RuntimeError: Error(s) in loading state_dict for ProjModelFaceIdPlus

[Finasia]

My checkpoint、lora is baseon sdxl and I use the following nodes ↓

but i got these error below↓

got prompt
[EasyUse] easy ipadapterApply: Using IpAdapterModel ip-adapter-faceid-plusv2_sdxl.bin Cached
[EasyUse] Load LORA: ip-adapter-faceid-plusv2_sdxl_lora.safetensors cached
[EasyUse] easy ipadapterApply: Using InsightFaceModel insightface-CUDA Cached
INFO: the IPAdapter reference image is not a square, CLIPImageProcessor will resize and crop it at the center. If the main focus of the picture is not in the middle the result might not be what you are expecting.
D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface\utils\transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
  P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
INFO: InsightFace detection resolution lowered to (448, 448).
!!! Exception during processing !!! Error(s) in loading state_dict for ProjModelFaceIdPlus:
        size mismatch for perceiver_resampler.proj_in.weight: copying a param with shape torch.Size([2048, 1280]) from checkpoint, the shape in current model is torch.Size([2048, 1664]).
Traceback (most recent call last):
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute
    output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, in get_output_data
    return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use\py\easyNodes.py", line 3381, in apply
    model, images = cls().apply_ipadapter(model, ipadapter, weight=weight, weight_type=weight_type, start_at=start_at, end_at=end_at, combine_embeds=combine_embeds, weight_faceidv2=weight_faceidv2, image=image, image_negative=image_negative, weight_style=1.0, weight_composition=1.0, image_style=image_style, image_composition=image_composition, expand_style=expand_style, clip_vision=clip_vision, attn_mask=attn_mask, insightface=None, embeds_scaling=embeds_scaling, weight_kolors=weight_kolors)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 822, in apply_ipadapter
    work_model, face_image = ipadapter_execute(work_model, ipadapter_model, clip_vision, **ipa_args)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 441, in ipadapter_execute
    ipa = IPAdapter(
          ^^^^^^^^^^
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 71, in __init__
    self.image_proj_model.load_state_dict(ipadapter_model["image_proj"])
  File "D:\software\ai_tech\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2584, in load_state_dict
    raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for ProjModelFaceIdPlus:
        size mismatch for perceiver_resampler.proj_in.weight: copying a param with shape torch.Size([2048, 1280]) from checkpoint, the shape in current model is torch.Size([2048, 1664]).

Prompt executed in 1.43 seconds

But everything is right when I use SD1.5 -based Checkpoint and LoRa （clip switch to the CLIP-ViT-H-14-laion2B-s32B-b79K）

emmm... I wondered, what did I do wrong ?

---

and these two model.safetensors below

• https://huggingface.co/h94/IP-Adapter/resolve/main/models/image_encoder/model.safetensors
• https://huggingface.co/h94/IP-Adapter/resolve/main/sdxl_models/image_encoder/model.safetensors
  It is necessary to strictly follow the name written on the document or change it casually?