modelUNet:
  base_learning_rate: 1.0e-04
  target: optimizedSD.ddpm.UNet
  params:
    linear_start: 0.00085
    linear_end: 0.0120
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: "jpg"
    cond_stage_key: "txt"
    image_size: 64
    channels: 4
    cond_stage_trainable: false # Note: different from the one we trained before
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False

    unetConfigEncode:
      target: optimizedSD.openaimodelSplit.UNetModelEncode
      params:
        image_size: 32 # unused
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions: [4, 2, 1]
        num_res_blocks: 2
        channel_mult: [1, 2, 4, 4]
        num_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: True
        legacy: False

    unetConfigDecode:
      target: optimizedSD.openaimodelSplit.UNetModelDecode
      params:
        image_size: 32 # unused
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions: [4, 2, 1]
        num_res_blocks: 2
        channel_mult: [1, 2, 4, 4]
        num_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: True
        legacy: False

modelFirstStage:
  target: optimizedSD.ddpm.FirstStage
  params:
    linear_start: 0.00085
    linear_end: 0.0120
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: "jpg"
    cond_stage_key: "txt"
    image_size: 64
    channels: 4
    cond_stage_trainable: false # Note: different from the one we trained before
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False
    first_stage_config:
      target: ldmlib.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        monitor: val/rec_loss
        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
        lossconfig:
          target: torch.nn.Identity

modelCondStage:
  target: optimizedSD.ddpm.CondStage
  params:
    linear_start: 0.00085
    linear_end: 0.0120
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: "jpg"
    cond_stage_key: "txt"
    image_size: 64
    channels: 4
    cond_stage_trainable: false # Note: different from the one we trained before
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False
    cond_stage_config:
      target: ldmlib.modules.encoders.modules.FrozenCLIPEmbedder
      params:
        device: cpu