RuntimeError: Error(s) in loading state_dict for ImageProjModel:

[lizhen218]

(style) lhp@lhp-System-Product-Name:/media/lhp/40b453a9-de10-472d-b62b-a82509e34722/dell/lz/InstantStyle$ python 111.py
Loading pipeline components...: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:01<00:00, 5.91it/s]
Traceback (most recent call last):
File "/media/lhp/40b453a9-de10-472d-b62b-a82509e34722/dell/lz/InstantStyle/111.py", line 26, in
ip_model = IPAdapterXL(pipe, image_encoder_path, ip_ckpt, device, target_blocks=["up_blocks.0.attentions.1"])
File "/media/lhp/40b453a9-de10-472d-b62b-a82509e34722/dell/lz/InstantStyle/ip_adapter/ip_adapter.py", line 85, in init
self.load_ip_adapter()
File "/media/lhp/40b453a9-de10-472d-b62b-a82509e34722/dell/lz/InstantStyle/ip_adapter/ip_adapter.py", line 150, in load_ip_adapter
self.image_proj_model.load_state_dict(state_dict["image_proj"])
File "/home/lhp/miniconda3/envs/style/lib/python3.9/site-packages/torch/nn/modules/module.py", line 2581, in load_state_dict
raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for ImageProjModel:
size mismatch for proj.weight: copying a param with shape torch.Size([8192, 1280]) from checkpoint, the shape in current model is torch.Size([8192, 1024]).