model:
  base_learning_rate: 1.0e-04
  target: ldm.models.diffusion.ddpm.LatentDiffusion
  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: 32
    channels: 4
    cond_stage_trainable: true
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215

    scheduler_config: # 10000 warmup steps
      target: ldm.lr_scheduler.LambdaLinearScheduler
      params:
        warm_up_steps: [ 10000 ]
        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
        f_start: [ 1.e-6 ]
        f_max: [ 1. ]
        f_min: [ 1. ]

    unet_config:
      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
      params:
        image_size: 32
        in_channels: 4
        out_channels: 4
        model_channels: 32 # 320   # TODO increase
        attention_resolutions: [ ]  # is equal to fixed spatial resolution: 32 , 16 , 8
        num_res_blocks: 2
        channel_mult: [ 1, ]
        #num_head_channels: 32
        num_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 32
        use_checkpoint: False

    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        monitor: val/rec_loss
        ckpt_path: "models/first_stage_models/kl-f8/model.ckpt"
        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

    cond_stage_config:
      target: ldm.modules.encoders.modules.BERTEmbedder
      params:
        n_embed: 32
        n_layer: 1 #32 # TODO: increase


data:
  target: main.DataModuleFromConfig
  params:
    batch_size: 4
    num_workers: 4
    wrap: false
    train:
      target: ldm.data.dummy.DummyData
      params:
        length: 20000
        size: [256, 256, 3]
    validation:
      target: ldm.data.dummy.DummyData
      params:
        length: 10000
        size: [256, 256, 3]


lightning:
  callbacks:
    image_logger:
      target: main.ImageLogger
      params:
        batch_frequency: 500 # 5000
        max_images: 8
        increase_log_steps: False
        log_first_step: False


  trainer:
    #replace_sampler_ddp: False
    benchmark: True
    val_check_interval: 1000  # every 20k training steps
    num_sanity_val_steps: 0