Hugging Face's logo

mlx-community
/
OpenSora-VAE-v1.2

MLX
Safetensors
English
VideoAutoencoderPipeline
Model card Files Community
2

Upload folder using huggingface_hub

#1
by awni - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+608
-0
Files changed (4) hide show
  1. README.md +14 -0
  2. config.json +67 -0
  3. model.safetensors +3 -0
  4. model.safetensors.index.json +524 -0
README.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: other
4
+ tags:
5
+ - mlx
6
+ library: mlx
7
+ ---
8
+
9
+ The Model [mlx-community/OpenSora-VAE-v1.2](https://huggingface.co/mlx-community/OpenSora-VAE-v1.2) was
10
+ converted to MLX format from
11
+ [hpcai-tech/OpenSora-VAE-v1.2](https://huggingface.co/hpcai-tech/OpenSora-VAE-v1.2).
12
+
13
+ This model is intended to be used with the [Open-Sora MLX
14
+ Example](https://github.com/ml-explore/mlx-examples/tree/main/open-sora).
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VideoAutoencoderPipeline"
4
+ ],
5
+ "cal_loss": false,
6
+ "freeze_vae_2d": false,
7
+ "from_pretrained": null,
8
+ "micro_frame_size": 17,
9
+ "model_type": "VideoAutoencoderPipeline",
10
+ "scale": [
11
+ 3.85,
12
+ 2.32,
13
+ 2.33,
14
+ 3.06
15
+ ],
16
+ "shift": [
17
+ -0.1,
18
+ 0.34,
19
+ 0.27,
20
+ 0.98
21
+ ],
22
+ "spatial_vae": {
23
+ "_class_name": "AutoencoderKL",
24
+ "_diffusers_version": "0.18.0.dev0",
25
+ "_name_or_path": ".",
26
+ "act_fn": "silu",
27
+ "block_out_channels": [
28
+ 128,
29
+ 256,
30
+ 512,
31
+ 512
32
+ ],
33
+ "down_block_types": [
34
+ "DownEncoderBlock2D",
35
+ "DownEncoderBlock2D",
36
+ "DownEncoderBlock2D",
37
+ "DownEncoderBlock2D"
38
+ ],
39
+ "in_channels": 3,
40
+ "latent_channels": 4,
41
+ "layers_per_block": 2,
42
+ "norm_num_groups": 32,
43
+ "out_channels": 3,
44
+ "sample_size": 512,
45
+ "scaling_factor": 0.13025,
46
+ "up_block_types": [
47
+ "UpDecoderBlock2D",
48
+ "UpDecoderBlock2D",
49
+ "UpDecoderBlock2D",
50
+ "UpDecoderBlock2D"
51
+ ],
52
+ "force_upcast": false
53
+ },
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.36.2",
56
+ "vae_2d": {
57
+ "from_pretrained": "PixArt-alpha/pixart_sigma_sdxlvae_T5_diffusers",
58
+ "local_files_only": false,
59
+ "micro_batch_size": 4,
60
+ "subfolder": "vae",
61
+ "type": "VideoAutoencoderKL"
62
+ },
63
+ "vae_temporal": {
64
+ "from_pretrained": null,
65
+ "type": "VAE_Temporal_SD"
66
+ }
67
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7cd4d1aca71cc07745caa1ca579305af56e2faf2467dfb7ef7e05cce7f28b0
3
+ size 786748331
model.safetensors.index.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 786682030
4
+ },
5
+ "weight_map": {
6
+ "scale": "model.safetensors",
7
+ "shift": "model.safetensors",
8
+ "spatial_vae.module.decoder.conv_in.bias": "model.safetensors",
9
+ "spatial_vae.module.decoder.conv_in.weight": "model.safetensors",
10
+ "spatial_vae.module.decoder.conv_norm_out.bias": "model.safetensors",
11
+ "spatial_vae.module.decoder.conv_norm_out.weight": "model.safetensors",
12
+ "spatial_vae.module.decoder.conv_out.bias": "model.safetensors",
13
+ "spatial_vae.module.decoder.conv_out.weight": "model.safetensors",
14
+ "spatial_vae.module.decoder.mid_block.attentions.0.group_norm.bias": "model.safetensors",
15
+ "spatial_vae.module.decoder.mid_block.attentions.0.group_norm.weight": "model.safetensors",
16
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_k.bias": "model.safetensors",
17
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_k.weight": "model.safetensors",
18
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_out.0.bias": "model.safetensors",
19
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_out.0.weight": "model.safetensors",
20
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_q.bias": "model.safetensors",
21
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_q.weight": "model.safetensors",
22
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_v.bias": "model.safetensors",
23
+ "spatial_vae.module.decoder.mid_block.attentions.0.to_v.weight": "model.safetensors",
24
+ "spatial_vae.module.decoder.mid_block.resnets.0.conv1.bias": "model.safetensors",
25
+ "spatial_vae.module.decoder.mid_block.resnets.0.conv1.weight": "model.safetensors",
26
+ "spatial_vae.module.decoder.mid_block.resnets.0.conv2.bias": "model.safetensors",
27
+ "spatial_vae.module.decoder.mid_block.resnets.0.conv2.weight": "model.safetensors",
28
+ "spatial_vae.module.decoder.mid_block.resnets.0.norm1.bias": "model.safetensors",
29
