| format: civitai |
| pipeline: Wan |
| transformer_additional_kwargs: |
| transformer_low_noise_model_subpath: ./low_noise_model |
| transformer_high_noise_model_subpath: ./high_noise_model |
| transformer_combination_type: "moe" |
| boundary: 0.875 |
| dict_mapping: |
| in_dim: in_channels |
| dim: hidden_size |
|
|
| vae_kwargs: |
| vae_type: "AutoencoderKLWan" |
| vae_subpath: Wan2.1_VAE.pth |
| temporal_compression_ratio: 4 |
| spatial_compression_ratio: 8 |
|
|
| text_encoder_kwargs: |
| text_encoder_subpath: models_t5_umt5-xxl-enc-bf16.pth |
| tokenizer_subpath: google/umt5-xxl |
| text_length: 512 |
| vocab: 256384 |
| dim: 4096 |
| dim_attn: 4096 |
| dim_ffn: 10240 |
| num_heads: 64 |
| num_layers: 24 |
| num_buckets: 32 |
| shared_pos: False |
| dropout: 0.0 |
|
|
| scheduler_kwargs: |
| scheduler_subpath: null |
| num_train_timesteps: 1000 |
| shift: 12.0 |
| use_dynamic_shifting: false |
| base_shift: 0.5 |
| max_shift: 1.15 |
| base_image_seq_len: 256 |
| max_image_seq_len: 4096 |
|
|
| image_encoder_kwargs: |
| image_encoder_subpath: models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth |
