Hugging Face's logo

Comfy-Org
/
sigclip_vision_384

Model card Files Community
1

CLIPVisionLoader - Error

#1
by Elbatl - opened
Discussion
Elbatl

ComfyUI Error Report

Error Details

  • Node ID: 38
  • Node Type: CLIPVisionLoader
  • Exception Type: RuntimeError
  • Exception Message: Error(s) in loading state_dict for CLIPVisionModelProjection:
    size mismatch for vision_model.embeddings.patch_embedding.weight: copying a param with shape torch.Size([1152, 3, 14, 14]) from checkpoint, the shape in current model is torch.Size([1024, 3, 14, 14]).
    size mismatch for vision_model.embeddings.position_embedding.weight: copying a param with shape torch.Size([729, 1152]) from checkpoint, the shape in current model is torch.Size([257, 1024]).
    size mismatch for vision_model.encoder.layers.0.layer_norm1.weight: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([1024]).
    size mismatch for vision_model.encoder.layers.0.layer_norm1.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([1024]).
    ....
ezhfan

same result

mingdong04

same result + 1

mingdong04

update all is OK! cool model!!!

nolascoin
•
edited 6 days ago

update all is OK! cool model!!!

Had the same error, updating comfyui did the trick.
ComfyUI: 28118afb97
Manager: V2.51.9

Elbatl

update all is OK! cool model!!!

Had the same error, updating comfyui did the trick.
ComfyUI: 28118afb97
Manager: V2.51.9

Yesss Update sovled it! Thank you!!!!

parthwagh

update solved issue

Pedrotv

Udate solved but broke pulid on another workflow. I am trying to use reflux and pulid

ficoesbejo

I updated, but same error.

ComfyUI Error Report

Error Details

  • Node Type: CLIPVisionLoader
  • Exception Type: RuntimeError
  • Exception Message: Error(s) in loading state_dict for CLIPVisionModelProjection:
    size mismatch for vision_model.embeddings.patch_embedding.weight: copying a param with shape torch.Size([1152, 3, 14, 14]) from checkpoint, the shape in current model is torch.Size([1024, 3, 14, 14]).
    size mismatch for vision_model.embeddings.position_embedding.weight: copying a param with shape torch.Size([729, 1152]) from checkpoint, the shape in current model is torch.Size([257, 1024]).
    size mismatch for vision_model.encoder.layers.0.layer_norm1.weight: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([1024]).
    ........
yank

same here

Sign up or log in to comment