+ "spatial_vae.module.decoder.mid_block.resnets.0.norm1.weight": "model.safetensors",
30
+ "spatial_vae.module.decoder.mid_block.resnets.0.norm2.bias": "model.safetensors",
31
+ "spatial_vae.module.decoder.mid_block.resnets.0.norm2.weight": "model.safetensors",
32
+ "spatial_vae.module.decoder.mid_block.resnets.1.conv1.bias": "model.safetensors",
33
+ "spatial_vae.module.decoder.mid_block.resnets.1.conv1.weight": "model.safetensors",
34
+ "spatial_vae.module.decoder.mid_block.resnets.1.conv2.bias": "model.safetensors",
35
+ "spatial_vae.module.decoder.mid_block.resnets.1.conv2.weight": "model.safetensors",
36
+ "spatial_vae.module.decoder.mid_block.resnets.1.norm1.bias": "model.safetensors",
37
+ "spatial_vae.module.decoder.mid_block.resnets.1.norm1.weight": "model.safetensors",
38
+ "spatial_vae.module.decoder.mid_block.resnets.1.norm2.bias": "model.safetensors",
39
+ "spatial_vae.module.decoder.mid_block.resnets.1.norm2.weight": "model.safetensors",
40
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv1.bias": "model.safetensors",
41
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv1.weight": "model.safetensors",
42
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv2.bias": "model.safetensors",
43
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.conv2.weight": "model.safetensors",
44
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm1.bias": "model.safetensors",
45
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm1.weight": "model.safetensors",
46
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm2.bias": "model.safetensors",
47
+ "spatial_vae.module.decoder.up_blocks.0.resnets.0.norm2.weight": "model.safetensors",
48
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv1.bias": "model.safetensors",
49
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv1.weight": "model.safetensors",
50
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv2.bias": "model.safetensors",
51
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.conv2.weight": "model.safetensors",
52
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm1.bias": "model.safetensors",
53
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm1.weight": "model.safetensors",
54
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm2.bias": "model.safetensors",
55
+ "spatial_vae.module.decoder.up_blocks.0.resnets.1.norm2.weight": "model.safetensors",
56
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv1.bias": "model.safetensors",
57
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv1.weight": "model.safetensors",
58
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv2.bias": "model.safetensors",
59
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.conv2.weight": "model.safetensors",
60
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm1.bias": "model.safetensors",
61
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm1.weight": "model.safetensors",
62
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm2.bias": "model.safetensors",
63
+ "spatial_vae.module.decoder.up_blocks.0.resnets.2.norm2.weight": "model.safetensors",
64
+ "spatial_vae.module.decoder.up_blocks.0.upsamplers.0.conv.bias": "model.safetensors",
65
+ "spatial_vae.module.decoder.up_blocks.0.upsamplers.0.conv.weight": "model.safetensors",
66
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv1.bias": "model.safetensors",
67
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv1.weight": "model.safetensors",
68
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv2.bias": "model.safetensors",
69
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.conv2.weight": "model.safetensors",
70
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm1.bias": "model.safetensors",
71
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm1.weight": "model.safetensors",
72
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm2.bias": "model.safetensors",
73
+ "spatial_vae.module.decoder.up_blocks.1.resnets.0.norm2.weight": "model.safetensors",
74
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv1.bias": "model.safetensors",
75
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv1.weight": "model.safetensors",
76
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv2.bias": "model.safetensors",
77
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.conv2.weight": "model.safetensors",
78
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm1.bias": "model.safetensors",
79
