search

C0untFloyd / roop-unleashed

Evolved Fork of roop with Web Server and lots of additions
GNU Affero General Public License v3.0
2.23k stars 518 forks source link

AMD cuda error #688

Closed turkiet closed 5 months ago

turkiet commented 5 months ago

`FFmpeg is already installed. Skipping FFmpeg installation as it is already available. Launching roop unleashed Check for Updates? [y/n]n Launching App Using provider ['CUDAExecutionProvider'] - Device:cuda

Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). download_path: E:\yapay-zeka\roop-unleashed\roop-unleashed\models\buffalo_l Downloading E:\yapay-zeka\roop-unleashed\roop-unleashed\models\buffalo_l.zip from https://github.com/deepinsight/insightface/releases/download/v0.7/buffalo_l.zip... 100%|███████████████████████████████████████████████████████████████████████| 281857/281857 [00:13<00:00, 21374.96KB/s] EP Error EP Error D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=261996208 ; hostname=DOGUKAN ; file=D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_executionprovider.cc ; line=245 ; expr=cudaSetDevice(info.device_id);

when using ['CUDAExecutionProvider'] Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.

EP Error EP Error D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=264029904 ; hostname=DOGUKAN ; file=D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_executionprovider.cc ; line=245 ; expr=cudaSetDevice(info.device_id);

when using ['CUDAExecutionProvider'] Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.

Traceback (most recent call last): File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in init self._create_inference_session(providers, provider_options, disabled_optimizers) File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 483, in _create_inference_session sess.initialize_session(providers, provider_options, disabled_optimizers) RuntimeError: D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=264029904 ; hostname=DOGUKAN ; file=D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_executionprovider.cc ; line=245 ; expr=cudaSetDevice(info.device_id);

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\queueing.py", line 566, in process_events response = await route_utils.call_process_api( File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api output = await app.get_blocks().process_api( File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\blocks.py", line 1847, in process_api result = await self.call_function( File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\blocks.py", line 1445, in call_function prediction = await utils.async_iteration(iterator) File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\utils.py", line 629, in async_iteration return await iterator.anext() File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\utils.py", line 622, in anext return await anyio.to_thread.run_sync( File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\anyio_backends_asyncio.py", line 2144, in run_sync_in_worker_thread return await future File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\anyio_backends_asyncio.py", line 851, in run result = context.run(func, *args) File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\utils.py", line 605, in run_sync_iterator_async return next(iterator) File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\gradio\utils.py", line 788, in gen_wrapper response = next(iterator) File "E:\yapay-zeka\roop-unleashed\roop-unleashed\ui\tabs\faceswap_tab.py", line 621, in start_swap batch_process_regular(list_files_process, mask_engine, clip_text, processing_method == "In-Memory processing", imagemask, num_swap_steps, progress, SELECTED_INPUT_FACE_INDEX) File "E:\yapay-zeka\roop-unleashed\roop-unleashed\roop\core.py", line 218, in batch_process_regular process_mgr.initialize(roop.globals.INPUT_FACESETS, roop.globals.TARGET_FACES, options) File "E:\yapay-zeka\roop-unleashed\roop-unleashed\roop\ProcessMgr.py", line 126, in initialize p.Initialize(extoption) File "E:\yapay-zeka\roop-unleashed\roop-unleashed\roop\processors\FaceSwapInsightFace.py", line 36, in Initialize self.model_swap_insightface = onnxruntime.InferenceSession(model_path, sess_options, providers=roop.globals.execution_providers) File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 432, in init raise fallback_error from e File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 427, in init self._create_inference_session(self._fallback_providers, None) File "E:\yapay-zeka\roop-unleashed\installer_files\env\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 483, in _create_inference_session sess.initialize_session(providers, provider_options, disabled_optimizers) RuntimeError: D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=264029904 ; hostname=DOGUKAN ; file=D:\a_work\1\s\onnxruntime\core\providers\cuda\cuda_executionprovider.cc ; line=245 ; expr=cudaSetDevice(info.device_id);`

My gpu is AMD. my OS is Windows 10

https://github.com/C0untFloyd/roop-unleashed/wiki/Installation I did what it says here for AMD. I get this error when I add a face and press "start" (both times it gives me an error) hata

lysxelapsed commented 5 months ago

Cuda is for Nvidia cards, directml for AMD cards (which one?). If everything is installed properly, directml should show up as provider in the settings tab. Select that, apply settings and restart roop-unleashed.

turkiet commented 5 months ago

Cuda is for Nvidia cards, directml for AMD cards (which one?). If everything is installed properly, directml should show up as provider in the settings tab. Select that, apply settings and restart roop-unleashed.

directml is not visible.

https://github.com/C0untFloyd/roop-unleashed/wiki/Installation I followed this link for the AMD installation. My gpu is RX 6600. (pip uninstall onnxruntime onnxruntime-directml & pip install onnxruntime-directml==1.15.1 commands) Python version is 3.10.6 I'm sure I set install up correctly.

Adsız adsız2

turkiet commented 5 months ago

I fixed it.

I made sure to specify the path for anaconda beforehand. https://eduand-alvarez.medium.com/setting-up-anaconda-on-your-windows-pc-6e39800c1afb My conda folder location is: "E:\yapay-zeka\roop-unleashed\installer_files\conda" I have specified the required 3 paths. Ekran Alıntısı Then I opened cmd and checked if the command worked with "conda --version" and it worked.

https://github.com/C0untFloyd/roop-unleashed/issues/625#issuecomment-2072361976

Then I opened CMD and started it by saying "start windows_run.bat". When the browser opened, I exited by saying "Y" with the ctrl+c combination and it gave me write permission. I entered the command "pip install onnxruntime-directml" and it fixed it. And so "dml" appears in the settings.