Ref2VA/transformer/config.json

{
  "_class_name": "MiniMaxH3DiTModel",
  "_diffusers_version": "0.32.2",
  "hidden_size": 5376,
  "num_layers": 50,
  "token_refiner_num_layers": 2,
  "num_attention_heads": 56,
  "attention_head_dim": 128,
  "ffn_hidden_size": 14336,
  "latents_dim": 24,
  "audio_latents_dim": 32,
  "patch_size": [
    1,
    2,
    2
  ],
  "text_dim": 5120,
  "timestep_input_dim": 256,
  "time_embed_hidden_size": 5376,
  "time_embed_dim": 2688,
  "adaln_out_features": 96768,
  "final_adaln_out_features": 10752,
  "rope_inv_freq_len": 16,
  "norm_eps": 1e-05,
  "qk_norm_eps": 1e-05,
  "final_norm_eps": 1e-05
}