Hugging Face's logo

sand-ai
/
MAGI-1

Image-to-Video
Diffusers
Safetensors
English
MAGI-1
Model card Files Community
20
xiguan97 commited on
Commit
7a12971
·
verified ·
1 Parent(s): 3e6cbc8

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. ckpt/magi/4.5B_base/inference_weight/model-00001-of-00003.safetensors +3 -0
  2. ckpt/magi/4.5B_base/inference_weight/model-00002-of-00003.safetensors +3 -0
  3. ckpt/magi/4.5B_base/inference_weight/model-00003-of-00003.safetensors +3 -0
  4. ckpt/magi/4.5B_base/inference_weight/model.safetensors.index.json +905 -0
ckpt/magi/4.5B_base/inference_weight/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8decc4bd82daf9c61586acf432a205107be65cfa5e8d47eb158ab83f693ce4b
3
+ size 2647706200
ckpt/magi/4.5B_base/inference_weight/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3cadb037a0ce8b0a99a8f35c50c9abe21479c29d26c80ba3646ee45ef38a0a4
3
+ size 4708294960
ckpt/magi/4.5B_base/inference_weight/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8489d5fc2ada87b8b23439c5132fffcbb0e8966ca19aaa49f3b319a92c832a
3
+ size 1605174136
ckpt/magi/4.5B_base/inference_weight/model.safetensors.index.json ADDED
@@ -0,0 +1,905 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8961059904
4
+ },
5
+ "weight_map": {
6
+ "final_linear.linear.weight": "model-00001-of-00003.safetensors",
7
+ "rope.bands": "model-00001-of-00003.safetensors",
8
+ "t_embedder.mlp.0.bias": "model-00001-of-00003.safetensors",
9
+ "t_embedder.mlp.0.weight": "model-00001-of-00003.safetensors",
10
+ "t_embedder.mlp.2.bias": "model-00001-of-00003.safetensors",
11
+ "t_embedder.mlp.2.weight": "model-00001-of-00003.safetensors",
12
+ "videodit_blocks.final_layernorm.bias": "model-00001-of-00003.safetensors",
13
+ "videodit_blocks.final_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "videodit_blocks.layers.0.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
15
+ "videodit_blocks.layers.0.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
16
+ "videodit_blocks.layers.0.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
17
+ "videodit_blocks.layers.0.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
18
+ "videodit_blocks.layers.0.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
19
+ "videodit_blocks.layers.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
20
+ "videodit_blocks.layers.0.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
21
+ "videodit_blocks.layers.0.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
22
+ "videodit_blocks.layers.0.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
23
+ "videodit_blocks.layers.0.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
24
+ "videodit_blocks.layers.0.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
25
+ "videodit_blocks.layers.0.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
26
+ "videodit_blocks.layers.0.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
27
+ "videodit_blocks.layers.0.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
28
+ "videodit_blocks.layers.0.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
29
+ "videodit_blocks.layers.0.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
30
+ "videodit_blocks.layers.0.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
31
+ "videodit_blocks.layers.0.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
32
+ "videodit_blocks.layers.0.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
33
+ "videodit_blocks.layers.0.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
34
+ "videodit_blocks.layers.0.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
35
+ "videodit_blocks.layers.0.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "videodit_blocks.layers.0.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
37
+ "videodit_blocks.layers.0.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
38
+ "videodit_blocks.layers.0.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
39
+ "videodit_blocks.layers.0.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
40
+ "videodit_blocks.layers.1.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
41
+ "videodit_blocks.layers.1.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
42
+ "videodit_blocks.layers.1.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
43
+ "videodit_blocks.layers.1.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
44
+ "videodit_blocks.layers.1.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
45
+ "videodit_blocks.layers.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
46
+ "videodit_blocks.layers.1.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
47
+ "videodit_blocks.layers.1.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
48
+ "videodit_blocks.layers.1.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
49
+ "videodit_blocks.layers.1.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
50
+ "videodit_blocks.layers.1.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
51
+ "videodit_blocks.layers.1.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
52
+ "videodit_blocks.layers.1.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
53
+ "videodit_blocks.layers.1.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
54
+ "videodit_blocks.layers.1.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
55
+ "videodit_blocks.layers.1.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
56
+ "videodit_blocks.layers.1.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
57
+ "videodit_blocks.layers.1.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
58
+ "videodit_blocks.layers.1.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
59
+ "videodit_blocks.layers.1.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
60
+ "videodit_blocks.layers.1.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
61
+ "videodit_blocks.layers.1.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "videodit_blocks.layers.1.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
63
+ "videodit_blocks.layers.1.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
64
+ "videodit_blocks.layers.1.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
65
+ "videodit_blocks.layers.1.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
66
+ "videodit_blocks.layers.10.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
67
+ "videodit_blocks.layers.10.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
68
+ "videodit_blocks.layers.10.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
69
+ "videodit_blocks.layers.10.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
70
+ "videodit_blocks.layers.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
71
+ "videodit_blocks.layers.10.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
72
+ "videodit_blocks.layers.10.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
73
+ "videodit_blocks.layers.10.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
74
+ "videodit_blocks.layers.10.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
75
+ "videodit_blocks.layers.10.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "videodit_blocks.layers.10.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
77
+ "videodit_blocks.layers.10.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
78
+ "videodit_blocks.layers.10.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
79
+ "videodit_blocks.layers.10.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
80
+ "videodit_blocks.layers.10.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
81
+ "videodit_blocks.layers.10.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
82
+ "videodit_blocks.layers.10.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
83
+ "videodit_blocks.layers.10.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
84
+ "videodit_blocks.layers.10.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
85
+ "videodit_blocks.layers.10.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
86
+ "videodit_blocks.layers.10.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
87
+ "videodit_blocks.layers.10.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
88
+ "videodit_blocks.layers.10.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
89
+ "videodit_blocks.layers.10.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
90
+ "videodit_blocks.layers.10.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
91
+ "videodit_blocks.layers.10.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
92
+ "videodit_blocks.layers.11.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
93
+ "videodit_blocks.layers.11.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
94
+ "videodit_blocks.layers.11.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
95
+ "videodit_blocks.layers.11.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
96
+ "videodit_blocks.layers.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
97
+ "videodit_blocks.layers.11.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
98
+ "videodit_blocks.layers.11.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
99
+ "videodit_blocks.layers.11.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
100
+ "videodit_blocks.layers.11.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
101
+ "videodit_blocks.layers.11.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "videodit_blocks.layers.11.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
103
+ "videodit_blocks.layers.11.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
104
+ "videodit_blocks.layers.11.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
105
+ "videodit_blocks.layers.11.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
106
+ "videodit_blocks.layers.11.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
107
+ "videodit_blocks.layers.11.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
108
+ "videodit_blocks.layers.11.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
