tokenizer/vqgan/configs/vqgan_imagenet_f16_1024.yaml

model:
  base_learning_rate: 4.5e-06
  target: taming.models.vqgan.VQModel
  params:
    embed_dim: 256
    n_embed: 1024
    ddconfig:
      double_z: false
      z_channels: 256
      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: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
      params:
        disc_conditional: false
        disc_in_channels: 3
        disc_start: 0
        disc_weight: 0.8
        codebook_weight: 1.0