though this is to be expected since you just released it. Anyway, when I attempt to generate an output I get the following console error. A1111 is up to date, as are all my dependencies. I have downloaded the appropriate models and placed them in the correcto folders. Do you have any idea what I'm doing wrong, or is this in fact a problem with you extension? Thanks!
The author of roop said that the project would not be updated, and facefusion is a replacement project based on roop. So I suggest author integrate this project. Project address is: https://github.com/facefusion/facefusion
Can someone help with this error?
Hi,
Thanks for your great work, can you provide how to use it by command lines? Or do you have any related scripts?
你能给我提供cmd控制台日志吗?
Originally posted by @numz in #39 (comment)
note: This error originates from a subprocess, and is likely not a problem with pip.
Traceback (most recent call last):
File "C:\Users\Derry\Desktop\sd-webui-aki\sd-webui-aki-v4.4\extensions\sd-wav2lip-uhq\install.py", line 10, in
launch.run_pip(f"install {lib}", f"wav2lip_uhq requirement: {lib}")
File "C:\Users\Derry\Desktop\sd-webui-aki\sd-webui-aki-v4.4.launcher\pyinterop.hfkx1kkk0g4q7.zip\swlpatches\progress\launch.py", line 49, in wrapped_run_pip
File "C:\Users\Derry\Desktop\sd-webui-aki\sd-webui-aki-v4.4\modules\launch_utils.py", line 138, in run_pip
return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live)
File "C:\Users\Derry\Desktop\sd-webui-aki\sd-webui-aki-v4.4\modules\launch_utils.py", line 115, in run
raise RuntimeError("\n".join(error_bits))
RuntimeError: Couldn't install wav2lip_uhq requirement: git+https://github.com/suno-ai/bark.git.
Can't make it work. Can you help me with this? ThankYou.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.5.1
Commit hash: 68f336bd994bed5442ad95bad6b6ad5564a5409a
Installing wav2lip_uhq requirement: dlib-bin
Installing wav2lip_uhq requirement: opencv-python
Installing wav2lip_uhq requirement: pillow
Installing wav2lip_uhq requirement: librosa==0.10.0.post2
Installing wav2lip_uhq requirement: opencv-contrib-python
Launching Web UI with arguments: --autolaunch --xformers
*** Error loading script: ui.py
Traceback (most recent call last):
File "C:\AI\SDXL\webui\modules\scripts.py", line 319, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "C:\AI\SDXL\webui\modules\script_loading.py", line 10, in load_module
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "C:\AI\SDXL\webui\extensions\sd-wav2lip-uhq\scripts\ui.py", line 4, in
from scripts.wav2lip.wav2lip_uhq import Wav2LipUHQ
File "C:\AI\SDXL\webui\extensions\sd-wav2lip-uhq\scripts\wav2lip\wav2lip_uhq.py", line 8, in
import dlib
File "C:\AI\SDXL\system\python\lib\site-packages\dlib_init.py", line 19, in
from _dlib_pybind11 import *
ImportError: DLL load failed while importing _dlib_pybind11: A dynamic link library (DLL) initialization routine failed.
*** Error loading script: wav2lip_uhq.py
Traceback (most recent call last):
File "C:\AI\SDXL\webui\modules\scripts.py", line 319, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "C:\AI\SDXL\webui\modules\script_loading.py", line 10, in load_module
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "C:\AI\SDXL\webui\extensions\sd-wav2lip-uhq\scripts\wav2lip_uhq.py", line 15, in
init_wav2lip_uhq()
File "C:\AI\SDXL\webui\extensions\sd-wav2lip-uhq\scripts\wav2lip_uhq.py", line 9, in init_wav2lip_uhq
from ui import on_ui_tabs
File "C:\AI\SDXL\webui\extensions\sd-wav2lip-uhq\scripts\ui.py", line 4, in
from scripts.wav2lip.wav2lip_uhq import Wav2LipUHQ
File "C:\AI\SDXL\webui\extensions\sd-wav2lip-uhq\scripts\wav2lip\wav2lip_uhq.py", line 8, in
import dlib
File "C:\AI\SDXL\system\python\lib\site-packages\dlib_init.py", line 19, in
from _dlib_pybind11 import *
ImportError: DLL load failed while importing _dlib_pybind11: A dynamic link library (DLL) initialization routine failed.
