ApoorvBrooklyn/stable-diffusion-implementation

1import torch2 3def load_from_standard_weights(input_file: str, device: str) -> dict[str, torch.Tensor]:4    # Taken from: https://github.com/kjsman/stable-diffusion-pytorch/issues/7#issuecomment-14268394475    original_model = torch.load(input_file, map_location=device, weights_only = False)["state_dict"]6 7    converted = {}8    converted['diffusion'] = {}9    converted['encoder'] = {}10    converted['decoder'] = {}11    converted['clip'] = {}12 13    converted['diffusion']['time_embedding.linear_1.weight'] = original_model['model.diffusion_model.time_embed.0.weight']14    converted['diffusion']['time_embedding.linear_1.bias'] = original_model['model.diffusion_model.time_embed.0.bias']15    converted['diffusion']['time_embedding.linear_2.weight'] = original_model['model.diffusion_model.time_embed.2.weight']16    converted['diffusion']['time_embedding.linear_2.bias'] = original_model['model.diffusion_model.time_embed.2.bias']17    converted['diffusion']['unet.encoders.0.0.weight'] = original_model['model.diffusion_model.input_blocks.0.0.weight']18    converted['diffusion']['unet.encoders.0.0.bias'] = original_model['model.diffusion_model.input_blocks.0.0.bias']19    converted['diffusion']['unet.encoders.1.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.1.0.in_layers.0.weight']20    converted['diffusion']['unet.encoders.1.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.1.0.in_layers.0.bias']21    converted['diffusion']['unet.encoders.1.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.1.0.in_layers.2.weight']22    converted['diffusion']['unet.encoders.1.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.1.0.in_layers.2.bias']23    converted['diffusion']['unet.encoders.1.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.1.0.emb_layers.1.weight']24    converted['diffusion']['unet.encoders.1.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.1.0.emb_layers.1.bias']25    converted['diffusion']['unet.encoders.1.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.1.0.out_layers.0.weight']26    converted['diffusion']['unet.encoders.1.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.1.0.out_layers.0.bias']27    converted['diffusion']['unet.encoders.1.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.1.0.out_layers.3.weight']28    converted['diffusion']['unet.encoders.1.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.1.0.out_layers.3.bias']29    converted['diffusion']['unet.encoders.1.1.groupnorm.weight'] = original_model['model.diffusion_model.input_blocks.1.1.norm.weight']30    converted['diffusion']['unet.encoders.1.1.groupnorm.bias'] = original_model['model.diffusion_model.input_blocks.1.1.norm.bias']31    converted['diffusion']['unet.encoders.1.1.conv_input.weight'] = original_model['model.diffusion_model.input_blocks.1.1.proj_in.weight']32    converted['diffusion']['unet.encoders.1.1.conv_input.bias'] = original_model['model.diffusion_model.input_blocks.1.1.proj_in.bias']33    converted['diffusion']['unet.encoders.1.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.weight']34    converted['diffusion']['unet.encoders.1.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.bias']35    converted['diffusion']['unet.encoders.1.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.weight']36    converted['diffusion']['unet.encoders.1.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.bias']37    converted['diffusion']['unet.encoders.1.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.weight']38    converted['diffusion']['unet.encoders.1.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.bias']39    converted['diffusion']['unet.encoders.1.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_q.weight']40    converted['diffusion']['unet.encoders.1.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_k.weight']41    converted['diffusion']['unet.encoders.1.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_v.weight']42    converted['diffusion']['unet.encoders.1.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.weight']43    converted['diffusion']['unet.encoders.1.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.bias']44    converted['diffusion']['unet.encoders.1.1.layernorm_1.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm1.weight']45    converted['diffusion']['unet.encoders.1.1.layernorm_1.bias'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm1.bias']46    converted['diffusion']['unet.encoders.1.1.layernorm_2.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm2.weight']47    converted['diffusion']['unet.encoders.1.1.layernorm_2.bias'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm2.bias']48    converted['diffusion']['unet.encoders.1.1.layernorm_3.weight'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm3.weight']49    converted['diffusion']['unet.encoders.1.1.layernorm_3.bias'] = original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm3.bias']50    converted['diffusion']['unet.encoders.1.1.conv_output.weight'] = original_model['model.diffusion_model.input_blocks.1.1.proj_out.weight']51    converted['diffusion']['unet.encoders.1.1.conv_output.bias'] = original_model['model.diffusion_model.input_blocks.1.1.proj_out.bias']52    converted['diffusion']['unet.encoders.2.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.2.0.in_layers.0.weight']53    converted['diffusion']['unet.encoders.2.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.2.0.in_layers.0.bias']54    converted['diffusion']['unet.encoders.2.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.2.0.in_layers.2.weight']55    converted['diffusion']['unet.encoders.2.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.2.0.in_layers.2.bias']56    converted['diffusion']['unet.encoders.2.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.2.0.emb_layers.1.weight']57    converted['diffusion']['unet.encoders.2.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.2.0.emb_layers.1.bias']58    converted['diffusion']['unet.encoders.2.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.2.0.out_layers.0.weight']59    converted['diffusion']['unet.encoders.2.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.2.0.out_layers.0.bias']60    converted['diffusion']['unet.encoders.2.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.2.0.out_layers.3.weight']61    converted['diffusion']['unet.encoders.2.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.2.0.out_layers.3.bias']62    converted['diffusion']['unet.encoders.2.1.groupnorm.weight'] = original_model['model.diffusion_model.input_blocks.2.1.norm.weight']63    converted['diffusion']['unet.encoders.2.1.groupnorm.bias'] = original_model['model.diffusion_model.input_blocks.2.1.norm.bias']64    converted['diffusion']['unet.encoders.2.1.conv_input.weight'] = original_model['model.diffusion_model.input_blocks.2.1.proj_in.weight']65    converted['diffusion']['unet.encoders.2.1.conv_input.bias'] = original_model['model.diffusion_model.input_blocks.2.1.proj_in.bias']66    converted['diffusion']['unet.encoders.2.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.weight']67    converted['diffusion']['unet.encoders.2.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.bias']68    converted['diffusion']['unet.encoders.2.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.weight']69    converted['diffusion']['unet.encoders.2.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.bias']70    converted['diffusion']['unet.encoders.2.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.weight']71    converted['diffusion']['unet.encoders.2.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.bias']72    converted['diffusion']['unet.encoders.2.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_q.weight']73    converted['diffusion']['unet.encoders.2.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight']74    converted['diffusion']['unet.encoders.2.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_v.weight']75    converted['diffusion']['unet.encoders.2.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.weight']76    converted['diffusion']['unet.encoders.2.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.bias']77    converted['diffusion']['unet.encoders.2.1.layernorm_1.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm1.weight']78    converted['diffusion']['unet.encoders.2.1.layernorm_1.bias'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm1.bias']79    converted['diffusion']['unet.encoders.2.1.layernorm_2.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm2.weight']80    converted['diffusion']['unet.encoders.2.1.layernorm_2.bias'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm2.bias']81    converted['diffusion']['unet.encoders.2.1.layernorm_3.weight'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm3.weight']82    converted['diffusion']['unet.encoders.2.1.layernorm_3.bias'] = original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm3.bias']83    converted['diffusion']['unet.encoders.2.1.conv_output.weight'] = original_model['model.diffusion_model.input_blocks.2.1.proj_out.weight']84    converted['diffusion']['unet.encoders.2.1.conv_output.bias'] = original_model['model.diffusion_model.input_blocks.2.1.proj_out.bias']85    converted['diffusion']['unet.encoders.3.0.weight'] = original_model['model.diffusion_model.input_blocks.3.0.op.weight']86    converted['diffusion']['unet.encoders.3.0.bias'] = original_model['model.diffusion_model.input_blocks.3.0.op.bias']87    converted['diffusion']['unet.encoders.4.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.4.0.in_layers.0.weight']88    converted['diffusion']['unet.encoders.4.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.4.0.in_layers.0.bias']89    converted['diffusion']['unet.encoders.4.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.4.0.in_layers.2.weight']90    converted['diffusion']['unet.encoders.4.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.4.0.in_layers.2.bias']91    converted['diffusion']['unet.encoders.4.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.4.0.emb_layers.1.weight']92    converted['diffusion']['unet.encoders.4.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.4.0.emb_layers.1.bias']93    converted['diffusion']['unet.encoders.4.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.4.0.out_layers.0.weight']94    converted['diffusion']['unet.encoders.4.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.4.0.out_layers.0.bias']95    converted['diffusion']['unet.encoders.4.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.4.0.out_layers.3.weight']96    converted['diffusion']['unet.encoders.4.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.4.0.out_layers.3.bias']97    converted['diffusion']['unet.encoders.4.0.residual_layer.weight'] = original_model['model.diffusion_model.input_blocks.4.0.skip_connection.weight']98    converted['diffusion']['unet.encoders.4.0.residual_layer.bias'] = original_model['model.diffusion_model.input_blocks.4.0.skip_connection.bias']99    converted['diffusion']['unet.encoders.4.1.groupnorm.weight'] = original_model['model.diffusion_model.input_blocks.4.1.norm.weight']100    converted['diffusion']['unet.encoders.4.1.groupnorm.bias'] = original_model['model.diffusion_model.input_blocks.4.1.norm.bias']101    converted['diffusion']['unet.encoders.4.1.conv_input.weight'] = original_model['model.diffusion_model.input_blocks.4.1.proj_in.weight']102    converted['diffusion']['unet.encoders.4.1.conv_input.bias'] = original_model['model.diffusion_model.input_blocks.4.1.proj_in.bias']103    converted['diffusion']['unet.encoders.4.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight']104    converted['diffusion']['unet.encoders.4.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias']105    converted['diffusion']['unet.encoders.4.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight']106    converted['diffusion']['unet.encoders.4.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias']107    converted['diffusion']['unet.encoders.4.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.weight']108    converted['diffusion']['unet.encoders.4.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.bias']109    converted['diffusion']['unet.encoders.4.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_q.weight']110    converted['diffusion']['unet.encoders.4.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight']111    converted['diffusion']['unet.encoders.4.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight']112    converted['diffusion']['unet.encoders.4.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight']113    converted['diffusion']['unet.encoders.4.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias']114    converted['diffusion']['unet.encoders.4.1.layernorm_1.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm1.weight']115    converted['diffusion']['unet.encoders.4.1.layernorm_1.bias'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm1.bias']116    converted['diffusion']['unet.encoders.4.1.layernorm_2.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm2.weight']117    converted['diffusion']['unet.encoders.4.1.layernorm_2.bias'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm2.bias']118    converted['diffusion']['unet.encoders.4.1.layernorm_3.weight'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm3.weight']119    converted['diffusion']['unet.encoders.4.1.layernorm_3.bias'] = original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm3.bias']120    converted['diffusion']['unet.encoders.4.1.conv_output.weight'] = original_model['model.diffusion_model.input_blocks.4.1.proj_out.weight']121    converted['diffusion']['unet.encoders.4.1.conv_output.bias'] = original_model['model.diffusion_model.input_blocks.4.1.proj_out.bias']122    converted['diffusion']['unet.encoders.5.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.5.0.in_layers.0.weight']123    converted['diffusion']['unet.encoders.5.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.5.0.in_layers.0.bias']124    converted['diffusion']['unet.encoders.5.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.5.0.in_layers.2.weight']125    converted['diffusion']['unet.encoders.5.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.5.0.in_layers.2.bias']126    converted['diffusion']['unet.encoders.5.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.5.0.emb_layers.1.weight']127    converted['diffusion']['unet.encoders.5.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.5.0.emb_layers.1.bias']128    converted['diffusion']['unet.encoders.5.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.5.0.out_layers.0.weight']129    converted['diffusion']['unet.encoders.5.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.5.0.out_layers.0.bias']130    converted['diffusion']['unet.encoders.5.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.5.0.out_layers.3.weight']131    converted['diffusion']['unet.encoders.5.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.5.0.out_layers.3.bias']132    converted['diffusion']['unet.encoders.5.1.groupnorm.weight'] = original_model['model.diffusion_model.input_blocks.5.1.norm.weight']133    converted['diffusion']['unet.encoders.5.1.groupnorm.bias'] = original_model['model.diffusion_model.input_blocks.5.1.norm.bias']134    converted['diffusion']['unet.encoders.5.1.conv_input.weight'] = original_model['model.diffusion_model.input_blocks.5.1.proj_in.weight']135    converted['diffusion']['unet.encoders.5.1.conv_input.bias'] = original_model['model.diffusion_model.input_blocks.5.1.proj_in.bias']136    converted['diffusion']['unet.encoders.5.