109
+ "videodit_blocks.layers.11.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
110
+ "videodit_blocks.layers.11.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
111
+ "videodit_blocks.layers.11.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
112
+ "videodit_blocks.layers.11.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
113
+ "videodit_blocks.layers.11.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
114
+ "videodit_blocks.layers.11.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
115
+ "videodit_blocks.layers.11.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
116
+ "videodit_blocks.layers.11.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
117
+ "videodit_blocks.layers.11.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
118
+ "videodit_blocks.layers.12.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
119
+ "videodit_blocks.layers.12.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
120
+ "videodit_blocks.layers.12.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
121
+ "videodit_blocks.layers.12.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
122
+ "videodit_blocks.layers.12.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
123
+ "videodit_blocks.layers.12.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
124
+ "videodit_blocks.layers.12.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
125
+ "videodit_blocks.layers.12.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
126
+ "videodit_blocks.layers.12.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
127
+ "videodit_blocks.layers.12.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
128
+ "videodit_blocks.layers.12.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
129
+ "videodit_blocks.layers.12.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
130
+ "videodit_blocks.layers.12.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
131
+ "videodit_blocks.layers.12.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
132
+ "videodit_blocks.layers.12.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
133
+ "videodit_blocks.layers.12.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
134
+ "videodit_blocks.layers.12.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
135
+ "videodit_blocks.layers.12.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
136
+ "videodit_blocks.layers.12.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
137
+ "videodit_blocks.layers.12.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
138
+ "videodit_blocks.layers.12.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
139
+ "videodit_blocks.layers.12.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
140
+ "videodit_blocks.layers.12.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
141
+ "videodit_blocks.layers.12.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
142
+ "videodit_blocks.layers.12.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
143
+ "videodit_blocks.layers.12.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
144
+ "videodit_blocks.layers.13.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
145
+ "videodit_blocks.layers.13.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
146
+ "videodit_blocks.layers.13.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
147
+ "videodit_blocks.layers.13.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
148
+ "videodit_blocks.layers.13.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
149
+ "videodit_blocks.layers.13.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
150
+ "videodit_blocks.layers.13.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
151
+ "videodit_blocks.layers.13.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
152
+ "videodit_blocks.layers.13.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
153
+ "videodit_blocks.layers.13.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
154
+ "videodit_blocks.layers.13.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
155
+ "videodit_blocks.layers.13.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
156
+ "videodit_blocks.layers.13.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
157
+ "videodit_blocks.layers.13.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
158
+ "videodit_blocks.layers.13.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
159
+ "videodit_blocks.layers.13.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
160
+ "videodit_blocks.layers.13.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
161
+ "videodit_blocks.layers.13.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
162
+ "videodit_blocks.layers.13.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
163
+ "videodit_blocks.layers.13.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
164
+ "videodit_blocks.layers.13.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
165
+ "videodit_blocks.layers.13.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "videodit_blocks.layers.13.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
167
+ "videodit_blocks.layers.13.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
168
+ "videodit_blocks.layers.13.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
169
+ "videodit_blocks.layers.13.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
170
+ "videodit_blocks.layers.14.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
171
+ "videodit_blocks.layers.14.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
172
+ "videodit_blocks.layers.14.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
173
+ "videodit_blocks.layers.14.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
174
+ "videodit_blocks.layers.14.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
175
+ "videodit_blocks.layers.14.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
176
+ "videodit_blocks.layers.14.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
177
+ "videodit_blocks.layers.14.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
178
+ "videodit_blocks.layers.14.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
179
+ "videodit_blocks.layers.14.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "videodit_blocks.layers.14.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
181
+ "videodit_blocks.layers.14.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
182
+ "videodit_blocks.layers.14.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
183
+ "videodit_blocks.layers.14.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
184
+ "videodit_blocks.layers.14.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
185
+ "videodit_blocks.layers.14.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
186
+ "videodit_blocks.layers.14.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
187
+ "videodit_blocks.layers.14.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
188
+ "videodit_blocks.layers.14.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
189
+ "videodit_blocks.layers.14.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
190
+ "videodit_blocks.layers.14.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
191
+ "videodit_blocks.layers.14.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
192
+ "videodit_blocks.layers.14.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
193
+ "videodit_blocks.layers.14.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
194
+ "videodit_blocks.layers.14.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
195
+ "videodit_blocks.layers.14.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
196
+ "videodit_blocks.layers.15.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
197
+ "videodit_blocks.layers.15.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
198
+ "videodit_blocks.layers.15.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
199
+ "videodit_blocks.layers.15.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
200
+ "videodit_blocks.layers.15.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
201
+ "videodit_blocks.layers.15.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
202
+ "videodit_blocks.layers.15.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
203
+ "videodit_blocks.layers.15.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
204
+ "videodit_blocks.layers.15.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
205
+ "videodit_blocks.layers.15.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
206
+ "videodit_blocks.layers.15.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
207
+ "videodit_blocks.layers.15.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
208
+ "videodit_blocks.layers.15.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
209
+ "videodit_blocks.layers.15.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
210
+ "videodit_blocks.layers.15.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
211
+ "videodit_blocks.layers.15.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
212
+ "videodit_blocks.layers.15.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
213
+ "videodit_blocks.layers.15.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
214
+ "videodit_blocks.layers.15.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
215
+ "videodit_blocks.layers.15.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
216
+ "videodit_blocks.layers.15.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
217
+ "videodit_blocks.layers.15.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
218
+ "videodit_blocks.layers.15.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
219
+ "videodit_blocks.layers.15.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
220
+ "videodit_blocks.layers.15.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
221
+ "videodit_blocks.layers.15.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
222
+ "videodit_blocks.layers.16.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
