Post "Most Advanced 1-Click DeepFake / FaceSwap App Rope, Rope Live, Rope Alucard and Rope NEXT Installers for Windows and Massed Compute and Linux" by "Furkan Gözükara" from patreon

Furkan Gözükara

hey thanks. you are the first one actually joined for fix. i had promised if anyone upgrades to gold tier. lets see if total 5 people joins or you upgrade. i will wait few days and if no one else does i will fix it for you. thanks for join

Shubra Bhatiya

hey furkan im very new in this field and i join you here because of your work if this message reached to you then please fix your google colab 1click_deep_fake_free. thank you

Furkan Gözükara

yes i recommend install tensorrt dlls and set into system path.

patrikeon

Hello Furkan. Do I have to have separate install of Tensor rt in system or just in the gui and wait (for compile). On my system RopeNext seems be running almost only on cpu, got 24gb 4090? Thanks

Furkan Gözükara

yes everything wrong with your setup. first follow this video every step. then install into c:/rope_ai and don't run anything as administrator : https://youtu.be/DrhUHnYfwC0

Greg Thanasoulis

hey my friend can you help me with this? C:\Users\Admin>rope.py Traceback (most recent call last): File "C:\Users\Admin\Rope.py", line 3, in from rope import Coordinator ImportError: cannot import name 'Coordinator' from 'rope' (C:\Users\Admin\AppData\Local\Programs\Python\Python313\Lib\site-packages\rope\__init__.py)

Furkan Gözükara

VisoMaster better newer, Also FaceFusion. I am trying to make VisoMaster working with RTX 5000 series at the moment

Myche Barrett

In your opinion, which would you say is the better of the two... Rope Alucard 24 v13, or the VisoMaster that you recently posted?

Furkan Gözükara

fixed ty for reporting

Hiago Ramos

Rope_Alucard V14 link is broken right now.

Furkan Gözükara

that means you dont have git installed. please follow every step of this video : https://youtu.be/-NjNy7afOQ0

bot

I keep getting this error: ERROR: Could not open requirements file: [Errno 2] No such file or directory: 'requirements_cu124.txt' When I try to run I get this error: D:\Python310\python.exe: can't open file 'D:\\AI\\Rope_Alucard24_V13\\Rope\\Rope.py': [Errno 2] No such file or directory . Can you please help me thank you so much :D

Furkan Gözükara

it still should work ignore it

Furkan Gözükara

you are welcome

Alba

I changed my PC and I forgot to add the ffmpeg to the PATH... thank you very much for your help!

VN Shop

tensorrt-cu12 is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.tom l' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '-- use-pep517' option. Discussion can be found at https://github.com/pypa/pip/issues/8559

Furkan Gözükara

did you install ffmpeg as shown in this video? https://youtu.be/DrhUHnYfwC0

Alba

Hi! When I try to save the video, it doesn't save, and this error appears in the terminal:Unrecognized file type: C:/Users/fym/Desktop/Rope_Alucard24_V13/Faces\Thumbs.db Exception in Tkinter callback Traceback (most recent call last): File "C:\python\lib\tkinter\__init__.py", line 1921, in __call__ return self.func(*args) File "C:\python\lib\tkinter\__init__.py", line 839, in callit func(*args) File "C:\Users\fym\Desktop\Rope_Alucard24_V13\Rope\rope\Coordinator.py", line 54, in coordinator vm.play_video(action[0][1]) File "C:\Users\fym\Desktop\Rope_Alucard24_V13\Rope\rope\VideoManager.py", line 451, in play_video self.sp = subprocess.Popen(args, stdin=subprocess.PIPE) File "C:\python\lib\subprocess.py", line 971, in __init__ self._execute_child(args, executable, preexec_fn, close_fds, File "C:\python\lib\subprocess.py", line 1456, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] El sistema no puede encontrar el archivo especificado Do you know what it could be? Thank you!

Furkan Gözükara

hi it is webcam error and related to your computer. i can connect your pc and try to fix if you upgrade to gold tier. that error not related to my installer

Jonathan Brown

Hi, when I click on Start Rope to use webcam, I get this error [ WARN:0@33.394] global cap_msmf.cpp:1769 CvCapture_MSMF::grabFrame videoio(MSMF): can't grab frame. Error: -2147483638. Please help.

Furkan Gözükara

yes just Rope_Alucard24_V13.zip is good. your error means that you had error during install. please reinstall and email me logs so i can see reason : monstermmorpg@gmail.com also if you upgrade gold tier i can setup for your via connecting your pc

Jackson Lim

Furkan Gözükara

v3 v4 not working anymore. but we have roop unleashed here : https://www.patreon.com/posts/119081500 and we have face fusion here : https://www.patreon.com/posts/103765029

Steve Mrohy

can you share the older version installation files please like v3 and v4 ?

Furkan Gözükara

you are welcome

Todd Duncan

Thank you!

Furkan Gözükara

i have this one did you see? https://youtu.be/whDt36YwEKQ yes rope is not anymore getting updated you can try face fusion too most updated one : https://www.patreon.com/posts/103765029

Todd Duncan

Do you have any tutorials on how to properly set up Rope Alucard's settings? I've been using Rope v4, but it appears it's not supported anymore. I'm just not getting the same results with alucard.

Furkan Gözükara

you are welcome

Furkan Gözükara

sadly it is due to poor programming of the apps by the developers :(

Markus

is there anything I can do to make the GUI not freeze, doesnt seem like its using a lot of resources but its still freezing quite often..

Markus

Now its working perfectly, really impressive work! Thank you so much for doing this man, and so quickly aswell.

Furkan Gözükara

installers updated please download latest version

Markus

Oh okay, thank you for the quick response!