Stable diffision 1.6.0 version, during use, after downloading the plug-in, the name changed to wav2lip studio, and it cannot be used. When opening the plug-in interface, it keeps reporting errors.Is it currently unavailable in version 1.6.0, and is there a limit to the voice duration? python 3.10.11
最终视频的长度是取决于音频长度么?
Hello
I am currently making video+sound. 1080x1920
But I don't see the process in the console, I only see that the video card's cuda is triggered. Somehow it is possible to display the process as when generating in automation, so that the process is visible. Since it is not clear how much more he has to do.
Using cuda for inference.
Reading video frames...
Number of frames available for inference: 114
(80, 1335)
Length of mel chunks: 496
0% 0/4 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 422, in run_predict
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1323, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1051, in call_function
prediction = await anyio.to_thread.run_sync(
File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 867, in run
result = context.run(func, *args)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/ui.py", line 154, in generate
w2l.execute()
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/w2l.py", line 250, in execute
for i, (img_batch, mel_batch, frames, coords) in enumerate(tqdm(gen,
File "/usr/local/lib/python3.10/dist-packages/tqdm/std.py", line 1195, in iter
for obj in iterable:
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/w2l.py", line 114, in datagen
face_det_results = self.face_detect(frames) # BGR2RGB for CNN face detection
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/w2l.py", line 65, in face_detect
detector = face_detection.FaceAlignment(face_detection.LandmarksType._2D,
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/face_detection/api.py", line 59, in init
self.face_detector = face_detector_module.FaceDetector(device=device, verbose=verbose)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/face_detection/detection/sfd/sfd_detector.py", line 24, in init
model_weights = torch.load(path_to_detector)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/safe.py", line 108, in load
return load_with_extra(filename, *args, extra_handler=global_extra_handler, **kwargs)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/safe.py", line 156, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1051, in _legacy_load
typed_storage._untyped_storage._set_from_file(
RuntimeError: unexpected EOF, expected 9218993 more bytes. The file might be corrupted.
Already tried restarting Automatic1111.
still can't see the "Wav2Lip UHQ" menu
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. Please install the TorchAudio version that matches your PyTorch version.
Hi there
I finale understand the issue with code errors so there should not be an interruptions in video/frames where there is no fase on the screen, so the face should always be on the screen to make it works.
So it works but did nothing.
I choose the video, cut out the audio and then insers that video and the same cut audio as an audio.
program perform the task for several hours and as a result now I have the same video with audio. No any animations no effects there were nothing. looks like and output of video converter where I just merge video and audio.
May me I did somethig wrong. I choose revanimated checkpoint and the rest as it was shown in 'code' page.
安装这个插件的时候, ERROR: Could not find a version that satisfies the requirement dlib-bin (from versions: none);
报错电脑,Macbook M1 Pro
尝试指定最新的版本 pip install dlib-bin 19.21.0 也没用;
有木有兄弟解决的,求分享办法;
have any brother solve this problem? give me a handthank you
Hi,
I receive the above error. Is there something I'm missing or need to do to get this to load in A1111? Thank you.
Hi,
My video is not English! and I've created a video using SD+CN using Img2img. (creating a video from existing Video)
So i was wondering if it is possible to use your great project to map the original Video Lips and face motions to the generated Video ( which lacks the accuracy on Lips and face motions)?