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm1.weight": "model.safetensors",
80
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm2.bias": "model.safetensors",
81
+ "spatial_vae.module.decoder.up_blocks.1.resnets.1.norm2.weight": "model.safetensors",
82
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv1.bias": "model.safetensors",
83
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv1.weight": "model.safetensors",
84
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv2.bias": "model.safetensors",
85
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.conv2.weight": "model.safetensors",
86
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm1.bias": "model.safetensors",
87
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm1.weight": "model.safetensors",
88
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm2.bias": "model.safetensors",
89
+ "spatial_vae.module.decoder.up_blocks.1.resnets.2.norm2.weight": "model.safetensors",
90
+ "spatial_vae.module.decoder.up_blocks.1.upsamplers.0.conv.bias": "model.safetensors",
91
+ "spatial_vae.module.decoder.up_blocks.1.upsamplers.0.conv.weight": "model.safetensors",
92
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv1.bias": "model.safetensors",
93
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv1.weight": "model.safetensors",
94
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv2.bias": "model.safetensors",
95
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv2.weight": "model.safetensors",
96
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv_shortcut.bias": "model.safetensors",
97
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.conv_shortcut.weight": "model.safetensors",
98
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm1.bias": "model.safetensors",
99
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm1.weight": "model.safetensors",
100
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm2.bias": "model.safetensors",
101
+ "spatial_vae.module.decoder.up_blocks.2.resnets.0.norm2.weight": "model.safetensors",
102
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv1.bias": "model.safetensors",
103
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv1.weight": "model.safetensors",
104
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv2.bias": "model.safetensors",
105
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.conv2.weight": "model.safetensors",
106
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm1.bias": "model.safetensors",
107
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm1.weight": "model.safetensors",
108
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm2.bias": "model.safetensors",
109
+ "spatial_vae.module.decoder.up_blocks.2.resnets.1.norm2.weight": "model.safetensors",
110
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv1.bias": "model.safetensors",
111
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv1.weight": "model.safetensors",
112
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv2.bias": "model.safetensors",
113
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.conv2.weight": "model.safetensors",
114
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm1.bias": "model.safetensors",
115
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm1.weight": "model.safetensors",
116
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm2.bias": "model.safetensors",
117
+ "spatial_vae.module.decoder.up_blocks.2.resnets.2.norm2.weight": "model.safetensors",
118
+ "spatial_vae.module.decoder.up_blocks.2.upsamplers.0.conv.bias": "model.safetensors",
119
+ "spatial_vae.module.decoder.up_blocks.2.upsamplers.0.conv.weight": "model.safetensors",
120
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv1.bias": "model.safetensors",
121
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv1.weight": "model.safetensors",
122
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv2.bias": "model.safetensors",
123
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv2.weight": "model.safetensors",
124
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv_shortcut.bias": "model.safetensors",
125
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.conv_shortcut.weight": "model.safetensors",
126
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm1.bias": "model.safetensors",
127
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm1.weight": "model.safetensors",
128
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm2.bias": "model.safetensors",