Furkan Gözükara

yes scripts need update hopefully will update tomorrow. sorry for delay. this is due to we updated massed compute image like yesterday

Markus

hey im trying to use the alucard_v12 on mass compute like in the tutorial, but im having problems. When I select the folders in Rope, the video shows up but wont actually play, and the pics doesnt even show up... im getting these two errors: Traceback (most recent call last): File "/usr/lib/python3.10/tkinter/__init__.py", line 1921, in __call__ return self.func(*args) File "/usr/lib/python3.10/tkinter/__init__.py", line 839, in callit func(*args) File "/home/Ubuntu/Desktop/rope_ai/Rope/rope/Coordinator.py", line 58, in coordinator vm.get_requested_video_frame(action[0][1], marker=True) File "/home/Ubuntu/Desktop/rope_ai/Rope/rope/VideoManager.py", line 312, in get_requested_video_frame temp = [self.swap_video(target_image, self.current_frame, marker), self.current_frame] # temp = RGB File "/home/Ubuntu/Desktop/rope_ai/Rope/rope/VideoManager.py", line 885, in swap_video bboxes, kpss_5, kpss = self.func_w_test("detect", self.models.run_detect, img, parameters['DetectTypeTextSel'], max_num=20, score=parameters['DetectScoreSlider']/100.0, use_landmark_detection=use_landmark_detection, landmark_detect_mode=landmark_detect_mode, landmark_score=parameters["LandmarksDetectScoreSlider"]/100.0, from_points=from_points, rotation_angles=rotation_angles) File "/home/Ubuntu/Desktop/rope_ai/Rope/rope/VideoManager.py", line 1038, in func_w_test result = func(*args, **argsv) File "/home/Ubuntu/Desktop/rope_ai/Rope/rope/Models.py", line 195, in run_detect self.retinaface_model = onnxruntime.InferenceSession('./models/det_10g.onnx', providers=self.providers) File "/home/Ubuntu/Desktop/rope_ai/Rope/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 432, in __init__ raise fallback_error from e File "/home/Ubuntu/Desktop/rope_ai/Rope/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 427, in __init__ self._create_inference_session(self._fallback_providers, None) File "/home/Ubuntu/Desktop/rope_ai/Rope/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 483, in _create_inference_session sess.initialize_session(providers, provider_options, disabled_optimizers) RuntimeError: /onnxruntime_src/onnxruntime/python/onnxruntime_pybind_state.cc:887 std::unique_ptr onnxruntime::python::CreateExecutionProviderInstance(const onnxruntime::SessionOptions&, const string&, const ProviderOptionsMap&) CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. *************** EP Error *************** EP Error /onnxruntime_src/onnxruntime/python/onnxruntime_pybind_state.cc:887 std::unique_ptr onnxruntime::python::CreateExecutionProviderInstance(const onnxruntime::SessionOptions&, const string&, const ProviderOptionsMap&) CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. when using ['CUDAExecutionProvider', 'CPUExecutionProvider'] Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying. **************************************** No media selected

Furkan Gözükara

hi yes. facefusion supports check it out but it may require some modifications of .bat files and i dont have amd gpu : https://www.patreon.com/posts/103765029

Griselda

I don't have a Nvidia GPU, it's a AMD, any answer?

Griselda

C:\Rope_Live_Stream_V12>cd Rope-Live C:\Rope_Live_Stream_V12\Rope-Live>set CUDA_PATH= C:\Rope_Live_Stream_V12\Rope-Live>if exist "tensorrt-engines" rmdir "tensorrt-engines" The directory is not empty. C:\Rope_Live_Stream_V12\Rope-Live>if not exist "tensorrt-engines-cu124" mkdir "tensorrt-engines-cu124" C:\Rope_Live_Stream_V12\Rope-Live>call venv\Scripts\activate.bat Traceback (most recent call last): File "C:\Rope_Live_Stream_V12\Rope-Live\Rope.py", line 5, in Coordinator.run() File "C:\Rope_Live_Stream_V12\Rope-Live\rope\Coordinator.py", line 215, in run models = Models.Models() File "C:\Rope_Live_Stream_V12\Rope-Live\rope\Models.py", line 349, in __init__ self.syncvec = torch.empty((1,1), dtype=torch.float32, device='cuda:0') File "C:\Rope_Live_Stream_V12\Rope-Live\venv\lib\site-packages\torch\cuda\__init__.py", line 319, in _lazy_init torch._C._cuda_init() RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx Press any key to continue . . .

Furkan Gözükara

hi dont run as administrator

Griselda

C:\Windows\system32>cd Rope-Live The system cannot find the path specified. C:\Windows\system32>set CUDA_PATH= C:\Windows\system32>if exist "tensorrt-engines" rmdir "tensorrt-engines" C:\Windows\system32>if not exist "tensorrt-engines-cu124" mkdir "tensorrt-engines-cu124" C:\Windows\system32>call venv\Scripts\activate.bat The system cannot find the path specified. C:\Windows\system32>python Rope.py python: can't open file 'C:\\Windows\\system32\\Rope.py': [Errno 2] No such file or directory C:\Windows\system32>pause Press any key to continue . . .

Furkan Gözükara

awesome

Daniels MV

Thanks very much, work on windows and Massed Compute

Furkan Gözükara

ok i just made update to model download repo. can you install again? i added faceparser_resnet34.onnx to remote repo so it should get downloaded

Furkan Gözükara

so maybe alucard need update. i will check it asap hopefully thanks

Daniels MV

On massed coupute with Alucard, when activate : FACE PASER, error : Traceback (most recent call last): File "/usr/lib/python3.10/tkinter/__init__.py", line 1921, in __call__ return self.func(*args) File "/usr/lib/python3.10/tkinter/__init__.py", line 839, in callit func(*args) File "/home/Ubuntu/Downloads/rope_ai/Rope/rope/Coordinator.py", line 62, in coordinator vm.get_requested_video_frame(action[0][1], marker=False) File "/home/Ubuntu/Downloads/rope_ai/Rope/rope/VideoManager.py", line 312, in get_requested_video_frame temp = [self.swap_video(target_image, self.current_frame, marker), self.current_frame] # temp = RGB File "/home/Ubuntu/Downloads/rope_ai/Rope/rope/VideoManager.py", line 948, in swap_video img = self.func_w_test("swap_video", self.swap_core, img, fface[0], fface[1], s_e, fface[2], found_face.get('DFLModel', False), parameters, control) File "/home/Ubuntu/Downloads/rope_ai/Rope/rope/VideoManager.py", line 1038, in func_w_test result = func(*args, **argsv) File "/home/Ubuntu/Downloads/rope_ai/Rope/rope/VideoManager.py", line 1296, in swap_core mask = self.apply_face_parser(swap, parameters) File "/home/Ubuntu/Downloads/rope_ai/Rope/rope/VideoManager.py", line 1679, in apply_face_parser self.models.run_faceparser(img, outpred) File "/home/Ubuntu/Downloads/rope_ai/Rope/rope/Models.py", line 918, in run_faceparser self.faceparser_model = onnxruntime.InferenceSession("./models/faceparser_resnet34.onnx", providers=self.providers) File "/home/Ubuntu/Downloads/rope_ai/Rope/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 419, in __init__ self._create_inference_session(providers, provider_options, disabled_optimizers) File "/home/Ubuntu/Downloads/rope_ai/Rope/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 472, in _create_inference_session sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model) onnxruntime.capi.onnxruntime_pybind11_state.NoSuchFile: [ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from ./models/faceparser_resnet34.onnx failed:Load model ./models/faceparser_resnet34.onnx failed. File doesn't exist edit: i have the same error on windows with ALUCARD, ROPE live work perfect on windows or massed compute

Furkan Gözükara

v4 is not maintained anymore not updated therefore i deleted it. best is rope alucard and rope live. also face fusion 3 : https://www.patreon.com/posts/103765029 - rope alucard and rope live has all features of v4 and more

Gia Bảo Cao

I don't see v4.zip to download. How can I download it?

