[Bug]: Why does onnxr start?

EygenCat commented 9 months ago

Checklist

[ ] The issue exists after disabling all extensions
[X] The issue exists on a clean installation of webui
[ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
[X] The issue exists in the current version of the webui
[ ] The issue has not been reported before recently
[ ] The issue has been reported before but has not been fixed yet

What happened?

I downloaded the last commit, used the launch options --use-directml

Steps to reproduce the problem

@echo off

set PYTHON=py -3.10 set GIT= set VENV_DIR= set COMMANDLINE_ARGS=--opt-sub-quad-attention --disable-nan-check --precision autocast --autolaunch --use-directml --listen

call webui.bat

What should have happened?

WebUI should start in directml mode

What browsers do you use to access the UI ?

Microsoft Edge

Sysinfo

none

Console logs

Creating venv in directory F:\IL\4\stable-diffusion-webui-directml\venv using python "C:\Users\Polzovatel\AppData\Local\Programs\Python\Python310\python.exe"
venv "F:\IL\4\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
NVIDIA driver was found.
fatal: No names found, cannot describe anything.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: 1.7.0
Commit hash: adaea46e1c19d9a7091f89b0a7c6e66dfa732528
Installing torch and torchvision
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cu121
Collecting torch==2.2.0
  Downloading https://download.pytorch.org/whl/cu121/torch-2.2.0%2Bcu121-cp310-cp310-win_amd64.whl (2454.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.5/2.5 GB 1.1 MB/s eta 0:00:00
Collecting torchvision==0.17.0
  Downloading https://download.pytorch.org/whl/cu121/torchvision-0.17.0%2Bcu121-cp310-cp310-win_amd64.whl (5.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.7/5.7 MB 18.1 MB/s eta 0:00:00
Collecting networkx
  Downloading https://download.pytorch.org/whl/networkx-3.2.1-py3-none-any.whl (1.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 9.6 MB/s eta 0:00:00
Collecting fsspec
  Using cached fsspec-2024.2.0-py3-none-any.whl (170 kB)
Collecting filelock
  Using cached filelock-3.13.1-py3-none-any.whl (11 kB)
Collecting typing-extensions>=4.8.0
  Using cached typing_extensions-4.9.0-py3-none-any.whl (32 kB)
Collecting sympy
  Using cached https://download.pytorch.org/whl/sympy-1.12-py3-none-any.whl (5.7 MB)
Collecting jinja2
  Using cached Jinja2-3.1.3-py3-none-any.whl (133 kB)
Collecting pillow!=8.3.*,>=5.3.0
  Downloading https://download.pytorch.org/whl/pillow-10.2.0-cp310-cp310-win_amd64.whl (2.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.6/2.6 MB 16.7 MB/s eta 0:00:00
Collecting requests
  Using cached requests-2.31.0-py3-none-any.whl (62 kB)
Collecting numpy
  Using cached numpy-1.26.4-cp310-cp310-win_amd64.whl (15.8 MB)
Collecting MarkupSafe>=2.0
  Using cached MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl (17 kB)
Collecting certifi>=2017.4.17
  Using cached certifi-2024.2.2-py3-none-any.whl (163 kB)
Collecting charset-normalizer<4,>=2
  Using cached charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl (100 kB)
Collecting urllib3<3,>=1.21.1
  Using cached urllib3-2.2.0-py3-none-any.whl (120 kB)
Collecting idna<4,>=2.5
  Using cached idna-3.6-py3-none-any.whl (61 kB)
Collecting mpmath>=0.19
  Using cached https://download.pytorch.org/whl/mpmath-1.3.0-py3-none-any.whl (536 kB)
Installing collected packages: mpmath, urllib3, typing-extensions, sympy, pillow, numpy, networkx, MarkupSafe, idna, fsspec, filelock, charset-normalizer, certifi, requests, jinja2, torch, torchvision
Successfully installed MarkupSafe-2.1.5 certifi-2024.2.2 charset-normalizer-3.3.2 filelock-3.13.1 fsspec-2024.2.0 idna-3.6 jinja2-3.1.3 mpmath-1.3.0 networkx-3.2.1 numpy-1.26.4 pillow-10.2.0 requests-2.31.0 sympy-1.12 torch-2.2.0+cu121 torchvision-0.17.0+cu121 typing-extensions-4.9.0 urllib3-2.2.0

