วีดีโอ

Interesting tool. 👍

how can we run this on Google colab?

THANK YOU!!!

please help me after installing everything when i try to run the it it show python run.py /Users/XXX/Development/Deep-Live-Cam/myenv/lib/python3.10/site-packages/albumentations/check_version.py:49: UserWarning: Error fetching version info <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:997)> data = fetch_version_info()

How i do lunch this app next time to rerun

Its a nice AI tool, I am trying to convert it into a locally run tool without API and a UI, hopefully it works. Good tutorials by the way.

followed all steps. Doesn't work as pip install -r requirements.txt and afterwards running pip list. Only about 6 files are installed. not the long list that you show in the video

Hello sir can you please install on my hugging face ? i am not into tech thats why

I've spent hours upon hours trying to get this to work. I had watch one of your previous videos and when I saw this video was posted on 9/29. I figured you had the solution, and you came through. Thank you. You've got a new subscriber.

hello, i installed and when i click on submimt, these error come: ModuleNotFoundError: No module named 'face_alignment' No module named 'dlib' No module named 'cv2'

What happened to your face in the end of video 😆

Intro girl looks good. Quality looks better than before. Any new tool you are using?

Another GREAT video tutorial! (I appreciate that you use VENV it's so easy to follow) Sadly, I always get a BLACK image as result (no out of memory). I've tried with 512, 256 and 64... I always get a black image as result. Also, Is it possible to use the DeBlur and the InPaint to the Gradio App? instead of commands? If so can you please make a video or update file to download and share? Thanks ahead! 🙏

Why would you make it fp32 and not keep it fp16? Is this necessary?

after long waiting finally the sadtalker is running again. But one point is not working right for me. after starting i get displayed error in the result field, but the app is running on gpu and saving the result. And it is not in darkmode as in video shown. Any idea what could be the last thing that everything runs perfect`?

Hi - I realize this is not a completely new video - but i'll try anyway. I have followed the steps and gotten to the end without problems - but when i start it (Python app.py) i get the following error: File "F:\V-Express\venv\lib\site-packages\onnx\__init__.py", line 77, in <module> from onnx.onnx_cpp2py_export import ONNX_ML ImportError: DLL load failed while importing onnx_cpp2py_export: A dynamic link library (DLL) initialization routine failed. Any help will be appreciated.

I have updated the installation steps to fix the error related to pydantic. The step is missing in video.

Please IDM-ViTON per again vedio bana den ...... please please......us me bhoot error aa rhy....😢😢😢

Please IDM-ViTON per again vedio bana den ...... please please......us me bhoot error aa rhy....

Please create more tutorials. Your Channel is one of the best for learning easy installations of AI open source tools. 🙂

Thank you, this works flawlessly.

Brother, i tried so many image + audio file models, try to search so many model. It is very few model for this type of create ai avatar speaker. only websites were good but they need subscription. now i announce this video and this model is the first rank model i ever used and i am happy. 1- the time of process is really faster than others. 2- the result of video is very good, 3- eyes + face + lips sync very very good. i installed it and use it immediately. Thank you so much for share this video. thank you.

What are your device specs? + How can this run on Colab and Kaggle?

Please keep posting. There are very few covering Windows installation.

Amazing tutorial. No one create free guide like you. Thank you.

Thank you very much for everything. The only problem is that it takes a long time (more than 30 minutes) to generate one of the sample images. I have a RTX 3060 with 12 GB and 64 GB of RAM, is this normal?

tutorial please

I've tried installing this but the mask doesn't seem to work.

Perfect guide. I tried to install it couple of months back and could not resolve the config.json issue. TQVM

.virtualenvs/oot_diffision/lib/python3.10/site-packages/torch/serialization.py", line 1033, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'. i have error, what do i need?

good explainatiojn thank you so much

29 second audio for 2 hours? my gpu 4070 super. wow, what is your gpu sir? this is so long. maybe we should go for something faster. btw thank you.

amazing, it's enough and good. i hope i can install it.

Interesting ! Does it generate better results than upscayl ?

