stable_diffusion 是能正常跑的, sd-webui安装时参考 https://gitee.com/ascend/ModelZoo-PyTorch/blob/master/MindIE/MindIE-Torch/built-in/foundation/sd-webui/mindietorch_extension/README.md，官网没找到以下 mindietorch-xxx.whl的包
其他步骤按文档进行，运行报错。以下是启动到报错的log
root@pc:/home/zero/Downloads/weights/stable-diffusion-webui# python3 launch.py --skip-torch-cuda-test --enable-insecure-extension-access --listen --log-startup --disable-safe-unpickle --no-half --skip-prepare-environment
initial startup: done in 0.010s
prepare environment:
Launching Web UI with arguments: --skip-torch-cuda-test --enable-insecure-extension-access --listen --log-startup --disable-safe-unpickle --no-half --skip-prepare-environment
launcher: done in 0.001s
import torch: done in 1.426s
import torch: done in 1.936s
import gradio: done in 0.855s
setup paths: done in 0.666s
import ldm: done in 0.003s
import sgm: done in 0.000s
No module 'xformers'. Proceeding without it.
Warning: caught exception 'Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx', memory monitor disabled
initialize shared: done in 0.803s
other imports: done in 0.432s
==============================================================================
You are running torch 2.1.0+cu121.
The program is tested to work with torch 2.1.2.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.
Use --skip-version-check commandline argument to disable this check.
==============================================================================
opts onchange: done in 0.000s
setup SD model: done in 0.000s
setup codeformer: done in 0.001s
setup gfpgan: done in 0.006s
set samplers: done in 0.000s
list extensions: done in 0.001s
restore config state file: done in 0.000s
list SD models: done in 0.019s
list localizations: done in 0.000s
load scripts:
custom_code.py: done in 0.001s
img2imgalt.py: done in 0.000s
loopback.py: done in 0.000s
outpainting_mk_2.py: done in 0.000s
poor_mans_outpainting.py: done in 0.000s
postprocessing_codeformer.py: done in 0.000s
postprocessing_gfpgan.py: done in 0.000s
postprocessing_upscale.py: done in 0.000s
prompt_matrix.py: done in 0.000s
prompts_from_file.py: done in 0.000s
sd_upscale.py: done in 0.000s
xyz_grid.py: done in 0.002s
ldsr_model.py: done in 0.246s
lora_script.py: done in 4.583s
scunet_model.py: done in 0.276s
swinir_model.py: done in 0.081s
hotkey_config.py: done in 0.000s
extra_options_section.py: done in 0.000s
hypertile_script.py: done in 0.162s
postprocessing_autosized_crop.py: done in 0.000s
postprocessing_caption.py: done in 0.000s
postprocessing_create_flipped_copies.py: done in 0.000s
postprocessing_focal_crop.py: done in 0.002s
postprocessing_split_oversized.py: done in 0.000s
soft_inpainting.py: done in 0.000s
mindie_plugin.py: done in 0.437s
comments.py: done in 0.111s
refiner.py: done in 0.000s
sampler.py: done in 0.000s
seed.py: done in 0.000s
load upscalers: done in 0.003s
refresh VAE: done in 0.002s
refresh textual inversion templates: done in 0.000s
scripts list_optimizers: done in 0.001s
scripts list_unets: done in 0.000s
reload hypernetworks: done in 0.001s
Loading weights [6ce0161689] from /home/zero/Downloads/weights/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
initialize extra networks: done in 0.013s
scripts before_ui_callback: done in 0.004s
2024-11-27 11:21:46,154 INFO: import MindIEPlugin
create ui: done in 0.661s
Running on local URL: http://0.0.0.0:7860
To create a public link, set `share=True` in `launch()`.
gradio launch: done in 0.176s
add APIs: done in 0.010s
app_started_callback:
lora_script.py: done in 0.000s
Startup time: 12.9s (import torch: 3.4s, import gradio: 0.9s, setup paths: 0.7s, initialize shared: 0.8s, other imports: 0.4s, load scripts: 5.9s, create ui: 0.7s, gradio launch: 0.2s).
