| exclude_from_checkpoint: false | |
| trainable: true | |
| model_type: VideoKontextLDM | |
| ldm: | |
| exclude_from_checkpoint: false | |
| trainable: true | |
| dit: | |
| model_type: mmmssflux | |
| max_description_length: 77 | |
| max_seq_len: 501 | |
| rope_len_multiplier: 2 | |
| dim: 1024 | |
| inter_dim: 4096 | |
| fixed_timestep_features: false | |
| timestep_features_dim: 256 | |
| n_layers: 12 | |
| n_heads: 8 | |
| n_multimodal_layers: 6 | |
| qk_nope_head_dim: 16 | |
| qk_rope_head_dim: 112 | |
| qkv_head_dim: 128 | |
| n_memory_tokens_rope: 1 | |
| n_memory_tokens_description: 0 | |
| original_seq_len: 501 | |
| rope_theta: 10000.0 | |
| rope_factor: 40.0 | |
| beta_fast: 32 | |
| beta_slow: 1 | |
| io_channels: 128 | |
| cond_token_dim: 1024 | |
| adaln_last_layer: true | |
| adaln_last_layer_nomod: false | |
| non_checkpoint_layers: 14 | |
| mask_out_before: -1 | |
| estimate_logvar: true | |
| no_description_mask: true | |
| symmetric_attention_init: false | |
| patch_size: 1 | |
| num_sinks: 0 | |
| mlp_act: gelu | |
| conditioners: | |
| text: | |
| exclude_from_checkpoint: true | |
| trainable: false | |
| path: checkpoints/TextConditionerV | |
| autoencoder: | |
| exclude_from_checkpoint: true | |
| trainable: false | |
| path: checkpoints/Woosh-AE | |
| sigma_data: 1.0 | |
| pred_type: v_pred | |
| audio_fps: 100 | |
| video_fps: 24 | |
| embed_dim: 768 | |
| embed_key: synch_out | |
| pts_seconds_key: synch_pts_seconds | |
| non_checkpoint_layers: 14 | |
| n_layers_encoder: 0 | |
| trainable_no_cond: false | |
| use_batch_mask: true | |