config.json

{
  "model_type": "anima_style_embedding",
  "version": "1.0",
  "architecture": {
    "width": 512,
    "blocks": 4,
    "heads": 8,
    "embedding_dim": 512,
    "dropout": 0.1,
    "reference_grounding": true,
    "functional_factors": true,
    "reference_count": [
      1,
      8
    ],
    "trainable_parameters": 17488353
  },
  "inputs": {
    "siglip2_full": {
      "shape": [
        30,
        1152
      ],
      "dtype": "bfloat16"
    },
    "siglip2_face": {
      "shape": [
        30,
        1152
      ],
      "dtype": "bfloat16",
      "optional": true
    },
    "anima": {
      "shape": [
        3,
        4096
      ],
      "dtype": "bfloat16"
    }
  },
  "vision_backbone": {
    "repo_id": "timm/vit_so400m_patch16_siglip_gap_512.v2_webli",
    "image_size": 512,
    "layer_fractions": [
      0.25,
      0.55,
      1.0
    ],
    "pool_sizes": [
      2,
      4,
      2
    ]
  },
  "anima_features": {
    "image_size": 768,
    "blocks": [
      8,
      18,
      26
    ],
    "sigma": 0.1,
    "noise_seed": 20260715
  },
  "training": {
    "checkpoint_step": 4500,
    "face_dropout": 0.3,
    "query_count": 2,
    "optimizer": "AdamW(fused)",
    "scheduler": "cosine_with_linear_warmup",
    "learning_rate": 0.0001,
    "packed_manifest_sha256": "c1267b9fd45c6e0d222b91d6ae2291b36b763277cc39cbc32484874ffeae9b32"
  }
}