AttributeError: 'ControlNet' object has no attribute 'load_device'

[0xech0]

'ControlNet' object has no attribute 'load_device'. Fresh install of steerable motion

Full error:

'ControlNet' object has no attribute 'load_device'

File "/opt/rd/ComfyUI/execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/opt/rd/ComfyUI/execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/opt/rd/ComfyUI/execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/SteerableMotion.py", line 323, in combined_function control_net = control_net_loader.load_controlnet(control_net_name, timestep_keyframe)[0] File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/nodes.py", line 86, in load_controlnet controlnet = load_controlnet(controlnet_path, timestep_keyframe) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/control.py", line 728, in load_controlnet return convert_to_advanced(control, timestep_keyframe=timestep_keyframe) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/control.py", line 737, in convert_to_advanced return ControlNetAdvancedImport.from_vanilla(v=control, timestep_keyframe=timestep_keyframe) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/control.py", line 630, in from_vanilla global_average_pooling=v.global_average_pooling, device=v.device, load_device=v.load_device, manual_cast_dtype=v.manual_cast_dtype)`

[pdbarma]

Same Issue

'ControlNet' object has no attribute 'load_device'. Fresh install of steerable motion

Full error:

'ControlNet' object has no attribute 'load_device' File "/opt/rd/ComfyUI/execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/opt/rd/ComfyUI/execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/opt/rd/ComfyUI/execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/SteerableMotion.py", line 323, in combined_function control_net = control_net_loader.load_controlnet(control_net_name, timestep_keyframe)[0] File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/nodes.py", line 86, in load_controlnet controlnet = load_controlnet(controlnet_path, timestep_keyframe) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/control.py", line 728, in load_controlnet return convert_to_advanced(control, timestep_keyframe=timestep_keyframe) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/control.py", line 737, in convert_to_advanced return ControlNetAdvancedImport.from_vanilla(v=control, timestep_keyframe=timestep_keyframe) File "/opt/rd/ComfyUI/custom_nodes/steerable-motion/imports/AdvancedControlNet/control.py", line 630, in from_vanilla global_average_pooling=v.global_average_pooling, device=v.device, load_device=v.load_device, manual_cast_dtype=v.manual_cast_dtype)`

[peteromallet]

Others have fixed this by pressing Update All - and updating to the latest versino of Comfy. Think that this is due to a change in Comfy that happened last week

[0xech0]

Ye

Others have fixed this by pressing Update All - and updating to the latest versino of Comfy. Think that this is due to a change in Comfy that happened last week

Tried that and it didn't work for me

[peteromallet]

Are you 100% sure you have the latest version of Comfy? This has been revolved in other cases with that + latest nodes - maybe try a reinstall if need be

[agustincaniglia]

I am getting this: Error occurred when executing BatchCreativeInterpolation:

Error(s) in loading state_dict for ResamplerImport: size mismatch for proj_in.weight: copying a param with shape torch.Size([768, 1280]) from checkpoint, the shape in current model is torch.Size([768, 1664]).

File "H:\AUTOMATIC\COMFYUI\ComfyUI_windows_portable_nvidia_cu118_or_cpu (1)\ComfyUI_windows_portable\ComfyUI\execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "H:\AUTOMATIC\COMFYUI\ComfyUI_windows_portable_nvidia_cu118_or_cpu (1)\ComfyUI_windows_portable\ComfyUI\execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "H:\AUTOMATIC\COMFYUI\ComfyUI_windows_portable_nvidia_cu118_or_cpu (1)\ComfyUI_windows_portable\ComfyUI\execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "H:\AUTOMATIC\COMFYUI\ComfyUI_windows_portable_nvidia_cu118_or_cpu (1)\ComfyUI_windows_portable\ComfyUI\custom_nodes\steerable-motion\SteerableMotion.py", line 347, in combined_function model, = ipadapter_application.apply_ipadapter(ipadapter=ipadapter, model=model, weight=1.0, image=None, weight_type="original", File "H:\AUTOMATIC\COMFYUI\ComfyUI_windows_portable_nvidia_cu118_or_cpu (1)\ComfyUI_windows_portable\ComfyUI\custom_nodes\steerable-motion\imports\IPAdapterPlus.py", line 501, in apply_ipadapter self.ipadapter = IPAdapterImport( File "H:\AUTOMATIC\COMFYUI\ComfyUI_windows_portable_nvidia_cu118_or_cpu (1)\ComfyUI_windows_portable\ComfyUI\custom_nodes\steerable-motion\imports\IPAdapterPlus.py", line 241, in init self.image_proj_model.load_state_dict(ipadapter_model["image_proj"]) File "H:\AUTOMATIC\COMFYUI\ComfyUI_windows_portable_nvidia_cu118_or_cpu (1)\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 2041, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(

I have updated all custom nodes and comfyUI

[peteromallet]

Hi @agustincaniglia, that looks like you're either using a non-SD1.5-based model or differently sized images - this is usually what the tensors not matching means

[agustincaniglia]

Hi @agustincaniglia, that looks like you're either using a non-SD1.5-based model or differently sized images - this is usually what the tensors not matching means

I am using 512x512 images and 1.5 models and get the same error.

[peteromallet]

Are you sure you're not using a XL VAE or IPA or something? Definitely something mismatching

Hi @agustincaniglia, that looks like you're either using a non-SD1.5-based model or differently sized images - this is usually what the tensors not matching means

I am using 512x512 images and 1.5 models and get the same error.

[agustincaniglia]

okay I think i had a wrong clip model version. its working now apparently.

[shaaraa]

I updated comfyUI and it works.

[peteromallet]

Great!

[microvswind]

Hi @agustincaniglia, that looks like you're either using a non-SD1.5-based model or differently sized images - this is usually what the tensors not matching means

I am using 512x512 images and 1.5 models and updated comfyui and get the same issue,

[peteromallet]

Hi @microvswind, is your VAE and other models definitely 1.5?

[peteromallet]

Ah see you don't have one - could you try uninstalling and reinstalling it?