129
+ "spatial_vae.module.decoder.up_blocks.3.resnets.0.norm2.weight": "model.safetensors",
130
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv1.bias": "model.safetensors",
131
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv1.weight": "model.safetensors",
132
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv2.bias": "model.safetensors",
133
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.conv2.weight": "model.safetensors",
134
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm1.bias": "model.safetensors",
135
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm1.weight": "model.safetensors",
136
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm2.bias": "model.safetensors",
137
+ "spatial_vae.module.decoder.up_blocks.3.resnets.1.norm2.weight": "model.safetensors",
138
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv1.bias": "model.safetensors",
139
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv1.weight": "model.safetensors",
140
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv2.bias": "model.safetensors",
141
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.conv2.weight": "model.safetensors",
142
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm1.bias": "model.safetensors",
143
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm1.weight": "model.safetensors",
144
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm2.bias": "model.safetensors",
145
+ "spatial_vae.module.decoder.up_blocks.3.resnets.2.norm2.weight": "model.safetensors",
146
+ "spatial_vae.module.encoder.conv_in.bias": "model.safetensors",
147
+ "spatial_vae.module.encoder.conv_in.weight": "model.safetensors",
148
+ "spatial_vae.module.encoder.conv_norm_out.bias": "model.safetensors",
149
+ "spatial_vae.module.encoder.conv_norm_out.weight": "model.safetensors",
150
+ "spatial_vae.module.encoder.conv_out.bias": "model.safetensors",
151
+ "spatial_vae.module.encoder.conv_out.weight": "model.safetensors",
152
+ "spatial_vae.module.encoder.down_blocks.0.downsamplers.0.conv.bias": "model.safetensors",
153
+ "spatial_vae.module.encoder.down_blocks.0.downsamplers.0.conv.weight": "model.safetensors",
154
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv1.bias": "model.safetensors",
155
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv1.weight": "model.safetensors",
156
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv2.bias": "model.safetensors",
157
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.conv2.weight": "model.safetensors",
158
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm1.bias": "model.safetensors",
159
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm1.weight": "model.safetensors",
160
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm2.bias": "model.safetensors",
161
+ "spatial_vae.module.encoder.down_blocks.0.resnets.0.norm2.weight": "model.safetensors",
162
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv1.bias": "model.safetensors",
163
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv1.weight": "model.safetensors",
164
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv2.bias": "model.safetensors",
165
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.conv2.weight": "model.safetensors",
166
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm1.bias": "model.safetensors",
167
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm1.weight": "model.safetensors",
168
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm2.bias": "model.safetensors",
169
+ "spatial_vae.module.encoder.down_blocks.0.resnets.1.norm2.weight": "model.safetensors",
170
+ "spatial_vae.module.encoder.down_blocks.1.downsamplers.0.conv.bias": "model.safetensors",
171
+ "spatial_vae.module.encoder.down_blocks.1.downsamplers.0.conv.weight": "model.safetensors",
172
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv1.bias": "model.safetensors",
173
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv1.weight": "model.safetensors",
174
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv2.bias": "model.safetensors",
175
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv2.weight": "model.safetensors",
176
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "model.safetensors",
177
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "model.safetensors",
178
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm1.bias": "model.safetensors",
179
