Replies: 1 comment
-
Looks like I switched the names of the clipvision models when I downloaded them, as a result it was using the SDXL model with SD15 and visa versa! Found it while troubleshooting... Thanks anyhow... |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello,
I downloaded a workflow (ipadapter related group in image 1) used to exchange clothing for a generated model which uses the unified loader . The person who created it features it in a youtube video where he demonstrates/explains how to use it.
Having added my own clothing to be used (no, they are not the final clothes to used), I ran the workflow and it stopped with the following error on the IPAdaptor Advanced node (image 2):
!!! Exception during processing!!! Error(s) in loading state_dict for Resampler: size mismatch for proj_in.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1280, 1664]). Traceback (most recent call last): File "F:\ComfyUI_New\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_New\ComfyUI_windows_portable\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 "F:\ComfyUI_New\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_New\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 769, in apply_ipadapter work_model, face_image = ipadapter_execute(work_model, ipadapter_model, clip_vision, **ipa_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_New\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 396, in ipadapter_execute ipa = IPAdapter( ^^^^^^^^^^ File "F:\ComfyUI_New\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 70, in __init__ self.image_proj_model.load_state_dict(ipadapter_model["image_proj"]) File "F:\ComfyUI_New\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2189, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for Resampler: size mismatch for proj_in.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1280, 1664]).
I have the latest updates to ComfyUI and custom nodes and what I believe is the correct model files and filenames:
Lora:
Clipvision:
What I did was 'retrofit' the workflow with the 'old' ip model, clipvision and ipadapter apply nodes and I got the result I was expecting without any errors (image 3).
Can anyone tell me why the unified loader produced an error?
Beta Was this translation helpful? Give feedback.
All reactions