Here's a port for graphics/stable-diffusion.cpp
Description
Diffusion model inference in pure C/C++
WWW: https://github.com/leejet/stable-diffusion.cpp
Maintainer
The OpenBSD ports mailing-list
While it *is* based on libggml, the sd-cpp ggml is built with
GGML_MAX_NAME=128, so we can't use devel/libggml from ports.
Likewise, we can't dynamically select the backend as in llama.cpp,
hence the -vulkan FLAVOR.
Works fine on amd64 - it's a bit more pointless without a discrete
graphics card and substantial amounts of VRAM, however.
ok?
No comments:
Post a Comment