Furkan Gözükara

please follow this without a single step skip : https://youtu.be/DrhUHnYfwC0 and don't install into there install into C drive

momen sree

its look li i have proplem with "tensorrt-engines" and "tensorrt-engines-cu124" : C:\Users\USER\Documents\Rope>cd Rope-Live C:\Users\USER\Documents\Rope\Rope-Live>set CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4 C:\Users\USER\Documents\Rope\Rope-Live>if exist "tensorrt-engines" rmdir "tensorrt-engines" The directory is not empty. C:\Users\USER\Documents\Rope\Rope-Live>if not exist "tensorrt-engines-cu124" mkdir "tensorrt-engines-cu124" C:\Users\USER\Documents\Rope\Rope-Live>call venv\Scripts\activate.bat how can I solve this please ?

Furkan Gözükara

v4 is not maintained anymore just deleted it. please use rope live or alucard. my mistake

Kirb

buntu@0059-kci-prxmx10122:~/Downloads/Rope_v4$ cd Rope source venv/bin/activate python3 Rope.py bash: venv/bin/activate: No such file or directory Traceback (most recent call last): File "/home/Ubuntu/Downloads/Rope_v4/Rope/Rope.py", line 3, in from rope import Coordinator File "/home/Ubuntu/Downloads/Rope_v4/Rope/rope/Coordinator.py", line 7, in import rope.GUI as GUI File "/home/Ubuntu/Downloads/Rope_v4/Rope/rope/GUI.py", line 3, in import tkinter as tk ModuleNotFoundError: No module named 'tkinter'

Kirb

Followed it with alucard and v4 but still getting the error

Furkan Gözükara

please follow this 5 minute video : https://youtu.be/C1B6U8I14aA

Kirb

Loaded the Alucard into Mass compute but got this when tried to start it cd Rope source venv/bin/activate python3 Rope.py bash: venv/bin/activate: No such file or directory

Furkan Gözükara

well in that case you can only use in massed compute :( we have tutorial for that did you see?

Andrew Tate

I guess I don't have an NVIDIA GPU, since my Display Adapter in device manager only shows Intel(R) UHD Graphics :(

Andrew Tate

After the installation completed, and I start the application through Windows_Start.bat, I get a runtime error saying no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and an installed driver from www.nvidia.com/Download/index.aspx

Furkan Gözükara

True. I will ask massed compute developers whether are there any better remote connection client or not. Rope Client itself works slower on Ubuntu sadly

John Doe

Im using Massed Compute with the A6000 GPU like you mentioned, but using the ThinLinc Client it's super slow, like when i move the terminal windows around its laggy. As for the Rope client, selecting folders is slow too

Furkan Gözükara

you are welcome

Nabil Boulezaz

Got it thank you

Furkan Gözükara

this video shows that : https://youtu.be/whDt36YwEKQ

Nabil Boulezaz

How do you use webcam with this ?

Flynn

Thank you. I'll try that

Furkan Gözükara

amd for facefusion ideas https://poe.com/s/MkUjDKnqsOzFr7l7vbTb if you upgrade to gold member i can connect pc and try

Furkan Gözükara

ok i checked and rope doesnt work without nvidia gpu. however facefusion works both with AMD and CPU. can you install it? https://www.patreon.com/posts/103765029 it has all the features edit bat file and try --execution-providers rocm

Flynn

will do, thank you!

Furkan Gözükara

can you install rope live it is latest version. and let me know if it gives same error. meanwhile i will look command to start it on cpu

Flynn

Rope_V4.zip

Furkan Gözükara

sure i will try. which zip file you installed?

Flynn

can you point me to where I would reconfigure for cpu? When I run the Windows_Start.bat, I am getting the below and not clear how to reconfigure to use the cpu instead: C:\rope_ai\Rope>call venv\Scripts\activate.bat Traceback (most recent call last): File "C:\rope_ai\Rope\Rope.py", line 5, in Coordinator.run() File "C:\rope_ai\Rope\rope\Coordinator.py", line 158, in run models = Models.Models() File "C:\rope_ai\Rope\rope\Models.py", line 42, in __init__ self.syncvec = torch.empty((1,1), dtype=torch.float32, device='cuda:0') File "C:\rope_ai\Rope\venv\lib\site-packages\torch\cuda\__init__.py", line 247, in _lazy_init torch._C._cuda_init() RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

Furkan Gözükara

sadly i don't know. i think facefusion supporting AMD but i don't have AMD so cant test. but it works on CPU

Flynn

is it possible to run your install with an AMD video, not NVidia GPU? Thanks!

Furkan Gözükara

watch this video please and install python 3.10, c++ tools, cuda, cudnn, visual studio : https://youtu.be/DrhUHnYfwC0

Furkan Gözükara

hi you are missing c++ tools and visual studio. please watch this video and apply all without a skip : https://youtu.be/DrhUHnYfwC0

kosak mike

when i run the Window_install.bat i got this erorr: Getting requirements to build wheel ... error error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> [23 lines of output] :28: DeprecationWarning: Use shutil.which instead of find_executable fatal: not a git repository (or any of the parent directories): .git fatal: not a git repository (or any of the parent directories): .git Traceback (most recent call last): File "C:\Users\Sc-Store\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 353, in main() File "C:\Users\Sc-Store\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 335, in main json_out['return_val'] = hook(**hook_input['kwargs']) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Sc-Store\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 118, in get_requires_for_build_wheel return hook(config_settings) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Sc-Store\AppData\Local\Temp\pip-build-env-zhxw5n9j\overlay\Lib\site-packages\setuptools\build_meta.py", line 332, in get_requires_for_build_wheel return self._get_build_requires(config_settings, requirements=[]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Sc-Store\AppData\Local\Temp\pip-build-env-zhxw5n9j\overlay\Lib\site-packages\setuptools\build_meta.py", line 302, in _get_build_requires self.run_setup() File "C:\Users\Sc-Store\AppData\Local\Temp\pip-build-env-zhxw5n9j\overlay\Lib\site-packages\setuptools\build_meta.py", line 503, in run_setup super().run_setup(setup_script=setup_script) File "C:\Users\Sc-Store\AppData\Local\Temp\pip-build-env-zhxw5n9j\overlay\Lib\site-packages\setuptools\build_meta.py", line 318, in run_setup exec(code, locals()) File "", line 67, in AssertionError: Could not find "cmake" executable! [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. error: subprocess-exited-with-error

