config_xl.yaml

model_config:
  model_name: HunyuanVideo-Foley-XL
  model_type: 1d
  model_precision: bf16
  model_kwargs:
    depth_triple_blocks: 12
    depth_single_blocks: 24
    hidden_size: 1408
    num_heads: 11
    mlp_ratio: 4
    mlp_act_type: "gelu_tanh"
    qkv_bias: True
    qk_norm: True
    qk_norm_type: "rms"
    attn_mode: "torch"
    embedder_type: "default"
    interleaved_audio_visual_rope: True
    enable_learnable_empty_visual_feat: True
    sync_modulation: False
    add_sync_feat_to_audio: True
    cross_attention: True
    use_attention_mask: False
    condition_projection: "linear"
    sync_feat_dim: 768 # syncformer 768 dim
    condition_dim: 768  # clap 768 text condition dim (clip-text)
    clip_dim: 768  # siglip2 visual dim
    audio_vae_latent_dim: 128 
    audio_frame_rate: 50
    patch_size: 1
    rope_dim_list: null
    rope_theta: 10000
    text_length: 77
    clip_length: 64 
    sync_length: 192
    depth_triple_ssl_encoder: null
    depth_single_ssl_encoder: 8
    use_repa_with_audiossl: True

diffusion_config:
  denoise_type: "flow"
  flow_path_type: "linear"
  flow_predict_type: "velocity"
  flow_reverse: True
  flow_solver: "euler"
  sample_flow_shift: 1.0
  sample_use_flux_shift: False
  flux_base_shift: 0.5
  flux_max_shift: 1.15