Skip to content

comfyui,v1正常使用,v2报错 #4

Description

@zxwwa

LSNetModelLoader

Error(s) in loading state_dict for LSNetArtist:
size mismatch for blocks4.3.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.3.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.5.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.5.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.7.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.7.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.9.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.9.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.11.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.11.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.13.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.13.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.15.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.15.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.17.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.17.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.19.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.19.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).
size mismatch for blocks4.21.mixer.m.attention_biases: copying a param with shape torch.Size([6, 49]) from checkpoint, the shape in current model is torch.Size([6, 16]).
size mismatch for blocks4.21.mixer.m.attention_bias_idxs: copying a param with shape torch.Size([49, 49]) from checkpoint, the shape in current model is torch.Size([16, 16]).

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions