[Issue]: 'OnnxRawPipeline' object is not callable

[AdmiralTriggerHappy]

Issue Description

When setting up SD.next using Olive/ONNX as per the instructions I get that 'OnnxRawPipeline' object is not callable
Its happening with another SD platform on my machine so I suspect its due to a change in one of the dependencies they both share but can't narrow it down

Version Platform Description

Windows 11
Checked out from Git the latest today

16:30:25-344558 INFO Starting SD.Next
16:30:25-347832 INFO Logger: file="C:\Users\UsernameHere\sd\automatic\sdnext.log" level=DEBUG size=65 mode=create
16:30:25-349834 INFO Python version=3.10.6 platform=Windows bin="C:\Users\UsernameHere\sd\automatic\venv\Scripts\python.exe" venv="C:\Users\UsernameHere\sd\automatic\venv"
16:30:25-512603 INFO Version: app=sd.next updated=2024-07-24 hash=a874b27e branch=master url=https://github.com/vladmandic/automatic/tree/master ui=main
16:30:26-103683 INFO Platform: arch=AMD64 cpu=AMD64 Family 25 Model 33 Stepping 2, AuthenticAMD system=Windows release=Windows-10-10.0.22631-SP0 python=3.10.6
16:30:26-105683 DEBUG Setting environment tuning
16:30:26-106683 INFO HF cache folder: C:\Users\UsernameHere.cache\huggingface\hub
16:30:26-107685 DEBUG Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
16:30:26-108683 DEBUG Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False
16:30:26-109684 DEBUG Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True
16:30:26-122549 INFO Using CPU-only Torch
16:30:26-288087 INFO Verifying requirements
16:30:26-293607 INFO Verifying packages
16:30:26-334580 DEBUG Repository update time: Thu Jul 25 06:16:33 2024
16:30:26-335581 INFO Startup: standard
16:30:26-336584 INFO Verifying submodules
16:30:28-374541 DEBUG Submodule: extensions-builtin/sd-extension-chainner / main
16:30:28-445303 DEBUG Submodule: extensions-builtin/sd-extension-system-info / main
16:30:28-516571 DEBUG Submodule: extensions-builtin/sd-webui-agent-scheduler / main
16:30:28-615484 DEBUG Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=main
16:30:28-616483 DEBUG Submodule: extensions-builtin/sdnext-modernui / main
16:30:28-707030 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
16:30:28-775338 DEBUG Submodule: modules/k-diffusion / master
16:30:28-870221 DEBUG Git detached head detected: folder="wiki" reattach=master
16:30:28-871221 DEBUG Submodule: wiki / master
16:30:28-912235 DEBUG Register paths
16:30:28-997725 DEBUG Installed packages: 191
16:30:28-999727 DEBUG Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
16:30:29-245228 DEBUG Running extension installer: C:\Users\UsernameHere\sd\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
16:30:29-694641 DEBUG Running extension installer: C:\Users\UsernameHere\sd\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
16:30:30-040482 DEBUG Extensions all: []
16:30:30-041482 INFO Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sdnext-modernui',
'stable-diffusion-webui-rembg']
16:30:30-042996 INFO Verifying requirements
16:30:30-043996 DEBUG Setup complete without errors: 1722493830
16:30:30-046997 DEBUG Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
16:30:30-048995 DEBUG Starting module: <module 'webui' from 'C:\Users\UsernameHere\sd\automatic\webui.py'>
16:30:30-049995 INFO Command line args: ['--debug'] debug=True
16:30:30-051502 DEBUG Env flags: []
16:30:35-605268 INFO Load packages: {'torch': '2.4.0+cpu', 'diffusers': '0.29.1', 'gradio': '3.43.2'}
16:30:36-163068 DEBUG Read: file="config.json" json=32 bytes=1440 time=0.000
16:30:36-165074 INFO Engine: backend=Backend.DIFFUSERS compute=cpu device=cpu attention="Scaled-Dot-Product" mode=no_grad
16:30:36-166073 INFO Device:
16:30:36-167076 DEBUG Read: file="html\reference.json" json=45 bytes=25986 time=0.000
16:30:36-567590 DEBUG ONNX: version=1.18.1 provider=CPUExecutionProvider, available=['AzureExecutionProvider', 'CPUExecutionProvider']
16:30:36-779814 DEBUG Importing LDM
16:30:36-797863 DEBUG Entering start sequence
16:30:36-799869 DEBUG Initializing

Relevant log output

16:36:18-785816 ERROR    gradio call: TypeError
╭──────────────────────────────────────────────────────────────────────── Traceback (most recent call last) ─────────────────────────────────────────────────────────────────────────╮
│ C:\Users\UsernameHere\sd\automatic\modules\call_queue.py:31 in f                                                                                                                  │
│                                                                                                                                                                                    │
│   30 │   │   │   try:                                                                                                                                                              │
│ ❱ 31 │   │   │   │   res = func(*args, **kwargs)                                                                                                                                   │
│   32 │   │   │   │   progress.record_results(id_task, res)                                                                                                                         │
│                                                                                                                                                                                    │
│ C:\Users\UsernameHere\sd\automatic\modules\txt2img.py:91 in txt2img                                                                                                               │
│                                                                                                                                                                                    │
│   90 │   if processed is None:                                                                                                                                                     │
│ ❱ 91 │   │   processed = processing.process_images(p)                                                                                                                              │
│   92 │   p.close()                                                                                                                                                                 │
│                                                                                                                                                                                    │
│ C:\Users\UsernameHere\sd\automatic\modules\processing.py:191 in process_images                                                                                                    │
│                                                                                                                                                                                    │
│   190 │   │   │   with context_hypertile_vae(p), context_hypertile_unet(p):                                                                                                        │
│ ❱ 191 │   │   │   │   processed = process_images_inner(p)                                                                                                                          │
│   192                                                                                                                                                                              │
│                                                                                                                                                                                    │
│ C:\Users\UsernameHere\sd\automatic\modules\processing.py:312 in process_images_inner                                                                                              │
│                                                                                                                                                                                    │
│   311 │   │   │   │   │   from modules.processing_diffusers import process_diffusers                                                                                               │
│ ❱ 312 │   │   │   │   │   x_samples_ddim = process_diffusers(p)                                                                                                                    │
│   313 │   │   │   │   else:                                                                                                                                                        │
│                                                                                                                                                                                    │
│ C:\Users\UsernameHere\sd\automatic\modules\processing_diffusers.py:122 in process_diffusers                                                                                       │
│                                                                                                                                                                                    │
│   121 │   │   else:                                                                                                                                                                │
│ ❱ 122 │   │   │   output = shared.sd_model(**base_args)                                                                                                                            │
│   123 │   │   if isinstance(output, dict):                                                                                                                                         │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
TypeError: 'OnnxRawPipeline' object is not callable

Backend

Diffusers

UI

Standard

Branch

Master

Model

StableDiffusion 1.5

Acknowledgements

• I have read the above and searched for existing issues
• I confirm that this is classified correctly and its not an extension issue

[timhagen]

I had the same issue. The text encoder and VAE appeared to compile, hung on the model. After a restart, received the above message.

[vladmandic]

cc @lshqqytiger

[lshqqytiger]

This occurs when a broken cache remains under models/ONNX/cache.
A full log of previous conversion (or optimization) is needed to figure out why it failed.

[vladmandic]

@AdmiralTriggerHappy what is the status of this issue after lshqqytiger provided an update?