config.json

{
  "_class_name": "LensTransformer2DModel",
  "_diffusers_version": "0.37.1",
  "attention_head_dim": 64,
  "axes_dims_rope": [
    8,
    28,
    28
  ],
  "enc_hidden_dim": 2880,
  "gate_mlp": true,
  "in_channels": 128,
  "inner_dim": 1536,
  "multi_layer_encoder_feature": true,
  "num_attention_heads": 24,
  "num_layers": 48,
  "out_channels": 32,
  "patch_size": 2,
  "rms_norm": true,
  "selected_layer_index": [
    5,
    11,
    17,
    23
  ],
  "mlx_format": true,
  "quantization": {
    "group_size": 64,
    "bits": 8,
    "keep_hi_precision": [
      "img_in",
      "txt_in",
      "proj_out",
      "time_text_embed",
      "norm_out"
    ]
  }
}