Describe the problem
When using Depth Image prompt, the model file ZoeD_M12_N.pt is always corrupted and gets redownloaded. I checked the checksum of the file with the checksum on huggingface and it matches.
WARNING: Running on CPU. This will be slow. Check your CUDA installation.
img_size [384, 512]
/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/native/TensorShape.cpp:3527.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Params passed to Resize transform:
width: 512
height: 384
resize_target: True
keep_aspect_ratio: True
ensure_multiple_of: 32
resize_method: minimal
Traceback (most recent call last):
File "/Users/testing/Fooocus-ControlNet-SDXL/modules/patch.py", line 497, in loader
result = original_loader(*args, **kwargs)
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/serialization.py", line 1014, in load
return _load(opened_zipfile,
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/serialization.py", line 1422, in _load
result = unpickler.load()
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/serialization.py", line 1392, in persistent_load
typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/serialization.py", line 1366, in load_tensor
wrap_storage=restore_location(storage, location),
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/serialization.py", line 381, in default_restore_location
result = fn(storage, location)
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/serialization.py", line 274, in _cuda_deserialize
device = validate_cuda_device(location)
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/serialization.py", line 258, in validate_cuda_device
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/testing/Fooocus-ControlNet-SDXL/modules/async_worker.py", line 704, in worker
handler(task)
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/testing/Fooocus-ControlNet-SDXL/modules/async_worker.py", line 250, in handler
pipeline.refresh_controlnets(
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/testing/miniconda3/envs/fooocus-controlnet/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/testing/Fooocus-ControlNet-SDXL/modules/default_pipeline.py", line 69, in refresh_controlnets
cache_controlnet_preprocess = {get_1st_path(get_paths(ms)): cache_loader(l, ms) for l, ms in preprocess_loaders.items()}
File "/Users/testing/Fooocus-ControlNet-SDXL/modules/default_pipeline.py", line 69, in <dictcomp>
cache_controlnet_preprocess = {get_1st_path(get_paths(ms)): cache_loader(l, ms) for l, ms in preprocess_loaders.items()}
File "/Users/testing/Fooocus-ControlNet-SDXL/modules/default_pipeline.py", line 57, in cache_loader
return loader(path_1st if 1 == len(paths) else paths) if not path_1st in loaded_ControlNets else \
File "/Users/testing/Fooocus-ControlNet-SDXL/fooocus_extras/controlnet_preprocess_model/ZeoDepth/__init__.py", line 26, in __init__
model.load_state_dict(torch.load(model_path)['model'])
File "/Users/testing/Fooocus-ControlNet-SDXL/modules/patch.py", line 513, in loader
raise ValueError(exp)
ValueError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
File corrupted: /Users/testing/Fooocus-ControlNet-SDXL/models/controlnet/ZoeD_M12_N.pt
Fooocus has tried to move the corrupted file to /Users/testing/Fooocus-ControlNet-SDXL/models/controlnet/ZoeD_M12_N.pt.corrupted
You may try again now and Fooocus will download models again
Describe the problem When using Depth Image prompt, the model file
ZoeD_M12_N.pt
is always corrupted and gets redownloaded. I checked the checksum of the file with the checksum on huggingface and it matches.Full Console Log