File size: 1,582 Bytes
7253725 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | {
"_class_name": "CogVideoXTransformer3DMOTModel",
"_diffusers_version": "0.34.0.dev0",
"_name_or_path": "/mnt/bn/cx-space-hl03/yuxuan/reference_video_gen_outputs/train_multi_node_v5_alignment>10/model_weights/010000/transformer",
"ablation_residual_addition": false,
"ablation_single_encoder": false,
"activation_fn": "gelu-approximate",
"attention_bias": true,
"attention_head_dim": 64,
"attention_head_dim_mot_ref": null,
"block_idx_with_mot_ref": [
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
24,
25,
26,
27,
28,
29,
30,
31,
32,
33,
34,
35,
36,
37,
38,
39,
40
],
"dropout": 0.0,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 32,
"max_text_seq_length": 226,
"norm_elementwise_affine": true,
"norm_eps": 1e-05,
"num_attention_heads": 48,
"num_layers": 42,
"num_ref_embeddings": null,
"ofs_embed_dim": null,
"out_channels": 16,
"patch_bias": true,
"patch_size": 2,
"patch_size_t": null,
"reference_train_mode": null,
"sample_frames": 49,
"sample_height": 60,
"sample_width": 90,
"spatial_interpolation_scale": 1.875,
"supported_effect_types": null,
"temporal_compression_ratio": 4,
"temporal_interpolation_scale": 1.0,
"text_embed_dim": 4096,
"time_embed_dim": 512,
"timestep_activation_fn": "silu",
"use_learned_positional_embeddings": true,
"use_rotary_positional_embeddings": true
}
|