{
  "use_checkpoint": true,
  "use_fp16": true,
  "image_size": 64,
  "in_channels": 3,
  "out_channels": 3,
  "model_channels": 192,
  "attention_resolutions": [
    8,
    4,
    2
  ],
  "num_res_blocks": 2,
  "channel_mult": [
    1,
    2,
    3,
    5
  ],
  "num_heads": 1,
  "use_spatial_transformer": true,
  "transformer_depth": 1,
  "context_dim": 512
}