Thanks
Regards
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
File "http\client.py", line 1283, in request
File "http\client.py", line 1329, in _send_request
File "http\client.py", line 1278, in endheaders
File "http\client.py", line 1038, in _send_output
File "http\client.py", line 976, in send
File "http\client.py", line 1448, in connect
File "http\client.py", line 942, in connect
File "socket.py", line 845, in create_connection
File "socket.py", line 833, in create_connection
TimeoutError: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。
提示:Python 运行时抛出了一个异常。请检查疑难解答页面。
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\sd-webui-aki-v4\modules\scripts.py", line 382, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "D:\sd-webui-aki-v4\modules\script_loading.py", line 10, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 883, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "D:\sd-webui-aki-v4\extensions\sd-wav2lip-uhq-main\scripts\ui.py", line 8, in <module>
from scripts.faceswap.swap import FaceSwap
File "D:\sd-webui-aki-v4\extensions\sd-wav2lip-uhq-main\scripts\faceswap\swap.py", line 16, in <module>
from ifnude import detect
File "D:\sd-webui-aki-v4\py310\lib\site-packages\ifnude\__init__.py", line 1, in <module>
from .detector import detect
File "D:\sd-webui-aki-v4\py310\lib\site-packages\ifnude\detector.py", line 36, in <module>
download(model_url, model_path)
File "D:\sd-webui-aki-v4\py310\lib\site-packages\ifnude\detector.py", line 16, in download
request = urllib.request.urlopen(url)
File "urllib\request.py", line 216, in urlopen
File "urllib\request.py", line 519, in open
File "urllib\request.py", line 536, in _open
File "urllib\request.py", line 496, in _call_chain
File "urllib\request.py", line 1391, in https_open
File "urllib\request.py", line 1351, in do_open
urllib.error.URLError: <urlopen error [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。>
Downloading the detection model to C:\Users\unis.ifnude/detector.onnx
*** Error loading script: wav2lip_uhq.py
Traceback (most recent call last):
File "urllib\request.py", line 1348, in do_open
File "http\client.py", line 1283, in request
File "http\client.py", line 1329, in _send_request
File "http\client.py", line 1278, in endheaders
File "http\client.py", line 1038, in _send_output
File "http\client.py", line 976, in send
File "http\client.py", line 1448, in connect
File "http\client.py", line 942, in connect
File "socket.py", line 845, in create_connection
File "socket.py", line 833, in create_connection
TimeoutError: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。
提示:Python 运行时抛出了一个异常。请检查疑难解答页面。
/test/SDXL/stable-diffusion-webui$ ./webui.sh --listen
################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################
################################################################
Running on aiteam user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
Using TCMalloc: libtcmalloc_minimal.so.4
Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]
Version: v1.5.2
Commit hash: c9c8485bc1e8720aba70f029d25cba1c4abf2b5c
Installing wav2lip_uhq requirement: dlib-bin
Installing wav2lip_uhq requirement: opencv-python
Installing wav2lip_uhq requirement: pillow
Installing wav2lip_uhq requirement: librosa==0.10.0.post2
Installing wav2lip_uhq requirement: opencv-contrib-python
Installing wav2lip_uhq requirement: git+https://github.com/suno-ai/bark.git
Launching Web UI with arguments: --listen
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
./webui.sh: line 254: 1963 Illegal instruction (core dumped) "${python_cmd}" "${LAUNCH_SCRIPT}" "$@"
Hello,
I installed automatic1111 and It wrk well. I follow instruction of installation but menu not appear. I try to reboot server and menu not appear.
Is there anything I can do to see if there is an error?
Hi. First, the link to s3fd.pth is broken. But I found it elsewhere.
