ERROR lora diffusion_model.img_in.weight shape '[3072, 384]' is invalid for input of size 196608
#14
by
art13
- opened
I'm getting an error,
Requested to load Flux
ERROR lora diffusion_model.img_in.weight shape '[3072, 384]' is invalid for input of size 196608
loaded partially 4176.170965667725 4173.437561035156 238
100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [01:09<00:00, 8.66s/it]
Requested to load AutoencodingEngine
0 models unloaded.
loaded completely 9.5367431640625e+25 159.87335777282715 True
Prompt executed in 91.91 seconds
does anyone know what can be done about it?
I'm having the exact same issue. There are others who are too. Has anyone found a solution?
This helped others https://github.com/comfyanonymous/ComfyUI/issues/5868#issuecomment-2544734133 only one of those custom nodes mentioned installed for me and after uninstalling I still see the error.