Awesome. Thanks. Works much better than the background removal plug-in.

hi. do you know any model for comfy ui or any other on windows 10 os so we can create ai avatar speaker? i am searching for a comfy ui model that i give him a photo (my avatar) and a voice file , then comfy ui give me ai avatar speaker video with lip+eye+face sync. i know there are websites to do it but i want to make it in my local pc for free. i have pretty good gpu (4070 super 12gb).

how to make the ai avatar talking with lip and eye and face sync? please tell me i really need the tutorial video. i installed comfy ui and generate image but i want to create ai avatart. i am searching for a way to get image and a voice file and ouput is a video of my ai avatar talking while lip, eyes and face synce.

Thank you

cant find virtual enviornment

Great video, could you tell me how did you make the virtual talking woman at the beginning of this video? Thank you.

Interesting tool. Does it work for only face?

Sir ap ak hindi channel banao please

Add chapters

Looks good 😊

Face restoration feature looks good 👍

EMOPortraits is now available

is it possible to clone hindi language voice and generation of text to speech in hindi langauge

You asked me to show my pip list regarding my the very slow process This is the pip list I’ve been trying to send it as a reply to put previous conversations but it fails Package Version ----------------------- --------------- absl-py 2.1.0 addict 2.4.0 aiofiles 23.2.1 annotated-types 0.7.0 anyio 4.4.0 audioread 3.0.1 basicsr 1.4.2 certifi 2024.8.30 cffi 1.17.0 charset-normalizer 3.3.2 click 8.1.7 colorama 0.4.6 contourpy 1.3.0 cycler 0.12.1 decorator 5.1.1 dlib 19.24.0 einops 0.4.1 exceptiongroup 1.2.2 face_alignment 1.3.4 facexlib 0.2.5 fastapi 0.112.2 ffmpy 0.4.0 filelock 3.15.4 filterpy 1.4.5 fonttools 4.53.1 fsspec 2024.6.1 future 1.0.0 gradio 4.42.0 gradio_client 1.3.0 grpcio 1.66.1 h11 0.14.0 httpcore 1.0.5 httpx 0.27.2 huggingface-hub 0.24.6 idna 3.8 imageio 2.35.1 importlib_metadata 8.4.0 importlib_resources 6.4.4 Jinja2 3.1.4 joblib 1.4.2 kiwisolver 1.4.6 kornia 0.5.1 lazy_loader 0.4 librosa 0.9.2 llvmlite 0.43.0 lmdb 1.5.1 Markdown 3.7 markdown-it-py 3.0.0 MarkupSafe 2.1.5 matplotlib 3.9.2 mdurl 0.1.2 mpmath 1.3.0 networkx 3.3 ninja 1.10.2.3 numba 0.60.0 numpy 1.23.4 opencv-python 4.10.0.84 orjson 3.10.7 packaging 24.1 pandas 2.2.2 pillow 10.4.0 pip 24.2 platformdirs 4.2.2 pooch 1.8.2 protobuf 5.28.0 pycparser 2.22 pydantic 2.8.2 pydantic_core 2.20.1 pydub 0.25.1 Pygments 2.18.0 pyparsing 3.1.4 python-dateutil 2.9.0.post0 python-multipart 0.0.9 pytz 2024.1 PyYAML 6.0.2 requests 2.32.3 resampy 0.4.3 rich 13.8.0 ruff 0.6.3 scikit-image 0.24.0 scikit-learn 1.5.1 scipy 1.13.1 semantic-version 2.10.0 setuptools 63.2.0 shellingham 1.5.4 six 1.16.0 sniffio 1.3.1 soundfile 0.12.1 starlette 0.38.4 sympy 1.13.2 tb-nightly 2.18.0a20240903 tensorboard-data-server 0.7.2 threadpoolctl 3.5.0 tifffile 2024.8.30 tomli 2.0.1 tomlkit 0.12.0 torch 2.1.2+cu121 torchvision 0.16.2+cu121 tqdm 4.66.5 typer 0.12.5 typing_extensions 4.12.2 tzdata 2024.1 urllib3 2.2.2 uvicorn 0.30.6 websockets 12.0 Werkzeug 3.0.4 yapf 0.40.2 zipp 3.20.1

In step 5 I got this response “ python was not found; run without arguments to install from the Microsoft store, or disable this shortcut from settings…”

Great i was looking for this