ckpt_path: null
ddpm:
  prediction_type: v_prediction
exp_name: 128-hdit_fm_scale_bf16
hdit_model:
  depths:
  - 2
  - 2
  - 12
  input_channels: 1
  input_size:
  - 128
  - 128
  - 128
  patch_size:
  - 4
  - 4
  - 4
  self_attns:
  - d_head: 64
    kernel_size: 7
    type: neighborhood
  - d_head: 64
    kernel_size: 7
    type: neighborhood
  - d_head: 64
    type: global
  type: image_transformer_v2
  widths:
  - 320
  - 640
  - 1280
keep_last_k: null
model_type: hdit
num_val_samples: 3
optimizer:
  lr: 0.0001
  warmup: 2000
patch_size: 128
process: fm
seed: 42
work_dir: work_dirs/128-hdit_fm_scale_bf16_00
z_crop: null
z_scale:
  mean: 0.04
  std: 0.09