3 Commits

Author SHA1 Message Date
layerdiffusion
a985afd857 thread safety 2024-08-13 15:45:45 -07:00
layerdiffusion
bb58520a4c completely solve 'NoneType' object is not iterable 2024-08-13 15:36:18 -07:00
lllyasviel
f06ba8e60b Significantly reduce thread abuse for faster model moving
This will move all major gradio calls into the main thread rather than random gradio threads.
This ensures that all torch.module.to() are performed in main thread to completely possible avoid GPU fragments.
In my test now model moving is 0.7 ~ 1.2 seconds faster, which means all 6GB/8GB VRAM users will get 0.7 ~ 1.2 seconds faster per image on SDXL.
2024-02-08 10:13:59 -08:00