Latest update Erros

[kakachiex2]

I update the MimicMotionWrapper and I'm getting this errors.

Error occurred when executing DownloadAndLoadMimicMotionModel:

'UNetSpatioTemporalConditionModel' object has no attribute 'pose_net'

File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\custom_nodes\ComfyUI-MimicMotionWrapper\nodes.py", line 109, in loadmodel set_module_tensor_to_device(self.unet, key, dtype=dtype, device=device, value=sd[key]) File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\accelerate\utils\modeling.py", line 269, in set_module_tensor_to_device new_module = getattr(module, split) ^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\diffusers\models\modeling_utils.py", line 218, in getattr return super().getattr(name) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\torch\nn\modules\module.py", line 1688, in getattr raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

[Luisellap]

Same here...

[kijai]

You have to reselect one of the new models after the update, the old one wont work.

[TenaciousDean]

I'm very new to all this and not sure exactly what you mean - could you clarify? I've tried putting the new mimic_motion_pose_net file into a bunch of different folders and it hasn't worked. I'm assuming I'm putting it in the wrong folder/s ?

[kijai]

I'm very new to all this and not sure exactly what you mean - could you clarify? I've tried putting the new mimic_motion_pose_net file into a bunch of different folders and it hasn't worked. I'm assuming I'm putting it in the wrong folder/s ?

The pose net is automatically put in right place, it's a tiny model so I included it in this repository. Along with the new 1.1 model, I also updated the 1.0 model, the old one wont work, but neither no longer needs the SVD unet so end result is everyone saving that much disk space.

[TenaciousDean]

I'm very new to all this and not sure exactly what you mean - could you clarify? I've tried putting the new mimic_motion_pose_net file into a bunch of different folders and it hasn't worked. I'm assuming I'm putting it in the wrong folder/s ?

The pose net is automatically put in right place, it's a tiny model so I included it in this repository. Along with the new 1.1 model, I also updated the 1.0 model, the old one wont work, but neither no longer needs the SVD unet so end result is everyone saving that much disk space.

Thank you for responding!

So what exactly do I need to do to get this sorted? I've been tearing my hair out and ChatGPT hasn't got a scooby

Should I just reinstall everything fresh? I've tried updating through Model Manager on ComfyUI and I'm still getting this erro. Do I just need to delete the old model?

Sorry for being a pain but I'm sure others will have this issue crop up in the future

[kijai]

I'm very new to all this and not sure exactly what you mean - could you clarify? I've tried putting the new mimic_motion_pose_net file into a bunch of different folders and it hasn't worked. I'm assuming I'm putting it in the wrong folder/s ?

The pose net is automatically put in right place, it's a tiny model so I included it in this repository. Along with the new 1.1 model, I also updated the 1.0 model, the old one wont work, but neither no longer needs the SVD unet so end result is everyone saving that much disk space.

Thank you for responding!

So what exactly do I need to do to get this sorted? I've been tearing my hair out and ChatGPT hasn't got a scooby

Should I just reinstall everything fresh? I've tried updating through Model Manager on ComfyUI and I'm still getting this erro. Do I just need to delete the old model?

Sorry for being a pain but I'm sure others will have this issue crop up in the future

If you have successfully updated the node to latest version, all you should need to do is reselect the used model in the model loader node. It's also possible it just didn't update properly, then best bet would be remove the node and re-install.

[TenaciousDean]

all you should need to do is reselect the used model in the model loader node

jfc yeah that's literally it smh I don't know why I didn't think of that or even look there

Thank you!!!

[Edit] Whilst I have you here, is there somewhere I can go to discuss optimisations/tips ? Struggling to get stuff at a decent frame rate/length with my GPU (4070ti)

[kijai]

all you should need to do is reselect the used model in the model loader node

jfc yeah that's literally it smh I don't know why I didn't think of that or even look there

Thank you!!!

[Edit] Whilst I have you here, is there somewhere I can go to discuss optimisations/tips ? Struggling to get stuff at a decent frame rate/length with my GPU (4070ti)

I can't force set the new model for old workflows, but I should try to see if I can make the error message clearer at least.

The latest update should have made memory use smarter, other than that it's just about the resolution/frame count.

[TenaciousDean]

What's the best way to get natural frame rate though? Putting at 24fps on all the nodes seems to make it go unnaturally quickly (much faster than the input)