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm1.weight": "model.safetensors",
180
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm2.bias": "model.safetensors",
181
+ "spatial_vae.module.encoder.down_blocks.1.resnets.0.norm2.weight": "model.safetensors",
182
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv1.bias": "model.safetensors",
183
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv1.weight": "model.safetensors",
184
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv2.bias": "model.safetensors",
185
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.conv2.weight": "model.safetensors",
186
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm1.bias": "model.safetensors",
187
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm1.weight": "model.safetensors",
188
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm2.bias": "model.safetensors",
189
+ "spatial_vae.module.encoder.down_blocks.1.resnets.1.norm2.weight": "model.safetensors",
190
+ "spatial_vae.module.encoder.down_blocks.2.downsamplers.0.conv.bias": "model.safetensors",
191
+ "spatial_vae.module.encoder.down_blocks.2.downsamplers.0.conv.weight": "model.safetensors",
192
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv1.bias": "model.safetensors",
193
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv1.weight": "model.safetensors",
194
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv2.bias": "model.safetensors",
195
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv2.weight": "model.safetensors",
196
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv_shortcut.bias": "model.safetensors",
197
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.conv_shortcut.weight": "model.safetensors",
198
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm1.bias": "model.safetensors",
199
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm1.weight": "model.safetensors",
200
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm2.bias": "model.safetensors",
201
+ "spatial_vae.module.encoder.down_blocks.2.resnets.0.norm2.weight": "model.safetensors",
202
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv1.bias": "model.safetensors",
203
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv1.weight": "model.safetensors",
204
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv2.bias": "model.safetensors",
205
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.conv2.weight": "model.safetensors",
206
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm1.bias": "model.safetensors",
207
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm1.weight": "model.safetensors",
208
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm2.bias": "model.safetensors",
209
+ "spatial_vae.module.encoder.down_blocks.2.resnets.1.norm2.weight": "model.safetensors",
210
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv1.bias": "model.safetensors",
211
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv1.weight": "model.safetensors",
212
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv2.bias": "model.safetensors",
213
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.conv2.weight": "model.safetensors",
214
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm1.bias": "model.safetensors",
215
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm1.weight": "model.safetensors",
216
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm2.bias": "model.safetensors",
217
+ "spatial_vae.module.encoder.down_blocks.3.resnets.0.norm2.weight": "model.safetensors",
218
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv1.bias": "model.safetensors",
219
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv1.weight": "model.safetensors",
220
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv2.bias": "model.safetensors",
221
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.conv2.weight": "model.safetensors",
222
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm1.bias": "model.safetensors",
223
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm1.weight": "model.safetensors",
224
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm2.bias": "model.safetensors",
225
+ "spatial_vae.module.encoder.down_blocks.3.resnets.1.norm2.weight": "model.safetensors",
226
+ "spatial_vae.module.encoder.mid_block.attentions.0.group_norm.bias": "model.safetensors",
227
+ "spatial_vae.module.encoder.mid_block.attentions.0.group_norm.weight": "model.safetensors",
228