Creating model from config: /home/zero/Downloads/weights/stable-diffusion-webui/configs/v1-inference.yaml
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
File "/usr/local/lib/python3.10/threading.py", line 973, in _bootstrap
self._bootstrap_inner()
File "/usr/local/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/local/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/initialize.py", line 149, in load_model
shared.sd_model # noqa: B018
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/shared_items.py", line 175, in sd_model
return modules.sd_models.model_data.get_sd_model()
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_models.py", line 693, in get_sd_model
load_model()
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_models.py", line 845, in load_model
load_model_weights(sd_model, checkpoint_info, state_dict, timer)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_models.py", line 440, in load_model_weights
model.load_state_dict(state_dict, strict=False)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 223, in <lambda>
module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 221, in load_state_dict
original(module, state_dict, strict=strict)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2138, in load_state_dict
load(self, state_dict)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
[Previous line repeated 1 more time]
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2120, in load
module._load_from_state_dict(
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 225, in <lambda>
linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 191, in load_from_state_dict
module._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device, dtype=dtype), requires_grad=param.requires_grad)
File "/usr/local/lib/python3.10/site-packages/torch/_meta_registrations.py", line 4507, in zeros_like
res = aten.empty_like.default(
File "/usr/local/lib/python3.10/site-packages/torch/_ops.py", line 448, in __call__
return self._op(*args, **kwargs or {})
File "/usr/local/lib/python3.10/site-packages/torch/_refs/__init__.py", line 4681, in empty_like
return torch.empty_permuted(
RuntimeError: unknown format type:77
Stable diffusion model failed to load
Applying attention optimization: InvokeAI... done.
Exception in thread Thread-3 (load_model):
Traceback (most recent call last):
File "/usr/local/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/local/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/initialize.py", line 154, in load_model
devices.first_time_calculation()
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/devices.py", line 276, in first_time_calculation
linear = torch.nn.Linear(1, 1).to(device, dtype)
File "/usr/local/lib/python3.10/site-packages/torch_npu/utils/_module.py", line 78, in to
return self._apply(convert)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 833, in _apply
param_applied = fn(param)
File "/usr/local/lib/python3.10/site-packages/torch_npu/utils/_module.py", line 76, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
RuntimeError: unknown format type:-1140785152
点赞
收藏
回复
分享
举报
已解决
stable_diffusion 是能正常跑的, sd-webui安装时参考 https://gitee.com/ascend/ModelZoo-PyTorch/blob/master/MindIE/MindIE-Torch/built-in/foundation/sd-webui/mindietorch_extension/README.md，官网没找到以下 mindietorch-xxx.whl的包
其他步骤按文档进行，运行报错。以下是启动到报错的log
root@pc:/home/zero/Downloads/weights/stable-diffusion-webui# python3 launch.py --skip-torch-cuda-test --enable-insecure-extension-access --listen --log-startup --disable-safe-unpickle --no-half --skip-prepare-environment
initial startup: done in 0.010s
prepare environment:
Launching Web UI with arguments: --skip-torch-cuda-test --enable-insecure-extension-access --listen --log-startup --disable-safe-unpickle --no-half --skip-prepare-environment
launcher: done in 0.001s
import torch: done in 1.426s
import torch: done in 1.936s
import gradio: done in 0.855s
setup paths: done in 0.666s
import ldm: done in 0.003s
import sgm: done in 0.000s
No module 'xformers'. Proceeding without it.
Warning: caught exception 'Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx', memory monitor disabled
initialize shared: done in 0.803s
other imports: done in 0.432s
==============================================================================
You are running torch 2.1.0+cu121.
The program is tested to work with torch 2.1.2.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.
Use --skip-version-check commandline argument to disable this check.