Furkan Gözükara

hi this happens in few cases first verify your default cuda is 12.4 and also cudnn is 8.9.7 also verify that it downloaded all files when installing

kosak mike

At the moment, I'm having trouble with RopeAlucard not picking up Faces files when chose where the Face Folder location is. And thrown this error: D:\Documents\Faker\ROPEALUCARD\Rope>call venv\Scripts\activate.bat D:\Documents\Faker\ROPEALUCARD\Rope\venv\lib\site-packages\kornia\feature\lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead. @torch.cuda.amp.custom_fwd(cast_inputs=torch.float32) Exception in Tkinter callback Traceback (most recent call last): File "C:\Users\Sc-Store\AppData\Local\Programs\Python\Python310\lib\tkinter\__init__.py", line 1921, in __call__ return self.func(*args) File "D:\Documents\Faker\ROPEALUCARD\Rope\rope\GUIElements.py", line 763, in self.button.configure(command=lambda: self.function()) File "D:\Documents\Faker\ROPEALUCARD\Rope\rope\GUI.py", line 2000, in select_faces_path self.load_input_faces() File "D:\Documents\Faker\ROPEALUCARD\Rope\rope\GUI.py", line 2134, in load_input_faces bboxes, kpss_5, _ = self.models.run_detect(img, detect_mode=self.parameters["DetectTypeTextSel"], max_num=1, score=0.5, use_landmark_detection=self.parameters['LandmarksDetectionAdjSwitch'], landmark_detect_mode=self.parameters["LandmarksDetectTypeTextSel"], landmark_score=0.5, from_points=self.parameters["LandmarksAlignModeFromPointsSwitch"], rotation_angles=rotation_angles) # Just one face here File "D:\Documents\Faker\ROPEALUCARD\Rope\rope\Models.py", line 197, in run_detect bboxes, kpss_5, kpss = self.detect_retinaface(img, max_num=max_num, score=score, use_landmark_detection=use_landmark_detection, landmark_detect_mode=landmark_detect_mode, landmark_score=landmark_score, from_points=from_points, rotation_angles=rotation_angles) File "D:\Documents\Faker\ROPEALUCARD\Rope\rope\Models.py", line 1030, in detect_retinaface io_binding.bind_input(name='input.1', device_type=self.device, device_id=0, element_type=np.float32, shape=aimg.size(), buffer_ptr=aimg.data_ptr()) File "D:\Documents\Faker\ROPEALUCARD\Rope\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 555, in bind_input self._iobinding.bind_input( RuntimeError: Error when binding input: There's no data transfer registered for copying tensors from Device:[DeviceType:1 MemoryType:0 DeviceId:0] to Device:[DeviceType:0 MemoryType:0 DeviceId:0]

kosak mike

what's the performance utilization difference between the Rope_V4 and The RopeAlucard, I'm using a RTX 2070 Graphic Card. And Which Providers Priority for the my system.

Furkan Gözükara

hi i am editing a video that will help you. we need cuda 12.4 and cudnn 8.9.7 - the video will be published hopefully today

Mobs

Hi, I am running in the following error: C:\Rope_Live_Stream_V11>cd Rope-Live C:\Rope_Live_Stream_V11\Rope-Live>call venv\Scripts\activate.bat [ERROR:0@20.224] global obsensor_uvc_stream_channel.cpp:158 cv::obsensor::getStreamChannelGroup Camera index out of range *************** EP Error *************** EP Error C:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:866 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. when using ['CUDAExecutionProvider', 'CPUExecutionProvider'] Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying. **************************************** Exception in Tkinter callback Traceback (most recent call last): File "C:\Rope_Live_Stream_V11\Rope-Live\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in __init__ self._create_inference_session(providers, provider_options, disabled_optimizers) File "C:\Rope_Live_Stream_V11\Rope-Live\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 483, in _create_inference_session sess.initialize_session(providers, provider_options, disabled_optimizers) RuntimeError: C:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:866 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "C:\Python3_10_11\lib\tkinter\__init__.py", line 1921, in __call__ return self.func(*args) File "C:\Rope_Live_Stream_V11\Rope-Live\rope\GUIElements.py", line 763, in self.button.configure(command=lambda: self.function()) File "C:\Rope_Live_Stream_V11\Rope-Live\rope\GUI.py", line 2144, in select_faces_path self.load_input_faces() File "C:\Rope_Live_Stream_V11\Rope-Live\rope\GUI.py", line 2278, in load_input_faces bboxes, kpss_5, _ = self.models.run_detect(img, detect_mode=self.parameters["DetectTypeTextSel"], max_num=1, score=0.5, use_landmark_detection=self.parameters['LandmarksDetectionAdjSwitch'], landmark_detect_mode=self.parameters["LandmarksDetectTypeTextSel"], landmark_score=0.5, from_points=self.parameters["LandmarksAlignModeFromPointsSwitch"], rotation_angles=rotation_angles) # Just one face here File "C:\Rope_Live_Stream_V11\Rope-Live\rope\Models.py", line 435, in run_detect self.retinaface_model = onnxruntime.InferenceSession('./models/det_10g.onnx', providers=self.providers) File "C:\Rope_Live_Stream_V11\Rope-Live\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 432, in __init__ raise fallback_error from e File "C:\Rope_Live_Stream_V11\Rope-Live\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 427, in __init__ self._create_inference_session(self._fallback_providers, None) File "C:\Rope_Live_Stream_V11\Rope-Live\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 483, in _create_inference_session sess.initialize_session(providers, provider_options, disabled_optimizers) RuntimeError: C:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:866 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. I have a fresh install of CUDA 11.8 from your tutorials Running a Geforce A4500 on a virtual machine (could be the reason) I remember having managed a Rope install before so I dont really know what is causing this. Path is set correctly

Furkan Gözükara

you are welcome

DanO..