[notice] A new release of pip available: 22.2.1 -> 24.0
[notice] To update, run: F:\IL\4\stable-diffusion-webui-directml\venv\Scripts\python.exe -m pip install --upgrade pip
Installing clip
Installing open_clip
Cloning Stable Diffusion into F:\IL\4\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai...
Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai'...
remote: Enumerating objects: 580, done.
remote: Counting objects: 100% (357/357), done.
remote: Compressing objects: 100% (128/128), done.
Receiving objects: 100% (580/580), 73.44 MiB | 20.74 MiB/s, done.
remote: Total 580 (delta 260), reused 229 (delta 229), pack-reused 223
Resolving deltas: 100% (279/279), done.
Cloning Stable Diffusion XL into F:\IL\4\stable-diffusion-webui-directml\repositories\generative-models...
Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\generative-models'...
remote: Enumerating objects: 860, done.
remote: Counting objects: 100% (489/489), done.
remote: Compressing objects: 100% (224/224), done.
remote: Total 860 (delta 368), reused 265 (delta 265), pack-reused 371
Receiving objects: 100% (860/860), 42.67 MiB | 17.01 MiB/s, done.
Resolving deltas: 100% (445/445), done.
Cloning K-diffusion into F:\IL\4\stable-diffusion-webui-directml\repositories\k-diffusion...
Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\k-diffusion'...
remote: Enumerating objects: 1340, done.
remote: Counting objects: 100% (622/622), done.
remote: Compressing objects: 100% (86/86), done.
remote: Total 1340 (delta 576), reused 547 (delta 536), pack-reused 718
Receiving objects: 100% (1340/1340), 242.04 KiB | 1.82 MiB/s, done.
Resolving deltas: 100% (939/939), done.
Cloning CodeFormer into F:\IL\4\stable-diffusion-webui-directml\repositories\CodeFormer...
Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\CodeFormer'...
remote: Enumerating objects: 594, done.
remote: Counting objects: 100% (594/594), done.
remote: Compressing objects: 100% (316/316), done.
remote: Total 594 (delta 287), reused 493 (delta 269), pack-reused 0
Receiving objects: 100% (594/594), 17.31 MiB | 13.76 MiB/s, done.
Resolving deltas: 100% (287/287), done.
Cloning BLIP into F:\IL\4\stable-diffusion-webui-directml\repositories\BLIP...
Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\BLIP'...
remote: Enumerating objects: 277, done.
remote: Counting objects: 100% (165/165), done.
remote: Compressing objects: 100% (30/30), done.
remote: Total 277 (delta 137), reused 136 (delta 135), pack-reused 112Receiving objects:  99% (275/277), 6.72 MiB | 4.31 MiB/s
Receiving objects: 100% (277/277), 7.03 MiB | 4.46 MiB/s, done.
Resolving deltas: 100% (152/152), done.
Installing requirements for CodeFormer
Installing requirements
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: `pytorch_lightning.utilities.distributed.rank_zero_only` has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from `pytorch_lightning.utilities` instead.
  rank_zero_deprecation(
Installing onnxruntime-gpu
Traceback (most recent call last):
  File "F:\IL\4\stable-diffusion-webui-directml\launch.py", line 48, in <module>
    main()
  File "F:\IL\4\stable-diffusion-webui-directml\launch.py", line 39, in main
    prepare_environment()
  File "F:\IL\4\stable-diffusion-webui-directml\modules\launch_utils.py", line 635, in prepare_environment
    run_pip("install onnxruntime-gpu", "onnxruntime-gpu")
  File "F:\IL\4\stable-diffusion-webui-directml\modules\launch_utils.py", line 150, in run_pip
    return run(
  File "F:\IL\4\stable-diffusion-webui-directml\modules\launch_utils.py", line 122, in run
    raise RuntimeError("\n".join(error_bits))
RuntimeError: Couldn't install onnxruntime-gpu.
Command: "F:\IL\4\stable-diffusion-webui-directml\venv\Scripts\python.exe" -m pip install onnxruntime-gpu --prefer-binary
Error code: 1
stdout: Collecting onnxruntime-gpu
  Using cached onnxruntime_gpu-1.17.0-cp310-cp310-win_amd64.whl (148.6 MB)
Requirement already satisfied: protobuf in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (3.20.3)
Requirement already satisfied: coloredlogs in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (15.0.1)
Requirement already satisfied: packaging in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (23.2)
Requirement already satisfied: sympy in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (1.12)
Requirement already satisfied: numpy>=1.21.6 in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (1.23.5)
Requirement already satisfied: flatbuffers in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (23.5.26)
Requirement already satisfied: humanfriendly>=9.1 in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from coloredlogs->onnxruntime-gpu) (10.0)
Requirement already satisfied: mpmath>=0.19 in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from sympy->onnxruntime-gpu) (1.3.0)
Requirement already satisfied: pyreadline3 in f:\il\4\stable-diffusion-webui-directml\venv\lib\site-packages (from humanfriendly>=9.1->coloredlogs->onnxruntime-gpu) (3.4.1)
Installing collected packages: onnxruntime-gpu

stderr: ERROR: Could not install packages due to an OSError: [WinError 5]   : 'F:\\IL\\4\\stable-diffusion-webui-directml\\venv\\Lib\\site-packages\\onnxruntime\\capi\\onnxruntime_providers_shared.dll'
Check the permissions.

