mirror of
https://github.com/leejet/stable-diffusion.cpp.git
synced 2026-07-23 11:20:53 -05:00
feat: add max-vram based segmented param offload (#1476)
This commit is contained in:
@@ -156,6 +156,8 @@ Context Options:
|
||||
-t, --threads <int> number of threads to use during computation (default: -1). If threads <= 0,
|
||||
then threads will be set to the number of CPU physical cores
|
||||
--chroma-t5-mask-pad <int> t5 mask pad size of chroma
|
||||
--max-vram <float> maximum VRAM budget in GiB for graph-cut segmented execution. 0 disables
|
||||
graph splitting
|
||||
--force-sdxl-vae-conv-scale force use of conv scale on sdxl vae
|
||||
--offload-to-cpu place the weights in RAM to save VRAM, and automatically load them into VRAM
|
||||
when needed
|
||||
|
||||
Reference in New Issue
Block a user