Thanks buddy.

Furkan Gözükara

hi welcome. it is not necessary anymore with rope live and rope alucard. rope v4 doesnt have tensorrt - use rope live it is best

DanO..

Hi, I'm coming to this late. I downloaded all three zips but none of them had the "Windows_Install_TensorRT_Step2.bat" file in them and I was looking forward to see how it might help with my 3060 which should be able to use it. I don't want to do this live so I just installed Rope_V4. I'm a little lost. Looks like a lot has changed.

Jeff Penny

I'm getting the same error. Did you figure it out?

Furkan Gözükara

you can report in their discord : https://discord.gg/FkFbUQsw

dgtl native

I did. I use the slider. It stays there in idle mode but after starting rec it jumps back to 5.

dgtl native

I did. I moved it with the slider up to 50 and it stays there in idle mode. After I start recording it jumps back to 5

Furkan Gözükara

after putting hit enter or user slider :D

dgtl native

Why does my thread count always jump back to 5, no matter on which value in put it.

Furkan Gözükara

installation error. sadly i cant know which part failed. reinstall and email me install logs : monstermmorpg@gmail.com

jw

RuntimeError: Error when binding input: There's no data transfer registered for copying tensors from Device:[DeviceType:1 MemoryType:0 DeviceId:0] to Device:[DeviceType:0 MemoryType:0 DeviceId:0]

jw

same problem here

Furkan Gözükara

it depends on versions. but usually extract into same folder and overwrite previous files. it should work in almost all cases

Bob Doyle - VR Films

Embarrased to ask such a simple question, but if I have a previous installation from you, should we unzip this on top that installation? Create a new one? Exactly how does this work? Or is this meant to be an entirely new installation? Thank you for your patience.

Tobe2d

Thank you so much!

Furkan Gözükara

you are right just added it to zip files thanks for reply

Tobe2d

Just saw Rope_Live_Stream_V10 This is so cool, but why you stop including the one click update? cant keep up with downloads and remove and install etc etc 😁

Furkan Gözükara

it is unique to do each pc sadly i dont know. maybe you can ask in rope server : https://discord.gg/KneJzHAc

Tobe2d

I did follow the video you attached Kindly, check this screenshot: https://i.ibb.co/VxFB4Wv/2024-09-06-04-07-48-Rope-Next-00.png it is showing my elgato video card not the webcam ;-)

Furkan Gözükara

i dont know give it a try and let me know if works. they added so many new features

Valics Lehel

Would also work lipsync part? I need only lipsync to fix on some videos

Furkan Gözükara

hatta az önce face edit modellerini de ekledim calisiyor

Rollin90sCrips

Çok teşerkkürler.

Furkan Gözükara

şimdi sıfır makine kurdum hata yok. bu şekilde https://pasteboard.co/ilhQkYP44Zlv.png

Furkan Gözükara

what do you mean by? did you follow this video? https://youtu.be/whDt36YwEKQ

Rollin90sCrips

Selam Hocam; Yine aynı hata mesajını alıyorum,resim klasörünü yüklediğimde ve zaten yükleme olmuyor.Video sekmesinde bir ptoblem yok.xception in Tkinter callback Traceback (most recent call last): File "/home/Ubuntu/miniconda3/lib/python3.10/tkinter/__init__.py", line 1921, in __call__ return self.func(*args) File "/home/Ubuntu/Desktop/Rope_Live_Stream_V7/Rope-Live/rope/GUIElements.py", line 763, in self.button.configure(command=lambda: self.function()) File "/home/Ubuntu/Desktop/Rope_Live_Stream_V7/Rope-Live/rope/GUI.py", line 2144, in select_faces_path self.load_input_faces() File "/home/Ubuntu/Desktop/Rope_Live_Stream_V7/Rope-Live/rope/GUI.py", line 2278, in load_input_faces bboxes, kpss_5, _ = self.models.run_detect(img, detect_mode=self.parameters["DetectTypeTextSel"], max_num=1, score=0.5, use_landmark_detection=self.parameters['LandmarksDetectionAdjSwitch'], landmark_detect_mode=self.parameters["LandmarksDetectTypeTextSel"], landmark_score=0.5, from_points=self.parameters["LandmarksAlignModeFromPointsSwitch"], rotation_angles=rotation_angles) # Just one face here File "/home/Ubuntu/Desktop/Rope_Live_Stream_V7/Rope-Live/rope/Models.py", line 437, in run_detect bboxes, kpss_5, kpss = self.detect_retinaface(img, max_num=max_num, score=score, use_landmark_detection=use_landmark_detection, landmark_detect_mode=landmark_detect_mode, landmark_score=landmark_score, from_points=from_points, rotation_angles=rotation_angles) File "/home/Ubuntu/Desktop/Rope_Live_Stream_V7/Rope-Live/rope/Models.py", line 1139, in detect_retinaface io_binding.bind_input(name='input.1', device_type='cuda', device_id=0, element_type=np.float32, shape=aimg.size(), buffer_ptr=aimg.data_ptr()) File "/home/Ubuntu/Desktop/Rope_Live_Stream_V7/Rope-Live/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 555, in bind_input self._iobinding.bind_input( RuntimeError: Error when binding input: There's no data transfer registered for copying tensors from Device:[DeviceType:1 MemoryType:0 DeviceId:0] to Device:[DeviceType:0 MemoryType:0 DeviceId:0]

Tobe2d

Hey, How to change the webcam? as of now I see only the video capturecard and I couldnot find how to change the device to my webcam.

Rollin90sCrips

Elleriniz kollarınız dert görmesin sayın Hocam.saygılarımla,iyi çalışmalar.