[notice] A new release of pip available: 22.2.1 -> 24.0
[notice] To update, run: F:\IL\4\stable-diffusion-webui-directml\venv\Scripts\python.exe -m pip install --upgrade pip

Для продолжения нажмите любую клавишу . . .

Additional information

RX 6700xt, r5600x, 32 gb ram

lshqqytiger commented 9 months ago

You have nvidia-smi. Please remove NVIDIA driver if you don't have any NVIDIA card. According to your log, there's no --use-directml in your commandline arguments. Try this:

.\venv\Scripts\activate
python launch.py --use-directml [put other commandline arguments here]

k0zer0g commented 9 months ago

similar error appeared after today's update. Everything worked fine yesterday. But I can't install "onnxruntime-directml"

Installing collected packages: onnxruntime-directml stderr: ERROR: Could not install packages due to an OSError: [WinError 5] : 'C:\StableDiffuionWebUI\stable-diffusion-webui-directml\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_shared.dll' Check the permissions.

RX580 8gb, Updated: I solved my problem, the torch-directml component was not working. Reinstalled it, and everything worked again.

EygenCat commented 9 months ago

I really had the nvidia driver, ONNX is starting anyway, is that ok?

Снимок экрана 2024-02-07 151505

Creating venv in directory F:\IL\4\stable-diffusion-webui-directml\venv using python "C:\Users\Polzovatel\AppData\Local\Programs\Python\Python310\python.exe" venv "F:\IL\4\stable-diffusion-webui-directml\venv\Scripts\Python.exe" fatal: No names found, cannot describe anything. Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: 1.7.0 Commit hash: adaea46e1c19d9a7091f89b0a7c6e66dfa732528 Installing torch and torchvision Collecting torch==2.0.0 Using cached torch-2.0.0-cp310-cp310-win_amd64.whl (172.3 MB) Collecting torchvision==0.15.1 Using cached torchvision-0.15.1-cp310-cp310-win_amd64.whl (1.2 MB) Collecting torch-directml Using cached torch_directml-0.2.0.dev230426-cp310-cp310-win_amd64.whl (8.2 MB) Collecting typing-extensions Using cached typing_extensions-4.9.0-py3-none-any.whl (32 kB) Collecting jinja2 Using cached Jinja2-3.1.3-py3-none-any.whl (133 kB) Collecting sympy Using cached sympy-1.12-py3-none-any.whl (5.7 MB) Collecting filelock Using cached filelock-3.13.1-py3-none-any.whl (11 kB) Collecting networkx Using cached networkx-3.2.1-py3-none-any.whl (1.6 MB) Collecting numpy Using cached numpy-1.26.4-cp310-cp310-win_amd64.whl (15.8 MB) Collecting requests Using cached requests-2.31.0-py3-none-any.whl (62 kB) Collecting pillow!=8.3.*,>=5.3.0 Using cached pillow-10.2.0-cp310-cp310-win_amd64.whl (2.6 MB) Collecting MarkupSafe>=2.0 Using cached MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl (17 kB) Collecting urllib3<3,>=1.21.1 Using cached urllib3-2.2.0-py3-none-any.whl (120 kB) Collecting charset-normalizer<4,>=2 Using cached charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl (100 kB) Collecting idna<4,>=2.5 Using cached idna-3.6-py3-none-any.whl (61 kB) Collecting certifi>=2017.4.17 Using cached certifi-2024.2.2-py3-none-any.whl (163 kB) Collecting mpmath>=0.19 Using cached mpmath-1.3.0-py3-none-any.whl (536 kB) Installing collected packages: mpmath, urllib3, typing-extensions, sympy, pillow, numpy, networkx, MarkupSafe, idna, filelock, charset-normalizer, certifi, requests, jinja2, torch, torchvision, torch-directml Successfully installed MarkupSafe-2.1.5 certifi-2024.2.2 charset-normalizer-3.3.2 filelock-3.13.1 idna-3.6 jinja2-3.1.3mpmath-1.3.0 networkx-3.2.1 numpy-1.26.4 pillow-10.2.0 requests-2.31.0 sympy-1.12 torch-2.0.0 torch-directml-0.2.0.dev230426 torchvision-0.15.1 typing-extensions-4.9.0 urllib3-2.2.0

[notice] A new release of pip available: 22.2.1 -> 24.0 [notice] To update, run: F:\IL\4\stable-diffusion-webui-directml\venv\Scripts\python.exe -m pip install --upgrade pip Installing clip Installing open_clip Cloning Stable Diffusion into F:\IL\4\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai... Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai'... remote: Enumerating objects: 580, done. remote: Counting objects: 100% (357/357), done. remote: Compressing objects: 100% (128/128), done. remote: Total 580 (delta 260), reused 229 (delta 229), pack-reused 223Receiving objects: 98% (569/580), 65.63 MiB | 15.Receiving objects: 100% (580/580), 73.44 MiB | 16.14 MiB/s, done.

