| { | |
| "_class_name": "CausalChunkDiTModel", | |
| "_diffusers_version": "0.37.1", | |
| "action_dim": 3, | |
| "action_temporal_scale": 1.0, | |
| "chunk_overlap_frames": 0, | |
| "cross_attn_norm": true, | |
| "cross_attn_type": "cross_attn", | |
| "dim": 3072, | |
| "eps": 1e-06, | |
| "ffn_dim": 14336, | |
| "freq_dim": 256, | |
| "hidden_size": 3072, | |
| "in_channels": 48, | |
| "in_dim": 48, | |
| "max_attn_chunks": 4, | |
| "model_type": "ti2v", | |
| "num_heads": 24, | |
| "num_layers": 30, | |
| "num_special_tokens": 8, | |
| "out_dim": 48, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "qk_norm": true, | |
| "special_memory_recent_chunks": 2, | |
| "text_dim": 4096, | |
| "text_len": 512, | |
| "traj_head_hidden_dim": 768, | |
| "traj_head_type": "deep", | |
| "use_continuous_history": true, | |
| "use_special_memory": false, | |
| "window_size": [ | |
| -1, | |
| -1 | |
| ] | |
| } | |