transformer/config.json

{
  "_class_name": "QwenImage21FusionTransformer2DModel",
  "_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,
  "text_fusion_config": {
    "in_dim": 6144,
    "out_dim": 4096,
    "hidden": 6144,
    "proj_layers": 3,
    "norm": "ln-per-layer",
    "n_slices": 6,
    "attention": 2,
    "attn_dim": 1024,
    "attn_heads": 8,
    "max_len": 512,
    "mixer": 2,
    "mixer_heads": 8,
    "mixer_ffn": 2,
    "student_layers": [
      4,
      8,
      12,
      16,
      20,
      24
    ],
    "drop_idx": 14
  }
}