223
+ "videodit_blocks.layers.16.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
224
+ "videodit_blocks.layers.16.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
225
+ "videodit_blocks.layers.16.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
226
+ "videodit_blocks.layers.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
227
+ "videodit_blocks.layers.16.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
228
+ "videodit_blocks.layers.16.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
229
+ "videodit_blocks.layers.16.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
230
+ "videodit_blocks.layers.16.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
231
+ "videodit_blocks.layers.16.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
232
+ "videodit_blocks.layers.16.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
233
+ "videodit_blocks.layers.16.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
234
+ "videodit_blocks.layers.16.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
235
+ "videodit_blocks.layers.16.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
236
+ "videodit_blocks.layers.16.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
237
+ "videodit_blocks.layers.16.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
238
+ "videodit_blocks.layers.16.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
239
+ "videodit_blocks.layers.16.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
240
+ "videodit_blocks.layers.16.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
241
+ "videodit_blocks.layers.16.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
242
+ "videodit_blocks.layers.16.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
243
+ "videodit_blocks.layers.16.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
244
+ "videodit_blocks.layers.16.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
245
+ "videodit_blocks.layers.16.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
246
+ "videodit_blocks.layers.16.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
247
+ "videodit_blocks.layers.16.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
248
+ "videodit_blocks.layers.17.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
249
+ "videodit_blocks.layers.17.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
250
+ "videodit_blocks.layers.17.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
251
+ "videodit_blocks.layers.17.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
252
+ "videodit_blocks.layers.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
253
+ "videodit_blocks.layers.17.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
254
+ "videodit_blocks.layers.17.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
255
+ "videodit_blocks.layers.17.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
256
+ "videodit_blocks.layers.17.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
257
+ "videodit_blocks.layers.17.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
258
+ "videodit_blocks.layers.17.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
259
+ "videodit_blocks.layers.17.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
260
+ "videodit_blocks.layers.17.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
261
+ "videodit_blocks.layers.17.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
262
+ "videodit_blocks.layers.17.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
263
+ "videodit_blocks.layers.17.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
264
+ "videodit_blocks.layers.17.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
265
+ "videodit_blocks.layers.17.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
266
+ "videodit_blocks.layers.17.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
267
+ "videodit_blocks.layers.17.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
268
+ "videodit_blocks.layers.17.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
269
+ "videodit_blocks.layers.17.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
270
+ "videodit_blocks.layers.17.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
271
+ "videodit_blocks.layers.17.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
272
+ "videodit_blocks.layers.17.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
273
+ "videodit_blocks.layers.17.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
274
+ "videodit_blocks.layers.18.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
275
+ "videodit_blocks.layers.18.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
276
+ "videodit_blocks.layers.18.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
277
+ "videodit_blocks.layers.18.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
278
+ "videodit_blocks.layers.18.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
279
+ "videodit_blocks.layers.18.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
280
+ "videodit_blocks.layers.18.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
281
+ "videodit_blocks.layers.18.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
282
+ "videodit_blocks.layers.18.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
283
+ "videodit_blocks.layers.18.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
284
+ "videodit_blocks.layers.18.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
285
+ "videodit_blocks.layers.18.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
286
+ "videodit_blocks.layers.18.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
287
+ "videodit_blocks.layers.18.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
288
+ "videodit_blocks.layers.18.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
289
+ "videodit_blocks.layers.18.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
290
+ "videodit_blocks.layers.18.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
291
+ "videodit_blocks.layers.18.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
292
+ "videodit_blocks.layers.18.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
293
+ "videodit_blocks.layers.18.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
294
+ "videodit_blocks.layers.18.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
295
+ "videodit_blocks.layers.18.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
296
+ "videodit_blocks.layers.18.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
297
+ "videodit_blocks.layers.18.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
298
+ "videodit_blocks.layers.18.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
299
+ "videodit_blocks.layers.18.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
300
+ "videodit_blocks.layers.19.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
301
+ "videodit_blocks.layers.19.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
302
+ "videodit_blocks.layers.19.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
303
+ "videodit_blocks.layers.19.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
304
+ "videodit_blocks.layers.19.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
305
+ "videodit_blocks.layers.19.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
306
+ "videodit_blocks.layers.19.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
307
+ "videodit_blocks.layers.19.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
308
+ "videodit_blocks.layers.19.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
309
+ "videodit_blocks.layers.19.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
310
+ "videodit_blocks.layers.19.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
311
+ "videodit_blocks.layers.19.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
312
+ "videodit_blocks.layers.19.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
313
+ "videodit_blocks.layers.19.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
314
+ "videodit_blocks.layers.19.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
315
+ "videodit_blocks.layers.19.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
316
+ "videodit_blocks.layers.19.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
317
+ "videodit_blocks.layers.19.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
318
+ "videodit_blocks.layers.19.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
319
+ "videodit_blocks.layers.19.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
320
+ "videodit_blocks.layers.19.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
321
+ "videodit_blocks.layers.19.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
322
+ "videodit_blocks.layers.19.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
323
+ "videodit_blocks.layers.19.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
324
+ "videodit_blocks.layers.19.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
325
+ "videodit_blocks.layers.19.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
326
+ "videodit_blocks.layers.2.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
327
+ "videodit_blocks.layers.2.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
328
+ "videodit_blocks.layers.2.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
329
+ "videodit_blocks.layers.2.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
330
+ "videodit_blocks.layers.2.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
331
+ "videodit_blocks.layers.2.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
332
+ "videodit_blocks.layers.2.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
333
+ "videodit_blocks.layers.2.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
334
+ "videodit_blocks.layers.2.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
335
+ "videodit_blocks.layers.2.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
336
+ "videodit_blocks.layers.2.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