==============================================================================
opts onchange: done in 0.000s
setup SD model: done in 0.000s
setup codeformer: done in 0.001s
setup gfpgan: done in 0.006s
set samplers: done in 0.000s
list extensions: done in 0.001s
restore config state file: done in 0.000s
list SD models: done in 0.019s
list localizations: done in 0.000s
load scripts:
custom_code.py: done in 0.001s
img2imgalt.py: done in 0.000s
loopback.py: done in 0.000s
outpainting_mk_2.py: done in 0.000s
poor_mans_outpainting.py: done in 0.000s
postprocessing_codeformer.py: done in 0.000s
postprocessing_gfpgan.py: done in 0.000s
postprocessing_upscale.py: done in 0.000s
prompt_matrix.py: done in 0.000s
prompts_from_file.py: done in 0.000s
sd_upscale.py: done in 0.000s
xyz_grid.py: done in 0.002s
ldsr_model.py: done in 0.246s
lora_script.py: done in 4.583s
scunet_model.py: done in 0.276s
swinir_model.py: done in 0.081s
hotkey_config.py: done in 0.000s
extra_options_section.py: done in 0.000s
hypertile_script.py: done in 0.162s
postprocessing_autosized_crop.py: done in 0.000s
postprocessing_caption.py: done in 0.000s
postprocessing_create_flipped_copies.py: done in 0.000s
postprocessing_focal_crop.py: done in 0.002s
postprocessing_split_oversized.py: done in 0.000s
soft_inpainting.py: done in 0.000s
mindie_plugin.py: done in 0.437s
comments.py: done in 0.111s
refiner.py: done in 0.000s
sampler.py: done in 0.000s
seed.py: done in 0.000s
load upscalers: done in 0.003s
refresh VAE: done in 0.002s
refresh textual inversion templates: done in 0.000s
scripts list_optimizers: done in 0.001s
scripts list_unets: done in 0.000s
reload hypernetworks: done in 0.001s
Loading weights [6ce0161689] from /home/zero/Downloads/weights/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
initialize extra networks: done in 0.013s
scripts before_ui_callback: done in 0.004s
2024-11-27 11:21:46,154 INFO: import MindIEPlugin
create ui: done in 0.661s
Running on local URL: http://0.0.0.0:7860
To create a public link, set `share=True` in `launch()`.
gradio launch: done in 0.176s
add APIs: done in 0.010s
app_started_callback:
lora_script.py: done in 0.000s
Startup time: 12.9s (import torch: 3.4s, import gradio: 0.9s, setup paths: 0.7s, initialize shared: 0.8s, other imports: 0.4s, load scripts: 5.9s, create ui: 0.7s, gradio launch: 0.2s).
Creating model from config: /home/zero/Downloads/weights/stable-diffusion-webui/configs/v1-inference.yaml
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
File "/usr/local/lib/python3.10/threading.py", line 973, in _bootstrap
self._bootstrap_inner()
File "/usr/local/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/local/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/initialize.py", line 149, in load_model
shared.sd_model # noqa: B018
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/shared_items.py", line 175, in sd_model
return modules.sd_models.model_data.get_sd_model()
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_models.py", line 693, in get_sd_model
load_model()
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_models.py", line 845, in load_model
load_model_weights(sd_model, checkpoint_info, state_dict, timer)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_models.py", line 440, in load_model_weights
model.load_state_dict(state_dict, strict=False)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 223, in <lambda>
module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 221, in load_state_dict
original(module, state_dict, strict=strict)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2138, in load_state_dict
load(self, state_dict)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
[Previous line repeated 1 more time]
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2120, in load
module._load_from_state_dict(
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 225, in <lambda>
linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/sd_disable_initialization.py", line 191, in load_from_state_dict
module._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device, dtype=dtype), requires_grad=param.requires_grad)
File "/usr/local/lib/python3.10/site-packages/torch/_meta_registrations.py", line 4507, in zeros_like
res = aten.empty_like.default(
File "/usr/local/lib/python3.10/site-packages/torch/_ops.py", line 448, in __call__
return self._op(*args, **kwargs or {})
File "/usr/local/lib/python3.10/site-packages/torch/_refs/__init__.py", line 4681, in empty_like
return torch.empty_permuted(
RuntimeError: unknown format type:77
Stable diffusion model failed to load
Applying attention optimization: InvokeAI... done.
Exception in thread Thread-3 (load_model):
Traceback (most recent call last):
File "/usr/local/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/local/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/initialize.py", line 154, in load_model
devices.first_time_calculation()
File "/home/zero/Downloads/weights/stable-diffusion-webui/modules/devices.py", line 276, in first_time_calculation
linear = torch.nn.Linear(1, 1).to(device, dtype)
File "/usr/local/lib/python3.10/site-packages/torch_npu/utils/_module.py", line 78, in to
return self._apply(convert)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 833, in _apply
param_applied = fn(param)
File "/usr/local/lib/python3.10/site-packages/torch_npu/utils/_module.py", line 76, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
RuntimeError: unknown format type:-1140785152