Hugging Face's logo

Plaguekind
/
ltx2.3

LTX.io
workflow
i2v
comfyui
int8
convrot
nvfp4
int8 convrot
Model card Files
xet
 Community
2

Pruna vae error

#2
by fishmann-g - opened
Discussion
fishmann-g
•
edited 3 days ago

ComfyUI Error Report

Error Details

  • Node ID: 5310:5222
  • Node Type: VAELoader
  • Exception Type: RuntimeError
  • Exception Message: RuntimeError: Error(s) in loading state_dict for VideoVAE:
    size mismatch for decoder.conv_in.conv.weight: copying a param with shape torch.Size([1024, 128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([2048, 128, 3, 3, 3]).
    size mismatch for decoder.conv_in.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.weight: copying a param with shape torch.Size([1024, 1024, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([2048, 2048, 3, 3, 3]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
    <....>
fishmann-g changed discussion title from Prune error to Pruna vae error
Plaguekind
 Owner

ComfyUI Error Report

Error Details

  • Node ID: 5310:5222
  • Node Type: VAELoader
  • Exception Type: RuntimeError
  • Exception Message: RuntimeError: Error(s) in loading state_dict for VideoVAE:
    size mismatch for decoder.conv_in.conv.weight: copying a param with shape torch.Size([1024, 128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([2048, 128, 3, 3, 3]).
    size mismatch for decoder.conv_in.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.weight: copying a param with shape torch.Size([1024, 1024, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([2048, 2048, 3, 3, 3]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
    <....>

You need to update comfyui to use pruna. Support was just added.
liuxingsyue

ComfyUI Error Report

Error Details

  • Node ID: 5310:5222
  • Node Type: VAELoader
  • Exception Type: RuntimeError
  • Exception Message: RuntimeError: Error(s) in loading state_dict for VideoVAE:
    size mismatch for decoder.conv_in.conv.weight: copying a param with shape torch.Size([1024, 128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([2048, 128, 3, 3, 3]).
    size mismatch for decoder.conv_in.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.weight: copying a param with shape torch.Size([1024, 1024, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([2048, 2048, 3, 3, 3]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
    <....>

You need to update comfyui to use pruna. Support was just added.

I've already updated to the latest version, 0.29.2, but I'm still getting the same error—it's completely unusable.

Sign up or log in to comment