337
+ "videodit_blocks.layers.2.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
338
+ "videodit_blocks.layers.2.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
339
+ "videodit_blocks.layers.2.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
340
+ "videodit_blocks.layers.2.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
341
+ "videodit_blocks.layers.2.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
342
+ "videodit_blocks.layers.2.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
343
+ "videodit_blocks.layers.2.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
344
+ "videodit_blocks.layers.2.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
345
+ "videodit_blocks.layers.2.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
346
+ "videodit_blocks.layers.2.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
347
+ "videodit_blocks.layers.2.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
348
+ "videodit_blocks.layers.2.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
349
+ "videodit_blocks.layers.2.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
350
+ "videodit_blocks.layers.2.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
351
+ "videodit_blocks.layers.2.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
352
+ "videodit_blocks.layers.20.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
353
+ "videodit_blocks.layers.20.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
354
+ "videodit_blocks.layers.20.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
355
+ "videodit_blocks.layers.20.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
356
+ "videodit_blocks.layers.20.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
357
+ "videodit_blocks.layers.20.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
358
+ "videodit_blocks.layers.20.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
359
+ "videodit_blocks.layers.20.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
360
+ "videodit_blocks.layers.20.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
361
+ "videodit_blocks.layers.20.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
362
+ "videodit_blocks.layers.20.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
363
+ "videodit_blocks.layers.20.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
364
+ "videodit_blocks.layers.20.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
365
+ "videodit_blocks.layers.20.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
366
+ "videodit_blocks.layers.20.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
367
+ "videodit_blocks.layers.20.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
368
+ "videodit_blocks.layers.20.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
369
+ "videodit_blocks.layers.20.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
370
+ "videodit_blocks.layers.20.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
371
+ "videodit_blocks.layers.20.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
372
+ "videodit_blocks.layers.20.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
373
+ "videodit_blocks.layers.20.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
374
+ "videodit_blocks.layers.20.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
375
+ "videodit_blocks.layers.20.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
376
+ "videodit_blocks.layers.20.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
377
+ "videodit_blocks.layers.20.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
378
+ "videodit_blocks.layers.21.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
379
+ "videodit_blocks.layers.21.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
380
+ "videodit_blocks.layers.21.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
381
+ "videodit_blocks.layers.21.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
382
+ "videodit_blocks.layers.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
383
+ "videodit_blocks.layers.21.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
384
+ "videodit_blocks.layers.21.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
385
+ "videodit_blocks.layers.21.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
386
+ "videodit_blocks.layers.21.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
387
+ "videodit_blocks.layers.21.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
388
+ "videodit_blocks.layers.21.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
389
+ "videodit_blocks.layers.21.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
390
+ "videodit_blocks.layers.21.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
391
+ "videodit_blocks.layers.21.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
392
+ "videodit_blocks.layers.21.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
393
+ "videodit_blocks.layers.21.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
394
+ "videodit_blocks.layers.21.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
395
+ "videodit_blocks.layers.21.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
396
+ "videodit_blocks.layers.21.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
397
+ "videodit_blocks.layers.21.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
398
+ "videodit_blocks.layers.21.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
399
+ "videodit_blocks.layers.21.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
400
+ "videodit_blocks.layers.21.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
401
+ "videodit_blocks.layers.21.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
402
+ "videodit_blocks.layers.21.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
403
+ "videodit_blocks.layers.21.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
404
+ "videodit_blocks.layers.22.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
405
+ "videodit_blocks.layers.22.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
406
+ "videodit_blocks.layers.22.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
407
+ "videodit_blocks.layers.22.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
408
+ "videodit_blocks.layers.22.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
409
+ "videodit_blocks.layers.22.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
410
+ "videodit_blocks.layers.22.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
411
+ "videodit_blocks.layers.22.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
412
+ "videodit_blocks.layers.22.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
413
+ "videodit_blocks.layers.22.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
414
+ "videodit_blocks.layers.22.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
415
+ "videodit_blocks.layers.22.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
416
+ "videodit_blocks.layers.22.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
417
+ "videodit_blocks.layers.22.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
418
+ "videodit_blocks.layers.22.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
419
+ "videodit_blocks.layers.22.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
420
+ "videodit_blocks.layers.22.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
421
+ "videodit_blocks.layers.22.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
422
+ "videodit_blocks.layers.22.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
423
+ "videodit_blocks.layers.22.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
424
+ "videodit_blocks.layers.22.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
425
+ "videodit_blocks.layers.22.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
426
+ "videodit_blocks.layers.22.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
427
+ "videodit_blocks.layers.22.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
428
+ "videodit_blocks.layers.22.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
429
+ "videodit_blocks.layers.22.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
430
+ "videodit_blocks.layers.23.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
431
+ "videodit_blocks.layers.23.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
432
+ "videodit_blocks.layers.23.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
433
+ "videodit_blocks.layers.23.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
434
+ "videodit_blocks.layers.23.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
435
+ "videodit_blocks.layers.23.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
436
+ "videodit_blocks.layers.23.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
437
+ "videodit_blocks.layers.23.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
438
+ "videodit_blocks.layers.23.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
439
+ "videodit_blocks.layers.23.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
440
+ "videodit_blocks.layers.23.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
441
+ "videodit_blocks.layers.23.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
442
+ "videodit_blocks.layers.23.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
443
+ "videodit_blocks.layers.23.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
444
+ "videodit_blocks.layers.23.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
445
+ "videodit_blocks.layers.23.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
446
+ "videodit_blocks.layers.23.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
447
+ "videodit_blocks.layers.23.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
448
+ "videodit_blocks.layers.23.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
449
+ "videodit_blocks.layers.23.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
450
+ "videodit_blocks.layers.23.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