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_k.bias": "model.safetensors",
229
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_k.weight": "model.safetensors",
230
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_out.0.bias": "model.safetensors",
231
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_out.0.weight": "model.safetensors",
232
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_q.bias": "model.safetensors",
233
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_q.weight": "model.safetensors",
234
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_v.bias": "model.safetensors",
235
+ "spatial_vae.module.encoder.mid_block.attentions.0.to_v.weight": "model.safetensors",
236
+ "spatial_vae.module.encoder.mid_block.resnets.0.conv1.bias": "model.safetensors",
237
+ "spatial_vae.module.encoder.mid_block.resnets.0.conv1.weight": "model.safetensors",
238
+ "spatial_vae.module.encoder.mid_block.resnets.0.conv2.bias": "model.safetensors",
239
+ "spatial_vae.module.encoder.mid_block.resnets.0.conv2.weight": "model.safetensors",
240
+ "spatial_vae.module.encoder.mid_block.resnets.0.norm1.bias": "model.safetensors",
241
+ "spatial_vae.module.encoder.mid_block.resnets.0.norm1.weight": "model.safetensors",
242
+ "spatial_vae.module.encoder.mid_block.resnets.0.norm2.bias": "model.safetensors",
243
+ "spatial_vae.module.encoder.mid_block.resnets.0.norm2.weight": "model.safetensors",
244
+ "spatial_vae.module.encoder.mid_block.resnets.1.conv1.bias": "model.safetensors",
245
+ "spatial_vae.module.encoder.mid_block.resnets.1.conv1.weight": "model.safetensors",
246
+ "spatial_vae.module.encoder.mid_block.resnets.1.conv2.bias": "model.safetensors",
247
+ "spatial_vae.module.encoder.mid_block.resnets.1.conv2.weight": "model.safetensors",
248
+ "spatial_vae.module.encoder.mid_block.resnets.1.norm1.bias": "model.safetensors",
249
+ "spatial_vae.module.encoder.mid_block.resnets.1.norm1.weight": "model.safetensors",
250
+ "spatial_vae.module.encoder.mid_block.resnets.1.norm2.bias": "model.safetensors",
251
+ "spatial_vae.module.encoder.mid_block.resnets.1.norm2.weight": "model.safetensors",
252
+ "spatial_vae.module.post_quant_conv.bias": "model.safetensors",
253
+ "spatial_vae.module.post_quant_conv.weight": "model.safetensors",
254
+ "spatial_vae.module.quant_conv.bias": "model.safetensors",
255
+ "spatial_vae.module.quant_conv.weight": "model.safetensors",
256
+ "temporal_vae.decoder.block_res_blocks.0.0.conv1.conv.weight": "model.safetensors",
257
+ "temporal_vae.decoder.block_res_blocks.0.0.conv2.conv.weight": "model.safetensors",
258
+ "temporal_vae.decoder.block_res_blocks.0.0.conv3.conv.weight": "model.safetensors",
259
+ "temporal_vae.decoder.block_res_blocks.0.0.norm1.bias": "model.safetensors",
260
+ "temporal_vae.decoder.block_res_blocks.0.0.norm1.weight": "model.safetensors",
261
+ "temporal_vae.decoder.block_res_blocks.0.0.norm2.bias": "model.safetensors",
262
+ "temporal_vae.decoder.block_res_blocks.0.0.norm2.weight": "model.safetensors",
263
+ "temporal_vae.decoder.block_res_blocks.0.1.conv1.conv.weight": "model.safetensors",
264
+ "temporal_vae.decoder.block_res_blocks.0.1.conv2.conv.weight": "model.safetensors",
265
+ "temporal_vae.decoder.block_res_blocks.0.1.norm1.bias": "model.safetensors",
266
+ "temporal_vae.decoder.block_res_blocks.0.1.norm1.weight": "model.safetensors",
267
+ "temporal_vae.decoder.block_res_blocks.0.1.norm2.bias": "model.safetensors",
268
+ "temporal_vae.decoder.block_res_blocks.0.1.norm2.weight": "model.safetensors",
269
+ "temporal_vae.decoder.block_res_blocks.0.2.conv1.conv.weight": "model.safetensors",
270
+ "temporal_vae.decoder.block_res_blocks.0.2.conv2.conv.weight": "model.safetensors",
271
+ "temporal_vae.decoder.block_res_blocks.0.2.norm1.bias": "model.safetensors",
272
+ "temporal_vae.decoder.block_res_blocks.0.2.norm1.weight": "model.safetensors",
273
+ "temporal_vae.decoder.block_res_blocks.0.2.norm2.bias": "model.safetensors",
274
+ "temporal_vae.decoder.block_res_blocks.0.2.norm2.weight": "model.safetensors",
275
+ "temporal_vae.decoder.block_res_blocks.0.3.conv1.conv.weight": "model.safetensors",
276
+ "temporal_vae.decoder.block_res_blocks.0.3.conv2.conv.weight": "model.safetensors",
277
+ "temporal_vae.decoder.block_res_blocks.0.3.norm1.bias": "model.safetensors",
278
+ "temporal_vae.decoder.block_res_blocks.0.3.norm1.weight": "model.safetensors",
279
+ "temporal_vae.decoder.block_res_blocks.0.3.norm2.bias": "model.safetensors",
