xizaoqu/MOFT

Issues

• Question about motion channel filter

  #4 opened a month ago
  1

• initial latents

  #3 opened 3 months ago
  3

• huggingface_hub version

  #2 opened 3 months ago
  0

• size mismatch for up_blocks.3.motion_modules.0.temporal_transformer.transformer_blocks.0.attention_blocks.1.pos_encoder.pe: copying a param with shape torch.Size([1, 24, 320]) from checkpoint, the shape in current model is torch.Size([1, 32, 320]).

  #1 opened 4 months ago
  4