Then, when I try to generate, I get the following errors:
File "C:\StableDiff\venv\lib\site-packages\gradio\routes.py", line 422, in run_predict
output = await app.get_blocks().process_api(
File "C:\StableDiff\venv\lib\site-packages\gradio\blocks.py", line 1323, in process_api
result = await self.call_function(
File "C:\StableDiff\venv\lib\site-packages\gradio\blocks.py", line 1051, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\StableDiff\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\StableDiff\venv\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "C:\StableDiff\venv\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "C:\StableDiff\extensions\sd-wav2lip-uhq\scripts\ui.py", line 43, in generate
w2l.execute()
File "C:\StableDiff\extensions\sd-wav2lip-uhq\scripts\wav2lip\w2l.py", line 223, in execute
mel = audio.melspectrogram(wav)
File "C:\StableDiff\extensions\sd-wav2lip-uhq\scripts\wav2lip\audio.py", line 47, in melspectrogram
S = _amp_to_db(_linear_to_mel(np.abs(D))) - hp.ref_level_db
File "C:\StableDiff\extensions\sd-wav2lip-uhq\scripts\wav2lip\audio.py", line 95, in _linear_to_mel
_mel_basis = _build_mel_basis()
File "C:\StableDiff\extensions\sd-wav2lip-uhq\scripts\wav2lip\audio.py", line 100, in _build_mel_basis
return librosa.filters.mel(hp.sample_rate, hp.n_fft, n_mels=hp.num_mels,
TypeError: mel() takes 0 positional arguments but 2 positional arguments (and 3 keyword-only arguments) were given
Hello...
Thanks for your adaptation of Wav2LIp for Automatic1111 !!
I encountered such a problem. Creating the low resolution video was successful. But the HD process stopped after 279 frames as if the movie was finished.
Processing frame: 265 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 266 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.62it/s]
Processing frame: 267 of 1133 -- 44s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 268 of 1133 -- 44s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 269 of 1133 -- 44s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.64it/s]
Processing frame: 270 of 1133 -- 44s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.66it/s]
Processing frame: 271 of 1133 -- 44s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 272 of 1133 -- 44s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.66it/s]
Processing frame: 273 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 274 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.63it/s]
Processing frame: 275 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 276 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.64it/s]
Processing frame: 277 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 278 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 279 of 1133 -- 43s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.65it/s]
Processing frame: 280 of 1133 -- 43s/it]
[INFO] Create Video output!
[INFO] Extract Audio from input!
[INFO] Add Audio to Video!
[INFO] Done! file save in output/video_output.mp4
系统:mac M1 pro 16G
sd版本:1.4
已经git了[sd-wav2lip-uhq],模型文件也放入了正确文件夹,就是sd的菜单不显示,请各位大佬指导,谢谢。
I'm trying to reuse a video of someone talking to make them say something else but when I process the video using Wav2Lip I can still see the original mouth talking between silence / gaps in the new audio
Is it possible to close the original mouth on a video before adding the new lip movements?
Or is there something we could add to the text prompt to close the mouth as a 1st pass?
Thanks and keep up the good work! 👍
*** Error loading script: wav2lip_uhq.py
Traceback (most recent call last):
File "/Users/chief/stable-diffusion-webui/modules/scripts.py", line 319, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/Users/chief/stable-diffusion-webui/modules/script_loading.py", line 10, in load_module
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in _call_with_frames_removed
File "/Users/chief/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip_uhq.py", line 11, in
init_wav2lip_uhq()
File "/Users/chief/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip_uhq.py", line 7, in init_wav2lip_uhq
from ui import on_ui_tabs
File "/Users/chief/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/ui.py", line 5, in
from scripts.wav2lip.wav2lip_uhq import Wav2LipUHQ
File "/Users/chief/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/wav2lip_uhq.py", line 4, in
import dlib
File "/Users/chief/stable-diffusion-webui/venv/lib/python3.10/site-packages/dlib/init.py", line 19, in
from _dlib_pybind11 import *
ImportError: dlopen(/Users/chief/stable-diffusion-webui/venv/lib/python3.10/site-packages/_dlib_pybind11.cpython-310-darwin.so, 0x0002): Library not loaded: '/opt/homebrew/opt/ffmpeg/lib/libavdevice.59.dylib'
Referenced from: '/Users/chief/stable-diffusion-webui/venv/lib/python3.10/site-packages/_dlib_pybind11.cpython-310-darwin.so'
Reason: tried: '/opt/homebrew/opt/ffmpeg/lib/libavdevice.59.dylib' (no such file), '/usr/local/lib/libavdevice.59.dylib' (no such file), '/usr/lib/libavdevice.59.dylib' (no such file), '/opt/homebrew/Cellar/ffmpeg/6.0_1/lib/libavdevice.59.dylib' (no such file), '/usr/local/lib/libavdevice.59.dylib' (no such file), '/usr/lib/libavdevice.59.dylib' (no such file)
Any way to get around his error?
