Can't process video on Ubuntu 25.10

[gfl43r9nd]

I can process photos easily but video gives me errors.

I using Deep live cam on Ubuntu 25.10 with NVIDIA GeForce RTX™ 3050 Ti Laptop GPU with python 3.11. I run deep live cam with python run.py --execution-provider cuda and the window opens successfully but in the terminal I get these errors

python run.py --execution-provider cuda
2025-12-11 23:55:07.435637: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1765497307.471432    5353 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1765497307.482528    5353 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1765497307.559017    5353 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1765497307.559031    5353 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1765497307.559033    5353 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1765497307.559034    5353 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.

After picking a face and then a video the face swapping starts. This message displays a few times

Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'sdpa_kernel': '0', 'use_tf32': '1', 'fuse_conv_bias': '0', 'prefer_nhwc': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_enable': '0', 'use_ep_level_unified_stream': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'user_compute_stream': '0', 'cudnn_conv_use_max_workspace': '1'}}

But then this message repeats a few times

2025-12-11 23:56:35.696925921 [E:onnxruntime:, inference_session.cc:2196 operator()] Exception during initialization: /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:129 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cublasStatus_t; bool THRW = true; SUCCTYPE = cublasStatus_t; std::conditional_t<THRW, void, common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:121 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cublasStatus_t; bool THRW = true; SUCCTYPE = cublasStatus_t; std::conditional_t<THRW, void, common::Status> = void] CUBLAS failure 3: CUBLAS_STATUS_ALLOC_FAILED ; GPU=0 ; hostname=computerfish ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider.cc ; line=178 ; expr=cublasCreate(&cublas_handle_); 


DLC.FACE-SWAPPER: Caught exception during source image processing for /media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/inputimage.jpg:
find model: /home/fishcake/.insightface/models/buffalo_l/genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'sdpa_kernel': '0', 'use_tf32': '1', 'fuse_conv_bias': '0', 'prefer_nhwc': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_enable': '0', 'use_ep_level_unified_stream': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'user_compute_stream': '0', 'cudnn_conv_use_max_workspace': '1'}}
find model: /home/fishcake/.insightface/models/buffalo_l/genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
find model: /home/fishcake/.insightface/models/buffalo_l/2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
2025-12-11 23:56:35.885060810 [E:onnxruntime:, inference_session.cc:2196 operator()] Exception during initialization: /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:129 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cublasStatus_t; bool THRW = true; SUCCTYPE = cublasStatus_t; std::conditional_t<THRW, void, common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:121 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cublasStatus_t; bool THRW = true; SUCCTYPE = cublasStatus_t; std::conditional_t<THRW, void, common::Status> = void] CUBLAS failure 3: CUBLAS_STATUS_ALLOC_FAILED ; GPU=0 ; hostname=computerfish ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider.cc ; line=178 ; expr=cublasCreate(&cublas_handle_); 

After that repeats a few times this error is repeated several times

DLC.FACE-SWAPPER: Caught exception during source image processing for /media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/inputimage.jpg:
find model: /home/fishcake/.insightface/models/buffalo_l/w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (640, 640)
Traceback (most recent call last):
Traceback (most recent call last):
Traceback (most recent call last):
Traceback (most recent call last):
Traceback (most recent call last):
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/processors/frame/face_swapper.py", line 525, in process_frames
	source_face = get_one_face(source_img)
				  ^^^^^^^^^^^^^^^^^^^^^^^^
Traceback (most recent call last):
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/processors/frame/face_swapper.py", line 525, in process_frames
	source_face = get_one_face(source_img)
				  ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/face_analyser.py", line 28, in get_one_face
	face = get_face_analyser().get(frame)
		   ^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/face_analyser.py", line 22, in get_face_analyser
	FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=modules.globals.execution_providers)
					^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/processors/frame/face_swapper.py", line 525, in process_frames
	source_face = get_one_face(source_img)
				  ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/processors/frame/face_swapper.py", line 525, in process_frames
	source_face = get_one_face(source_img)
				  ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/processors/frame/face_swapper.py", line 525, in process_frames
	source_face = get_one_face(source_img)
				  ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/face_analyser.py", line 28, in get_one_face
	face = get_face_analyser().get(frame)
		   ^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/processors/frame/face_swapper.py", line 525, in process_frames
	source_face = get_one_face(source_img)
				  ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/face_analyser.py", line 22, in get_face_analyser
	FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=modules.globals.execution_providers)
					^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/modules/face_analyser.py", line 28, in get_one_face
	face = get_face_analyser().get(frame)
		   ^^^^^^^^^^^^^^^^^^^

Finally, it stalls after this error

[DLC.FACE-SWAPPER] Error during source image reading or analysis /media/fishcake/2efa062e-20a2-4abf-8b05-62c48c449a31/Other/Deep-Live-Cam/inputimage.jpg: [ONNXRuntimeError] : 1 : FAIL : /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:129 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cublasStatus_t; bool THRW = true; SUCCTYPE = cublasStatus_t; std::conditional_t<THRW, void, common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:121 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cublasStatus_t; bool THRW = true; SUCCTYPE = cublasStatus_t; std::conditional_t<THRW, void, common::Status> = void] CUBLAS failure 3: CUBLAS_STATUS_ALLOC_FAILED ; GPU=0 ; hostname=computerfish ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_stream_handle.cc ; line=74 ; expr=cublasCreate(&cublas_handle_); 

Can anyone help?

[Decassidyc]

for linux, You should use python 3.10 not python 3.11.

[gfl43r9nd]

The readme says Python (3.11 recommended)

[hacksider]

The readme says Python (3.11 recommended)

I usually update it to which version I'm using in windows. Right now I'm using 3.14 as it is faster on my end. But of course not all environments are perfect. But 3.10 should work fine.