vugenti
vugenti
I am having the same issue on a similar GPU, does stable-diffusion.cpp need to be rebuilt from source for this GPU? ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1...
> This indicates you're using a sd.cpp build that had API changes and is not compatible (most likely to recent if you build yourself, the API has been compeltely reworked...
This doesn't seem to be the case as using the build you reference, StableSiffusion.NET has the same error, but sd.exe works fine. I use the cpu-only build to be on...
I've tried with both sd-master-dafc32d-bin-win-noavx-x64.zip and sd-master-dafc32d-bin-win-avx512-x64.zip In both cases, sd.exe functions properly but the StableDiffusion.NET app using CPU Backend receives SEHException as detailed above. This happened with both the...
If you have any suggestions how I could enable more verbose / debug / trace level output to help determine root cause of this issue on my machine?
Yes it still throws the exception, here is the output: LOG [Debug]: stable-diffusion.cpp:201 - Using CPU backend LOG [Info]: stable-diffusion.cpp:210 - loading model from 'C:\stable-diffusion-webui-docker-master\data\models\Stable-diffusion\dreamshaper_8.safetensors' LOG [Info]: model.cpp:970 - load...