model:
  base_learning_rate: 1.0e-4
  params:
    parameterization: "v"
    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
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False # we set this to false because this is an inference only config

    unet_config:
      use_checkpoint: True
      use_fp16: True
      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_head_channels: 64 # need to fix for flash-attn
      use_spatial_transformer: True
      use_linear_in_transformer: True
      transformer_depth: 1
      context_dim: 1024
      legacy: False

    first_stage_config:
      embed_dim: 4
      monitor: val/rec_loss
      ddconfig:
        #attn_type: "vanilla-xformers"
        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

    cond_stage_config:
      freeze: True
      layer: "penultimate"