{ "metadata": { "total_size": 1099.3195629119873 }, "weight_map": { "scale": "pytorch_model-00001.bin", "shift": "pytorch_model-00001.bin", "spatial_vae.module.encoder.conv_in.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.conv_in.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.downsamplers.0.conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.0.downsamplers.0.conv.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.downsamplers.0.conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.1.downsamplers.0.conv.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.downsamplers.0.conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.2.downsamplers.0.conv.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.group_norm.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.group_norm.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_q.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_q.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_k.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_k.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_v.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_v.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_out.0.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.attentions.0.to_out.0.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.mid_block.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.conv_norm_out.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.conv_norm_out.bias": "pytorch_model-00001.bin", "spatial_vae.module.encoder.conv_out.weight": "pytorch_model-00001.bin", "spatial_vae.module.encoder.conv_out.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.conv_in.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.conv_in.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.upsamplers.0.conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.0.upsamplers.0.conv.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.upsamplers.0.conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.1.upsamplers.0.conv.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.upsamplers.0.conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.2.upsamplers.0.conv.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv_shortcut.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv_shortcut.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.group_norm.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.group_norm.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_q.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_q.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_k.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_k.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_v.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_v.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_out.0.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.attentions.0.to_out.0.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.0.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.norm1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.norm1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.conv1.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.conv1.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.norm2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.norm2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.conv2.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.mid_block.resnets.1.conv2.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.conv_norm_out.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.conv_norm_out.bias": "pytorch_model-00001.bin", "spatial_vae.module.decoder.conv_out.weight": "pytorch_model-00001.bin", "spatial_vae.module.decoder.conv_out.bias": "pytorch_model-00001.bin", "spatial_vae.module.quant_conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.quant_conv.bias": "pytorch_model-00001.bin", "spatial_vae.module.post_quant_conv.weight": "pytorch_model-00001.bin", "spatial_vae.module.post_quant_conv.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.conv_in.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.0.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.0.conv3.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.1.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.2.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.0.conv3.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.block_res_blocks.3.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.conv_blocks.1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.conv_blocks.1.conv.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.conv_blocks.2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.conv_blocks.2.conv.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.res_blocks.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.encoder.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.encoder.conv2.conv.bias": "pytorch_model-00001.bin", "temporal_vae.quant_conv.conv.weight": "pytorch_model-00001.bin", "temporal_vae.quant_conv.conv.bias": "pytorch_model-00001.bin", "temporal_vae.post_quant_conv.conv.weight": "pytorch_model-00001.bin", "temporal_vae.post_quant_conv.conv.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.conv1.conv.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.res_blocks.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.0.conv3.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.0.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.1.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.0.conv3.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.2.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.0.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.0.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.0.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.0.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.0.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.0.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.1.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.1.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.1.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.1.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.1.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.1.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.2.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.2.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.2.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.2.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.2.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.2.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.3.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.3.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.3.conv1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.3.norm2.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.3.norm2.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.block_res_blocks.3.3.conv2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.conv_blocks.1.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.conv_blocks.1.conv.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.conv_blocks.2.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.conv_blocks.2.conv.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.norm1.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.norm1.bias": "pytorch_model-00001.bin", "temporal_vae.decoder.conv_out.conv.weight": "pytorch_model-00001.bin", "temporal_vae.decoder.conv_out.conv.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.conv_in.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.conv_in.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.0.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.resnets.1.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.downsamplers.0.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.0.downsamplers.0.conv.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.resnets.1.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.downsamplers.0.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.1.downsamplers.0.conv.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.resnets.1.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.downsamplers.0.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.2.downsamplers.0.conv.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.0.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.down_blocks.3.resnets.1.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.group_norm.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.group_norm.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_q.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_q.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_k.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_k.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_v.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_v.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_out.0.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.attentions.0.to_out.0.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.0.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.conv1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.conv1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.conv2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.mid_block.resnets.1.conv2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.conv_norm_out.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.conv_norm_out.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.conv_out.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_2d.conv_out.bias": "pytorch_model-00001.bin", "sketch_vae.quant_conv_2d.weight": "pytorch_model-00001.bin", "sketch_vae.quant_conv_2d.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.conv_in.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.0.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.0.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.1.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.1.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.2.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.2.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.2.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.2.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.2.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.2.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.3.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.3.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.3.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.3.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.3.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.0.3.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.0.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.0.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.0.conv3.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.1.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.1.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.2.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.2.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.2.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.2.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.2.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.2.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.3.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.3.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.3.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.3.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.3.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.1.3.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.0.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.0.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.1.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.1.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.2.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.2.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.2.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.2.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.2.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.2.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.3.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.3.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.3.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.3.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.3.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.2.3.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.0.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.0.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.0.conv3.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.1.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.1.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.2.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.2.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.2.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.2.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.2.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.2.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.3.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.3.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.3.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.3.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.3.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.block_res_blocks.3.3.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.conv_blocks.1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.conv_blocks.1.conv.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.conv_blocks.2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.conv_blocks.2.conv.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.0.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.0.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.0.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.0.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.0.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.0.conv2.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.1.norm1.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.1.norm1.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.1.conv1.conv.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.1.norm2.weight": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.1.norm2.bias": "pytorch_model-00001.bin", "sketch_vae.encoder_3d.res_blocks.1.conv2.conv.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.2.norm1.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.2.norm1.bias": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.2.conv1.conv.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.2.norm2.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.2.norm2.bias": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.2.conv2.conv.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.3.norm1.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.3.norm1.bias": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.3.conv1.conv.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.3.norm2.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.3.norm2.bias": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.res_blocks.3.conv2.conv.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.norm1.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.norm1.bias": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.conv2.conv.weight": "pytorch_model-00002.bin", "sketch_vae.encoder_3d.conv2.conv.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.0.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.0.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.1.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.1.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.2.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.2.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.3.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.3.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.4.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.4.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.5.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.5.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.6.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.6.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.7.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.7.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.8.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.8.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.9.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_2d.9.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.0.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.0.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.1.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.1.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.2.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.2.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.3.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.3.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.4.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.4.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.5.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.5.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.6.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.6.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.7.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.7.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.8.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.8.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.9.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.9.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.10.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.10.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.11.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.11.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.12.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.12.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.13.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.13.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.14.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.14.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.15.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.15.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.16.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.16.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.17.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.17.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.18.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.18.bias": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.19.weight": "pytorch_model-00002.bin", "sketch_vae.zero_conv_3d.19.bias": "pytorch_model-00002.bin", "sketch_vae.quant_conv_3d.conv.weight": "pytorch_model-00002.bin", "sketch_vae.quant_conv_3d.conv.bias": "pytorch_model-00002.bin" } }