wangherr comments

Repositories
Issues
Comments

Results 2 comments of


                                            wangherr

Error when setting num_single_layers=0 while training flux-controlnet on a multi-GPU server using a single GPU

I solve it by: flux_controlnet.train() if args.num_single_layers == 0: flux_controlnet.transformer_blocks[-1].attn.to_add_out.requires_grad_(False) flux_controlnet.transformer_blocks[-1].ff_context.requires_grad_(False) ... # params_to_optimize = flux_controlnet.parameters() params_to_optimize = [param for param in flux_controlnet.parameters() if param.requires_grad] but I am not sure...

Error when setting num_single_layers=0 while training flux-controlnet on a multi-GPU server using a single GPU

> > I solve it by:↳ > > ``` > > flux_controlnet.train() > > if args.num_single_layers == 0: > > flux_controlnet.transformer_blocks[-1].attn.to_add_out.requires_grad_(False) > > flux_controlnet.transformer_blocks[-1].ff_context.requires_grad_(False) > > ... > > #...