Resolving deltas: 100% (279/279), done. Cloning Stable Diffusion XL into F:\IL\4\stable-diffusion-webui-directml\repositories\generative-models... Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\generative-models'... remote: Enumerating objects: 860, done. remote: Counting objects: 100% (489/489), done. remote: Compressing objects: 100% (224/224), done. remote: Total 860 (delta 368), reused 265 (delta 265), pack-reused 371 Receiving objects: 100% (860/860), 42.67 MiB | 19.69 MiB/s, done. Resolving deltas: 100% (445/445), done. Cloning K-diffusion into F:\IL\4\stable-diffusion-webui-directml\repositories\k-diffusion... Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\k-diffusion'... remote: Enumerating objects: 1340, done. remote: Counting objects: 100% (622/622), done. remote: Compressing objects: 100% (86/86), done. remote: Total 1340 (delta 576), reused 547 (delta 536), pack-reused 718 Receiving objects: 100% (1340/1340), 242.04 KiB | 1.78 MiB/s, done. Resolving deltas: 100% (939/939), done. Cloning CodeFormer into F:\IL\4\stable-diffusion-webui-directml\repositories\CodeFormer... Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\CodeFormer'... remote: Enumerating objects: 594, done. remote: Counting objects: 100% (594/594), done. remote: Compressing objects: 100% (316/316), done. remote: Total 594 (delta 287), reused 493 (delta 269), pack-reused 0 Receiving objects: 100% (594/594), 17.31 MiB | 14.41 MiB/s, done. Resolving deltas: 100% (287/287), done. Cloning BLIP into F:\IL\4\stable-diffusion-webui-directml\repositories\BLIP... Cloning into 'F:\IL\4\stable-diffusion-webui-directml\repositories\BLIP'... remote: Enumerating objects: 277, done. remote: Counting objects: 100% (165/165), done. remote: Compressing objects: 100% (30/30), done. remote: Total 277 (delta 137), reused 136 (delta 135), pack-reused 112Receiving objects: 99% (275/277), 4.97 MiB | 3.26 MiB/s Receiving objects: 100% (277/277), 7.03 MiB | 3.76 MiB/s, done. Resolving deltas: 100% (152/152), done. Installing requirements for CodeFormer Installing requirements no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: pytorch_lightning.utilities.distributed.rank_zero_only has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from pytorch_lightning.utilities instead. rank_zero_deprecation( Installing onnxruntime-directml Launching Web UI with arguments: --opt-sub-quad-attention --disable-nan-check --precision autocast --autolaunch --use-directml --listen Style database not found: F:\IL\4\stable-diffusion-webui-directml\styles.csv ONNX: selected=DmlExecutionProvider, available=['DmlExecutionProvider', 'CPUExecutionProvider'] Calculating sha256 for F:\IL\4\stable-diffusion-webui-directml\models\Stable-diffusion\airfucksWildMix_v10.safetensors:Running on local URL: http://0.0.0.0:7860

To create a public link, set share=True in launch(). Startup time: 120.6s (prepare environment: 119.4s, initialize shared: 1.8s, list SD models: 0.2s, load scripts: 1.9s, create ui: 0.4s, gradio launch: 4.3s). ERROR: Exception in ASGI application Traceback (most recent call last): File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 152, in jsonable_encoder data = dict(obj) TypeError: '_abc._abc_data' object is not iterable

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 157, in jsonable_encoder data = vars(obj) TypeError: vars() argument must have dict attribute

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 404, in run_asgi result = await app( # type: ignore[func-returns-value] File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 84, in call return await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\applications.py", line 273, in call await super().call(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\applications.py", line 122, in call await self.middleware_stack(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\errors.py", line 184, in call raise exc File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\errors.py", line 162, in call await self.app(scope, receive, _send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\cors.py", line 92, in call await self.simple_response(scope, receive, send, request_headers=headers) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\cors.py", line 147, in simple_response await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\gzip.py", line 24, in call await responder(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\gzip.py", line 44, in call await self.app(scope, receive, self.send_with_gzip) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\exceptions.py", line 79, incall raise exc File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\exceptions.py", line 68, incall await self.app(scope, receive, sender) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 21, in call raise e File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 18, in call await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\routing.py", line 718, in call await route.handle(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\routing.py", line 276, in handle await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\routing.py", line 66, in app response = await func(request) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\routing.py", line 255, in app content = await serialize_response( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\routing.py", line 152, in serialize_response return jsonable_encoder(response_content) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 131, in jsonable_encoder jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 161, in jsonable_encoder return jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 161, in jsonable_encoder return jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 160, in jsonable_encoder raise ValueError(errors) from e ValueError: [TypeError("'_abc._abc_data' object is not iterable"), TypeError('vars() argument must have dict attribute')] 70525c199b353cbe1ee3738079c5322c6bcf33d0d70cbb5ae903960bfefefd42 Loading weights [70525c199b] from F:\IL\4\stable-diffusion-webui-directml\models\Stable-diffusion\airfucksWildMix_v10.safetensors Creating model from config: F:\IL\4\stable-diffusion-webui-directml\configs\v1-inference.yaml Applying attention optimization: sub-quadratic... done. Model loaded in 17.7s (calculate hash: 11.9s, load weights from disk: 0.2s, create model: 0.3s, apply weights to model:4.9s, calculate empty prompt: 0.2s).

