Closed vitalbuttering closed 3 weeks ago
It seems I'm only getting this error when I run sd15_fbc_unet on the load diffusion model. Running fc_unet seems fine...
Error occurred when executing KSampler:
Given groups=1, weight of size [320, 4, 3, 3], expected input[2, 8, 64, 64] to have 4 channels, but got 8 channels instead
工作流是作者提供的,layerdiffuse已经安装,模型和节点也是按照作者的工作流设定的,仍然提示错误!
使用的是 fc_unet模型
Btw this has been fixed after a ComfyUI update.
Installed LayerDiffuse in custom node (like what was recommended), but still getting this error:
KSampler:
Given groups=1, weight of size [320, 12, 3, 3], expected input[2, 8, 96, 64] to have 12 channels, but got 8 channels instead
How do i fix this?