CS1o

@gogaletyaev have you downloaded the correct gfx files for gfx1200 and placed them in your rocm library? Also please provide a full cmd log. For rx9060 also see here: https://github.com/lshqqytiger/ZLUDA/issues/116

Hey, try follow the Forge with Zluda setup Guide from here: https://github.com/CS1o/Stable-Diffusion-Info/wiki/Webui-Installation-Guides Let me know if it works.

Hey, add `--skip-ort` to the launch args. That will skip the onnxruntime installation. Also add `--cuda-stream --attention-quad` for the best performance.

Hey, try to delete the venv. Then add --skip-ort again and rerun the webui-user.bat. Then let it install everything and then try again in offline mode.

Hey you didnt setup the webui the proper way. For DirectML the Launch args should be: `--use-directml --medvram --opt-sub-quad-attention --opt-split-attention --no-half-vae --upcast-sampling` Checkout the Install Guides from here: https://github.com/CS1o/Stable-Diffusion-Info/wiki/Webui-Installation-Guides But...

Hey, the cause of the error is this part here: ``` Failed to install ZLUDA: Using CPU-only torch ``` I dont know which Certificate has expired. but what you can...

HIP SDK found your APU (gfx1036) before your dedicated GPU. You can fix that by adding: `set HIP_VISIBLE_DEVICES=1` to the webui-user.bat. Or by opening up the Device Manager and under...

> Same issue here, i see the VRAM being consumed more and more by the generation using XL models. Latest drivers from Nvidia for my 3060 12GB, with CUDA System...

@target-bravo Hey, directml is known for beeing slow and vram hungry (bad optmised). AMD Users should use the Automatic1111 ZLUDA Version instead. Its very fast and uses much less vram....

> It's great that you're a ZLUDA fanboy and all. But please stop spreading your BS regarding DirectML. We sadly live in a world where nvidia is king and ruler...