transformer/config.json

{
  "_class_name": "HiImageTransformer2DModel",
  "_diffusers_version": "0.32.1",
  "attention_head_dim": 128,
  "axes_dims_rope": [
    64,
    32,
    32
  ],
  "caption_channels": [
    4096,
    4096
  ],
  "max_resolution": [
    128,
    128
  ],
  "in_channels": 16,
  "llama_layers": [
    0,
    1,
    2,
    3,
    4,
    5,
    6,
    7,
    8,
    9,
    10,
    11,
    12,
    13,
    14,
    15,
    16,
    17,
    18,
    19,
    20,
    21,
    22,
    23,
    24,
    25,
    26,
    27,
    28,
    29,
    30,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31,
    31
  ],
  "num_attention_heads": 20,
  "num_routed_experts": 4,
  "num_activated_experts": 2,
  "num_layers": 16,
  "num_single_layers": 32,
  "out_channels": 16,
  "patch_size": 2,
  "text_emb_dim": 2048
}