silvertuanzi

> I think it's a little bit early to add these samplers to the upstream. There are some possible issues with the original implementation (see [Koishi-Star/Euler-Smea-Dyn-Sampler#5 (comment)](https://github.com/Koishi-Star/Euler-Smea-Dyn-Sampler/issues/5#issue-2232652349) and [Koishi-Star/Euler-Smea-Dyn-Sampler#7 (comment)](https://github.com/Koishi-Star/Euler-Smea-Dyn-Sampler/issues/7#issue-2232823982))....

maybe you could try to update to the newest version, delete venv folder, and run webui-user.bat directly? openvino 2023.2.0 is released and the newest version use it.

> sorry , where its supposed to be torch-install.bat > > > PyTorch doesn't support torch.compile officially on windows yet. Launching torch-install.bat installs PyTorch and enables torch.compile for OpenVINO backend....

Same problem, but my console log is different. When only the positive prompts have more than 77 tokens, and negative prompts is empty, log is: > *** Error completing request...

> @ananosleep Hello. I also is a openvino stable-diffusion user. I think another ways is make negative prompt more than 77 tokens. The prompt and negative prompt should be same...

Firstly, remove `--reinstall-xformers`. It will install xformers with CUDA 12.1. You need to install xformers manually: ``` source venv/bin/activate pip install xformers -i https://download.pytorch.org/whl/rocm6.1 ```