model:
  base_learning_rate: 2.0e-06
  target: ldm.models.diffusion.ddpm.LatentDiffusion
  params:
    linear_start: 0.0015
    linear_end: 0.0205
    log_every_t: 100
    timesteps: 1000
    loss_type: l1
    first_stage_key: image
    cond_stage_key: coordinates_bbox
    image_size: 64
    channels: 3
    conditioning_key: crossattn
    cond_stage_trainable: true
    unet_config:
      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
      params:
        image_size: 64
        in_channels: 3
        out_channels: 3
        model_channels: 128
        attention_resolutions:
        - 8
        - 4
        - 2
        num_res_blocks: 2
        channel_mult:
        - 1
        - 2
        - 3
        - 4
        num_head_channels: 32
        use_spatial_transformer: true
        transformer_depth: 3
        context_dim: 512
    first_stage_config:
      target: ldm.models.autoencoder.VQModelInterface
      params:
        embed_dim: 3
        n_embed: 8192
        monitor: val/rec_loss
        ddconfig:
          double_z: false
          z_channels: 3
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult:
          - 1
          - 2
          - 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: 512
        n_layer: 16
        vocab_size: 8192
        max_seq_len: 92
        use_tokenizer: false
    monitor: val/loss_simple_ema
data:
  target: main.DataModuleFromConfig
  params:
    batch_size: 24
    wrap: false
    num_workers: 10
    train:
      target: ldm.data.openimages.OpenImagesBBoxTrain
      params:
        size: 256
    validation:
      target: ldm.data.openimages.OpenImagesBBoxValidation
      params:
        size: 256