451
+ "videodit_blocks.layers.23.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
452
+ "videodit_blocks.layers.23.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
453
+ "videodit_blocks.layers.23.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
454
+ "videodit_blocks.layers.23.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
455
+ "videodit_blocks.layers.23.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
456
+ "videodit_blocks.layers.24.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
457
+ "videodit_blocks.layers.24.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
458
+ "videodit_blocks.layers.24.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
459
+ "videodit_blocks.layers.24.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
460
+ "videodit_blocks.layers.24.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
461
+ "videodit_blocks.layers.24.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
462
+ "videodit_blocks.layers.24.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
463
+ "videodit_blocks.layers.24.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
464
+ "videodit_blocks.layers.24.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
465
+ "videodit_blocks.layers.24.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
466
+ "videodit_blocks.layers.24.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
467
+ "videodit_blocks.layers.24.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
468
+ "videodit_blocks.layers.24.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
469
+ "videodit_blocks.layers.24.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
470
+ "videodit_blocks.layers.24.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
471
+ "videodit_blocks.layers.24.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
472
+ "videodit_blocks.layers.24.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
473
+ "videodit_blocks.layers.24.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
474
+ "videodit_blocks.layers.24.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
475
+ "videodit_blocks.layers.24.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
476
+ "videodit_blocks.layers.24.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
477
+ "videodit_blocks.layers.24.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
478
+ "videodit_blocks.layers.24.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
479
+ "videodit_blocks.layers.24.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
480
+ "videodit_blocks.layers.24.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
481
+ "videodit_blocks.layers.24.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
482
+ "videodit_blocks.layers.25.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
483
+ "videodit_blocks.layers.25.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
484
+ "videodit_blocks.layers.25.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
485
+ "videodit_blocks.layers.25.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
486
+ "videodit_blocks.layers.25.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
487
+ "videodit_blocks.layers.25.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
488
+ "videodit_blocks.layers.25.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
489
+ "videodit_blocks.layers.25.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
490
+ "videodit_blocks.layers.25.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
491
+ "videodit_blocks.layers.25.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
492
+ "videodit_blocks.layers.25.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
493
+ "videodit_blocks.layers.25.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
494
+ "videodit_blocks.layers.25.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
495
+ "videodit_blocks.layers.25.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
496
+ "videodit_blocks.layers.25.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
497
+ "videodit_blocks.layers.25.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
498
+ "videodit_blocks.layers.25.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
499
+ "videodit_blocks.layers.25.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
500
+ "videodit_blocks.layers.25.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
501
+ "videodit_blocks.layers.25.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
502
+ "videodit_blocks.layers.25.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
503
+ "videodit_blocks.layers.25.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
504
+ "videodit_blocks.layers.25.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
505
+ "videodit_blocks.layers.25.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
506
+ "videodit_blocks.layers.25.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
507
+ "videodit_blocks.layers.25.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
508
+ "videodit_blocks.layers.26.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
509
+ "videodit_blocks.layers.26.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
510
+ "videodit_blocks.layers.26.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
511
+ "videodit_blocks.layers.26.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
512
+ "videodit_blocks.layers.26.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
513
+ "videodit_blocks.layers.26.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
514
+ "videodit_blocks.layers.26.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
515
+ "videodit_blocks.layers.26.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
516
+ "videodit_blocks.layers.26.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
517
+ "videodit_blocks.layers.26.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
518
+ "videodit_blocks.layers.26.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
519
+ "videodit_blocks.layers.26.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
520
+ "videodit_blocks.layers.26.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
521
+ "videodit_blocks.layers.26.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
522
+ "videodit_blocks.layers.26.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
523
+ "videodit_blocks.layers.26.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
524
+ "videodit_blocks.layers.26.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
525
+ "videodit_blocks.layers.26.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
526
+ "videodit_blocks.layers.26.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
527
+ "videodit_blocks.layers.26.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
528
+ "videodit_blocks.layers.26.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
529
+ "videodit_blocks.layers.26.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
530
+ "videodit_blocks.layers.26.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
531
+ "videodit_blocks.layers.26.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
532
+ "videodit_blocks.layers.26.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
533
+ "videodit_blocks.layers.26.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
534
+ "videodit_blocks.layers.27.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
535
+ "videodit_blocks.layers.27.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
536
+ "videodit_blocks.layers.27.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
537
+ "videodit_blocks.layers.27.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
538
+ "videodit_blocks.layers.27.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
539
+ "videodit_blocks.layers.27.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
540
+ "videodit_blocks.layers.27.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
541
+ "videodit_blocks.layers.27.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
542
+ "videodit_blocks.layers.27.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
543
+ "videodit_blocks.layers.27.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
544
+ "videodit_blocks.layers.27.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
545
+ "videodit_blocks.layers.27.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
546
+ "videodit_blocks.layers.27.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
547
+ "videodit_blocks.layers.27.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
548
+ "videodit_blocks.layers.27.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
549
+ "videodit_blocks.layers.27.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
550
+ "videodit_blocks.layers.27.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
551
+ "videodit_blocks.layers.27.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
552
+ "videodit_blocks.layers.27.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
553
+ "videodit_blocks.layers.27.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
554
+ "videodit_blocks.layers.27.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
555
+ "videodit_blocks.layers.27.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
556
+ "videodit_blocks.layers.27.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
557
+ "videodit_blocks.layers.27.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
558
+ "videodit_blocks.layers.27.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
559
+ "videodit_blocks.layers.27.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
560
+ "videodit_blocks.layers.28.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
561
+ "videodit_blocks.layers.28.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
562
+ "videodit_blocks.layers.28.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
563
+ "videodit_blocks.layers.28.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
564
