| { | |
| "_class_name": "WanT2TexTransformer3DModel", | |
| "_diffusers_version": "0.33.1", | |
| "_name_or_path": "/mnt/pfs/share/pretrained_model/.cache/huggingface/hub/models--Wan-AI--Wan2.1-T2V-1.3B-Diffusers/snapshots/0fad780a534b6463e45facd96134c9f345acfa5b/transformer", | |
| "added_kv_proj_dim": null, | |
| "attention_head_dim": 128, | |
| "cross_attn_norm": true, | |
| "eps": 1e-06, | |
| "ffn_dim": 8960, | |
| "freq_dim": 256, | |
| "image_dim": null, | |
| "in_channels": 16, | |
| "num_attention_heads": 12, | |
| "num_layers": 30, | |
| "out_channels": 16, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "qk_norm": "rms_norm_across_heads", | |
| "rope_max_seq_len": 1024, | |
| "text_dim": 4096 | |
| } | |