{
 "transformer": {
  "resolution": 512,
  "patch_size": 2,
  "mlp_ratio": 4,
  "use_qknorm": true,
  "use_swiglu": true,
  "use_rope": true,
  "use_rmsnorm": true,
  "wo_shift": false,
  "dim": 1536,
  "depth": 36,
  "num_heads": 24,
  "ae_type": "qwen",
  "ae_path": "preset/ckpts/Qwen-Image-vae-2d",
  "time_dist": [
   "lognorm",
   0,
   1.0
  ],
  "cfg_ratio": 0.1,
  "cfg_scale": 1.5,
  "dinov2_size": 448,
  "enc_type": "dinov2l",
  "enc_dim": 1024,
  "layer_dinov2b_list": [
   17
  ],
  "interp_type": "lin",
  "encdim_ratio": 3,
  "weak_cond_strength_aelq_list": [
   0,
   0
  ],
  "cond_strength_aelq_list": [
   5,
   1
  ],
  "t_start": 0,
  "t_end": 1,
  "auxiliary_time_cond": false,
  "distill_type": "onestep"
 },
 "vae": {
  "_class_name": "AutoencoderKLQwenImage2D",
  "_diffusers_version": "0.35.0",
  "attn_scales": [],
  "base_dim": 96,
  "dim_mult": [
   1,
   2,
   4,
   4
  ],
  "dropout": 0.0,
  "latents_mean": [
   -0.7571,
   -0.7089,
   -0.9113,
   0.1075,
   -0.1745,
   0.9653,
   -0.1517,
   1.5508,
   0.4134,
   -0.0715,
   0.5517,
   -0.3632,
   -0.1922,
   -0.9497,
   0.2503,
   -0.2921
  ],
  "latents_std": [
   2.8184,
   1.4541,
   2.3275,
   2.6558,
   1.2196,
   1.7708,
   2.6052,
   2.0743,
   3.2687,
   2.1526,
   2.8652,
   1.5579,
   1.6382,
   1.1253,
   2.8251,
   1.916
  ],
  "non_linearity": "silu",
  "num_res_blocks": 2,
  "temperal_downsample": [
   false,
   true,
   true
  ],
  "z_dim": 16
 },
 "dinov2": {
  "arch": "vit_large",
  "patch_size": 14,
  "embed_dim": 1024,
  "depth_kept": 18,
  "num_heads": 16,
  "mlp_ratio": 4,
  "layerscale": true,
  "qkv_bias": true,
  "ln_eps": 1e-06,
  "input_size": 448,
  "feature_layer": 17,
  "pos_embed": "interpolated to 448\u00b2 (offset 0.1, bicubic)"
 },
 "key_contract": "conv (O,kh,kw,I); Sequential children \u2192 layers.N; VAE gamma (C); DINOv2 blocks 0..17 only"
}