[Bug]: Visual artifacts when using DPM++ schedulers and SDXL without the refiner model

[meditat2001]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits

What happened?

When using OpenVino + SDXL 1.0 trained Model with 1024x1024 px and dpm samplers are used, artifacts occur (no refiner used).

Machine: Intel Iris Xe shared memory, 16GB Ram, PCIe 4, Windows 11, latest Chrome + Opera, OpenVino Toolkit, latest Intel Graphic driver.

Steps to reproduce the problem

Known Bug, please look at:
huggingface/diffusers#5433

maybe solution is: huggingface/diffusers#5541

Interestingly https://github.com/vladmandic/automatic with use of openvino
has not the problem.

What should have happened?

Generate no artifacts

Sysinfo

{
"Platform": "Windows-10-10.0.22631-SP0",
"Python": "3.10.6",
"Version": "1.6.0",
"Commit": "e5a634da06c62d72dbdc764b16c65ef3408aa588",
"Script path": "D:\sd6\sd",
"Data path": "D:\sd6\sd",
"Extensions dir": "D:\sd6\sd\extensions",
"Checksum": "564ad7b401cbfad4ee980db3c4aff31d7caa8904547bcd1593cff5be45671b22",
"Commandline": [
"launch.py",
"--skip-torch-cuda-test",
"--precision",
"full",
"--no-half"
],
"Torch env info": {
"torch_version": "2.1.0+cpu",
"is_debug_build": "False",
"cuda_compiled_version": null,
"gcc_version": null,
"clang_version": null,
"cmake_version": null,
"os": "Microsoft Windows 11 Pro",
"libc_version": "N/A",
"python_version": "3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] (64-bit runtime)",
"python_platform": "Windows-10-10.0.22631-SP0",
"is_cuda_available": "False",
"cuda_runtime_version": null,
"cuda_module_loading": "N/A",
"nvidia_driver_version": null,
"nvidia_gpu_models": null,
"cudnn_version": null,
"pip_version": "pip3",
"pip_packages": [
"numpy==1.23.5",
"open-clip-torch==2.20.0",
"pytorch-lightning==1.9.4",
"torch==2.1.0",
"torchdiffeq==0.2.3",
"torchmetrics==1.4.0.post0",
"torchsde==0.2.5",
"torchvision==0.16.0"
],
"conda_packages": null,
"hip_compiled_version": "N/A",
"hip_runtime_version": "N/A",
"miopen_runtime_version": "N/A",
"caching_allocator_config": "",
"is_xnnpack_available": "True",
"cpu_info": [
"Architecture=9",
"CurrentClockSpeed=907",
"DeviceID=CPU0",
"Family=205",
"L2CacheSize=5120",
"L2CacheSpeed=",
"Manufacturer=GenuineIntel",
"MaxClockSpeed=2419",
"Name=11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz",
"ProcessorType=3",
"Revision="
]
},
"Exceptions": [],
"CPU": {
"model": "Intel64 Family 6 Model 140 Stepping 1, GenuineIntel",
"count logical": 8,
"count physical": 4
},
"RAM": {
"total": "16GB",
"used": "10GB",
"free": "5GB"
},
"Extensions": [
{
"name": "adetailer",
"path": "D:\sd6\sd\extensions\adetailer",
"version": "a89c01d3",
"branch": "main",
"remote": "https://github.com/Bing-su/adetailer"
},
{
"name": "deforum-for-automatic1111-webui",
"path": "D:\sd6\sd\extensions\deforum-for-automatic1111-webui",
"version": "5d63a339",
"branch": "automatic1111-webui",
"remote": "https://github.com/deforum-art/deforum-for-automatic1111-webui.git"
},
{
"name": "sd-webui-agent-scheduler",
"path": "D:\sd6\sd\extensions\sd-webui-agent-scheduler",
"version": "721a36f5",
"branch": "main",
"remote": "https://github.com/ArtVentureX/sd-webui-agent-scheduler"
}
],
"Inactive extensions": [],
"Environment": {
"COMMANDLINE_ARGS": "--skip-torch-cuda-test --precision full --no-half",
"GRADIO_ANALYTICS_ENABLED": "False"
},

What browsers do you use to access the UI ?

Google Chrome, Other

Console logs

---

Additional information

No response