+ "videodit_blocks.layers.28.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
565
+ "videodit_blocks.layers.28.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
566
+ "videodit_blocks.layers.28.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
567
+ "videodit_blocks.layers.28.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
568
+ "videodit_blocks.layers.28.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
569
+ "videodit_blocks.layers.28.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
570
+ "videodit_blocks.layers.28.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
571
+ "videodit_blocks.layers.28.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
572
+ "videodit_blocks.layers.28.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
573
+ "videodit_blocks.layers.28.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
574
+ "videodit_blocks.layers.28.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
575
+ "videodit_blocks.layers.28.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
576
+ "videodit_blocks.layers.28.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
577
+ "videodit_blocks.layers.28.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
578
+ "videodit_blocks.layers.28.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
579
+ "videodit_blocks.layers.28.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
580
+ "videodit_blocks.layers.28.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
581
+ "videodit_blocks.layers.28.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
582
+ "videodit_blocks.layers.28.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
583
+ "videodit_blocks.layers.28.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
584
+ "videodit_blocks.layers.28.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
585
+ "videodit_blocks.layers.28.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
586
+ "videodit_blocks.layers.29.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
587
+ "videodit_blocks.layers.29.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
588
+ "videodit_blocks.layers.29.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
589
+ "videodit_blocks.layers.29.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
590
+ "videodit_blocks.layers.29.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
591
+ "videodit_blocks.layers.29.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
592
+ "videodit_blocks.layers.29.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
593
+ "videodit_blocks.layers.29.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
594
+ "videodit_blocks.layers.29.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
595
+ "videodit_blocks.layers.29.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
596
+ "videodit_blocks.layers.29.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
597
+ "videodit_blocks.layers.29.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
598
+ "videodit_blocks.layers.29.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
599
+ "videodit_blocks.layers.29.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
600
+ "videodit_blocks.layers.29.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
601
+ "videodit_blocks.layers.29.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
602
+ "videodit_blocks.layers.29.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
603
+ "videodit_blocks.layers.29.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
604
+ "videodit_blocks.layers.29.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
605
+ "videodit_blocks.layers.29.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
606
+ "videodit_blocks.layers.29.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
607
+ "videodit_blocks.layers.29.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
608
+ "videodit_blocks.layers.29.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
609
+ "videodit_blocks.layers.29.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
610
+ "videodit_blocks.layers.29.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
611
+ "videodit_blocks.layers.29.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
612
+ "videodit_blocks.layers.3.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
613
+ "videodit_blocks.layers.3.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
614
+ "videodit_blocks.layers.3.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
615
+ "videodit_blocks.layers.3.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
616
+ "videodit_blocks.layers.3.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
617
+ "videodit_blocks.layers.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
618
+ "videodit_blocks.layers.3.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
619
+ "videodit_blocks.layers.3.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
620
+ "videodit_blocks.layers.3.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
621
+ "videodit_blocks.layers.3.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
622
+ "videodit_blocks.layers.3.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
623
+ "videodit_blocks.layers.3.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
624
+ "videodit_blocks.layers.3.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
625
+ "videodit_blocks.layers.3.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
626
+ "videodit_blocks.layers.3.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
627
+ "videodit_blocks.layers.3.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
628
+ "videodit_blocks.layers.3.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
629
+ "videodit_blocks.layers.3.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
630
+ "videodit_blocks.layers.3.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
631
+ "videodit_blocks.layers.3.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
632
+ "videodit_blocks.layers.3.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
633
+ "videodit_blocks.layers.3.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
634
+ "videodit_blocks.layers.3.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
635
+ "videodit_blocks.layers.3.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
636
+ "videodit_blocks.layers.3.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
637
+ "videodit_blocks.layers.3.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
638
+ "videodit_blocks.layers.30.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
639
+ "videodit_blocks.layers.30.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
640
+ "videodit_blocks.layers.30.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
641
+ "videodit_blocks.layers.30.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
642
+ "videodit_blocks.layers.30.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
643
+ "videodit_blocks.layers.30.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
644
+ "videodit_blocks.layers.30.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
645
+ "videodit_blocks.layers.30.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
646
+ "videodit_blocks.layers.30.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
647
+ "videodit_blocks.layers.30.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
648
+ "videodit_blocks.layers.30.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
649
+ "videodit_blocks.layers.30.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
650
+ "videodit_blocks.layers.30.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
651
+ "videodit_blocks.layers.30.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
652
+ "videodit_blocks.layers.30.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
653
+ "videodit_blocks.layers.30.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
654
+ "videodit_blocks.layers.30.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
655
+ "videodit_blocks.layers.30.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
656
+ "videodit_blocks.layers.30.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
657
+ "videodit_blocks.layers.30.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
658
+ "videodit_blocks.layers.30.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
659
+ "videodit_blocks.layers.30.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
660
+ "videodit_blocks.layers.30.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
661
+ "videodit_blocks.layers.30.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
662
+ "videodit_blocks.layers.30.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
663
+ "videodit_blocks.layers.30.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
664
+ "videodit_blocks.layers.31.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
665
+ "videodit_blocks.layers.31.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
666
+ "videodit_blocks.layers.31.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
667
+ "videodit_blocks.layers.31.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
668
+ "videodit_blocks.layers.31.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
669
+ "videodit_blocks.layers.31.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
670
+ "videodit_blocks.layers.31.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
671
+ "videodit_blocks.layers.31.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
672
+ "videodit_blocks.layers.31.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
673
+ "videodit_blocks.layers.31.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
674
+ "videodit_blocks.layers.31.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
675
+ "videodit_blocks.layers.31.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
676
+ "videodit_blocks.layers.31.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
677
+ "videodit_blocks.layers.31.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
678
