search

TemryL / ComfyUI-IDM-VTON

ComfyUI adaptation of IDM-VTON for virtual try-on.
GNU General Public License v3.0
370 stars 40 forks source link

"LayerNormKernelImpl" not implemented for 'Half' #6

Closed ParticleDog closed 5 months ago

ParticleDog commented 5 months ago

After pulling the latest commit, error ocurred:

"LayerNormKernelImpl" not implemented for 'Half'

TemryL commented 5 months ago

are you running with mps accelerator?

@ParticleDog On the latest commit, everything is loaded on cpu to allow debuging, the issue you mentioned will be fixed once the weights will be properly loaded on GPU

ParticleDog commented 5 months ago

are you running with mps accelerator?

I am not sure what mps accelerator is ... Is it a kind of cpu accelerator for pytorch?

ParticleDog commented 5 months ago

I changed the code in pipeline_loader.py from "weight_dtype = torch.float16" to "weight_dtype = torch.float32", it seems that the error was bypassed. But another error occured, which also appeared before I pulled the latest commit:

!!! Exception during processing!!! Given groups=1, weight of size [128, 3, 3, 3], expected input[1, 1024, 1024, 768] to have 3 channels, but got 1024 channels instead

TemryL commented 5 months ago

yes, running on cpu needs float32 but float16 works on gpu. Concerning the last error you mentioned, it will be fixed very soon in the next commit Thanks for your precious feedbacks!!

TemryL commented 5 months ago

@ParticleDog dimension issue should be fix now