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight']137    converted['diffusion']['unet.encoders.5.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias']138    converted['diffusion']['unet.encoders.5.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight']139    converted['diffusion']['unet.encoders.5.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias']140    converted['diffusion']['unet.encoders.5.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.weight']141    converted['diffusion']['unet.encoders.5.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.bias']142    converted['diffusion']['unet.encoders.5.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_q.weight']143    converted['diffusion']['unet.encoders.5.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight']144    converted['diffusion']['unet.encoders.5.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight']145    converted['diffusion']['unet.encoders.5.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight']146    converted['diffusion']['unet.encoders.5.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias']147    converted['diffusion']['unet.encoders.5.1.layernorm_1.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm1.weight']148    converted['diffusion']['unet.encoders.5.1.layernorm_1.bias'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm1.bias']149    converted['diffusion']['unet.encoders.5.1.layernorm_2.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm2.weight']150    converted['diffusion']['unet.encoders.5.1.layernorm_2.bias'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm2.bias']151    converted['diffusion']['unet.encoders.5.1.layernorm_3.weight'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm3.weight']152    converted['diffusion']['unet.encoders.5.1.layernorm_3.bias'] = original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm3.bias']153    converted['diffusion']['unet.encoders.5.1.conv_output.weight'] = original_model['model.diffusion_model.input_blocks.5.1.proj_out.weight']154    converted['diffusion']['unet.encoders.5.1.conv_output.bias'] = original_model['model.diffusion_model.input_blocks.5.1.proj_out.bias']155    converted['diffusion']['unet.encoders.6.0.weight'] = original_model['model.diffusion_model.input_blocks.6.0.op.weight']156    converted['diffusion']['unet.encoders.6.0.bias'] = original_model['model.diffusion_model.input_blocks.6.0.op.bias']157    converted['diffusion']['unet.encoders.7.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.7.0.in_layers.0.weight']158    converted['diffusion']['unet.encoders.7.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.7.0.in_layers.0.bias']159    converted['diffusion']['unet.encoders.7.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.7.0.in_layers.2.weight']160    converted['diffusion']['unet.encoders.7.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.7.0.in_layers.2.bias']161    converted['diffusion']['unet.encoders.7.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.7.0.emb_layers.1.weight']162    converted['diffusion']['unet.encoders.7.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.7.0.emb_layers.1.bias']163    converted['diffusion']['unet.encoders.7.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.7.0.out_layers.0.weight']164    converted['diffusion']['unet.encoders.7.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.7.0.out_layers.0.bias']165    converted['diffusion']['unet.encoders.7.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.7.0.out_layers.3.weight']166    converted['diffusion']['unet.encoders.7.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.7.0.out_layers.3.bias']167    converted['diffusion']['unet.encoders.7.0.residual_layer.weight'] = original_model['model.diffusion_model.input_blocks.7.0.skip_connection.weight']168    converted['diffusion']['unet.encoders.7.0.residual_layer.bias'] = original_model['model.diffusion_model.input_blocks.7.0.skip_connection.bias']169    converted['diffusion']['unet.encoders.7.1.groupnorm.weight'] = original_model['model.diffusion_model.input_blocks.7.1.norm.weight']170    converted['diffusion']['unet.encoders.7.1.groupnorm.bias'] = original_model['model.diffusion_model.input_blocks.7.1.norm.bias']171    converted['diffusion']['unet.encoders.7.1.conv_input.weight'] = original_model['model.diffusion_model.input_blocks.7.1.proj_in.weight']172    converted['diffusion']['unet.encoders.7.1.conv_input.bias'] = original_model['model.diffusion_model.input_blocks.7.1.proj_in.bias']173    converted['diffusion']['unet.encoders.7.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight']174    converted['diffusion']['unet.encoders.7.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias']175    converted['diffusion']['unet.encoders.7.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight']176    converted['diffusion']['unet.encoders.7.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias']177    converted['diffusion']['unet.encoders.7.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.weight']178    converted['diffusion']['unet.encoders.7.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.bias']179    converted['diffusion']['unet.encoders.7.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_q.weight']180    converted['diffusion']['unet.encoders.7.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight']181    converted['diffusion']['unet.encoders.7.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight']182    converted['diffusion']['unet.encoders.7.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight']183    converted['diffusion']['unet.encoders.7.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias']184    converted['diffusion']['unet.encoders.7.1.layernorm_1.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm1.weight']185    converted['diffusion']['unet.encoders.7.1.layernorm_1.bias'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm1.bias']186    converted['diffusion']['unet.encoders.7.1.layernorm_2.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm2.weight']187    converted['diffusion']['unet.encoders.7.1.layernorm_2.bias'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm2.bias']188    converted['diffusion']['unet.encoders.7.1.layernorm_3.weight'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm3.weight']189    converted['diffusion']['unet.encoders.7.1.layernorm_3.bias'] = original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm3.bias']190    converted['diffusion']['unet.encoders.7.1.conv_output.weight'] = original_model['model.diffusion_model.input_blocks.7.1.proj_out.weight']191    converted['diffusion']['unet.encoders.7.1.conv_output.bias'] = original_model['model.diffusion_model.input_blocks.7.1.proj_out.bias']192    converted['diffusion']['unet.encoders.8.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.8.0.in_layers.0.weight']193    converted['diffusion']['unet.encoders.8.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.8.0.in_layers.0.bias']194    converted['diffusion']['unet.encoders.8.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.8.0.in_layers.2.weight']195    converted['diffusion']['unet.encoders.8.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.8.0.in_layers.2.bias']196    converted['diffusion']['unet.encoders.8.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.8.0.emb_layers.1.weight']197    converted['diffusion']['unet.encoders.8.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.8.0.emb_layers.1.bias']198    converted['diffusion']['unet.encoders.8.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.8.0.out_layers.0.weight']199    converted['diffusion']['unet.encoders.8.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.8.0.out_layers.0.bias']200    converted['diffusion']['unet.encoders.8.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.8.0.out_layers.3.weight']201    converted['diffusion']['unet.encoders.8.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.8.0.out_layers.3.bias']202    converted['diffusion']['unet.encoders.8.1.groupnorm.weight'] = original_model['model.diffusion_model.input_blocks.8.1.norm.weight']203    converted['diffusion']['unet.encoders.8.1.groupnorm.bias'] = original_model['model.diffusion_model.input_blocks.8.1.norm.bias']204    converted['diffusion']['unet.encoders.8.1.conv_input.weight'] = original_model['model.diffusion_model.input_blocks.8.1.proj_in.weight']205    converted['diffusion']['unet.encoders.8.1.conv_input.bias'] = original_model['model.diffusion_model.input_blocks.8.1.proj_in.bias']206    converted['diffusion']['unet.encoders.8.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight']207    converted['diffusion']['unet.encoders.8.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias']208    converted['diffusion']['unet.encoders.8.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight']209    converted['diffusion']['unet.encoders.8.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias']210    converted['diffusion']['unet.encoders.8.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.weight']211    converted['diffusion']['unet.encoders.8.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.bias']212    converted['diffusion']['unet.encoders.8.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_q.weight']213    converted['diffusion']['unet.encoders.8.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight']214    converted['diffusion']['unet.encoders.8.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight']215    converted['diffusion']['unet.encoders.8.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight']216    converted['diffusion']['unet.encoders.8.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias']217    converted['diffusion']['unet.encoders.8.1.layernorm_1.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm1.weight']218    converted['diffusion']['unet.encoders.8.1.layernorm_1.bias'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm1.bias']219    converted['diffusion']['unet.encoders.8.1.layernorm_2.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm2.weight']220    converted['diffusion']['unet.encoders.8.1.layernorm_2.bias'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm2.bias']221    converted['diffusion']['unet.encoders.8.1.layernorm_3.weight'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm3.weight']222    converted['diffusion']['unet.encoders.8.1.layernorm_3.bias'] = original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm3.bias']223    converted['diffusion']['unet.encoders.8.1.conv_output.weight'] = original_model['model.diffusion_model.input_blocks.8.1.proj_out.weight']224    converted['diffusion']['unet.encoders.8.1.conv_output.bias'] = original_model['model.diffusion_model.input_blocks.8.1.proj_out.bias']225    converted['diffusion']['unet.encoders.9.0.weight'] = original_model['model.diffusion_model.input_blocks.9.0.op.weight']226    converted['diffusion']['unet.encoders.9.0.bias'] = original_model['model.diffusion_model.input_blocks.9.0.op.bias']227    converted['diffusion']['unet.encoders.10.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.10.0.in_layers.0.weight']228    converted['diffusion']['unet.encoders.10.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.10.0.in_layers.0.bias']229    converted['diffusion']['unet.encoders.10.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.10.0.in_layers.2.weight']230    converted['diffusion']['unet.encoders.10.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.10.0.in_layers.2.bias']231    converted['diffusion']['unet.encoders.10.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.10.0.emb_layers.1.weight']232    converted['diffusion']['unet.encoders.10.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.10.0.emb_layers.1.bias']233    converted['diffusion']['unet.encoders.10.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.10.0.out_layers.0.weight']234    converted['diffusion']['unet.encoders.10.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.10.0.out_layers.0.bias']235    converted['diffusion']['unet.encoders.10.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.10.0.out_layers.3.weight']236    converted['diffusion']['unet.encoders.10.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.10.0.out_layers.3.bias']237    converted['diffusion']['unet.encoders.11.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.input_blocks.11.0.in_layers.0.weight']238    converted['diffusion']['unet.encoders.11.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.input_blocks.11.0.in_layers.0.bias']239    converted['diffusion']['unet.encoders.11.0.conv_feature.weight'] = original_model['model.diffusion_model.input_blocks.11.0.in_layers.2.weight']240    converted['diffusion']['unet.encoders.11.0.conv_feature.bias'] = original_model['model.diffusion_model.input_blocks.11.0.in_layers.2.bias']241    converted['diffusion']['unet.encoders.11.0.linear_time.weight'] = original_model['model.diffusion_model.input_blocks.11.0.emb_layers.1.weight']242    converted['diffusion']['unet.encoders.11.0.linear_time.bias'] = original_model['model.diffusion_model.input_blocks.11.0.emb_layers.1.bias']243    converted['diffusion']['unet.encoders.11.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.input_blocks.11.0.out_layers.0.weight']244    converted['diffusion']['unet.encoders.11.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.input_blocks.11.0.out_layers.0.bias']245    converted['diffusion']['unet.encoders.11.0.conv_merged.weight'] = original_model['model.diffusion_model.input_blocks.11.0.out_layers.3.weight']246    converted['diffusion']['unet.encoders.11.0.conv_merged.bias'] = original_model['model.diffusion_model.input_blocks.11.0.out_layers.3.bias']247    converted['diffusion']['unet.bottleneck.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.middle_block.0.in_layers.0.weight']248    converted['diffusion']['unet.bottleneck.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.middle_block.0.in_layers.0.bias']249    converted['diffusion']['unet.bottleneck.0.conv_feature.weight'] = original_model['model.diffusion_model.middle_block.0.in_layers.2.weight']250    converted['diffusion']['unet.bottleneck.0.conv_feature.bias'] = original_model['model.diffusion_model.middle_block.0.in_layers.2.bias']251    converted['diffusion']['unet.bottleneck.0.linear_time.weight'] = original_model['model.diffusion_model.middle_block.0.emb_layers.1.weight']252    converted['diffusion']['unet.bottleneck.0.linear_time.bias'] = original_model['model.diffusion_model.middle_block.0.emb_layers.1.bias']253    converted['diffusion']['unet.bottleneck.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.middle_block.0.out_layers.0.weight']254    converted['diffusion']['unet.bottleneck.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.middle_block.0.out_layers.0.bias']255    converted['diffusion']['unet.bottleneck.0.conv_merged.weight'] = original_model['model.diffusion_model.middle_block.0.out_layers.3.weight']256    converted['diffusion']['unet.bottleneck.0.conv_merged.bias'] = original_model['model.diffusion_model.middle_block.0.out_layers.3.bias']257    converted['diffusion']['unet.bottleneck.1.groupnorm.weight'] = original_model['model.diffusion_model.middle_block.1.norm.weight']258    converted['diffusion']['unet.bottleneck.1.groupnorm.bias'] = original_model['model.diffusion_model.middle_block.1.norm.bias']259    converted['diffusion']['unet.bottleneck.1.conv_input.weight'] = original_model['model.diffusion_model.middle_block.1.proj_in.weight']260    converted['diffusion']['unet.bottleneck.1.conv_input.bias'] = original_model['model.diffusion_model.middle_block.1.proj_in.bias']261    converted['diffusion']['unet.bottleneck.