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 422, in run_predict
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1323, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1051, in call_function
prediction = await anyio.to_thread.run_sync(
File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 867, in run
result = context.run(func, *args)
File "/storage/stable-diffusion/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/ui.py", line 46, in generate
w2luhq.execute()
File "/storage/stable-diffusion/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/wav2lip_uhq.py", line 173, in execute
detector, predictor = self.initialize_dlib_predictor()
File "/storage/stable-diffusion/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/wav2lip_uhq.py", line 146, in initialize_dlib_predictor
predictor = dlib.shape_predictor(self.wav2lip_folder + "/predicator/shape_predictor_68_face_landmarks.dat")
RuntimeError: Unexpected version found while deserializing dlib::shape_predictor.
HI. Thanks so much for implementing this in A1111.
I'm running in Paperspace and confirmed FFmpeg -version: "ffmpeg version 4.2.7-0ubuntu0.1"
However I keep getting this error:
FileNotFoundError: [Errno 2] No such file or directory: 'ffmpeg -y -i /tmp/gradio/5aeb60fa9989b9e4f701c6358b152a2d62947b62/21028_Infiniti_WildWorld-AIRedux_071823_RK.wav -i /notebooks/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/temp/result.avi -strict -2 -q:v 1 /notebooks/sd/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/results/result_voice.mp4'
Any idea if its an FFmpeg issue or something else?
Thanks
这个代码 --face_det_batch_size 1 能不能加到执行代码中,不然没法运行
Right here, motionless,
Still the same after waiting for several hours
python: 3.10.11 • torch: 2.0.1+cu118 • xformers: 0.0.20 • gradio: 3.41.2 •
set det-size: (640, 640)
Reading video frames for face swap...
Using cuda for inference.176 of 176 -
Reading video frames...
Number of frames available for inference: 176
(80, 481)
Length of mel chunks: 176
0%| | 0/2 [00:00<?, ?it/s]
0%|
dev branch 60183eebc37a69545e41cb6b00189609b85129b0
sd-wav2lip-uhq launch error
here`s console log
*** Error loading script: ui.py
Traceback (most recent call last):
File "J:\SDWebUI\modules\scripts.py", line 319, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "J:\SDWebUI\modules\script_loading.py", line 10, in load_module
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\ui.py", line 3, in
from scripts.wav2lip.w2l import W2l
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\wav2lip\w2l.py", line 2, in
import cv2, os, scripts.wav2lip.audio as audio
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\wav2lip\audio.py", line 1, in
import librosa
File "J:\SDWebUI\venv\Lib\site-packages\librosa_init.py", line 211, in
from . import core
File "J:\SDWebUI\venv\Lib\site-packages\librosa\core_init_.py", line 9, in
from .constantq import * # pylint: disable=wildcard-import
^^^^^^^^^^^^^^^^^^^^^^^^
File "J:\SDWebUI\venv\Lib\site-packages\librosa\core\constantq.py", line 1058, in
dtype=np.complex,
^^^^^^^^^^
File "J:\SDWebUI\venv\Lib\site-packages\numpy_init_.py", line 305, in getattr
raise AttributeError(former_attrs[attr])
AttributeError: module 'numpy' has no attribute 'complex'.