280
+ "temporal_vae.decoder.block_res_blocks.0.3.norm2.weight": "model.safetensors",
281
+ "temporal_vae.decoder.block_res_blocks.1.0.conv1.conv.weight": "model.safetensors",
282
+ "temporal_vae.decoder.block_res_blocks.1.0.conv2.conv.weight": "model.safetensors",
283
+ "temporal_vae.decoder.block_res_blocks.1.0.norm1.bias": "model.safetensors",
284
+ "temporal_vae.decoder.block_res_blocks.1.0.norm1.weight": "model.safetensors",
285
+ "temporal_vae.decoder.block_res_blocks.1.0.norm2.bias": "model.safetensors",
286
+ "temporal_vae.decoder.block_res_blocks.1.0.norm2.weight": "model.safetensors",
287
+ "temporal_vae.decoder.block_res_blocks.1.1.conv1.conv.weight": "model.safetensors",
288
+ "temporal_vae.decoder.block_res_blocks.1.1.conv2.conv.weight": "model.safetensors",
289
+ "temporal_vae.decoder.block_res_blocks.1.1.norm1.bias": "model.safetensors",
290
+ "temporal_vae.decoder.block_res_blocks.1.1.norm1.weight": "model.safetensors",
291
+ "temporal_vae.decoder.block_res_blocks.1.1.norm2.bias": "model.safetensors",
292
+ "temporal_vae.decoder.block_res_blocks.1.1.norm2.weight": "model.safetensors",
293
+ "temporal_vae.decoder.block_res_blocks.1.2.conv1.conv.weight": "model.safetensors",
294
+ "temporal_vae.decoder.block_res_blocks.1.2.conv2.conv.weight": "model.safetensors",
295
+ "temporal_vae.decoder.block_res_blocks.1.2.norm1.bias": "model.safetensors",
296
+ "temporal_vae.decoder.block_res_blocks.1.2.norm1.weight": "model.safetensors",
297
+ "temporal_vae.decoder.block_res_blocks.1.2.norm2.bias": "model.safetensors",
298
+ "temporal_vae.decoder.block_res_blocks.1.2.norm2.weight": "model.safetensors",
299
+ "temporal_vae.decoder.block_res_blocks.1.3.conv1.conv.weight": "model.safetensors",
300
+ "temporal_vae.decoder.block_res_blocks.1.3.conv2.conv.weight": "model.safetensors",
301
+ "temporal_vae.decoder.block_res_blocks.1.3.norm1.bias": "model.safetensors",
302
+ "temporal_vae.decoder.block_res_blocks.1.3.norm1.weight": "model.safetensors",
303
+ "temporal_vae.decoder.block_res_blocks.1.3.norm2.bias": "model.safetensors",
304
+ "temporal_vae.decoder.block_res_blocks.1.3.norm2.weight": "model.safetensors",
305
+ "temporal_vae.decoder.block_res_blocks.2.0.conv1.conv.weight": "model.safetensors",
306
+ "temporal_vae.decoder.block_res_blocks.2.0.conv2.conv.weight": "model.safetensors",
307
+ "temporal_vae.decoder.block_res_blocks.2.0.conv3.conv.weight": "model.safetensors",
308
+ "temporal_vae.decoder.block_res_blocks.2.0.norm1.bias": "model.safetensors",
309
+ "temporal_vae.decoder.block_res_blocks.2.0.norm1.weight": "model.safetensors",
310
+ "temporal_vae.decoder.block_res_blocks.2.0.norm2.bias": "model.safetensors",
311
+ "temporal_vae.decoder.block_res_blocks.2.0.norm2.weight": "model.safetensors",
312
+ "temporal_vae.decoder.block_res_blocks.2.1.conv1.conv.weight": "model.safetensors",
313
+ "temporal_vae.decoder.block_res_blocks.2.1.conv2.conv.weight": "model.safetensors",
314
+ "temporal_vae.decoder.block_res_blocks.2.1.norm1.bias": "model.safetensors",
315
+ "temporal_vae.decoder.block_res_blocks.2.1.norm1.weight": "model.safetensors",
316
+ "temporal_vae.decoder.block_res_blocks.2.1.norm2.bias": "model.safetensors",
317
+ "temporal_vae.decoder.block_res_blocks.2.1.norm2.weight": "model.safetensors",
318
+ "temporal_vae.decoder.block_res_blocks.2.2.conv1.conv.weight": "model.safetensors",
319
+ "temporal_vae.decoder.block_res_blocks.2.2.conv2.conv.weight": "model.safetensors",
320
+ "temporal_vae.decoder.block_res_blocks.2.2.norm1.bias": "model.safetensors",
321
+ "temporal_vae.decoder.block_res_blocks.2.2.norm1.weight": "model.safetensors",
322
+ "temporal_vae.decoder.block_res_blocks.2.2.norm2.bias": "model.safetensors",
323
+ "temporal_vae.decoder.block_res_blocks.2.2.norm2.weight": "model.safetensors",
324
+ "temporal_vae.decoder.block_res_blocks.2.3.conv1.conv.weight": "model.safetensors",
325
+ "temporal_vae.decoder.block_res_blocks.2.3.conv2.conv.weight": "model.safetensors",
326
+ "temporal_vae.decoder.block_res_blocks.2.3.norm1.bias": "model.safetensors",
327
+ "temporal_vae.decoder.block_res_blocks.2.3.norm1.weight": "model.safetensors",
328
+ "temporal_vae.decoder.block_res_blocks.2.3.norm2.bias": "model.safetensors",
329
+ "temporal_vae.decoder.block_res_blocks.2.3.norm2.weight": "model.safetensors",
330
+ "temporal_vae.decoder.block_res_blocks.3.0.conv1.conv.weight": "model.safetensors",
331
+ "temporal_vae.decoder.block_res_blocks.3.0.conv2.conv.weight": "model.safetensors",