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.weight']262    converted['diffusion']['unet.bottleneck.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.bias']263    converted['diffusion']['unet.bottleneck.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.weight']264    converted['diffusion']['unet.bottleneck.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.bias']265    converted['diffusion']['unet.bottleneck.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.2.weight']266    converted['diffusion']['unet.bottleneck.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.2.bias']267    converted['diffusion']['unet.bottleneck.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_q.weight']268    converted['diffusion']['unet.bottleneck.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_k.weight']269    converted['diffusion']['unet.bottleneck.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_v.weight']270    converted['diffusion']['unet.bottleneck.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.weight']271    converted['diffusion']['unet.bottleneck.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.bias']272    converted['diffusion']['unet.bottleneck.1.layernorm_1.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.norm1.weight']273    converted['diffusion']['unet.bottleneck.1.layernorm_1.bias'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.norm1.bias']274    converted['diffusion']['unet.bottleneck.1.layernorm_2.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.norm2.weight']275    converted['diffusion']['unet.bottleneck.1.layernorm_2.bias'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.norm2.bias']276    converted['diffusion']['unet.bottleneck.1.layernorm_3.weight'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.norm3.weight']277    converted['diffusion']['unet.bottleneck.1.layernorm_3.bias'] = original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.norm3.bias']278    converted['diffusion']['unet.bottleneck.1.conv_output.weight'] = original_model['model.diffusion_model.middle_block.1.proj_out.weight']279    converted['diffusion']['unet.bottleneck.1.conv_output.bias'] = original_model['model.diffusion_model.middle_block.1.proj_out.bias']280    converted['diffusion']['unet.bottleneck.2.groupnorm_feature.weight'] = original_model['model.diffusion_model.middle_block.2.in_layers.0.weight']281    converted['diffusion']['unet.bottleneck.2.groupnorm_feature.bias'] = original_model['model.diffusion_model.middle_block.2.in_layers.0.bias']282    converted['diffusion']['unet.bottleneck.2.conv_feature.weight'] = original_model['model.diffusion_model.middle_block.2.in_layers.2.weight']283    converted['diffusion']['unet.bottleneck.2.conv_feature.bias'] = original_model['model.diffusion_model.middle_block.2.in_layers.2.bias']284    converted['diffusion']['unet.bottleneck.2.linear_time.weight'] = original_model['model.diffusion_model.middle_block.2.emb_layers.1.weight']285    converted['diffusion']['unet.bottleneck.2.linear_time.bias'] = original_model['model.diffusion_model.middle_block.2.emb_layers.1.bias']286    converted['diffusion']['unet.bottleneck.2.groupnorm_merged.weight'] = original_model['model.diffusion_model.middle_block.2.out_layers.0.weight']287    converted['diffusion']['unet.bottleneck.2.groupnorm_merged.bias'] = original_model['model.diffusion_model.middle_block.2.out_layers.0.bias']288    converted['diffusion']['unet.bottleneck.2.conv_merged.weight'] = original_model['model.diffusion_model.middle_block.2.out_layers.3.weight']289    converted['diffusion']['unet.bottleneck.2.conv_merged.bias'] = original_model['model.diffusion_model.middle_block.2.out_layers.3.bias']290    converted['diffusion']['unet.decoders.0.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.0.0.in_layers.0.weight']291    converted['diffusion']['unet.decoders.0.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.0.0.in_layers.0.bias']292    converted['diffusion']['unet.decoders.0.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.0.0.in_layers.2.weight']293    converted['diffusion']['unet.decoders.0.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.0.0.in_layers.2.bias']294    converted['diffusion']['unet.decoders.0.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.0.0.emb_layers.1.weight']295    converted['diffusion']['unet.decoders.0.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.0.0.emb_layers.1.bias']296    converted['diffusion']['unet.decoders.0.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.0.0.out_layers.0.weight']297    converted['diffusion']['unet.decoders.0.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.0.0.out_layers.0.bias']298    converted['diffusion']['unet.decoders.0.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.0.0.out_layers.3.weight']299    converted['diffusion']['unet.decoders.0.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.0.0.out_layers.3.bias']300    converted['diffusion']['unet.decoders.0.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.0.0.skip_connection.weight']301    converted['diffusion']['unet.decoders.0.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.0.0.skip_connection.bias']302    converted['diffusion']['unet.decoders.1.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.1.0.in_layers.0.weight']303    converted['diffusion']['unet.decoders.1.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.1.0.in_layers.0.bias']304    converted['diffusion']['unet.decoders.1.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.1.0.in_layers.2.weight']305    converted['diffusion']['unet.decoders.1.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.1.0.in_layers.2.bias']306    converted['diffusion']['unet.decoders.1.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.1.0.emb_layers.1.weight']307    converted['diffusion']['unet.decoders.1.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.1.0.emb_layers.1.bias']308    converted['diffusion']['unet.decoders.1.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.1.0.out_layers.0.weight']309    converted['diffusion']['unet.decoders.1.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.1.0.out_layers.0.bias']310    converted['diffusion']['unet.decoders.1.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.1.0.out_layers.3.weight']311    converted['diffusion']['unet.decoders.1.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.1.0.out_layers.3.bias']312    converted['diffusion']['unet.decoders.1.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.1.0.skip_connection.weight']313    converted['diffusion']['unet.decoders.1.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.1.0.skip_connection.bias']314    converted['diffusion']['unet.decoders.2.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.2.0.in_layers.0.weight']315    converted['diffusion']['unet.decoders.2.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.2.0.in_layers.0.bias']316    converted['diffusion']['unet.decoders.2.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.2.0.in_layers.2.weight']317    converted['diffusion']['unet.decoders.2.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.2.0.in_layers.2.bias']318    converted['diffusion']['unet.decoders.2.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.2.0.emb_layers.1.weight']319    converted['diffusion']['unet.decoders.2.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.2.0.emb_layers.1.bias']320    converted['diffusion']['unet.decoders.2.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.2.0.out_layers.0.weight']321    converted['diffusion']['unet.decoders.2.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.2.0.out_layers.0.bias']322    converted['diffusion']['unet.decoders.2.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.2.0.out_layers.3.weight']323    converted['diffusion']['unet.decoders.2.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.2.0.out_layers.3.bias']324    converted['diffusion']['unet.decoders.2.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.2.0.skip_connection.weight']325    converted['diffusion']['unet.decoders.2.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.2.0.skip_connection.bias']326    converted['diffusion']['unet.decoders.2.1.conv.weight'] = original_model['model.diffusion_model.output_blocks.2.1.conv.weight']327    converted['diffusion']['unet.decoders.2.1.conv.bias'] = original_model['model.diffusion_model.output_blocks.2.1.conv.bias']328    converted['diffusion']['unet.decoders.3.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.3.0.in_layers.0.weight']329    converted['diffusion']['unet.decoders.3.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.3.0.in_layers.0.bias']330    converted['diffusion']['unet.decoders.3.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.3.0.in_layers.2.weight']331    converted['diffusion']['unet.decoders.3.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.3.0.in_layers.2.bias']332    converted['diffusion']['unet.decoders.3.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.3.0.emb_layers.1.weight']333    converted['diffusion']['unet.decoders.3.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.3.0.emb_layers.1.bias']334    converted['diffusion']['unet.decoders.3.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.3.0.out_layers.0.weight']335    converted['diffusion']['unet.decoders.3.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.3.0.out_layers.0.bias']336    converted['diffusion']['unet.decoders.3.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.3.0.out_layers.3.weight']337    converted['diffusion']['unet.decoders.3.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.3.0.out_layers.3.bias']338    converted['diffusion']['unet.decoders.3.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.3.0.skip_connection.weight']339    converted['diffusion']['unet.decoders.3.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.3.0.skip_connection.bias']340    converted['diffusion']['unet.decoders.3.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.3.1.norm.weight']341    converted['diffusion']['unet.decoders.3.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.3.1.norm.bias']342    converted['diffusion']['unet.decoders.3.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.3.1.proj_in.weight']343    converted['diffusion']['unet.decoders.3.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.3.1.proj_in.bias']344    converted['diffusion']['unet.decoders.3.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.weight']345    converted['diffusion']['unet.decoders.3.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.bias']346    converted['diffusion']['unet.decoders.3.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight']347    converted['diffusion']['unet.decoders.3.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.bias']348    converted['diffusion']['unet.decoders.3.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.2.weight']349    converted['diffusion']['unet.decoders.3.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.2.bias']350    converted['diffusion']['unet.decoders.3.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_q.weight']351    converted['diffusion']['unet.decoders.3.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight']352    converted['diffusion']['unet.decoders.3.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight']353    converted['diffusion']['unet.decoders.3.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.weight']354    converted['diffusion']['unet.decoders.3.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.bias']355    converted['diffusion']['unet.decoders.3.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm1.weight']356    converted['diffusion']['unet.decoders.3.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm1.bias']357    converted['diffusion']['unet.decoders.3.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm2.weight']358    converted['diffusion']['unet.decoders.3.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm2.bias']359    converted['diffusion']['unet.decoders.3.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm3.weight']360    converted['diffusion']['unet.decoders.3.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm3.bias']361    converted['diffusion']['unet.decoders.3.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.3.1.proj_out.weight']362    converted['diffusion']['unet.decoders.3.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.3.1.proj_out.bias']363    converted['diffusion']['unet.decoders.4.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.4.0.in_layers.0.weight']364    converted['diffusion']['unet.decoders.4.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.4.0.in_layers.0.bias']365    converted['diffusion']['unet.decoders.4.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.4.0.in_layers.2.weight']366    converted['diffusion']['unet.decoders.4.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.4.0.in_layers.2.bias']367    converted['diffusion']['unet.decoders.4.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.4.0.emb_layers.1.weight']368    converted['diffusion']['unet.decoders.4.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.4.0.emb_layers.1.bias']369    converted['diffusion']['unet.decoders.4.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.4.0.out_layers.0.weight']370    converted['diffusion']['unet.decoders.4.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.4.0.out_layers.0.bias']371    converted['diffusion']['unet.decoders.4.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.4.0.out_layers.3.weight']372    converted['diffusion']['unet.decoders.4.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.4.0.out_layers.3.bias']373    converted['diffusion']['unet.decoders.4.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.4.0.skip_connection.weight']374    converted['diffusion']['unet.decoders.4.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.4.0.skip_connection.bias']375    converted['diffusion']['unet.decoders.4.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.4.1.norm.weight']376    converted['diffusion']['unet.decoders.4.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.4.1.norm.bias']377    converted['diffusion']['unet.decoders.4.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.4.1.proj_in.weight']378    converted['diffusion']['unet.decoders.4.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.4.1.proj_in.bias']379    converted['diffusion']['unet.decoders.4.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight']380    converted['diffusion']['unet.decoders.4.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias']381    converted['diffusion']['unet.decoders.4.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight']382    converted['diffusion']['unet.decoders.4.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias']383    converted['diffusion']['unet.decoders.4.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.2.weight']384    converted['diffusion']['unet.decoders.4.