np.complex
was a deprecated alias for the builtin complex
. To avoid this error in existing code, use complex
by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use np.complex128
here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
*** Error loading script: wav2lip_uhq.py
Traceback (most recent call last):
File "J:\SDWebUI\modules\scripts.py", line 319, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "J:\SDWebUI\modules\script_loading.py", line 10, in load_module
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\wav2lip_uhq.py", line 15, in
init_wav2lip_uhq()
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\wav2lip_uhq.py", line 9, in init_wav2lip_uhq
from ui import on_ui_tabs
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\ui.py", line 3, in
from scripts.wav2lip.w2l import W2l
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\wav2lip\w2l.py", line 2, in
import cv2, os, scripts.wav2lip.audio as audio
File "J:\SDWebUI\extensions\sd-wav2lip-uhq\scripts\wav2lip\audio.py", line 1, in
import librosa
File "J:\SDWebUI\venv\Lib\site-packages\librosa_init.py", line 211, in
from . import core
File "J:\SDWebUI\venv\Lib\site-packages\librosa\core_init_.py", line 9, in
from .constantq import * # pylint: disable=wildcard-import
^^^^^^^^^^^^^^^^^^^^^^^^
File "J:\SDWebUI\venv\Lib\site-packages\librosa\core\constantq.py", line 1058, in
dtype=np.complex,
^^^^^^^^^^
File "J:\SDWebUI\venv\Lib\site-packages\numpy_init_.py", line 305, in getattr
raise AttributeError(former_attrs[attr])
AttributeError: module 'numpy' has no attribute 'complex'.
np.complex
was a deprecated alias for the builtin complex
. To avoid this error in existing code, use complex
by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use np.complex128
here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
Hi and thanks for great work. Thanks.
I have two issues.
They may be similar to some earlier issues, but being novice, I'm unsure...
Files greater than 896x512, like 720 or1080 it does not seem to work. Gpu stuck at 100%
What is the max video input resolution? I have a 2080 gpu
Tried installing the Nvidia specific A1111 installer, but it did not work, and I had to go with option 2
Every time i run A1111 it does this:
Installing wav2lip_uhq requirement: dlib-bin
Installing wav2lip_uhq requirement: opencv-python
Installing wav2lip_uhq requirement: pillow
Installing wav2lip_uhq requirement: librosa==0.10.0.post2
Installing wav2lip_uhq requirement: opencv-contrib-python
Installing wav2lip_uhq requirement: git+https://github.com/suno-ai/bark.git
If I start without network I get:
venv "C:\Users\Boya PC\sd.webui\webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.5.2
Commit hash: c9c8485bc1e8720aba70f029d25cba1c4abf2b5c
*** Error running install.py for extension C:\Users\Boya PC\sd.webui\webui\extensions\sd-wav2lip-uhq.
*** Command: "C:\Users\Boya PC\sd.webui\webui\venv\Scripts\python.exe" "C:\Users\Boya PC\sd.webui\webui\extensions\sd-wav2lip-uhq\install.py"