lshqqytiger commented 9 months ago

onnx won't work if you didn't enable it in Settings.

EygenCat commented 9 months ago

I didn't change anything, I downloaded the commit and the first thing I see is a lot of errors related to onnx. I didn't even have time to go into the settings.

I unchecked all the boxes, how can I disable it if it continues to work anyway?

venv "F:\IL\4\stable-diffusion-webui-directml\venv\Scripts\Python.exe" fatal: No names found, cannot describe anything. Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: 1.7.0 Commit hash: adaea46e1c19d9a7091f89b0a7c6e66dfa732528 no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: pytorch_lightning.utilities.distributed.rank_zero_only has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from pytorch_lightning.utilities instead. rank_zero_deprecation( Launching Web UI with arguments: --opt-sub-quad-attention --disable-nan-check --precision autocast --autolaunch --use-directml --listen Style database not found: F:\IL\4\stable-diffusion-webui-directml\styles.csv ONNX: selected=DmlExecutionProvider, available=['DmlExecutionProvider', 'CPUExecutionProvider'] Loading weights [0dd2276c04] from F:\IL\4\stable-diffusion-webui-directml\models\Stable-diffusion\indigoFurryMix_v105Hybrid.safetensors Running on local URL: http://0.0.0.0:7860 Creating model from config: F:\IL\4\stable-diffusion-webui-directml\configs\v1-inference.yaml

To create a public link, set share=True in launch(). Startup time: 7.3s (prepare environment: 4.0s, initialize shared: 1.3s, load scripts: 0.9s, create ui: 0.5s, gradio launch: 4.3s). Applying attention optimization: sub-quadratic... done. Model loaded in 5.8s (load weights from disk: 0.6s, create model: 0.2s, apply weights to model: 4.3s, apply half(): 0.3s, calculate empty prompt: 0.2s). ERROR: Exception in ASGI application Traceback (most recent call last): File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 152, in jsonable_encoder data = dict(obj) TypeError: '_abc._abc_data' object is not iterable

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 157, in jsonable_encoder data = vars(obj) TypeError: vars() argument must have dict attribute

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 404, in run_asgi result = await app( # type: ignore[func-returns-value] File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 84, in call return await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\applications.py", line 273, in call await super().call(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\applications.py", line 122, in call await self.middleware_stack(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\errors.py", line 184, in call raise exc File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\errors.py", line 162, in call await self.app(scope, receive, _send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\cors.py", line 92, in call await self.simple_response(scope, receive, send, request_headers=headers) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\cors.py", line 147, in simple_response await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\gzip.py", line 24, in call await responder(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\gzip.py", line 44, in call await self.app(scope, receive, self.send_with_gzip) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\exceptions.py", line 79, incall raise exc File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\middleware\exceptions.py", line 68, incall await self.app(scope, receive, sender) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 21, in call raise e File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 18, in call await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\routing.py", line 718, in call await route.handle(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\routing.py", line 276, in handle await self.app(scope, receive, send) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\starlette\routing.py", line 66, in app response = await func(request) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\routing.py", line 255, in app content = await serialize_response( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\routing.py", line 152, in serialize_response return jsonable_encoder(response_content) File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 131, in jsonable_encoder jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 161, in jsonable_encoder return jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 161, in jsonable_encoder return jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 117, in jsonable_encoder encoded_value = jsonable_encoder( File "F:\IL\4\stable-diffusion-webui-directml\venv\lib\site-packages\fastapi\encoders.py", line 160, in jsonable_encoder raise ValueError(errors) from e ValueError: [TypeError("'_abc._abc_data' object is not iterable"), TypeError('vars() argument must have dict attribute')]

lshqqytiger commented 9 months ago

That's all. onnx will be installed and initialized, although it is disabled.

EygenCat commented 9 months ago

Is this a bug? I just don't know what to do about it...

lshqqytiger commented 9 months ago

Did you mean this one? ONNX: selected=DmlExecutionProvider, available=['DmlExecutionProvider', 'CPUExecutionProvider'] Or errors from fastapi? fastapi seems to have an compatibility issue.