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.2.bias']385    converted['diffusion']['unet.decoders.4.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_q.weight']386    converted['diffusion']['unet.decoders.4.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight']387    converted['diffusion']['unet.decoders.4.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight']388    converted['diffusion']['unet.decoders.4.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight']389    converted['diffusion']['unet.decoders.4.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias']390    converted['diffusion']['unet.decoders.4.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm1.weight']391    converted['diffusion']['unet.decoders.4.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm1.bias']392    converted['diffusion']['unet.decoders.4.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm2.weight']393    converted['diffusion']['unet.decoders.4.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm2.bias']394    converted['diffusion']['unet.decoders.4.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm3.weight']395    converted['diffusion']['unet.decoders.4.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm3.bias']396    converted['diffusion']['unet.decoders.4.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.4.1.proj_out.weight']397    converted['diffusion']['unet.decoders.4.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.4.1.proj_out.bias']398    converted['diffusion']['unet.decoders.5.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.5.0.in_layers.0.weight']399    converted['diffusion']['unet.decoders.5.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.5.0.in_layers.0.bias']400    converted['diffusion']['unet.decoders.5.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.5.0.in_layers.2.weight']401    converted['diffusion']['unet.decoders.5.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.5.0.in_layers.2.bias']402    converted['diffusion']['unet.decoders.5.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.5.0.emb_layers.1.weight']403    converted['diffusion']['unet.decoders.5.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.5.0.emb_layers.1.bias']404    converted['diffusion']['unet.decoders.5.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.5.0.out_layers.0.weight']405    converted['diffusion']['unet.decoders.5.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.5.0.out_layers.0.bias']406    converted['diffusion']['unet.decoders.5.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.5.0.out_layers.3.weight']407    converted['diffusion']['unet.decoders.5.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.5.0.out_layers.3.bias']408    converted['diffusion']['unet.decoders.5.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.5.0.skip_connection.weight']409    converted['diffusion']['unet.decoders.5.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.5.0.skip_connection.bias']410    converted['diffusion']['unet.decoders.5.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.5.1.norm.weight']411    converted['diffusion']['unet.decoders.5.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.5.1.norm.bias']412    converted['diffusion']['unet.decoders.5.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.5.1.proj_in.weight']413    converted['diffusion']['unet.decoders.5.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.5.1.proj_in.bias']414    converted['diffusion']['unet.decoders.5.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight']415    converted['diffusion']['unet.decoders.5.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias']416    converted['diffusion']['unet.decoders.5.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight']417    converted['diffusion']['unet.decoders.5.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias']418    converted['diffusion']['unet.decoders.5.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.2.weight']419    converted['diffusion']['unet.decoders.5.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.2.bias']420    converted['diffusion']['unet.decoders.5.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_q.weight']421    converted['diffusion']['unet.decoders.5.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight']422    converted['diffusion']['unet.decoders.5.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight']423    converted['diffusion']['unet.decoders.5.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight']424    converted['diffusion']['unet.decoders.5.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias']425    converted['diffusion']['unet.decoders.5.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.weight']426    converted['diffusion']['unet.decoders.5.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.bias']427    converted['diffusion']['unet.decoders.5.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm2.weight']428    converted['diffusion']['unet.decoders.5.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm2.bias']429    converted['diffusion']['unet.decoders.5.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm3.weight']430    converted['diffusion']['unet.decoders.5.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm3.bias']431    converted['diffusion']['unet.decoders.5.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.5.1.proj_out.weight']432    converted['diffusion']['unet.decoders.5.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.5.1.proj_out.bias']433    converted['diffusion']['unet.decoders.5.2.conv.weight'] = original_model['model.diffusion_model.output_blocks.5.2.conv.weight']434    converted['diffusion']['unet.decoders.5.2.conv.bias'] = original_model['model.diffusion_model.output_blocks.5.2.conv.bias']435    converted['diffusion']['unet.decoders.6.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.6.0.in_layers.0.weight']436    converted['diffusion']['unet.decoders.6.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.6.0.in_layers.0.bias']437    converted['diffusion']['unet.decoders.6.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.6.0.in_layers.2.weight']438    converted['diffusion']['unet.decoders.6.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.6.0.in_layers.2.bias']439    converted['diffusion']['unet.decoders.6.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.6.0.emb_layers.1.weight']440    converted['diffusion']['unet.decoders.6.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.6.0.emb_layers.1.bias']441    converted['diffusion']['unet.decoders.6.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.6.0.out_layers.0.weight']442    converted['diffusion']['unet.decoders.6.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.6.0.out_layers.0.bias']443    converted['diffusion']['unet.decoders.6.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.6.0.out_layers.3.weight']444    converted['diffusion']['unet.decoders.6.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.6.0.out_layers.3.bias']445    converted['diffusion']['unet.decoders.6.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.6.0.skip_connection.weight']446    converted['diffusion']['unet.decoders.6.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.6.0.skip_connection.bias']447    converted['diffusion']['unet.decoders.6.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.6.1.norm.weight']448    converted['diffusion']['unet.decoders.6.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.6.1.norm.bias']449    converted['diffusion']['unet.decoders.6.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.6.1.proj_in.weight']450    converted['diffusion']['unet.decoders.6.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.6.1.proj_in.bias']451    converted['diffusion']['unet.decoders.6.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.weight']452    converted['diffusion']['unet.decoders.6.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.bias']453    converted['diffusion']['unet.decoders.6.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.weight']454    converted['diffusion']['unet.decoders.6.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.bias']455    converted['diffusion']['unet.decoders.6.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.2.weight']456    converted['diffusion']['unet.decoders.6.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.2.bias']457    converted['diffusion']['unet.decoders.6.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_q.weight']458    converted['diffusion']['unet.decoders.6.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_k.weight']459    converted['diffusion']['unet.decoders.6.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_v.weight']460    converted['diffusion']['unet.decoders.6.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.weight']461    converted['diffusion']['unet.decoders.6.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.bias']462    converted['diffusion']['unet.decoders.6.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm1.weight']463    converted['diffusion']['unet.decoders.6.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm1.bias']464    converted['diffusion']['unet.decoders.6.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm2.weight']465    converted['diffusion']['unet.decoders.6.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm2.bias']466    converted['diffusion']['unet.decoders.6.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm3.weight']467    converted['diffusion']['unet.decoders.6.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm3.bias']468    converted['diffusion']['unet.decoders.6.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.6.1.proj_out.weight']469    converted['diffusion']['unet.decoders.6.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.6.1.proj_out.bias']470    converted['diffusion']['unet.decoders.7.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.7.0.in_layers.0.weight']471    converted['diffusion']['unet.decoders.7.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.7.0.in_layers.0.bias']472    converted['diffusion']['unet.decoders.7.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.7.0.in_layers.2.weight']473    converted['diffusion']['unet.decoders.7.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.7.0.in_layers.2.bias']474    converted['diffusion']['unet.decoders.7.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.7.0.emb_layers.1.weight']475    converted['diffusion']['unet.decoders.7.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.7.0.emb_layers.1.bias']476    converted['diffusion']['unet.decoders.7.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.7.0.out_layers.0.weight']477    converted['diffusion']['unet.decoders.7.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.7.0.out_layers.0.bias']478    converted['diffusion']['unet.decoders.7.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.7.0.out_layers.3.weight']479    converted['diffusion']['unet.decoders.7.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.7.0.out_layers.3.bias']480    converted['diffusion']['unet.decoders.7.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.7.0.skip_connection.weight']481    converted['diffusion']['unet.decoders.7.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.7.0.skip_connection.bias']482    converted['diffusion']['unet.decoders.7.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.7.1.norm.weight']483    converted['diffusion']['unet.decoders.7.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.7.1.norm.bias']484    converted['diffusion']['unet.decoders.7.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.7.1.proj_in.weight']485    converted['diffusion']['unet.decoders.7.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.7.1.proj_in.bias']486    converted['diffusion']['unet.decoders.7.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight']487    converted['diffusion']['unet.decoders.7.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias']488    converted['diffusion']['unet.decoders.7.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight']489    converted['diffusion']['unet.decoders.7.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias']490    converted['diffusion']['unet.decoders.7.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.2.weight']491    converted['diffusion']['unet.decoders.7.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.2.bias']492    converted['diffusion']['unet.decoders.7.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_q.weight']493    converted['diffusion']['unet.decoders.7.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_k.weight']494    converted['diffusion']['unet.decoders.7.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_v.weight']495    converted['diffusion']['unet.decoders.7.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight']496    converted['diffusion']['unet.decoders.7.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias']497    converted['diffusion']['unet.decoders.7.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm1.weight']498    converted['diffusion']['unet.decoders.7.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm1.bias']499    converted['diffusion']['unet.decoders.7.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm2.weight']500    converted['diffusion']['unet.decoders.7.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm2.bias']501    converted['diffusion']['unet.decoders.7.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm3.weight']502    converted['diffusion']['unet.decoders.7.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm3.bias']503    converted['diffusion']['unet.decoders.7.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.7.1.proj_out.weight']504    converted['diffusion']['unet.decoders.7.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.7.1.proj_out.bias']505    converted['diffusion']['unet.decoders.8.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.8.0.in_layers.0.weight']506    converted['diffusion']['unet.decoders.8.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.8.0.in_layers.0.bias']507    converted['diffusion']['unet.decoders.8.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.8.0.in_layers.2.weight']508    converted['diffusion']['unet.decoders.8.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.8.0.in_layers.2.bias']509    converted['diffusion']['unet.decoders.8.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.8.0.emb_layers.1.weight']510    converted['diffusion']['unet.decoders.8.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.8.0.emb_layers.1.bias']511    converted['diffusion']['unet.decoders.8.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.8.0.out_layers.0.weight']512    converted['diffusion']['unet.decoders.8.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.8.0.out_layers.0.bias']513    converted['diffusion']['unet.decoders.8.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.8.0.out_layers.3.weight']514    converted['diffusion']['unet.decoders.8.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.8.0.out_layers.3.bias']515    converted['diffusion']['unet.decoders.8.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.8.0.skip_connection.weight']516    converted['diffusion']['unet.decoders.8.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.8.0.skip_connection.bias']517    converted['diffusion']['unet.decoders.8.