Th3Rom3

I can confirm this behaviour for the 20231009_984 release. In my case the files are stored in the main folder. I did not realize this wasn't intended behaviour. So far...

I have tested an additional variety of configurations and I figured that this problem only occurs when running the webui by invoking launch.py via an absolute path. Running it from...

@CarlosFdez Are there any infos on the progress or is it done as a separate fork?

Did you set the environment variable `HSA_OVERRIDE_GFX_VERSION=10.3.0` in order to override the gpu target for ROCm? 5700XT is not officially supported but you can try to make it work in...

Just to check, which version of pytorch are you running? `pip show torch` querying the [ROCm issues](https://github.com/ROCm/ROCm/issues/2536) also shows some other environment variables that might work in that conjunction. But...

Have you tried downgrading to pytorch 2.2 with rocm5.7? You can run this even with ROCm 6.0 binaries installed on the host. `pip uninstall torch torchvision torchaudio` `pip install torch...

To my knowledge the problem lies within the fact that current torch releases are compiled with hardware features that RDNA1 does not support. You might have to sequentially downgrade to...

You might want to look into setting up a virtual environment such that you don't need to run everything with the system python.

Just as a general word of advice: Using pip via `python -m pip` instead of just `pip` can reduce problems since it ensures that pip is invoked within the currently...

Getting an error when running the [example workflow](https://gist.github.com/comfyanonymous/0f09119a342d0dd825bb2d99d19b781c) for Stable Cascade with both bf16 and lite models: ``` Error occurred when executing CLIPTextEncode: output with shape [20, 77, 77] doesn't...