size mismatch
Closed this issue · 3 comments
[rgthree] Using rgthree's optimized recursive execution.
Prompt executor has been patched by Job Iterator!
2024-05-20 11:10:16,933- root:71- INFO- model_type EPS
2024-05-20 11:10:17,711- root:272- INFO- Using xformers attention in VAE
2024-05-20 11:10:17,713- root:272- INFO- Using xformers attention in VAE
2024-05-20 11:10:18,701- root:416- INFO- Requested to load SD1ClipModel
2024-05-20 11:10:18,702- root:426- INFO- Loading 1 new model
2024-05-20 11:10:28,539- root:416- INFO- Requested to load CLIPVisionModelProjection
2024-05-20 11:10:28,539- root:426- INFO- Loading 1 new model
2024-05-20 11:10:29,820- root:179- ERROR- !!! Exception during processing!!! 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, 1024]).
2024-05-20 11:10:29,822- root:180- ERROR- Traceback (most recent call last):
File "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\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 "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\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 "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\Steerable-Motion\SteerableMotion.py", line 568, in combined_function
model, *_ = ipadapter_application.apply_ipadapter(model=model, ipadapter=ipadapter, image=torch.cat(bin.imageBatch, dim=0), weight=[x * base_ipa_advanced_settings["ipa_weight"] for x in bin.weight_schedule], weight_type=base_ipa_advanced_settings["ipa_weight_type"], start_at=base_ipa_advanced_settings["ipa_starts_at"], end_at=base_ipa_advanced_settings["ipa_ends_at"], clip_vision=clip_vision,image_negative=negative_noise,embeds_scaling=base_ipa_advanced_settings["ipa_embeds_scaling"], encode_batch_size=1, image_schedule=bin.image_schedule)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\Steerable-Motion\imports\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 686, in apply_ipadapter
image = image if isinstance(image, list) else [image]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\Steerable-Motion\imports\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 334, in ipadapter_execute
if img_comp_cond_embeds is not None:
File "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\Steerable-Motion\imports\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 69, in init
File "K:\software\ComfyU\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2153, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: 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, 1024]).
All settings are default. I am running the creative_interpolation_example in the demo directory.
Check if your images are all the exact same dimensions. If they are, are you using the batch input or the load images inputs?
Check if your images are all the exact same dimensions. If they are, are you using the batch input or the load images inputs?
Kewk's is correct - your images look like different sizes. The current workflow should resize them though!