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.8.1.norm.weight']518    converted['diffusion']['unet.decoders.8.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.8.1.norm.bias']519    converted['diffusion']['unet.decoders.8.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.8.1.proj_in.weight']520    converted['diffusion']['unet.decoders.8.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.8.1.proj_in.bias']521    converted['diffusion']['unet.decoders.8.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight']522    converted['diffusion']['unet.decoders.8.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias']523    converted['diffusion']['unet.decoders.8.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight']524    converted['diffusion']['unet.decoders.8.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias']525    converted['diffusion']['unet.decoders.8.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.2.weight']526    converted['diffusion']['unet.decoders.8.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.2.bias']527    converted['diffusion']['unet.decoders.8.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_q.weight']528    converted['diffusion']['unet.decoders.8.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_k.weight']529    converted['diffusion']['unet.decoders.8.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_v.weight']530    converted['diffusion']['unet.decoders.8.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight']531    converted['diffusion']['unet.decoders.8.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias']532    converted['diffusion']['unet.decoders.8.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm1.weight']533    converted['diffusion']['unet.decoders.8.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm1.bias']534    converted['diffusion']['unet.decoders.8.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm2.weight']535    converted['diffusion']['unet.decoders.8.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm2.bias']536    converted['diffusion']['unet.decoders.8.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm3.weight']537    converted['diffusion']['unet.decoders.8.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm3.bias']538    converted['diffusion']['unet.decoders.8.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.8.1.proj_out.weight']539    converted['diffusion']['unet.decoders.8.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.8.1.proj_out.bias']540    converted['diffusion']['unet.decoders.8.2.conv.weight'] = original_model['model.diffusion_model.output_blocks.8.2.conv.weight']541    converted['diffusion']['unet.decoders.8.2.conv.bias'] = original_model['model.diffusion_model.output_blocks.8.2.conv.bias']542    converted['diffusion']['unet.decoders.9.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.9.0.in_layers.0.weight']543    converted['diffusion']['unet.decoders.9.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.9.0.in_layers.0.bias']544    converted['diffusion']['unet.decoders.9.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.9.0.in_layers.2.weight']545    converted['diffusion']['unet.decoders.9.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.9.0.in_layers.2.bias']546    converted['diffusion']['unet.decoders.9.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.9.0.emb_layers.1.weight']547    converted['diffusion']['unet.decoders.9.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.9.0.emb_layers.1.bias']548    converted['diffusion']['unet.decoders.9.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.9.0.out_layers.0.weight']549    converted['diffusion']['unet.decoders.9.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.9.0.out_layers.0.bias']550    converted['diffusion']['unet.decoders.9.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.9.0.out_layers.3.weight']551    converted['diffusion']['unet.decoders.9.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.9.0.out_layers.3.bias']552    converted['diffusion']['unet.decoders.9.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.9.0.skip_connection.weight']553    converted['diffusion']['unet.decoders.9.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.9.0.skip_connection.bias']554    converted['diffusion']['unet.decoders.9.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.9.1.norm.weight']555    converted['diffusion']['unet.decoders.9.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.9.1.norm.bias']556    converted['diffusion']['unet.decoders.9.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.9.1.proj_in.weight']557    converted['diffusion']['unet.decoders.9.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.9.1.proj_in.bias']558    converted['diffusion']['unet.decoders.9.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.weight']559    converted['diffusion']['unet.decoders.9.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.bias']560    converted['diffusion']['unet.decoders.9.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.weight']561    converted['diffusion']['unet.decoders.9.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.bias']562    converted['diffusion']['unet.decoders.9.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.2.weight']563    converted['diffusion']['unet.decoders.9.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.2.bias']564    converted['diffusion']['unet.decoders.9.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_q.weight']565    converted['diffusion']['unet.decoders.9.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_k.weight']566    converted['diffusion']['unet.decoders.9.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_v.weight']567    converted['diffusion']['unet.decoders.9.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.weight']568    converted['diffusion']['unet.decoders.9.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.bias']569    converted['diffusion']['unet.decoders.9.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm1.weight']570    converted['diffusion']['unet.decoders.9.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm1.bias']571    converted['diffusion']['unet.decoders.9.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm2.weight']572    converted['diffusion']['unet.decoders.9.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm2.bias']573    converted['diffusion']['unet.decoders.9.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm3.weight']574    converted['diffusion']['unet.decoders.9.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm3.bias']575    converted['diffusion']['unet.decoders.9.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.9.1.proj_out.weight']576    converted['diffusion']['unet.decoders.9.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.9.1.proj_out.bias']577    converted['diffusion']['unet.decoders.10.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.10.0.in_layers.0.weight']578    converted['diffusion']['unet.decoders.10.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.10.0.in_layers.0.bias']579    converted['diffusion']['unet.decoders.10.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.10.0.in_layers.2.weight']580    converted['diffusion']['unet.decoders.10.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.10.0.in_layers.2.bias']581    converted['diffusion']['unet.decoders.10.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.10.0.emb_layers.1.weight']582    converted['diffusion']['unet.decoders.10.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.10.0.emb_layers.1.bias']583    converted['diffusion']['unet.decoders.10.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.10.0.out_layers.0.weight']584    converted['diffusion']['unet.decoders.10.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.10.0.out_layers.0.bias']585    converted['diffusion']['unet.decoders.10.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.10.0.out_layers.3.weight']586    converted['diffusion']['unet.decoders.10.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.10.0.out_layers.3.bias']587    converted['diffusion']['unet.decoders.10.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.10.0.skip_connection.weight']588    converted['diffusion']['unet.decoders.10.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.10.0.skip_connection.bias']589    converted['diffusion']['unet.decoders.10.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.10.1.norm.weight']590    converted['diffusion']['unet.decoders.10.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.10.1.norm.bias']591    converted['diffusion']['unet.decoders.10.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.10.1.proj_in.weight']592    converted['diffusion']['unet.decoders.10.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.10.1.proj_in.bias']593    converted['diffusion']['unet.decoders.10.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.weight']594    converted['diffusion']['unet.decoders.10.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.bias']595    converted['diffusion']['unet.decoders.10.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.weight']596    converted['diffusion']['unet.decoders.10.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.bias']597    converted['diffusion']['unet.decoders.10.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.2.weight']598    converted['diffusion']['unet.decoders.10.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.2.bias']599    converted['diffusion']['unet.decoders.10.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_q.weight']600    converted['diffusion']['unet.decoders.10.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_k.weight']601    converted['diffusion']['unet.decoders.10.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_v.weight']602    converted['diffusion']['unet.decoders.10.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.weight']603    converted['diffusion']['unet.decoders.10.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.bias']604    converted['diffusion']['unet.decoders.10.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm1.weight']605    converted['diffusion']['unet.decoders.10.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm1.bias']606    converted['diffusion']['unet.decoders.10.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm2.weight']607    converted['diffusion']['unet.decoders.10.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm2.bias']608    converted['diffusion']['unet.decoders.10.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm3.weight']609    converted['diffusion']['unet.decoders.10.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm3.bias']610    converted['diffusion']['unet.decoders.10.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.10.1.proj_out.weight']611    converted['diffusion']['unet.decoders.10.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.10.1.proj_out.bias']612    converted['diffusion']['unet.decoders.11.0.groupnorm_feature.weight'] = original_model['model.diffusion_model.output_blocks.11.0.in_layers.0.weight']613    converted['diffusion']['unet.decoders.11.0.groupnorm_feature.bias'] = original_model['model.diffusion_model.output_blocks.11.0.in_layers.0.bias']614    converted['diffusion']['unet.decoders.11.0.conv_feature.weight'] = original_model['model.diffusion_model.output_blocks.11.0.in_layers.2.weight']615    converted['diffusion']['unet.decoders.11.0.conv_feature.bias'] = original_model['model.diffusion_model.output_blocks.11.0.in_layers.2.bias']616    converted['diffusion']['unet.decoders.11.0.linear_time.weight'] = original_model['model.diffusion_model.output_blocks.11.0.emb_layers.1.weight']617    converted['diffusion']['unet.decoders.11.0.linear_time.bias'] = original_model['model.diffusion_model.output_blocks.11.0.emb_layers.1.bias']618    converted['diffusion']['unet.decoders.11.0.groupnorm_merged.weight'] = original_model['model.diffusion_model.output_blocks.11.0.out_layers.0.weight']619    converted['diffusion']['unet.decoders.11.0.groupnorm_merged.bias'] = original_model['model.diffusion_model.output_blocks.11.0.out_layers.0.bias']620    converted['diffusion']['unet.decoders.11.0.conv_merged.weight'] = original_model['model.diffusion_model.output_blocks.11.0.out_layers.3.weight']621    converted['diffusion']['unet.decoders.11.0.conv_merged.bias'] = original_model['model.diffusion_model.output_blocks.11.0.out_layers.3.bias']622    converted['diffusion']['unet.decoders.11.0.residual_layer.weight'] = original_model['model.diffusion_model.output_blocks.11.0.skip_connection.weight']623    converted['diffusion']['unet.decoders.11.0.residual_layer.bias'] = original_model['model.diffusion_model.output_blocks.11.0.skip_connection.bias']624    converted['diffusion']['unet.decoders.11.1.groupnorm.weight'] = original_model['model.diffusion_model.output_blocks.11.1.norm.weight']625    converted['diffusion']['unet.decoders.11.1.groupnorm.bias'] = original_model['model.diffusion_model.output_blocks.11.1.norm.bias']626    converted['diffusion']['unet.decoders.11.1.conv_input.weight'] = original_model['model.diffusion_model.output_blocks.11.1.proj_in.weight']627    converted['diffusion']['unet.decoders.11.1.conv_input.bias'] = original_model['model.diffusion_model.output_blocks.11.1.proj_in.bias']628    converted['diffusion']['unet.decoders.11.1.attention_1.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.weight']629    converted['diffusion']['unet.decoders.11.1.attention_1.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.bias']630    converted['diffusion']['unet.decoders.11.1.linear_geglu_1.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.weight']631    converted['diffusion']['unet.decoders.11.1.linear_geglu_1.bias'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.bias']632    converted['diffusion']['unet.decoders.11.1.linear_geglu_2.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.2.weight']633    converted['diffusion']['unet.decoders.11.1.linear_geglu_2.bias'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.2.bias']634    converted['diffusion']['unet.decoders.11.1.attention_2.q_proj.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_q.weight']635    converted['diffusion']['unet.decoders.11.1.attention_2.k_proj.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_k.weight']636    converted['diffusion']['unet.decoders.11.1.attention_2.v_proj.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_v.weight']637    converted['diffusion']['unet.decoders.11.1.attention_2.out_proj.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.weight']638    converted['diffusion']['unet.decoders.11.1.attention_2.out_proj.bias'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.bias']639    converted['diffusion']['unet.decoders.11.1.layernorm_1.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm1.weight']640    converted['diffusion']['unet.decoders.11.1.layernorm_1.bias'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm1.bias']641    converted['diffusion']['unet.decoders.11.1.layernorm_2.