transformer/config.json

{
  "_class_name": "QwenImage21Transformer2DModel",
  "_diffusers_version": "0.37.0.dev0",
  "attention_head_dim": 128,
  "axes_dims_rope": [
    16,
    56,
    56
  ],
  "context_in_dim": 4096,
  "in_channels": 64,
  "num_attention_heads": 32,
  "num_layers": 32,
  "out_channels": 64,
  "patch_size": 1,
  "mlp_ratio": 3,
  "eps": 1e-06,
  "causal_condition": true,
  "quantization": {
    "bits": 8,
    "group_size": 64,
    "mode": "affine"
  },
  "mlx_format": true,
  "_modification_notice": "Modified by ixim / iximbox for Image21-MLX: converted from the pinned BF16 source to MLX layout; eligible linear weights use groupwise affine quantization. See conversion.json for precision and exceptions. Built with Qwen."
}