EygenCat commented 9 months ago

Take a look at the screenshots. In the error settings panel, select "Stable Diffusion checkpoint" - error. It gets in the way

I turned off all the checkboxes in the "ONNX Runtime", clicked on the "apply settings" and "ui interface" button. I completely rebooted the WebUI completely, errors remained in the console, it is inconvenient to work with the red inscription "error"

ONNX: selected=DmlExecutionProvider, available=['DmlExecutionProvider', 'CPUExecutionProvider']

lshqqytiger commented 9 months ago

Every error in console is from fastapi, which is out of my range and not critical for general usage. "Error" label on UI may be due to fastapi's errors. You can use webui and generate images as normal.

Omen090909 commented 9 months ago

@lshqqytiger where can we find onnx and olive page now to convert models?

lshqqytiger commented 9 months ago

You don't need to optimize the models manually. It will automatically optimize it when you try to generate an image with a new model that hasn't been optimized. You can find converted/optimized models under ./models/ONNX/cache.

Omen090909 commented 9 months ago

good to know, althou i meant to convert models to onnx, is this still a thing? (like in the olive tab before)

lshqqytiger commented 9 months ago

The user click generate button.
If there's no converted model cache and the user enabled onnx, convert selected checkpoint file to ONNX format.
If there's no optimized model cache and the user enabled Olive optimization, optimize converted model.
If optimized model exists, generate using optimized model. Otherwise, if converted model exists, generate using converted model. If both do not exist, generate using checkpoint file and LDM.

Omen090909 commented 9 months ago

ONNX: Failed to load ONNX pipeline: is_sdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. this is what i get when i choose non onnx model with onnx and olive enabled there are no other piplines to choose Edit: fuck, am a moron xd so it is sdxl only? how can i use it with 1.5 models?

lshqqytiger commented 9 months ago

Which model did you try? And please attach a full log. For SD models: use ONNX Stable Diffusion For SDXL models: use ONNX Stable Diffusion XL

Omen090909 commented 9 months ago

F:\Stable Diffusion\stable-diffusion-webui-directml new>git pull Already up to date. venv "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\Scripts\Python.exe" fatal: No names found, cannot describe anything. Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: 1.7.0 Commit hash: 9e8f9bcf14f68099bb3562488361bd1a8393b2a5 no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: pytorch_lightning.utilities.distributed.rank_zero_only has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from pytorch_lightning.utilities instead. rank_zero_deprecation( Launching Web UI with arguments: --use-cpu-torch Style database not found: F:\Stable Diffusion\stable-diffusion-webui-directml new\styles.csv Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled ONNX: selected=DmlExecutionProvider, available=['DmlExecutionProvider', 'CPUExecutionProvider'] Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Startup time: 3.9s (prepare environment: 34.5s, initialize shared: 1.2s, load scripts: 1.6s, create ui: 0.4s, gradio launch: 0.2s). In this conversion only the non-EMA weights are extracted. If you want to instead extract the EMA weights (usually better for inference), please make sure to add the --extract_ema flag. You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . ONNX: Failed to load ONNX pipeline: is_sdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. Applying attention optimization: InvokeAI... done. Exception in thread Thread-16 (load_model): Traceback (most recent call last): File "C:\Users\piosa\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrap_inner self.run() File "C:\Users\piosa\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run self._target(*self._args, self._kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\initialize.py", line 153, in load_model devices.first_time_calculation() File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\devices.py", line 178, in first_time_calculation linear(x) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\extensions-builtin\Lora\networks.py", line 486, in network_Linear_forward return originals.Linear_forward(self, input) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward return F.linear(input, self.weight, self.bias) RuntimeError: "addmm_implcpu" not implemented for 'Half' ONNX: Failed to convert model: model='v1-5-pruned.ckpt', error=[WinError 3] System nie może odnaleźć określonej ścieżki: 'F:\Stable Diffusion\backup\stable-diffusion-webui-directml old\models\ONNX\temp' In this conversion only the non-EMA weights are extracted. If you want to instead extract the EMA weights (usually better for inference), please make sure to add the --extract_ema flag. You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . ONNX: Failed to load ONNX pipeline: is_sdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. ONNX: processing=StableDiffusionProcessingTxt2Img, pipeline=OnnxRawPipeline Error completing request Arguments: ('task(6o16ajws8wml7oh)', '', '', [], 20, 'PNDM', 1, 1, 7, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x0000016FF6786EC0>, 0, False, '', 0.8, -1, False, -1, 0, 0, 0, False, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, False) {} Traceback (most recent call last): File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\call_queue.py", line 57, in f res = list(func(args, kwargs)) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\call_queue.py", line 36, in f res = func(*args, kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\txt2img.py", line 55, in txt2img processed = processing.process_images(p) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\processing.py", line 736, in process_images res = process_images_inner(p) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\processing.py", line 841, in process_images_inner result = shared.sd_model(kwargs) TypeError: 'OnnxRawPipeline' object is not callable

full log from starting to txt2img generate click. The error goes twice because it tries to load the model at startup I do not have any other diffusers pipeline than "ONNX Stable Diffusion" to choose in settings model is "v1-5-pruned.ckpt" , just a basic 1.5 sd model from here https://huggingface.co/runwayml/stable-diffusion-v1-5 i also did those just before this log, but it is providing the same error

