model:
  params:
    scale_factor: 0.13025
    network_config:
      params:
        adm_in_channels: 2816
        num_classes: sequential
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions: [4, 2]
        num_res_blocks: 2
        channel_mult: [1, 2, 4]
        num_head_channels: 64
        use_linear_in_transformer: true
        transformer_depth: [1, 2, 10]
        context_dim: 2048
    first_stage_config:
      params:
        ddconfig:
          double_z: true
          z_channels: 4
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult: [1, 2, 4, 4]
          num_res_blocks: 2
          attn_resolutions: []
          dropout: 0.0