Furkan Gözükara

all fixed

Furkan Gözükara

hepsini düzelttim

Furkan Gözükara

all fixed ty

Furkan Gözükara

hepsini düzelttim

Rollin90sCrips

peki hocam,ellerinize sağlık şimdiden

Furkan Gözükara

dünden beri bunla uğraşıyorum scriptleri güncelleyeceğim İnşallah çözersem

Rollin90sCrips

Değerli Hocam ;Merhaba, Yeni güncelleme ile splash versiyonuna geçti ve resim kısmı ,resim çağırmıyor ve aşağıda ki hatayı veriyor,ben düzeltmek için çok uğraştım fakat sonuç elde edemeyince size sormakl istedim ,teşekkürler; [ WARN:0@40.047] global cap_v4l.cpp:999 open VIDEOIO(V4L2:/dev/video0): can't open camera by index [ERROR:0@40.048] global obsensor_uvc_stream_channel.cpp:158 getStreamChannelGroup Camera index out of range Exception in Tkinter callback Traceback (most recent call last): File "/usr/lib/python3.10/tkinter/__init__.py", line 1921, in __call__ return self.func(*args) File "/home/Ubuntu/Desktop/Rope_Live_Stream_v6/Rope-Live/rope/GUIElements.py", line 763, in self.button.configure(command=lambda: self.function()) File "/home/Ubuntu/Desktop/Rope_Live_Stream_v6/Rope-Live/rope/GUI.py", line 2144, in select_faces_path self.load_input_faces() File "/home/Ubuntu/Desktop/Rope_Live_Stream_v6/Rope-Live/rope/GUI.py", line 2278, in load_input_faces bboxes, kpss_5, _ = self.models.run_detect(img, detect_mode=self.parameters["DetectTypeTextSel"], max_num=1, score=0.5, use_landmark_detection=self.parameters['LandmarksDetectionAdjSwitch'], landmark_detect_mode=self.parameters["LandmarksDetectTypeTextSel"], landmark_score=0.5, from_points=self.parameters["LandmarksAlignModeFromPointsSwitch"], rotation_angles=rotation_angles) # Just one face here File "/home/Ubuntu/Desktop/Rope_Live_Stream_v6/Rope-Live/rope/Models.py", line 437, in run_detect bboxes, kpss_5, kpss = self.detect_retinaface(img, max_num=max_num, score=score, use_landmark_detection=use_landmark_detection, landmark_detect_mode=landmark_detect_mode, landmark_score=landmark_score, from_points=from_points, rotation_angles=rotation_angles) File "/home/Ubuntu/Desktop/Rope_Live_Stream_v6/Rope-Live/rope/Models.py", line 1139, in detect_retinaface io_binding.bind_input(name='input.1', device_type='cuda', device_id=0, element_type=np.float32, shape=aimg.size(), buffer_ptr=aimg.data_ptr()) File "/home/Ubuntu/Desktop/Rope_Live_Stream_v6/Rope-Live/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 555, in bind_input self._iobinding.bind_input( RuntimeError: Error when binding input: There's no data transfer registered for copying tensors from Device:[DeviceType:1 MemoryType:0 DeviceId:0] to Device:[DeviceType:0 MemoryType:0 DeviceId:0] (venv) Ubuntu@0056-kci-prxmx10125:~/Desktop/Rope_Live_Stream_v6/Rope-Live$

Furkan Gözükara

i just verified both broken. i just messaged authors for fix. if they dont fix i will revert to an older working commit

Furkan Gözükara

i am working sorry for delay

Mike

Same problem with the demos. Terminal shows a long list of "Unrecognized file type" for everything in the Rope directory and sub-directories

Furkan Gözükara

did you try demo video and image? let me reinstall and try

Furkan Gözükara

Özel'den yazdım :)

Mike

I using the Massed Compute scripts. Rope_V4 works, but I'm having trouble with Live_stream_v6 and Alucard24_V4. When I select a video, it reports that I have not selected any media. It also fails to detect image directory

Osman Uzun

Osman Uzun just now Merhaba. C:\Users\GHOST\Desktop\Deep Fake\Rope>call venv\Scripts\activate.bat Sistem belirtilen yolu bulamıyor. böyle bir hata alıyorum. Videonuzu izleyip buraya geldim. Videoda Venv dosyayı otomatik olarak geliyordu. Şimdi gelmedi. Bunu nasıl çözebilirim ?

Furkan Gözükara

very nice tips ty. yes ffmpeg is mandatory to install and put into path

Exia Cyn

Managed to solve it after inserting; print("Executing:", args) self.sp = subprocess.Popen(args, stdin=subprocess.PIPE) into the videmanager.py script. Seems I needed to install ffmpeg and add it to Path in system variables before it would work. Might be useful for someone else.

Furkan Gözükara

please follow this tutorial without skipping any step and reinstall and it will work : https://youtu.be/-NjNy7afOQ0 also uninstall your existing python. install all things into directly like C:/xyz D:/xyz folders

Furkan Gözükara

won't work because you didn't follow requirements. follow this tutorial without skipping any step and reinstall and it will work : https://youtu.be/-NjNy7afOQ0

Exia Cyn

Unfortunately I can't get this to run; Exception in Tkinter callback Traceback (most recent call last): File "C:\Users\cyndr\AppData\Local\Programs\Python\Python310\lib\tkinter\__init__.py", line 1921, in __call__ return self.func(*args) File "C:\Users\cyndr\AppData\Local\Programs\Python\Python310\lib\tkinter\__init__.py", line 839, in callit func(*args) File "D:\AI Lora Training\Tools\Rope_V4\Rope\rope\Coordinator.py", line 49, in coordinator vm.play_video(action[0][1]) File "D:\AI Lora Training\Tools\Rope_V4\Rope\rope\VideoManager.py", line 370, in play_video self.sp = subprocess.Popen(args, stdin=subprocess.PIPE) File "C:\Users\cyndr\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 971, in __init__ self._execute_child(args, executable, preexec_fn, close_fds, File "C:\Users\cyndr\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 1456, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] The system cannot find the file specified ChatGPT says; The error traceback you've provided indicates that there's an issue with trying to execute a subprocess in a Python script using the subprocess.Popen method. Specifically, the FileNotFoundError: [WinError 2] indicates that the system cannot find the specified file that you are trying to execute. However the video and images are the ones in the tutorial and download. Their location is as installed with no changes.

Ayush Gupta

C:\Users\AYUSH GUPTA\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\python.exe: can't open file 'G:\\rope_ai\\Rope.py': [Errno 2] No such file or directory

Furkan Gözükara

yes get NVIDIA. if you can afford RTX 4090 if not RTX 3090

Ellema

Does it have to be exclusively an NVIDIA card?

Ellema

what kind of graphics card do you recommend?

