configs/retrieval-augmented-diffusion/768x768.yaml

model:
  base_learning_rate: 0.0001
  target: ldm.models.diffusion.ddpm.LatentDiffusion
  params:
    linear_start: 0.0015
    linear_end: 0.015
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: jpg
    cond_stage_key: nix
    image_size: 48
    channels: 16
    cond_stage_trainable: false
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_by_std: false
    scale_factor: 0.22765929
    unet_config:
      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
      params:
        image_size: 48
        in_channels: 16
        out_channels: 16
        model_channels: 448
        attention_resolutions:
        - 4
        - 2
        - 1
        num_res_blocks: 2
        channel_mult:
        - 1
        - 2
        - 3
        - 4
        use_scale_shift_norm: false
        resblock_updown: false
        num_head_channels: 32
        use_spatial_transformer: true
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: true
    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        monitor: val/rec_loss
        embed_dim: 16
        ddconfig:
          double_z: true
          z_channels: 16
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult:
          - 1
          - 1
          - 2
          - 2
          - 4
          num_res_blocks: 2
          attn_resolutions:
          - 16
          dropout: 0.0
        lossconfig:
          target: torch.nn.Identity
    cond_stage_config:
      target: torch.nn.Identity