transformer/config.json

{
  "_class_name": "EchoWMTransformer3DModel",
  "_diffusers_version": "0.41.0.dev0",
  "_name_or_path": "/tmp/tiny-echo-wm-base-diffusers",
  "activation_fn": "gelu-approximate",
  "attention_bias": true,
  "attention_head_dim": 8,
  "attention_out_bias": true,
  "audio_attention_head_dim": 4,
  "audio_cross_attention_dim": 8,
  "audio_cross_attn_mod": false,
  "audio_ff_bias": true,
  "audio_gated_attn": false,
  "audio_hop_length": 160,
  "audio_in_channels": 4,
  "audio_num_attention_heads": 2,
  "audio_out_channels": 4,
  "audio_patch_size": 1,
  "audio_patch_size_t": 1,
  "audio_pos_embed_max_pos": 20,
  "audio_sampling_rate": 16000,
  "audio_scale_factor": 4,
  "base_height": 2048,
  "base_width": 2048,
  "caption_channels": 32,
  "causal_offset": 1,
  "cross_attention_dim": 16,
  "cross_attn_mod": false,
  "cross_attn_timestep_scale_multiplier": 1000,
  "ff_bias": true,
  "gated_attn": false,
  "in_channels": 4,
  "norm_elementwise_affine": false,
  "norm_eps": 1e-06,
  "num_attention_heads": 2,
  "num_layers": 2,
  "out_channels": 4,
  "patch_size": 1,
  "patch_size_t": 1,
  "perturbed_attn": false,
  "pos_embed_max_pos": 20,
  "qk_norm": "rms_norm_across_heads",
  "rope_double_precision": false,
  "rope_theta": 10000.0,
  "rope_type": "split",
  "timestep_scale_multiplier": 1000,
  "ucpe_attention_dim": 16,
  "ucpe_block_indices": [
    0,
    1
  ],
  "ucpe_freq_base": 100.0,
  "ucpe_freq_scale": 1.0,
  "ucpe_image_height": 32,
  "ucpe_image_width": 32,
  "ucpe_num_attention_heads": 2,
  "ucpe_patches_x": 16,
  "ucpe_patches_y": 16,
  "use_keyframes_abs_pos_embedding": false,
  "use_prompt_adaln_single": true,
  "use_prompt_embeddings": true,
  "vae_scale_factors": [
    8,
    32,
    32
  ]
}