model:
  vq_model:
    codebook_size: 4096
    token_size: 12
    use_l2_norm: true
    commitment_cost: 0.25
    vit_enc_model_size: large
    vit_enc_patch_size: 16
    num_latent_tokens: 32
    quantize_mode: vq
    is_legacy: true
dataset:
  preprocessing:
    height_size: 256
    width_size: 256