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm2.weight']642    converted['diffusion']['unet.decoders.11.1.layernorm_2.bias'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm2.bias']643    converted['diffusion']['unet.decoders.11.1.layernorm_3.weight'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm3.weight']644    converted['diffusion']['unet.decoders.11.1.layernorm_3.bias'] = original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm3.bias']645    converted['diffusion']['unet.decoders.11.1.conv_output.weight'] = original_model['model.diffusion_model.output_blocks.11.1.proj_out.weight']646    converted['diffusion']['unet.decoders.11.1.conv_output.bias'] = original_model['model.diffusion_model.output_blocks.11.1.proj_out.bias']647    converted['diffusion']['final.groupnorm.weight'] = original_model['model.diffusion_model.out.0.weight']648    converted['diffusion']['final.groupnorm.bias'] = original_model['model.diffusion_model.out.0.bias']649    converted['diffusion']['final.conv.weight'] = original_model['model.diffusion_model.out.2.weight']650    converted['diffusion']['final.conv.bias'] = original_model['model.diffusion_model.out.2.bias']651    converted['encoder']['0.weight'] = original_model['first_stage_model.encoder.conv_in.weight']652    converted['encoder']['0.bias'] = original_model['first_stage_model.encoder.conv_in.bias']653    converted['encoder']['1.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.0.block.0.norm1.weight']654    converted['encoder']['1.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.0.block.0.norm1.bias']655    converted['encoder']['1.conv_1.weight'] = original_model['first_stage_model.encoder.down.0.block.0.conv1.weight']656    converted['encoder']['1.conv_1.bias'] = original_model['first_stage_model.encoder.down.0.block.0.conv1.bias']657    converted['encoder']['1.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.0.block.0.norm2.weight']658    converted['encoder']['1.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.0.block.0.norm2.bias']659    converted['encoder']['1.conv_2.weight'] = original_model['first_stage_model.encoder.down.0.block.0.conv2.weight']660    converted['encoder']['1.conv_2.bias'] = original_model['first_stage_model.encoder.down.0.block.0.conv2.bias']661    converted['encoder']['2.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.0.block.1.norm1.weight']662    converted['encoder']['2.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.0.block.1.norm1.bias']663    converted['encoder']['2.conv_1.weight'] = original_model['first_stage_model.encoder.down.0.block.1.conv1.weight']664    converted['encoder']['2.conv_1.bias'] = original_model['first_stage_model.encoder.down.0.block.1.conv1.bias']665    converted['encoder']['2.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.0.block.1.norm2.weight']666    converted['encoder']['2.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.0.block.1.norm2.bias']667    converted['encoder']['2.conv_2.weight'] = original_model['first_stage_model.encoder.down.0.block.1.conv2.weight']668    converted['encoder']['2.conv_2.bias'] = original_model['first_stage_model.encoder.down.0.block.1.conv2.bias']669    converted['encoder']['3.weight'] = original_model['first_stage_model.encoder.down.0.downsample.conv.weight']670    converted['encoder']['3.bias'] = original_model['first_stage_model.encoder.down.0.downsample.conv.bias']671    converted['encoder']['4.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.1.block.0.norm1.weight']672    converted['encoder']['4.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.1.block.0.norm1.bias']673    converted['encoder']['4.conv_1.weight'] = original_model['first_stage_model.encoder.down.1.block.0.conv1.weight']674    converted['encoder']['4.conv_1.bias'] = original_model['first_stage_model.encoder.down.1.block.0.conv1.bias']675    converted['encoder']['4.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.1.block.0.norm2.weight']676    converted['encoder']['4.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.1.block.0.norm2.bias']677    converted['encoder']['4.conv_2.weight'] = original_model['first_stage_model.encoder.down.1.block.0.conv2.weight']678    converted['encoder']['4.conv_2.bias'] = original_model['first_stage_model.encoder.down.1.block.0.conv2.bias']679    converted['encoder']['4.residual_layer.weight'] = original_model['first_stage_model.encoder.down.1.block.0.nin_shortcut.weight']680    converted['encoder']['4.residual_layer.bias'] = original_model['first_stage_model.encoder.down.1.block.0.nin_shortcut.bias']681    converted['encoder']['5.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.1.block.1.norm1.weight']682    converted['encoder']['5.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.1.block.1.norm1.bias']683    converted['encoder']['5.conv_1.weight'] = original_model['first_stage_model.encoder.down.1.block.1.conv1.weight']684    converted['encoder']['5.conv_1.bias'] = original_model['first_stage_model.encoder.down.1.block.1.conv1.bias']685    converted['encoder']['5.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.1.block.1.norm2.weight']686    converted['encoder']['5.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.1.block.1.norm2.bias']687    converted['encoder']['5.conv_2.weight'] = original_model['first_stage_model.encoder.down.1.block.1.conv2.weight']688    converted['encoder']['5.conv_2.bias'] = original_model['first_stage_model.encoder.down.1.block.1.conv2.bias']689    converted['encoder']['6.weight'] = original_model['first_stage_model.encoder.down.1.downsample.conv.weight']690    converted['encoder']['6.bias'] = original_model['first_stage_model.encoder.down.1.downsample.conv.bias']691    converted['encoder']['7.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.2.block.0.norm1.weight']692    converted['encoder']['7.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.2.block.0.norm1.bias']693    converted['encoder']['7.conv_1.weight'] = original_model['first_stage_model.encoder.down.2.block.0.conv1.weight']694    converted['encoder']['7.conv_1.bias'] = original_model['first_stage_model.encoder.down.2.block.0.conv1.bias']695    converted['encoder']['7.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.2.block.0.norm2.weight']696    converted['encoder']['7.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.2.block.0.norm2.bias']697    converted['encoder']['7.conv_2.weight'] = original_model['first_stage_model.encoder.down.2.block.0.conv2.weight']698    converted['encoder']['7.conv_2.bias'] = original_model['first_stage_model.encoder.down.2.block.0.conv2.bias']699    converted['encoder']['7.residual_layer.weight'] = original_model['first_stage_model.encoder.down.2.block.0.nin_shortcut.weight']700    converted['encoder']['7.residual_layer.bias'] = original_model['first_stage_model.encoder.down.2.block.0.nin_shortcut.bias']701    converted['encoder']['8.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.2.block.1.norm1.weight']702    converted['encoder']['8.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.2.block.1.norm1.bias']703    converted['encoder']['8.conv_1.weight'] = original_model['first_stage_model.encoder.down.2.block.1.conv1.weight']704    converted['encoder']['8.conv_1.bias'] = original_model['first_stage_model.encoder.down.2.block.1.conv1.bias']705    converted['encoder']['8.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.2.block.1.norm2.weight']706    converted['encoder']['8.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.2.block.1.norm2.bias']707    converted['encoder']['8.conv_2.weight'] = original_model['first_stage_model.encoder.down.2.block.1.conv2.weight']708    converted['encoder']['8.conv_2.bias'] = original_model['first_stage_model.encoder.down.2.block.1.conv2.bias']709    converted['encoder']['9.weight'] = original_model['first_stage_model.encoder.down.2.downsample.conv.weight']710    converted['encoder']['9.bias'] = original_model['first_stage_model.encoder.down.2.downsample.conv.bias']711    converted['encoder']['10.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.3.block.0.norm1.weight']712    converted['encoder']['10.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.3.block.0.norm1.bias']713    converted['encoder']['10.conv_1.weight'] = original_model['first_stage_model.encoder.down.3.block.0.conv1.weight']714    converted['encoder']['10.conv_1.bias'] = original_model['first_stage_model.encoder.down.3.block.0.conv1.bias']715    converted['encoder']['10.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.3.block.0.norm2.weight']716    converted['encoder']['10.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.3.block.0.norm2.bias']717    converted['encoder']['10.conv_2.weight'] = original_model['first_stage_model.encoder.down.3.block.0.conv2.weight']718    converted['encoder']['10.conv_2.bias'] = original_model['first_stage_model.encoder.down.3.block.0.conv2.bias']719    converted['encoder']['11.groupnorm_1.weight'] = original_model['first_stage_model.encoder.down.3.block.1.norm1.weight']720    converted['encoder']['11.groupnorm_1.bias'] = original_model['first_stage_model.encoder.down.3.block.1.norm1.bias']721    converted['encoder']['11.conv_1.weight'] = original_model['first_stage_model.encoder.down.3.block.1.conv1.weight']722    converted['encoder']['11.conv_1.bias'] = original_model['first_stage_model.encoder.down.3.block.1.conv1.bias']723    converted['encoder']['11.groupnorm_2.weight'] = original_model['first_stage_model.encoder.down.3.block.1.norm2.weight']724    converted['encoder']['11.groupnorm_2.bias'] = original_model['first_stage_model.encoder.down.3.block.1.norm2.bias']725    converted['encoder']['11.conv_2.weight'] = original_model['first_stage_model.encoder.down.3.block.1.conv2.weight']726    converted['encoder']['11.conv_2.bias'] = original_model['first_stage_model.encoder.down.3.block.1.conv2.bias']727    converted['encoder']['12.groupnorm_1.weight'] = original_model['first_stage_model.encoder.mid.block_1.norm1.weight']728    converted['encoder']['12.groupnorm_1.bias'] = original_model['first_stage_model.encoder.mid.block_1.norm1.bias']729    converted['encoder']['12.conv_1.weight'] = original_model['first_stage_model.encoder.mid.block_1.conv1.weight']730    converted['encoder']['12.conv_1.bias'] = original_model['first_stage_model.encoder.mid.block_1.conv1.bias']731    converted['encoder']['12.groupnorm_2.weight'] = original_model['first_stage_model.encoder.mid.block_1.norm2.weight']732    converted['encoder']['12.groupnorm_2.bias'] = original_model['first_stage_model.encoder.mid.block_1.norm2.bias']733    converted['encoder']['12.conv_2.weight'] = original_model['first_stage_model.encoder.mid.block_1.conv2.weight']734    converted['encoder']['12.conv_2.bias'] = original_model['first_stage_model.encoder.mid.block_1.conv2.bias']735    converted['encoder']['13.groupnorm.weight'] = original_model['first_stage_model.encoder.mid.attn_1.norm.weight']736    converted['encoder']['13.groupnorm.bias'] = original_model['first_stage_model.encoder.mid.attn_1.norm.bias']737    converted['encoder']['13.attention.out_proj.bias'] = original_model['first_stage_model.encoder.mid.attn_1.proj_out.bias']738    converted['encoder']['14.groupnorm_1.weight'] = original_model['first_stage_model.encoder.mid.block_2.norm1.weight']739    converted['encoder']['14.groupnorm_1.bias'] = original_model['first_stage_model.encoder.mid.block_2.norm1.bias']740    converted['encoder']['14.conv_1.weight'] = original_model['first_stage_model.encoder.mid.block_2.conv1.weight']741    converted['encoder']['14.conv_1.bias'] = original_model['first_stage_model.encoder.mid.block_2.conv1.bias']742    converted['encoder']['14.groupnorm_2.weight'] = original_model['first_stage_model.encoder.mid.block_2.norm2.weight']743    converted['encoder']['14.groupnorm_2.bias'] = original_model['first_stage_model.encoder.mid.block_2.norm2.bias']744    converted['encoder']['14.conv_2.weight'] = original_model['first_stage_model.encoder.mid.block_2.conv2.weight']745    converted['encoder']['14.conv_2.bias'] = original_model['first_stage_model.encoder.mid.block_2.conv2.bias']746    converted['encoder']['15.weight'] = original_model['first_stage_model.encoder.norm_out.weight']747    converted['encoder']['15.bias'] = original_model['first_stage_model.encoder.norm_out.bias']748    converted['encoder']['17.weight'] = original_model['first_stage_model.encoder.conv_out.weight']749    converted['encoder']['17.bias'] = original_model['first_stage_model.encoder.conv_out.bias']750    converted['decoder']['1.weight'] = original_model['first_stage_model.decoder.conv_in.weight']751    converted['decoder']['1.bias'] = original_model['first_stage_model.decoder.conv_in.bias']752    converted['decoder']['2.groupnorm_1.weight'] = original_model['first_stage_model.decoder.mid.block_1.norm1.weight']753    converted['decoder']['2.groupnorm_1.bias'] = original_model['first_stage_model.decoder.mid.block_1.norm1.bias']754    converted['decoder']['2.conv_1.weight'] = original_model['first_stage_model.decoder.mid.block_1.conv1.weight']755    converted['decoder']['2.conv_1.bias'] = original_model['first_stage_model.decoder.mid.block_1.conv1.bias']756    converted['decoder']['2.groupnorm_2.weight'] = original_model['first_stage_model.decoder.mid.block_1.norm2.weight']757    converted['decoder']['2.groupnorm_2.bias'] = original_model['first_stage_model.decoder.mid.block_1.norm2.bias']758    converted['decoder']['2.conv_2.weight'] = original_model['first_stage_model.decoder.mid.block_1.conv2.weight']759    converted['decoder']['2.conv_2.bias'] = original_model['first_stage_model.decoder.mid.block_1.conv2.bias']760    converted['decoder']['3.groupnorm.weight'] = original_model['first_stage_model.decoder.mid.attn_1.norm.weight']761    converted['decoder']['3.groupnorm.bias'] = original_model['first_stage_model.decoder.mid.attn_1.norm.bias']762    converted['decoder']['3.attention.out_proj.bias'] = original_model['first_stage_model.decoder.mid.attn_1.proj_out.bias']763    converted['decoder']['4.groupnorm_1.weight'] = original_model['first_stage_model.decoder.mid.block_2.norm1.weight']764    converted['decoder']['4.groupnorm_1.bias'] = original_model['first_stage_model.decoder.mid.block_2.norm1.bias']765    converted['decoder']['4.conv_1.weight'] = original_model['first_stage_model.decoder.mid.block_2.conv1.weight']766    converted['decoder']['4.conv_1.bias'] = original_model['first_stage_model.decoder.mid.block_2.conv1.bias']767    converted['decoder']['4.groupnorm_2.weight'] = original_model['first_stage_model.decoder.mid.block_2.norm2.weight']768    converted['decoder']['4.groupnorm_2.bias'] = original_model['first_stage_model.decoder.mid.block_2.norm2.bias']769    converted['decoder']['4.conv_2.weight'] = original_model['first_stage_model.decoder.mid.block_2.conv2.weight']770    converted['decoder']['4.conv_2.bias'] = original_model['first_stage_model.decoder.mid.block_2.conv2.bias']771    converted['decoder']['20.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.0.block.0.norm1.weight']772    converted['decoder']['20.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.0.block.0.norm1.bias']773    converted['decoder']['20.conv_1.weight'] = original_model['first_stage_model.decoder.up.0.block.0.conv1.weight']774    converted['decoder']['20.conv_1.bias'] = original_model['first_stage_model.decoder.up.0.block.0.conv1.bias']775    converted['decoder']['20.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.0.block.0.norm2.weight']776    converted['decoder']['20.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.0.block.0.norm2.bias']777    converted['decoder']['20.conv_2.weight'] = original_model['first_stage_model.decoder.up.0.block.0.conv2.weight']778    converted['decoder']['20.conv_2.bias'] = original_model['first_stage_model.decoder.up.0.block.0.conv2.bias']779    converted['decoder']['20.residual_layer.weight'] = original_model['first_stage_model.decoder.up.0.block.0.nin_shortcut.weight']780    converted['decoder']['20.residual_layer.bias'] = original_model['first_stage_model.decoder.up.0.block.0.nin_shortcut.bias']781    converted['decoder']['21.