+ "videodit_blocks.layers.31.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
679
+ "videodit_blocks.layers.31.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
680
+ "videodit_blocks.layers.31.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
681
+ "videodit_blocks.layers.31.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
682
+ "videodit_blocks.layers.31.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
683
+ "videodit_blocks.layers.31.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
684
+ "videodit_blocks.layers.31.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
685
+ "videodit_blocks.layers.31.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
686
+ "videodit_blocks.layers.31.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
687
+ "videodit_blocks.layers.31.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
688
+ "videodit_blocks.layers.31.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
689
+ "videodit_blocks.layers.31.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
690
+ "videodit_blocks.layers.32.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
691
+ "videodit_blocks.layers.32.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
692
+ "videodit_blocks.layers.32.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
693
+ "videodit_blocks.layers.32.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
694
+ "videodit_blocks.layers.32.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
695
+ "videodit_blocks.layers.32.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
696
+ "videodit_blocks.layers.32.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
697
+ "videodit_blocks.layers.32.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
698
+ "videodit_blocks.layers.32.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
699
+ "videodit_blocks.layers.32.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
700
+ "videodit_blocks.layers.32.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
701
+ "videodit_blocks.layers.32.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
702
+ "videodit_blocks.layers.32.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
703
+ "videodit_blocks.layers.32.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
704
+ "videodit_blocks.layers.32.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
705
+ "videodit_blocks.layers.32.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
706
+ "videodit_blocks.layers.32.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
707
+ "videodit_blocks.layers.32.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
708
+ "videodit_blocks.layers.32.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
709
+ "videodit_blocks.layers.32.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
710
+ "videodit_blocks.layers.32.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
711
+ "videodit_blocks.layers.32.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
712
+ "videodit_blocks.layers.32.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
713
+ "videodit_blocks.layers.32.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
714
+ "videodit_blocks.layers.32.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
715
+ "videodit_blocks.layers.32.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
716
+ "videodit_blocks.layers.33.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
717
+ "videodit_blocks.layers.33.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
718
+ "videodit_blocks.layers.33.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
719
+ "videodit_blocks.layers.33.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
720
+ "videodit_blocks.layers.33.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
721
+ "videodit_blocks.layers.33.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
722
+ "videodit_blocks.layers.33.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
723
+ "videodit_blocks.layers.33.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
724
+ "videodit_blocks.layers.33.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
725
+ "videodit_blocks.layers.33.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
726
+ "videodit_blocks.layers.33.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
727
+ "videodit_blocks.layers.33.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
728
+ "videodit_blocks.layers.33.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
729
+ "videodit_blocks.layers.33.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
730
+ "videodit_blocks.layers.33.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
731
+ "videodit_blocks.layers.33.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
732
+ "videodit_blocks.layers.33.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
733
+ "videodit_blocks.layers.33.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
734
+ "videodit_blocks.layers.33.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
735
+ "videodit_blocks.layers.33.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
736
+ "videodit_blocks.layers.33.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
737
+ "videodit_blocks.layers.33.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
738
+ "videodit_blocks.layers.33.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
739
+ "videodit_blocks.layers.33.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
740
+ "videodit_blocks.layers.33.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
741
+ "videodit_blocks.layers.33.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
742
+ "videodit_blocks.layers.4.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
743
+ "videodit_blocks.layers.4.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
744
+ "videodit_blocks.layers.4.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
745
+ "videodit_blocks.layers.4.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
746
+ "videodit_blocks.layers.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
747
+ "videodit_blocks.layers.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
748
+ "videodit_blocks.layers.4.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
749
+ "videodit_blocks.layers.4.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
750
+ "videodit_blocks.layers.4.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
751
+ "videodit_blocks.layers.4.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
752
+ "videodit_blocks.layers.4.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
753
+ "videodit_blocks.layers.4.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
754
+ "videodit_blocks.layers.4.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
755
+ "videodit_blocks.layers.4.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
756
+ "videodit_blocks.layers.4.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
757
+ "videodit_blocks.layers.4.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
758
+ "videodit_blocks.layers.4.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
759
+ "videodit_blocks.layers.4.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
760
+ "videodit_blocks.layers.4.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
761
+ "videodit_blocks.layers.4.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
762
+ "videodit_blocks.layers.4.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
763
+ "videodit_blocks.layers.4.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
764
+ "videodit_blocks.layers.4.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
765
+ "videodit_blocks.layers.4.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
766
+ "videodit_blocks.layers.4.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
767
+ "videodit_blocks.layers.4.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
768
+ "videodit_blocks.layers.5.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
769
+ "videodit_blocks.layers.5.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
770
+ "videodit_blocks.layers.5.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
771
+ "videodit_blocks.layers.5.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
772
+ "videodit_blocks.layers.5.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
773
+ "videodit_blocks.layers.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
774
+ "videodit_blocks.layers.5.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
775
+ "videodit_blocks.layers.5.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
776
+ "videodit_blocks.layers.5.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
777
+ "videodit_blocks.layers.5.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
778
+ "videodit_blocks.layers.5.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
779
+ "videodit_blocks.layers.5.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
780
+ "videodit_blocks.layers.5.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
781
+ "videodit_blocks.layers.5.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
782
+ "videodit_blocks.layers.5.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
783
+ "videodit_blocks.layers.5.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
784
+ "videodit_blocks.layers.5.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
785
+ "videodit_blocks.layers.5.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
786
+ "videodit_blocks.layers.5.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
787
+ "videodit_blocks.layers.5.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
788
+ "videodit_blocks.layers.5.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
789
+ "videodit_blocks.layers.5.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
790
+ "videodit_blocks.layers.5.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
791
+ "videodit_blocks.layers.5.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
792
+ "videodit_blocks.layers.5.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