*** Error code: 1
*** stdout: Installing wav2lip_uhq requirement: dlib-bin
*** Installing wav2lip_uhq requirement: opencv-python
*** Installing wav2lip_uhq requirement: pillow
*** Installing wav2lip_uhq requirement: librosa==0.10.0.post2
*** Installing wav2lip_uhq requirement: opencv-contrib-python
*** Installing wav2lip_uhq requirement: git+https://github.com/suno-ai/bark.git
*** stderr: Traceback (most recent call last):
*** File "C:\Users\Boya PC\sd.webui\webui\extensions\sd-wav2lip-uhq\install.py", line 10, in
*** launch.run_pip(f"install {lib}", f"wav2lip_uhq requirement: {lib}")
*** File "C:\Users\Boya PC\sd.webui\webui\modules\launch_utils.py", line 136, in run_pip
*** return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live)
*** File "C:\Users\Boya PC\sd.webui\webui\modules\launch_utils.py", line 113, in run
*** raise RuntimeError("\n".join(error_bits))
*** RuntimeError: Couldn't install wav2lip_uhq requirement: git+https://github.com/suno-ai/bark.git.
*** Command: "C:\Users\Boya PC\sd.webui\webui\venv\Scripts\python.exe" -m pip install git+https://github.com/suno-ai/bark.git --prefer-binary
*** Error code: 1
*** stdout: Collecting git+https://github.com/suno-ai/bark.git
*** Cloning https://github.com/suno-ai/bark.git to c:\users\boya pc\appdata\local\temp\pip-req-build-wo4lxrkr
*** stderr: Running command git clone --filter=blob:none --quiet https://github.com/suno-ai/bark.git 'C:\Users\Boya PC\AppData\Local\Temp\pip-req-build-wo4lxrkr'
*** fatal: unable to access 'https://github.com/suno-ai/bark.git/': Could not resolve host: github.com
*** error: subprocess-exited-with-error
*** git clone --filter=blob:none --quiet https://github.com/suno-ai/bark.git 'C:\Users\Boya PC\AppData\Local\Temp\pip-req-build-wo4lxrkr' did not run successfully.
*** exit code: 128
*** See above for output.
*** note: This error originates from a subprocess, and is likely not a problem with pip.
*** error: subprocess-exited-with-error
*** git clone --filter=blob:none --quiet https://github.com/suno-ai/bark.git 'C:\Users\Boya PC\AppData\Local\Temp\pip-req-build-wo4lxrkr' did not run successfully.
*** exit code: 128
*** See above for output.
*** note: This error originates from a subprocess, and is likely not a problem with pip.
Launching Web UI with arguments:
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
Loading weights [6ce0161689] from C:\Users\Boya PC\sd.webui\webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
*** Error executing callback ui_tabs_callback for C:\Users\Boya PC\sd.webui\webui\extensions\sd-wav2lip-uhq\scripts\wav2lip_uhq.py
Traceback (most recent call last):
File "C:\Users\Boya PC\sd.webui\webui\extensions\sd-wav2lip-uhq\scripts\ui.py", line 68, in on_ui_tabs
audio_example = gr.Audio(label="Audio example",
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\components.py", line 2390, in init
IOComponent.init(
File "C:\Users\Boya PC\sd.webui\webui\modules\scripts.py", line 654, in IOComponent_init
res = original_IOComponent_init(self, *args, **kwargs)
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\components.py", line 215, in init
else self.postprocess(initial_value)
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\components.py", line 2591, in postprocess
file_path = self.make_temp_copy_if_needed(y)
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\components.py", line 259, in make_temp_copy_if_needed
temp_dir = self.hash_file(file_path)
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\components.py", line 223, in hash_file
with open(file_path, "rb") as f:
OSError: [Errno 22] Invalid argument: 'https://dl.suno-models.io/bark/prompts/prompt_audio/en_speaker_0.mp3'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\Boya PC\sd.webui\webui\modules\script_callbacks.py", line 153, in ui_tabs_callback
res += c.callback() or []
File "C:\Users\Boya PC\sd.webui\webui\extensions\sd-wav2lip-uhq\scripts\ui.py", line 37, in on_ui_tabs
with gr.Blocks(analytics_enabled=False) as wav2lip_uhq_interface:
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\blocks.py", line 1411, in __exit__
self.config = self.get_config_file()
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\blocks.py", line 1378, in get_config_file
props = block.get_config() if hasattr(block, "get_config") else {}
File "C:\Users\Boya PC\sd.webui\webui\venv\lib\site-packages\gradio\components.py", line 2408, in get_config
"value": self.value,
AttributeError: 'Audio' object has no attribute 'value'
Creating model from config: C:\Users\Boya PC\sd.webui\webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Thanks for being a Gradio user! If you have questions or feedback, please join our Discord server and chat with us: https://discord.gg/feTf9x3ZSB
Running on local URL: http://127.0.0.1:7860
To create a public link, set share=True
in launch()
.