Furkan Gözükara

please do this. in the main rope-live folder there is data.json. this includes your selected folders etc. you are getting error due to this file. edit it and let me know what you see inside. you can also screenshot. i will forward your message to developer. if you upgrade 25$ gold tier i can connect your pc and solve it as well

Furkan Gözükara

Ok I talked with the author. he said he made so many new updates so it is best to reinstall into C:\rope_live_v4 and let me know the results. i also did a fresh install i see GUI updated and better

Furkan Gözükara

thanks testing now and also talking with developer of rope live

Furkan Gözükara

hello which one of these zip files you have installed? Rope_V4.zip Rope_LandMarks_V4.zip Rope_Live_Stream_v4.zip

Furkan Gözükara

there is this one give it a try after activating venv : https://onnxruntime.ai/docs/install/#install-onnx-runtime-gpu-cuda-12x

Goldwaters

Ah that's too bad. Are there any later CUDA versions that are compatible with onnx? I'd rather not downgrade. I see there is a CUDA 12.6 available but I don't want to update if it will just cause more compatibility issues.

Furkan Gözükara

yes your cuda version is not compatible with onnx runtime. we need 11.8. can you install that as shown in tutorial?

Goldwaters

Python: Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] on win32 Cuda: Cuda compilation tools, release 12.2, V12.2.140 Build cuda_12.2.r12.2/compiler.33191640_0

Furkan Gözükara

this happens when you have installation error. but lets verify something first. can you put demo images and videos into c:/demo and pick that folder and let me know? i wonder if your folder path has non-english letters characters

ku hao

Furkan Gözükara

hello. when do you get this error? like when selecting folder path? did you have any error while installing?

ku hao

Furkan Gözükara

great

Paula Kühn

I reinstalled everything now it works

Furkan Gözükara

please watch this video and follow every step and reinstall and should be fixed easiest way :) https://youtu.be/-NjNy7afOQ0

Paula Kühn

hm how do i check that :)? thing is- i also can export opencv once but then again the program freezes afterwards...

Furkan Gözükara

possibly you are missing ffmpeg. do you see anything on CMD?

Paula Kühn

Hi there! Everything works fine until i press record+play, then the whole program freezes, any hints?

Furkan Gözükara

hi. i need your python version and cuda version open cmd type python open cmd type nvcc --version

Goldwaters

Trying out the new Rope_Live_Stream_v4.zip and getting this error - "ImportError: DLL load failed while importing onnxruntime_pybind11_state: A dynamic link library (DLL) initialization routine failed." I've done a fresh install in a new folder and run the installer scripts (both of them) twice.

Furkan Gözükara

nice tips thanks

Patrick Major

Thank you. Reverting to that version fixed the issue for me. For anyone else having this issue, this is the link to the FFMPEG version that works with Rope_v4: https://github.com/BtbN/FFmpeg-Builds/releases/tag/autobuild-2023-01-31-12-37

Furkan Gözükara

enable audio is only necessary for preview. you dont need to enable it. still i got no error. both preview and replace works. tested on a fresh installation. my ffmpeg version is : C:\Users\King>ffmpeg ffmpeg version N-113484-g9949c1dd78-20240131 Copyright (c) 2000-2024 the FFmpeg developers built with gcc 13.2.0 (crosstool-NG 1.25.0.232_c175b21)

Patrick Major

I thought it was solved, I found that my fix causes audio issues later on in the stream. I was worried about that, am not sure what the mature fix will be and have been bogged down with 12 hr dev days already so might be a few weeks before I get more time to actually see why its broken. This is very easy to replicate from the v4 installer: 1) do fresh install from rope_v4 installer 2) make sure you have the latest FFMPEG installed and it is found correctly in the path 3) start rope 4) open the .\Rope_V4\Example_Face_Video folder for videos and choos the "test_video.mp4" file. 5) on the UX there is an "enable audio" button. click that. 6) click the play button to start the video. While you'll hear audio eventually, go check the python console and you'll possibly see the error message I indicated above. The error appears to be due to unexpected FFMPEG header information from the file. Let me know if this happens for you. It could just be environmental to me, though I checked everything, did a fresh install and same issues. When Rope_v2 was out, I had that running and working with audio fine, it has only been since the update to v4.

Furkan Gözükara

You could try to install ROCm, then install ROCm versions of torch, torchvision, torchaudio in your Rope python env and change "self.provider" in Models.py to "ROCMExecutionProvider" for onnxruntime.

Carlos Ibañez

Hi, i have a Radeon RX 580 Series GPU, will i be able to run it? I tried but at the end the CMD says this : RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx I installed CUDA, but i supose thats not the problem... Can you help me?

Furkan Gözükara

i was trying to replicate your issue with a fresh install but i am glad you solved

Patrick Major

Ok, I did some digging. Some people on the repo tried to find some answer or another, but their code didn't help. While I do not fully know if my code change is 100% the perfect way to go, things seem to be working now for me and I can play videos with audio as well as convert with audio. I have not submitted this to the repo git repo yet as I don't have the time for a bit, but here's the code fix for anyone who just wants this to work right now while we wait for the repo owner to update the code: Open Rope_v4\rope\rope\VideoManager.py at line 291 you will find the lines: if temp[:7] != b' nan': sought_time = float(temp[:7]) replace those lines with the following: if temp[:7] != b' nan': try: sought_time = float(temp[:7]) except: sought_time = 0. the code above and below are fine. Essentially if we a non-valid number we assume the sought_time is 0. This seems to be producing output just fine for me right now. Update: After doing a number of videos, I noticed later on in some of them that the audio starts to get cut-off. So the above solution is not the final solution. The issue appears to be coming due to an extra 8th column containing a header field instead of number data. I can't debug this for a while, so if anyone has solutions in the meantime, let me know as I'd love to see what the overall fix was. I suspect it's just handling the new column info, possibly the new ffmpeg includes columns that are not expected. That might be another workaround if anyone has a moment to try it, but use a version of ffmpeg from say last year and see if that fixes the issue.

Patrick Major

I've had this working with audio just fine not too long ago. I think that was Rope v2? With the v4 installer, I now find when I enable audio the following error: Traceback (most recent call last): File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\tkinter\__init__.py", line 1921, in __call__ return self.func(*args) File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\tkinter\__init__.py", line 839, in callit func(*args) File "G:\_AITools\Rope_V4\Rope\rope\Coordinator.py", line 49, in coordinator vm.play_video(action[0][1]) File "G:\_AITools\Rope_V4\Rope\rope\VideoManager.py", line 292, in play_video sought_time = float(temp[:7]) ValueError: could not convert string to float: b'M-A: ' Does anyone else find this, and if so how did they solve it? This error is occuring even on the video in the sample videos folder provided (test_video.mp4). I've checked my FFMPEG install and its in path and being found (am on Windows so just running the command WHERE FFMPEG allows me to see its install location. I've verified I've got the newest FFMPEG being run by way of activating the rope environment and checking the FFMPEG version and all looks good. From what I can see in the code, it looks like there may be slightly different columns coming from the ffmpeg decoder than expected.