Edit: Actually, when i click on diffuser pipeline ui goes broke, and i no longer can click anything, switch tabs or nothing, so maybe thats why i don't see any in here

Edit 2: btw, maybe i misread you somewhere and i actually need onnx model to run it here?

lshqqytiger commented 9 months ago

Diffusers pipeline option is fixed. Pull latest commit and try again.

Omen090909 commented 9 months ago

thanks, i can choose now, but getting the same error , tried img2img option, and also the same btw it's not a new bug, i m trying out onnx first time, but found out medvram instead of lowvram is working on my 6700 so i am having acceptable results without onnx, so if it won't work im fin

F:\Stable Diffusion\stable-diffusion-webui-directml new>git pull Already up to date. venv "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\Scripts\Python.exe" fatal: No names found, cannot describe anything. Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: 1.7.0 Commit hash: f2f190b73e7deb97a59386fc52d155e858355e42 no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: pytorch_lightning.utilities.distributed.rank_zero_only has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from pytorch_lightning.utilities instead. rank_zero_deprecation( Launching Web UI with arguments: --use-cpu-torch Style database not found: F:\Stable Diffusion\stable-diffusion-webui-directml new\styles.csv Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled ONNX: selected=DmlExecutionProvider, available=['DmlExecutionProvider', 'CPUExecutionProvider'] Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Startup time: 3.9s (prepare environment: 5.8s, initialize shared: 1.1s, load scripts: 1.6s, create ui: 0.4s, gradio launch: 0.2s). You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . ONNX: Failed to load ONNX pipeline: is_sdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. Applying attention optimization: InvokeAI... done. Exception in thread Thread-16 (load_model): Traceback (most recent call last): File "C:\Users\piosa\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrap_inner self.run() File "C:\Users\piosa\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run self._target(*self._args, self._kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\initialize.py", line 153, in load_model devices.first_time_calculation() File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\devices.py", line 178, in first_time_calculation linear(x) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\extensions-builtin\Lora\networks.py", line 486, in network_Linear_forward return originals.Linear_forward(self, input) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward return F.linear(input, self.weight, self.bias) RuntimeError: "addmm_implcpu" not implemented for 'Half' ONNX: Failed to convert model: model='v1-5-pruned-emaonly.ckpt', error=[WinError 3] System nie może odnaleźć określonej ścieżki: 'F:\Stable Diffusion\backup\stable-diffusion-webui-directml old\models\ONNX\temp' You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . ONNX: Failed to load ONNX pipeline: is_sdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. ONNX: processing=StableDiffusionProcessingTxt2Img, pipeline=OnnxRawPipeline Error completing request Arguments: ('task(ex0z03vb8yp9wm6)', '', '', [], 20, 'PNDM', 1, 1, 7, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x000001C1D1AA15D0>, 0, False, '', 0.8, -1, False, -1, 0, 0, 0, False, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, False) {} Traceback (most recent call last): File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\call_queue.py", line 57, in f res = list(func(args, kwargs)) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\call_queue.py", line 36, in f res = func(*args, kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\txt2img.py", line 55, in txt2img processed = processing.process_images(p) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\processing.py", line 736, in process_images res = process_images_inner(p) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\processing.py", line 841, in process_images_inner result = shared.sd_model(kwargs) TypeError: 'OnnxRawPipeline' object is not callable

lshqqytiger commented 9 months ago

Do you have a folder named ONNX under ./models? It should be automatically created.

Omen090909 commented 9 months ago

yes

lshqqytiger commented 9 months ago

Where can I get the same ckpt file? (v1-5-pruned-emaonly.ckpt) Did you download this one from huggingface?

Omen090909 commented 9 months ago

yes, but also tried some other models, same exact error

lshqqytiger commented 9 months ago

Please run this command and upload output.txt here.

.\venv\Scripts\activate
pip freeze > output.txt

Omen090909 commented 9 months ago

output.txt Edit: insides, so you don't have to download : coloredlogs==15.0.1 flatbuffers==23.5.26 humanfriendly==10.0 mpmath==1.3.0 numpy==1.26.4 onnxruntime-directml==1.17.0 packaging==23.2 protobuf==4.25.2 pyreadline3==3.4.1 sympy==1.12

lshqqytiger commented 9 months ago

Is that all? Was there an error when running .\venv\Scripts\activate?