Startup time: 21.4s (launcher: 12.9s, import torch: 3.3s, import gradio: 0.8s, setup paths: 0.8s, other imports: 0.9s, load scripts: 1.6s, create ui: 0.4s, gradio launch: 0.5s, app_started_callback: 0.1s).
Applying attention optimization: Doggettx... done.
Model loaded in 3.9s (load weights from disk: 0.7s, create model: 0.4s, apply weights to model: 0.8s, apply half(): 0.7s, move model to device: 1.1s).
This is really cool and I would like to request some kind of control for the lip-sync.
For example, the way the lips are moving should be based on some parameters and based on audio frequency (+Increase or -Decrease)
Or something that can help control the amount of movments to the lips.
Would love to see if this could be converted to ComfyUI as a node.
Hi!
Trying to install this extension. But after installing and restarting the UI an error is thrown.
I am using the portable build A1111 by Xpuct and all the extensions I have installed are working properly. This build is updated with the original version. FFMPEG and other dependencies are installed, paths are set.
Screenshots of the error THERE
Is there any solution to this problem?
I see the rpocess obviously running on cpu, and filling my memory in my task managerm cpu at 100%, even tough it said Using cuda for inference
. Would it be possible to add some more cheks and error raising to avoid this situation?
Hello, I installed your extension but sadly after it generates it crashes after the last frame is done.
I'm using Auto 1.5XX
Here is the error output:
Processing frame: 135 of 135 --
Traceback (most recent call last):
File "E:\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 422, in run_predict
output = await app.get_blocks().process_api(
File "E:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1323, in process_api
result = await self.call_function(
File "E:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1051, in call_function
prediction = await anyio.to_thread.run_sync(
File "E:\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "E:\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "E:\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "E:\stable-diffusion-webui\extensions\sd-wav2lip-uhq\scripts\ui.py", line 46, in generate
w2luhq.execute()
File "E:\stable-diffusion-webui\extensions\sd-wav2lip-uhq\scripts\wav2lip\wav2lip_uhq.py", line 243, in execute
cv2.destroyAllWindows()
cv2.error: OpenCV(4.7.0) D:\a\opencv-python\opencv-python\opencv\modules\highgui\src\window.cpp:1266: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvDestroyAllWindows'
thanks in advance for your help,
macbook m1 is using cpu to generate video, very slow
I found HDTR Net intereseting, tested it on CMD line, and seems to produce good results.
https://github.com/yylgoodlucky/HDTR-Net
Maybe it´s an good alternate for the mouth restauration.
What do you think @numz ?
*** Error loading script: wav2lip_uhq.py
Traceback (most recent call last):
File "D:\sd\sd-webui-aki-v4\modules\scripts.py", line 382, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "D:\sd\sd-webui-aki-v4\modules\script_loading.py", line 10, in load_module
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in _call_with_frames_removed
File "D:\sd\sd-webui-aki-v4\extensions\sd-wav2lip-uhq\scripts\wav2lip_uhq.py", line 11, in
init_wav2lip_uhq()
File "D:\sd\sd-webui-aki-v4\extensions\sd-wav2lip-uhq\scripts\wav2lip_uhq.py", line 7, in init_wav2lip_uhq
from ui import on_ui_tabs
File "D:\sd\sd-webui-aki-v4\extensions\sd-wav2lip-uhq\scripts\ui.py", line 7, in
from scripts.bark.tts import TTS
File "D:\sd\sd-webui-aki-v4\extensions\sd-wav2lip-uhq\scripts\bark\tts.py", line 5, in
from bark.generation import (
ModuleNotFoundError: No module named 'bark.generation'
提示:Python 运行时抛出了一个异常。请检查疑难解答页面。
I used this plugin in one of my recent projects and needed to rewrite the ui. Could you please provide the interface documentation? Thank you so much
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.