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.0.block.1.norm1.weight']782    converted['decoder']['21.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.0.block.1.norm1.bias']783    converted['decoder']['21.conv_1.weight'] = original_model['first_stage_model.decoder.up.0.block.1.conv1.weight']784    converted['decoder']['21.conv_1.bias'] = original_model['first_stage_model.decoder.up.0.block.1.conv1.bias']785    converted['decoder']['21.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.0.block.1.norm2.weight']786    converted['decoder']['21.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.0.block.1.norm2.bias']787    converted['decoder']['21.conv_2.weight'] = original_model['first_stage_model.decoder.up.0.block.1.conv2.weight']788    converted['decoder']['21.conv_2.bias'] = original_model['first_stage_model.decoder.up.0.block.1.conv2.bias']789    converted['decoder']['22.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.0.block.2.norm1.weight']790    converted['decoder']['22.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.0.block.2.norm1.bias']791    converted['decoder']['22.conv_1.weight'] = original_model['first_stage_model.decoder.up.0.block.2.conv1.weight']792    converted['decoder']['22.conv_1.bias'] = original_model['first_stage_model.decoder.up.0.block.2.conv1.bias']793    converted['decoder']['22.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.0.block.2.norm2.weight']794    converted['decoder']['22.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.0.block.2.norm2.bias']795    converted['decoder']['22.conv_2.weight'] = original_model['first_stage_model.decoder.up.0.block.2.conv2.weight']796    converted['decoder']['22.conv_2.bias'] = original_model['first_stage_model.decoder.up.0.block.2.conv2.bias']797    converted['decoder']['15.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.1.block.0.norm1.weight']798    converted['decoder']['15.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.1.block.0.norm1.bias']799    converted['decoder']['15.conv_1.weight'] = original_model['first_stage_model.decoder.up.1.block.0.conv1.weight']800    converted['decoder']['15.conv_1.bias'] = original_model['first_stage_model.decoder.up.1.block.0.conv1.bias']801    converted['decoder']['15.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.1.block.0.norm2.weight']802    converted['decoder']['15.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.1.block.0.norm2.bias']803    converted['decoder']['15.conv_2.weight'] = original_model['first_stage_model.decoder.up.1.block.0.conv2.weight']804    converted['decoder']['15.conv_2.bias'] = original_model['first_stage_model.decoder.up.1.block.0.conv2.bias']805    converted['decoder']['15.residual_layer.weight'] = original_model['first_stage_model.decoder.up.1.block.0.nin_shortcut.weight']806    converted['decoder']['15.residual_layer.bias'] = original_model['first_stage_model.decoder.up.1.block.0.nin_shortcut.bias']807    converted['decoder']['16.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.1.block.1.norm1.weight']808    converted['decoder']['16.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.1.block.1.norm1.bias']809    converted['decoder']['16.conv_1.weight'] = original_model['first_stage_model.decoder.up.1.block.1.conv1.weight']810    converted['decoder']['16.conv_1.bias'] = original_model['first_stage_model.decoder.up.1.block.1.conv1.bias']811    converted['decoder']['16.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.1.block.1.norm2.weight']812    converted['decoder']['16.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.1.block.1.norm2.bias']813    converted['decoder']['16.conv_2.weight'] = original_model['first_stage_model.decoder.up.1.block.1.conv2.weight']814    converted['decoder']['16.conv_2.bias'] = original_model['first_stage_model.decoder.up.1.block.1.conv2.bias']815    converted['decoder']['17.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.1.block.2.norm1.weight']816    converted['decoder']['17.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.1.block.2.norm1.bias']817    converted['decoder']['17.conv_1.weight'] = original_model['first_stage_model.decoder.up.1.block.2.conv1.weight']818    converted['decoder']['17.conv_1.bias'] = original_model['first_stage_model.decoder.up.1.block.2.conv1.bias']819    converted['decoder']['17.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.1.block.2.norm2.weight']820    converted['decoder']['17.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.1.block.2.norm2.bias']821    converted['decoder']['17.conv_2.weight'] = original_model['first_stage_model.decoder.up.1.block.2.conv2.weight']822    converted['decoder']['17.conv_2.bias'] = original_model['first_stage_model.decoder.up.1.block.2.conv2.bias']823    converted['decoder']['19.weight'] = original_model['first_stage_model.decoder.up.1.upsample.conv.weight']824    converted['decoder']['19.bias'] = original_model['first_stage_model.decoder.up.1.upsample.conv.bias']825    converted['decoder']['10.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.2.block.0.norm1.weight']826    converted['decoder']['10.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.2.block.0.norm1.bias']827    converted['decoder']['10.conv_1.weight'] = original_model['first_stage_model.decoder.up.2.block.0.conv1.weight']828    converted['decoder']['10.conv_1.bias'] = original_model['first_stage_model.decoder.up.2.block.0.conv1.bias']829    converted['decoder']['10.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.2.block.0.norm2.weight']830    converted['decoder']['10.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.2.block.0.norm2.bias']831    converted['decoder']['10.conv_2.weight'] = original_model['first_stage_model.decoder.up.2.block.0.conv2.weight']832    converted['decoder']['10.conv_2.bias'] = original_model['first_stage_model.decoder.up.2.block.0.conv2.bias']833    converted['decoder']['11.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.2.block.1.norm1.weight']834    converted['decoder']['11.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.2.block.1.norm1.bias']835    converted['decoder']['11.conv_1.weight'] = original_model['first_stage_model.decoder.up.2.block.1.conv1.weight']836    converted['decoder']['11.conv_1.bias'] = original_model['first_stage_model.decoder.up.2.block.1.conv1.bias']837    converted['decoder']['11.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.2.block.1.norm2.weight']838    converted['decoder']['11.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.2.block.1.norm2.bias']839    converted['decoder']['11.conv_2.weight'] = original_model['first_stage_model.decoder.up.2.block.1.conv2.weight']840    converted['decoder']['11.conv_2.bias'] = original_model['first_stage_model.decoder.up.2.block.1.conv2.bias']841    converted['decoder']['12.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.2.block.2.norm1.weight']842    converted['decoder']['12.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.2.block.2.norm1.bias']843    converted['decoder']['12.conv_1.weight'] = original_model['first_stage_model.decoder.up.2.block.2.conv1.weight']844    converted['decoder']['12.conv_1.bias'] = original_model['first_stage_model.decoder.up.2.block.2.conv1.bias']845    converted['decoder']['12.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.2.block.2.norm2.weight']846    converted['decoder']['12.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.2.block.2.norm2.bias']847    converted['decoder']['12.conv_2.weight'] = original_model['first_stage_model.decoder.up.2.block.2.conv2.weight']848    converted['decoder']['12.conv_2.bias'] = original_model['first_stage_model.decoder.up.2.block.2.conv2.bias']849    converted['decoder']['14.weight'] = original_model['first_stage_model.decoder.up.2.upsample.conv.weight']850    converted['decoder']['14.bias'] = original_model['first_stage_model.decoder.up.2.upsample.conv.bias']851    converted['decoder']['5.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.3.block.0.norm1.weight']852    converted['decoder']['5.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.3.block.0.norm1.bias']853    converted['decoder']['5.conv_1.weight'] = original_model['first_stage_model.decoder.up.3.block.0.conv1.weight']854    converted['decoder']['5.conv_1.bias'] = original_model['first_stage_model.decoder.up.3.block.0.conv1.bias']855    converted['decoder']['5.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.3.block.0.norm2.weight']856    converted['decoder']['5.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.3.block.0.norm2.bias']857    converted['decoder']['5.conv_2.weight'] = original_model['first_stage_model.decoder.up.3.block.0.conv2.weight']858    converted['decoder']['5.conv_2.bias'] = original_model['first_stage_model.decoder.up.3.block.0.conv2.bias']859    converted['decoder']['6.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.3.block.1.norm1.weight']860    converted['decoder']['6.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.3.block.1.norm1.bias']861    converted['decoder']['6.conv_1.weight'] = original_model['first_stage_model.decoder.up.3.block.1.conv1.weight']862    converted['decoder']['6.conv_1.bias'] = original_model['first_stage_model.decoder.up.3.block.1.conv1.bias']863    converted['decoder']['6.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.3.block.1.norm2.weight']864    converted['decoder']['6.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.3.block.1.norm2.bias']865    converted['decoder']['6.conv_2.weight'] = original_model['first_stage_model.decoder.up.3.block.1.conv2.weight']866    converted['decoder']['6.conv_2.bias'] = original_model['first_stage_model.decoder.up.3.block.1.conv2.bias']867    converted['decoder']['7.groupnorm_1.weight'] = original_model['first_stage_model.decoder.up.3.block.2.norm1.weight']868    converted['decoder']['7.groupnorm_1.bias'] = original_model['first_stage_model.decoder.up.3.block.2.norm1.bias']869    converted['decoder']['7.conv_1.weight'] = original_model['first_stage_model.decoder.up.3.block.2.conv1.weight']870    converted['decoder']['7.conv_1.bias'] = original_model['first_stage_model.decoder.up.3.block.2.conv1.bias']871    converted['decoder']['7.groupnorm_2.weight'] = original_model['first_stage_model.decoder.up.3.block.2.norm2.weight']872    converted['decoder']['7.groupnorm_2.bias'] = original_model['first_stage_model.decoder.up.3.block.2.norm2.bias']873    converted['decoder']['7.conv_2.weight'] = original_model['first_stage_model.decoder.up.3.block.2.conv2.weight']874    converted['decoder']['7.conv_2.bias'] = original_model['first_stage_model.decoder.up.3.block.2.conv2.bias']875    converted['decoder']['9.weight'] = original_model['first_stage_model.decoder.up.3.upsample.conv.weight']876    converted['decoder']['9.bias'] = original_model['first_stage_model.decoder.up.3.upsample.conv.bias']877    converted['decoder']['23.weight'] = original_model['first_stage_model.decoder.norm_out.weight']878    converted['decoder']['23.bias'] = original_model['first_stage_model.decoder.norm_out.bias']879    converted['decoder']['25.weight'] = original_model['first_stage_model.decoder.conv_out.weight']880    converted['decoder']['25.bias'] = original_model['first_stage_model.decoder.conv_out.bias']881    converted['encoder']['18.weight'] = original_model['first_stage_model.quant_conv.weight']882    converted['encoder']['18.bias'] = original_model['first_stage_model.quant_conv.bias']883    converted['decoder']['0.weight'] = original_model['first_stage_model.post_quant_conv.weight']884    converted['decoder']['0.bias'] = original_model['first_stage_model.post_quant_conv.bias']885    converted['clip']['embedding.token_embedding.weight'] = original_model['cond_stage_model.transformer.text_model.embeddings.token_embedding.weight']886    converted['clip']['embedding.position_embedding'] = original_model['cond_stage_model.transformer.text_model.embeddings.position_embedding.weight']887    converted['clip']['layers.0.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.out_proj.weight']888    converted['clip']['layers.0.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.out_proj.bias']889    converted['clip']['layers.0.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm1.weight']890    converted['clip']['layers.0.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm1.bias']891    converted['clip']['layers.0.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc1.weight']892    converted['clip']['layers.0.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc1.bias']893    converted['clip']['layers.0.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc2.weight']894    converted['clip']['layers.0.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc2.bias']895    converted['clip']['layers.0.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm2.weight']896    converted['clip']['layers.0.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm2.bias']897    converted['clip']['layers.1.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.out_proj.weight']898    converted['clip']['layers.1.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.out_proj.bias']899    converted['clip']['layers.1.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm1.weight']900    converted['clip']['layers.1.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm1.bias']901    converted['clip']['layers.1.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc1.weight']902    converted['clip']['layers.1.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc1.bias']903    converted['clip']['layers.1.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc2.weight']904    converted['clip']['layers.1.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc2.bias']905    converted['clip']['layers.1.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm2.weight']906    converted['clip']['layers.1.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm2.bias']907    converted['clip']['layers.2.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.out_proj.weight']908    converted['clip']['layers.2.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.out_proj.bias']909    converted['clip']['layers.2.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm1.weight']910    converted['clip']['layers.2.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm1.bias']911    converted['clip']['layers.2.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc1.weight']912    converted['clip']['layers.2.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc1.bias']913    converted['clip']['layers.2.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc2.weight']914    converted['clip']['layers.2.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc2.bias']915    converted['clip']['layers.2.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm2.weight']916    converted['clip']['layers.2.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm2.bias']917    converted['clip']['layers.3.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.out_proj.weight']918    converted['clip']['layers.3.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.out_proj.bias']919    converted['clip']['layers.3.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm1.weight']920    converted['clip']['layers.3.