793
+ "videodit_blocks.layers.5.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
794
+ "videodit_blocks.layers.6.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
795
+ "videodit_blocks.layers.6.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
796
+ "videodit_blocks.layers.6.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
797
+ "videodit_blocks.layers.6.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
798
+ "videodit_blocks.layers.6.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
799
+ "videodit_blocks.layers.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
800
+ "videodit_blocks.layers.6.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
801
+ "videodit_blocks.layers.6.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
802
+ "videodit_blocks.layers.6.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
803
+ "videodit_blocks.layers.6.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
804
+ "videodit_blocks.layers.6.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
805
+ "videodit_blocks.layers.6.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
806
+ "videodit_blocks.layers.6.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
807
+ "videodit_blocks.layers.6.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
808
+ "videodit_blocks.layers.6.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
809
+ "videodit_blocks.layers.6.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
810
+ "videodit_blocks.layers.6.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
811
+ "videodit_blocks.layers.6.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
812
+ "videodit_blocks.layers.6.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
813
+ "videodit_blocks.layers.6.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
814
+ "videodit_blocks.layers.6.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
815
+ "videodit_blocks.layers.6.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
816
+ "videodit_blocks.layers.6.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
817
+ "videodit_blocks.layers.6.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
818
+ "videodit_blocks.layers.6.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
819
+ "videodit_blocks.layers.6.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
820
+ "videodit_blocks.layers.7.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
821
+ "videodit_blocks.layers.7.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
822
+ "videodit_blocks.layers.7.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
823
+ "videodit_blocks.layers.7.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
824
+ "videodit_blocks.layers.7.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
825
+ "videodit_blocks.layers.7.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
826
+ "videodit_blocks.layers.7.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
827
+ "videodit_blocks.layers.7.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
828
+ "videodit_blocks.layers.7.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
829
+ "videodit_blocks.layers.7.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
830
+ "videodit_blocks.layers.7.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
831
+ "videodit_blocks.layers.7.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
832
+ "videodit_blocks.layers.7.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
833
+ "videodit_blocks.layers.7.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
834
+ "videodit_blocks.layers.7.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
835
+ "videodit_blocks.layers.7.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
836
+ "videodit_blocks.layers.7.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
837
+ "videodit_blocks.layers.7.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
838
+ "videodit_blocks.layers.7.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
839
+ "videodit_blocks.layers.7.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
840
+ "videodit_blocks.layers.7.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
841
+ "videodit_blocks.layers.7.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
842
+ "videodit_blocks.layers.7.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
843
+ "videodit_blocks.layers.7.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
844
+ "videodit_blocks.layers.7.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
845
+ "videodit_blocks.layers.7.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
846
+ "videodit_blocks.layers.8.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
847
+ "videodit_blocks.layers.8.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
848
+ "videodit_blocks.layers.8.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
849
+ "videodit_blocks.layers.8.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
850
+ "videodit_blocks.layers.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
851
+ "videodit_blocks.layers.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
852
+ "videodit_blocks.layers.8.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
853
+ "videodit_blocks.layers.8.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
854
+ "videodit_blocks.layers.8.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
855
+ "videodit_blocks.layers.8.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
856
+ "videodit_blocks.layers.8.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
857
+ "videodit_blocks.layers.8.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
858
+ "videodit_blocks.layers.8.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
859
+ "videodit_blocks.layers.8.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
860
+ "videodit_blocks.layers.8.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
861
+ "videodit_blocks.layers.8.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
862
+ "videodit_blocks.layers.8.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
863
+ "videodit_blocks.layers.8.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
864
+ "videodit_blocks.layers.8.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
865
+ "videodit_blocks.layers.8.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
866
+ "videodit_blocks.layers.8.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
867
+ "videodit_blocks.layers.8.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
868
+ "videodit_blocks.layers.8.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
869
+ "videodit_blocks.layers.8.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
870
+ "videodit_blocks.layers.8.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
871
+ "videodit_blocks.layers.8.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
872
+ "videodit_blocks.layers.9.ada_modulate_layer.proj.0.bias": "model-00003-of-00003.safetensors",
873
+ "videodit_blocks.layers.9.ada_modulate_layer.proj.0.weight": "model-00003-of-00003.safetensors",
874
+ "videodit_blocks.layers.9.mlp.layer_norm.bias": "model-00002-of-00003.safetensors",
875
+ "videodit_blocks.layers.9.mlp.layer_norm.weight": "model-00002-of-00003.safetensors",
876
+ "videodit_blocks.layers.9.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
877
+ "videodit_blocks.layers.9.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
878
+ "videodit_blocks.layers.9.mlp_post_norm.bias": "model-00003-of-00003.safetensors",
879
+ "videodit_blocks.layers.9.mlp_post_norm.weight": "model-00002-of-00003.safetensors",
880
+ "videodit_blocks.layers.9.self_attention.k_layernorm.bias": "model-00002-of-00003.safetensors",
881
+ "videodit_blocks.layers.9.self_attention.k_layernorm.weight": "model-00002-of-00003.safetensors",
882
+ "videodit_blocks.layers.9.self_attention.k_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
883
+ "videodit_blocks.layers.9.self_attention.k_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
884
+ "videodit_blocks.layers.9.self_attention.linear_kv_xattn.weight": "model-00002-of-00003.safetensors",
885
+ "videodit_blocks.layers.9.self_attention.linear_proj.weight": "model-00003-of-00003.safetensors",
886
+ "videodit_blocks.layers.9.self_attention.linear_qkv.k.weight": "model-00002-of-00003.safetensors",
887
+ "videodit_blocks.layers.9.self_attention.linear_qkv.layer_norm.bias": "model-00002-of-00003.safetensors",
888
+ "videodit_blocks.layers.9.self_attention.linear_qkv.layer_norm.weight": "model-00002-of-00003.safetensors",
889
+ "videodit_blocks.layers.9.self_attention.linear_qkv.q.weight": "model-00002-of-00003.safetensors",
890
+ "videodit_blocks.layers.9.self_attention.linear_qkv.qx.weight": "model-00002-of-00003.safetensors",
891
+ "videodit_blocks.layers.9.self_attention.linear_qkv.v.weight": "model-00002-of-00003.safetensors",
892
+ "videodit_blocks.layers.9.self_attention.q_layernorm.bias": "model-00002-of-00003.safetensors",
893
+ "videodit_blocks.layers.9.self_attention.q_layernorm.weight": "model-00002-of-00003.safetensors",
894
+ "videodit_blocks.layers.9.self_attention.q_layernorm_xattn.bias": "model-00002-of-00003.safetensors",
895
+ "videodit_blocks.layers.9.self_attention.q_layernorm_xattn.weight": "model-00002-of-00003.safetensors",
896
+ "videodit_blocks.layers.9.self_attn_post_norm.bias": "model-00002-of-00003.safetensors",
897
+ "videodit_blocks.layers.9.self_attn_post_norm.weight": "model-00002-of-00003.safetensors",
898
+ "x_embedder.weight": "model-00001-of-00003.safetensors",
899
+ "y_embedder.null_caption_embedding": "model-00001-of-00003.safetensors",
900
+ "y_embedder.y_proj_adaln.0.bias": "model-00001-of-00003.safetensors",
901
+ "y_embedder.y_proj_adaln.0.weight": "model-00001-of-00003.safetensors",
902
+ "y_embedder.y_proj_xattn.0.bias": "model-00001-of-00003.safetensors",
903
+ "y_embedder.y_proj_xattn.0.weight": "model-00001-of-00003.safetensors"
904
+ }
905
+ }