google.protobuf.message.DecodeError: Error parsing message

[M4NH3X]

Describe the bug
Face swap alone works, but if I choose enhancer like GFPGAN, Codeformer then I am seeing parsing error message.

My Settings & Setup:
Provider: cuda
Max. memory: 4
Number of threads: 1
Image format: jpg

I installed roop-unleashed via git clone and conda. Let me know if you have more questions.

Error Message (When GFPFAN/Codeformer was selected):

  File "/home/admin/miniconda3/envs/roop/lib/python3.10/site-packages/gradio/utils.py", line 675, in gen_wrapper
    response = next(iterator)
  File "/home/admin/SD/roop-unleashed/ui/tabs/faceswap_tab.py", line 575, in start_swap
    batch_process(list_files_process, use_clip, clip_text, processing_method == "In-Memory processing", imagemask, progress, SELECTED_INPUT_FACE_INDEX)
  File "/home/admin/SD/roop-unleashed/roop/core.py", line 256, in batch_process
    process_mgr.initialize(roop.globals.INPUT_FACESETS, roop.globals.TARGET_FACES, options)
  File "/home/admin/SD/roop-unleashed/roop/ProcessMgr.py", line 96, in initialize
    p.Initialize(devicename)
  File "/home/admin/SD/roop-unleashed/roop/processors/FaceSwapInsightFace.py", line 23, in Initialize
    self.model_swap_insightface = insightface.model_zoo.get_model(model_path, providers=roop.globals.execution_providers)
  File "/home/admin/miniconda3/envs/roop/lib/python3.10/site-packages/insightface/model_zoo/model_zoo.py", line 96, in get_model
    model = router.get_model(providers=providers, provider_options=provider_options)
  File "/home/admin/miniconda3/envs/roop/lib/python3.10/site-packages/insightface/model_zoo/model_zoo.py", line 54, in get_model
    return INSwapper(model_file=self.onnx_file, session=session)
  File "/home/admin/miniconda3/envs/roop/lib/python3.10/site-packages/insightface/model_zoo/inswapper.py", line 16, in __init__
    model = onnx.load(self.model_file)
  File "/home/admin/miniconda3/envs/roop/lib/python3.10/site-packages/onnx/__init__.py", line 208, in load_model
    model = _get_serializer(format, f).deserialize_proto(_load_bytes(f), ModelProto())
  File "/home/admin/miniconda3/envs/roop/lib/python3.10/site-packages/onnx/serialization.py", line 118, in deserialize_proto
    decoded = typing.cast(Optional[int], proto.ParseFromString(serialized))
google.protobuf.message.DecodeError: Error parsing message

Success message (When no enhancer is selected):

Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0', 'device_id': '0', 'has_user_compute_stream': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0'}}
find model: /home/admin/SD/roop-unleashed/models/buffalo_l/w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (640, 640)
Processing: 100%|█| 39/39 [00:34<00:00,  1.14frame/s, memory_usage=01.64GB, execution_threads
Finished

Details
What OS are you using?

• Linux
• Linux in WSL
• Windows
• Mac

Are you using a GPU?

• No. CPU FTW
• NVIDIA
• AMD
• Intel
• Mac

Which version of roop unleashed are you using?
v3.6.7

[lysxelapsed]

What's your GPU? Any errors when installing the requirements? Is "Force CPU for Face Analyser" checked by any chance?

[SuperSambat]

i have same problem, unless im on windows

[lennylen]

same here, on debian 12. 3090ti. swap works fine but enhancement gives parsing error.

[lysxelapsed]

Just spitting out googled stuff: try pip uninstall protobuf followed by pip install protobuf

[alonemoz]

same here. need help

[alonemoz]

Just spitting out googled stuff: try pip uninstall protobuf followed by pip install protobuf

tried this one and not working

[github-actions]

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.