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm1.bias']921    converted['clip']['layers.3.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc1.weight']922    converted['clip']['layers.3.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc1.bias']923    converted['clip']['layers.3.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc2.weight']924    converted['clip']['layers.3.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc2.bias']925    converted['clip']['layers.3.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm2.weight']926    converted['clip']['layers.3.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm2.bias']927    converted['clip']['layers.4.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.out_proj.weight']928    converted['clip']['layers.4.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.out_proj.bias']929    converted['clip']['layers.4.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm1.weight']930    converted['clip']['layers.4.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm1.bias']931    converted['clip']['layers.4.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc1.weight']932    converted['clip']['layers.4.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc1.bias']933    converted['clip']['layers.4.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc2.weight']934    converted['clip']['layers.4.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc2.bias']935    converted['clip']['layers.4.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm2.weight']936    converted['clip']['layers.4.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm2.bias']937    converted['clip']['layers.5.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.out_proj.weight']938    converted['clip']['layers.5.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.out_proj.bias']939    converted['clip']['layers.5.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm1.weight']940    converted['clip']['layers.5.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm1.bias']941    converted['clip']['layers.5.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc1.weight']942    converted['clip']['layers.5.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc1.bias']943    converted['clip']['layers.5.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc2.weight']944    converted['clip']['layers.5.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc2.bias']945    converted['clip']['layers.5.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm2.weight']946    converted['clip']['layers.5.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm2.bias']947    converted['clip']['layers.6.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.out_proj.weight']948    converted['clip']['layers.6.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.out_proj.bias']949    converted['clip']['layers.6.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm1.weight']950    converted['clip']['layers.6.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm1.bias']951    converted['clip']['layers.6.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc1.weight']952    converted['clip']['layers.6.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc1.bias']953    converted['clip']['layers.6.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc2.weight']954    converted['clip']['layers.6.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc2.bias']955    converted['clip']['layers.6.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm2.weight']956    converted['clip']['layers.6.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm2.bias']957    converted['clip']['layers.7.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.out_proj.weight']958    converted['clip']['layers.7.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.out_proj.bias']959    converted['clip']['layers.7.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm1.weight']960    converted['clip']['layers.7.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm1.bias']961    converted['clip']['layers.7.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc1.weight']962    converted['clip']['layers.7.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc1.bias']963    converted['clip']['layers.7.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc2.weight']964    converted['clip']['layers.7.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc2.bias']965    converted['clip']['layers.7.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm2.weight']966    converted['clip']['layers.7.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm2.bias']967    converted['clip']['layers.8.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.out_proj.weight']968    converted['clip']['layers.8.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.out_proj.bias']969    converted['clip']['layers.8.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm1.weight']970    converted['clip']['layers.8.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm1.bias']971    converted['clip']['layers.8.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc1.weight']972    converted['clip']['layers.8.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc1.bias']973    converted['clip']['layers.8.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc2.weight']974    converted['clip']['layers.8.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc2.bias']975    converted['clip']['layers.8.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm2.weight']976    converted['clip']['layers.8.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm2.bias']977    converted['clip']['layers.9.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.out_proj.weight']978    converted['clip']['layers.9.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.out_proj.bias']979    converted['clip']['layers.9.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm1.weight']980    converted['clip']['layers.9.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm1.bias']981    converted['clip']['layers.9.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc1.weight']982    converted['clip']['layers.9.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc1.bias']983    converted['clip']['layers.9.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc2.weight']984    converted['clip']['layers.9.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc2.bias']985    converted['clip']['layers.9.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm2.weight']986    converted['clip']['layers.9.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm2.bias']987    converted['clip']['layers.10.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.out_proj.weight']988    converted['clip']['layers.10.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.out_proj.bias']989    converted['clip']['layers.10.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm1.weight']990    converted['clip']['layers.10.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm1.bias']991    converted['clip']['layers.10.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc1.weight']992    converted['clip']['layers.10.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc1.bias']993    converted['clip']['layers.10.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc2.weight']994    converted['clip']['layers.10.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc2.bias']995    converted['clip']['layers.10.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm2.weight']996    converted['clip']['layers.10.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm2.bias']997    converted['clip']['layers.11.attention.out_proj.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.out_proj.weight']998    converted['clip']['layers.11.attention.out_proj.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.out_proj.bias']999    converted['clip']['layers.11.layernorm_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm1.weight']1000    converted['clip']['layers.11.layernorm_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm1.bias']1001    converted['clip']['layers.11.linear_1.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc1.weight']1002    converted['clip']['layers.11.linear_1.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc1.bias']1003    converted['clip']['layers.11.linear_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc2.weight']1004    converted['clip']['layers.11.linear_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc2.bias']1005    converted['clip']['layers.11.layernorm_2.weight'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm2.weight']1006    converted['clip']['layers.11.layernorm_2.bias'] = original_model['cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm2.bias']1007    converted['clip']['layernorm.weight'] = original_model['cond_stage_model.transformer.text_model.final_layer_norm.weight']1008    converted['clip']['layernorm.bias'] = original_model['cond_stage_model.transformer.text_model.final_layer_norm.bias']1009    converted['diffusion']['unet.encoders.1.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_v.weight']), 0)1010    converted['diffusion']['unet.encoders.2.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_v.weight']), 0)1011    converted['diffusion']['unet.encoders.4.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_v.weight']), 0)1012    converted['diffusion']['unet.encoders.5.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_v.weight']), 0)1013    converted['diffusion']['unet.encoders.7.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_v.weight']), 0)1014    converted['diffusion']['unet.encoders.8.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_v.weight']), 0)1015    converted['diffusion']['unet.bottleneck.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_v.weight']), 0)1016    converted['diffusion']['unet.decoders.3.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_v.weight']), 0)1017    converted['diffusion']['unet.decoders.4.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_v.weight']), 0)1018    converted['diffusion']['unet.decoders.5.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight']), 0)1019    converted['diffusion']['unet.decoders.6.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_v.weight']), 0)1020    converted['diffusion']['unet.decoders.7.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_v.weight']), 0)1021    converted['diffusion']['unet.decoders.8.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_v.weight']), 0)1022    converted['diffusion']['unet.decoders.9.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_v.weight']), 0)1023    converted['diffusion']['unet.decoders.10.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_v.weight']), 0)1024    converted['diffusion']['unet.decoders.11.1.attention_1.in_proj.weight'] = torch.cat((original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_q.weight'], original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_k.weight'], original_model['model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_v.weight']), 0)1025    converted['encoder']['13.attention.in_proj.weight'] = torch.cat((original_model['first_stage_model.encoder.mid.attn_1.q.weight'], original_model['first_stage_model.encoder.mid.attn_1.k.weight'], original_model['first_stage_model.encoder.mid.attn_1.v.weight']), 0).reshape((1536, 512))1026    converted['encoder']['13.attention.in_proj.bias'] = torch.cat((original_model['first_stage_model.encoder.mid.attn_1.q.bias'], original_model['first_stage_model.encoder.mid.attn_1.k.bias'], original_model['first_stage_model.encoder.mid.attn_1.v.bias']), 0)1027    converted['encoder']['13.attention.out_proj.weight'] = original_model['first_stage_model.encoder.mid.attn_1.proj_out.weight'].reshape((512, 512))1028    converted['decoder']['3.attention.in_proj.weight'] = torch.cat((original_model['first_stage_model.decoder.mid.attn_1.q.weight'], original_model['first_stage_model.decoder.mid.attn_1.k.weight'], original_model['first_stage_model.decoder.mid.attn_1.v.weight']), 0).reshape((1536, 512))1029    converted['decoder']['3.attention.in_proj.bias'] = torch.cat((original_model['first_stage_model.decoder.mid.attn_1.q.bias'], original_model['first_stage_model.decoder.mid.attn_1.k.bias'], original_model['first_stage_model.decoder.mid.attn_1.v.bias']), 0)1030    converted['decoder']['3.attention.out_proj.weight'] = original_model['first_stage_model.decoder.mid.attn_1.proj_out.weight'].reshape((512, 512))1031    converted['clip']['layers.0.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.v_proj.weight']), 0)1032    converted['clip']['layers.0.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.v_proj.bias']), 0)1033    converted['clip']['layers.1.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.v_proj.weight']), 0)1034    converted['clip']['layers.1.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.v_proj.bias']), 0)1035    converted['clip']['layers.2.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.v_proj.weight']), 0)1036    converted['clip']['layers.2.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.v_proj.bias']), 0)1037    converted['clip']['layers.3.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.v_proj.weight']), 0)1038    converted['clip']['layers.3.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.v_proj.bias']), 0)1039    converted['clip']['layers.4.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.v_proj.weight']), 0)1040    converted['clip']['layers.4.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.v_proj.bias']), 0)1041    converted['clip']['layers.5.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.v_proj.weight']), 0)1042    converted['clip']['layers.5.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.v_proj.bias']), 0)1043    converted['clip']['layers.6.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.v_proj.weight']), 0)1044    converted['clip']['layers.6.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.v_proj.bias']), 0)1045    converted['clip']['layers.7.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.v_proj.weight']), 0)1046    converted['clip']['layers.7.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.v_proj.bias']), 0)1047    converted['clip']['layers.8.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.v_proj.weight']), 0)1048    converted['clip']['layers.8.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.v_proj.bias']), 0)1049    converted['clip']['layers.9.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.v_proj.weight']), 0)1050    converted['clip']['layers.9.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.v_proj.bias']), 0)1051    converted['clip']['layers.10.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.v_proj.weight']), 0)1052    converted['clip']['layers.10.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.v_proj.bias']), 0)1053    converted['clip']['layers.11.attention.in_proj.weight'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.q_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.k_proj.weight'], original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.v_proj.weight']), 0)1054    converted['clip']['layers.11.attention.in_proj.bias'] = torch.cat((original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.q_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.k_proj.bias'], original_model['cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.v_proj.bias']), 0)1055 1056    return converted