{
  "in_channels": 3,
  "patch_size": 16,
  "model_dim": 896,
  "encoder_depth": 4,
  "decoder_depth": 8,
  "bottleneck_dim": 128,
  "mlp_ratio": 4.0,
  "depthwise_kernel_size": 7,
  "adaln_low_rank_rank": 128,
  "logsnr_min": -10.0,
  "logsnr_max": 10.0,
  "pixel_noise_std": 0.558
}