Closed dichter closed 4 months ago
Thanks for testing on your system. Can you show your startup console log, there should be an error
Sure, here is the startup console log with all extensions disabled but the sd-webui-hardware-info-in-metadata
The error seems to stem from the line torch.cuda.get_device_properties(torch.cuda.device(0)) that fails because the pytorch on a mac does not have cuda compiled in.
In my webui-user.sh I have the line export TORCH_COMMAND="pip install --pre torch torchvision -f https://download.pytorch.org/whl/nightly/cpu/torch_nightly.html"
Launching launch.py...
################################################################
Python 3.11.7 (main, Dec 15 2023, 12:09:56) [Clang 14.0.6 ]
Version: v1.9.4-169-ga30b19dd
Commit hash: a30b19dd5536f463222e484aef2daf466b49ee85
Launching Web UI with arguments: --skip-torch-cuda-test --upcast-sampling --opt-sub-quad-attention --no-half-vae --medvram-sdxl --use-cpu interrogate
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
*** Can't make hardware info for metadata
Traceback (most recent call last):
File "/Users/ge/stable-diffusion-webui/extensions/sd-webui-hardware-info-in-metadata/scripts/hardware_info_in_metadata.py", line 35, in <module>
HARDWARE_INFO = makeHardwareInfo()
^^^^^^^^^^^^^^^^^^
File "/Users/ge/stable-diffusion-webui/extensions/sd-webui-hardware-info-in-metadata/scripts/hardware_info_in_metadata.py", line 16, in makeHardwareInfo
gpuProp = torch.cuda.get_device_properties(torch.cuda.device(0))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ge/stable-diffusion-webui/venv-torch-nightly/lib/python3.11/site-packages/torch/cuda/__init__.py", line 452, in get_device_properties
_lazy_init() # will define _get_device_properties
^^^^^^^^^^^^
File "/Users/ge/stable-diffusion-webui/venv-torch-nightly/lib/python3.11/site-packages/torch/cuda/__init__.py", line 292, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
---
Loading weights [3e0a3274d0] from /Users/ge/stable-diffusion-webui/models/Stable-diffusion/zavychromaxl_v70.safetensors
Creating model from config: /Users/ge/stable-diffusion-webui/repositories/generative-models/configs/inference/sd_xl_base.yaml
/Users/ge/stable-diffusion-webui/venv-torch-nightly/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
Running on local URL: http://127.0.0.1:7860
By the way, cpuinfo would work just fine, but hardwareinfo fails before that and does not execute the other queries
% cpuinfo
Python Version: 3.11.7.final.0 (64 bit)
Cpuinfo Version: 9.0.0
Vendor ID Raw:
Hardware Raw:
Brand Raw: Apple M2 Max
Hz Advertised Friendly:
Hz Actual Friendly:
Hz Advertised:
Hz Actual:
Arch: ARM_8
Bits: 64
Count: 12
Arch String Raw: arm64
L1 Data Cache Size:
L1 Instruction Cache Size:
L2 Cache Size:
L2 Cache Line Size:
L2 Cache Associativity:
L3 Cache Size:
Stepping:
Model:
Family:
Processor Type:
Flags:
Thanks. Can you update and test it now?
Thanks! Now the extension writes the expected: Hardware Info: "Apple M2 Max, 32GB RAM"
Hi,
I get "Hardware Info: unknown" written in the metadata.
I am on a MacBook Pro 2023 with Apple M2 Max chip and 32 GB Ram