Furkan Gözükara

you need to upgrade your PC or use cloud services. i have full tutorial for cloud too : https://youtu.be/HLWLSszHwEc

Anshul Gupta

can you help me and guide me on how to solve the error "cuda out of memory", I think you should make a video on these types of error

Anshul Gupta

Please help on how to reduce the redundancy of large AI models that is large, how to set the path in each model for each AI program and tool, the same models are used by stable diffusion automatic 1111 web UI and stable swarm UI. How to collect all these models in one place and then how to use them for all AI tools to set the path of folders of these models. Please help me to save space in my pc

Anshul Gupta

this tool is not capable enough to face swap on more than 5-minute long 4k videos, due to overheating PC getting restarted repeatedly. is there a solution to this problem

Furkan Gözükara

awesome thanks for comment

Andrei Koneev

Awesome, works for me!

Furkan Gözükara

I will check and make installer for it hopefully but I am out of city until 17th July. Thanks for reminding me

Mike

The NEXT branch of Alucard’s repo looks like it offers more options for the face parser and different face swapper models (?).

Furkan Gözükara

sorry for late reply. rope landmarks installs latest version of https://github.com/Alucard24/Rope . are there any new repository?

Mike

Will you be updating this for the latest Alucard fork mods?

Mike

I'm experiencing lots of distortion when my target face blinks. Any suggestions?

Furkan Gözükara

awesome ty

Furkan Gözükara

thanks a lot for tips. i also would verify if ffmpeg is properly installed

Steve

This WAS working great. But lately its been stopping just a few frames before the end of the video and not saving the video with NO errors in the cmd window. Anyone know how to fix? TEMPORARY FIX: HITTING RECORD AGAIN seems to force the video to complete and save from the frame it was at which is pretty much good enough for me, normally its click play again to get it to save but that wasn't working. This doesn't happen on all videos I'll check to see if there is something similar about all the videos that have the problem. Also when it is happening its using less then 50% of my vram so not memory related.

Furkan Gözükara

they must have broken it. did you update to latest version? please report this in their discord they are active : https://discord.gg/EcdVAFJzqp

Sahil Sangani

Helllo thanks a lot. but i have one tiny problem GUI comes up merged on half screen. screenshot: https://i.imgur.com/3AfAjdw.png How i drag it ? i have tried a lot UI is just not draggable it seems?!

Furkan Gözükara

hello. what is your graphic card model?

ARFANJR 7

I am running on Windows 11 Pro. I have followed all the instructions given. But when I clicked on the Windows _start bat file, this appeared: C:\Users\USER\Documents\Rope_ai\Rope>call venv\Scripts\activate.bat Traceback (most recent call last): File "C:\Users\USER\Documents\Rope_ai\Rope\Rope.py", line 5, in Coordinator.run() File "C:\Users\USER\Documents\Rope_ai\Rope\rope\Coordinator.py", line 158, in run models = Models.Models() File "C:\Users\USER\Documents\Rope_ai\Rope\rope\Models.py", line 42, in __init__ self.syncvec = torch.empty((1,1), dtype=torch.float32, device='cuda:0') File "C:\Users\USER\Documents\Rope_ai\Rope\venv\lib\site-packages\torch\cuda\__init__.py", line 247, in _lazy_init torch._C._cuda_init() RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx Press any key to continue . . . Please help.

Lou

Everything works great. I appreciate your hard work. Using Windows Installers and have zero complaints. Thanks for keeping this updated!

Furkan Gözükara

message me from discord. i give special support to gold members

사이 진 Alinor

d. furkan, thank you so much , i did every thing you said and i opened rope the latest version but i still need your help with this app how i can get in toch with you?

Furkan Gözükara

updated and fixed. please download Rope_LandMarks_V3.zip

Furkan Gözükara

Nope check what you see in cmd

James Adams

I can't get any faces to appear in Rope. I select a folder that contains faces, then nothing happens. Is there a trick?

Furkan Gözükara

my installer installs python 3.10 if you have python relauncher and thanks for the tips

Jake Anderson

Keep an eye on the console BTW, python can crash but the UI will keep going it just won't do anything. You need to make sure you have ffmpeg installed for the video output to save

Jake Anderson

Shift click works BTW. Click first, hold shift, click last Also you might consider at least for windows bat file giving the option for a path to python. With all the different versions needed I have multiple python installs around. Not a big change to add it, just makes life easy.

Furkan Gözükara

awesome ty so much for the comment

Patrick Major

This works great! Will be sending the guy who developed the Rope app some money for support as its *that* good! I used Deep Face Lab for white a while and it is also very good. The difference is in the usability. DFL (at least when I used it before xmas) required that you have a bunch of normalized face shots and you train the system and it would take forever and ever (at least before I had a good GPU). Rope is a 1 shot inference with such minimal effort to tweaking things. There's still a lot to be improved if it was to get close to DFL or Machine Video Editor (MVE) but it was so good that I was able to get up and running within the hour and generate a high quality version of my daughter's favourite movie (Everything Everywhere all at Once) and I swapped her in for the daughter in the movie. I didn't tell her and it took a bit for her to notice as she stared at the TV strangely. Was awesome once she noticed.

Furkan Gözükara

thank you so much. preparing something else special right now :) first time gui and installer

s h a r k e y

Incredible, appreciate all the effort you are putting into this. 10/10

Furkan Gözükara

thanks a lot for comment

kaivan Doshi

works well, thanks for the tutorial.

Furkan Gözükara

Yes ui freezes. Just wait and you will see frames processing at right bottom. I have shown in tutorial . Also make sure that your vram usage is not max otherwise it may use shared vram and become so slow

Tree Stevens

It installed with no issue. Great work as always! The only thing I don't get yet is how to tell if it is actually running. I hit record, then play, and nothing happens

Furkan Gözükara

Not working on Massed Computer yet we are working on it. I will update thread once

Visalyar

Is it up on Massed Compute?

Furkan Gözükara

After you install git, python, cuda, ffmpeg on ubuntu Rope_V3.zip should work directly on your local computer

Furkan Gözükara

If you want to use on your local linux I have added Massed Compute installers. The repo owner also need to fix relative path though. Redownload zip file : https://github.com/Hillobar/Rope/pull/38