Omen090909 commented 9 months ago

no, no errors there, i see it's the same problem as with the new bug report, so i might post sth new there if i happen to have it Edit: btw, do i have to open it with just --use-cpu-torch or --use-directml too? Edit: tried it nothing new, and it's not the same error as the new bug report on model load i have this: ONNX: Failed to load ONNX pipeline: issdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. which is strange, cause it shows on non sdxl pipeline and sdxl one (just checked for sure) edit: also, i feel like the onnx temp folder may be corrupted, but i did so many reinstalls i have no more energy to try it now ><

EygenCat commented 9 months ago

Fix

lshqqytiger commented 9 months ago

no, no errors there, i see it's the same problem as with the new bug report, so i might post sth new there if i happen to have it Edit: btw, do i have to open it with just --use-cpu-torch or --use-directml too? Edit: tried it nothing new, and it's not the same error as the new bug report on model load i have this: ONNX: Failed to load ONNX pipeline: issdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. which is strange, cause it shows on non sdxl pipeline and sdxl one (just checked for sure) edit: also, i feel like the onnx temp folder may be corrupted, but i did so many reinstalls i have no more energy to try it now ><

Please attach full log

Omen090909 commented 9 months ago

F:\Stable Diffusion\stable-diffusion-webui-directml new>git pull Already up to date. venv "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\Scripts\Python.exe" fatal: No names found, cannot describe anything. Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: 1.7.0 Commit hash: 03a88617fcd9442313ce2ed7facfecf6cdf72c36 no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: pytorch_lightning.utilities.distributed.rank_zero_only has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from pytorch_lightning.utilities instead. rank_zero_deprecation( Launching Web UI with arguments: --use-cpu-torch Style database not found: F:\Stable Diffusion\stable-diffusion-webui-directml new\styles.csv Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled ONNX: selected=DmlExecutionProvider, available=['DmlExecutionProvider', 'CPUExecutionProvider'] Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Startup time: 4.7s (prepare environment: 9.0s, initialize shared: 1.9s, setup codeformer: 0.1s, load scripts: 1.6s, create ui: 0.4s, gradio launch: 0.3s). In this conversion only the non-EMA weights are extracted. If you want to instead extract the EMA weights (usually better for inference), please make sure to add the --extract_ema flag. You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . ONNX: Failed to load ONNX pipeline: is_sdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. Applying attention optimization: InvokeAI... done. Exception in thread Thread-16 (load_model): Traceback (most recent call last): File "C:\Users\piosa\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrap_inner self.run() File "C:\Users\piosa\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run self._target(*self._args, *self._kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\initialize.py", line 153, in load_model devices.first_time_calculation() File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\devices.py", line 178, in first_time_calculation linear(x) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, **kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\extensions-builtin\Lora\networks.py", line 486, in network_Linear_forward return originals.Linear_forward(self, input) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\venv\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward return F.linear(input, self.weight, self.bias) RuntimeError: "addmm_implcpu" not implemented for 'Half'

this is on launch

and when i click generate it shows this : ONNX: Failed to convert model: model='v1-5-pruned.ckpt', error=[WinError 3] System nie może odnaleźć określonej ścieżki: 'F:\Stable Diffusion\backup\stable-diffusion-webui-directml old\models\ONNX\temp' In this conversion only the non-EMA weights are extracted. If you want to instead extract the EMA weights (usually better for inference), please make sure to add the --extract_ema flag. You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . ONNX: Failed to load ONNX pipeline: is_sdxl=False ONNX: You cannot load this model using the pipeline you selected. Please check Diffusers pipeline in ONNX Runtime Settings. ONNX: processing=StableDiffusionProcessingTxt2Img, pipeline=OnnxRawPipeline Error completing request Arguments: ('task(qnsyrptphvyvfup)', '', '', [], 20, 'PNDM', 1, 1, 7, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x000002610E3FD0C0>, 0, False, '', 0.8, -1, False, -1, 0, 0, 0, False, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, False) {} Traceback (most recent call last): File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\call_queue.py", line 57, in f res = list(func(*args, *kwargs)) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\call_queue.py", line 36, in f res = func(args, kwargs) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\txt2img.py", line 55, in txt2img processed = processing.process_images(p) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\processing.py", line 736, in process_images res = process_images_inner(p) File "F:\Stable Diffusion\stable-diffusion-webui-directml new\modules\processing.py", line 841, in process_images_inner result = shared.sd_model(kwargs) TypeError: 'OnnxRawPipeline' object is not callable

"System nie może odnaleźć określonej ścieżki:" referrs to system couldn't find path

lshqqytiger / stable-diffusion-webui-amdgpu