Mattis Bergmann

When switching to sdxl-turbo, it disables the positive prompt, leaving only the negative one. Instead, I have to write the prompt while in sdxl-base mode, then switch to turbo.

The sdxl-turbo model works mostly fine for me, but trying to run sdxl-base results in `SystemExit: SharkifyStableDiffusionModel.get_unet_sdxl..UnetModel.forward() missing 2 required positional arguments: 'time_ids' and 'guidance_scale'` OS: EndeavourOS/Arch Linux GPU: RX...

> there's not going to be much reason left to use it. I think SHARK will still be of use. Even on linux I have to use SHARK since my...

On my arch installation I have run into this issue multiple times with rocm 5.6-6.0. I can't even open blender or libreoffice with hardware acceleration enabled. llama.cpp (with CLBlast) crashes...

Yesterday I tried running some AI workloads with ROCm 6.0.0 and PyTorch ROCm 6.0 on my main system, but already very simple tensor operations with pytorch crashed the driver with...