332
+ "temporal_vae.decoder.block_res_blocks.3.0.norm1.bias": "model.safetensors",
333
+ "temporal_vae.decoder.block_res_blocks.3.0.norm1.weight": "model.safetensors",
334
+ "temporal_vae.decoder.block_res_blocks.3.0.norm2.bias": "model.safetensors",
335
+ "temporal_vae.decoder.block_res_blocks.3.0.norm2.weight": "model.safetensors",
336
+ "temporal_vae.decoder.block_res_blocks.3.1.conv1.conv.weight": "model.safetensors",
337
+ "temporal_vae.decoder.block_res_blocks.3.1.conv2.conv.weight": "model.safetensors",
338
+ "temporal_vae.decoder.block_res_blocks.3.1.norm1.bias": "model.safetensors",
339
+ "temporal_vae.decoder.block_res_blocks.3.1.norm1.weight": "model.safetensors",
340
+ "temporal_vae.decoder.block_res_blocks.3.1.norm2.bias": "model.safetensors",
341
+ "temporal_vae.decoder.block_res_blocks.3.1.norm2.weight": "model.safetensors",
342
+ "temporal_vae.decoder.block_res_blocks.3.2.conv1.conv.weight": "model.safetensors",
343
+ "temporal_vae.decoder.block_res_blocks.3.2.conv2.conv.weight": "model.safetensors",
344
+ "temporal_vae.decoder.block_res_blocks.3.2.norm1.bias": "model.safetensors",
345
+ "temporal_vae.decoder.block_res_blocks.3.2.norm1.weight": "model.safetensors",
346
+ "temporal_vae.decoder.block_res_blocks.3.2.norm2.bias": "model.safetensors",
347
+ "temporal_vae.decoder.block_res_blocks.3.2.norm2.weight": "model.safetensors",
348
+ "temporal_vae.decoder.block_res_blocks.3.3.conv1.conv.weight": "model.safetensors",
349
+ "temporal_vae.decoder.block_res_blocks.3.3.conv2.conv.weight": "model.safetensors",
350
+ "temporal_vae.decoder.block_res_blocks.3.3.norm1.bias": "model.safetensors",
351
+ "temporal_vae.decoder.block_res_blocks.3.3.norm1.weight": "model.safetensors",
352
+ "temporal_vae.decoder.block_res_blocks.3.3.norm2.bias": "model.safetensors",
353
+ "temporal_vae.decoder.block_res_blocks.3.3.norm2.weight": "model.safetensors",
354
+ "temporal_vae.decoder.conv1.conv.bias": "model.safetensors",
355
+ "temporal_vae.decoder.conv1.conv.weight": "model.safetensors",
356
+ "temporal_vae.decoder.conv_blocks.1.conv.bias": "model.safetensors",
357
+ "temporal_vae.decoder.conv_blocks.1.conv.weight": "model.safetensors",
358
+ "temporal_vae.decoder.conv_blocks.2.conv.bias": "model.safetensors",
359
+ "temporal_vae.decoder.conv_blocks.2.conv.weight": "model.safetensors",
360
+ "temporal_vae.decoder.conv_out.conv.bias": "model.safetensors",
361
+ "temporal_vae.decoder.conv_out.conv.weight": "model.safetensors",
362
+ "temporal_vae.decoder.norm1.bias": "model.safetensors",
363
+ "temporal_vae.decoder.norm1.weight": "model.safetensors",
364
+ "temporal_vae.decoder.res_blocks.0.conv1.conv.weight": "model.safetensors",
365
+ "temporal_vae.decoder.res_blocks.0.conv2.conv.weight": "model.safetensors",
366
+ "temporal_vae.decoder.res_blocks.0.norm1.bias": "model.safetensors",
367
+ "temporal_vae.decoder.res_blocks.0.norm1.weight": "model.safetensors",
368
+ "temporal_vae.decoder.res_blocks.0.norm2.bias": "model.safetensors",
369
+ "temporal_vae.decoder.res_blocks.0.norm2.weight": "model.safetensors",
370
+ "temporal_vae.decoder.res_blocks.1.conv1.conv.weight": "model.safetensors",
371
+ "temporal_vae.decoder.res_blocks.1.conv2.conv.weight": "model.safetensors",
372
+ "temporal_vae.decoder.res_blocks.1.norm1.bias": "model.safetensors",
373
+ "temporal_vae.decoder.res_blocks.1.norm1.weight": "model.safetensors",
374
+ "temporal_vae.decoder.res_blocks.1.norm2.bias": "model.safetensors",
375
+ "temporal_vae.decoder.res_blocks.1.norm2.weight": "model.safetensors",
376
+ "temporal_vae.decoder.res_blocks.2.conv1.conv.weight": "model.safetensors",
377
+ "temporal_vae.decoder.res_blocks.2.conv2.conv.weight": "model.safetensors",
378
+ "temporal_vae.decoder.res_blocks.2.norm1.bias": "model.safetensors",
379
+ "temporal_vae.decoder.res_blocks.2.norm1.weight": "model.safetensors",
380
+ "temporal_vae.decoder.res_blocks.2.norm2.bias": "model.safetensors",
381
+ "temporal_vae.decoder.res_blocks.2.norm2.weight": "model.safetensors",
382
+ "temporal_vae.decoder.res_blocks.3.conv1.conv.weight": "model.safetensors",
383
+ "temporal_vae.decoder.res_blocks.3.conv2.conv.weight": "model.safetensors",
384
+ "temporal_vae.decoder.res_blocks.3.norm1.bias": "model.safetensors",
385
+ "temporal_vae.decoder.res_blocks.3.norm1.weight": "model.safetensors",
386
+ "temporal_vae.decoder.res_blocks.3.norm2.bias": "model.safetensors",
387
+ "temporal_vae.decoder.res_blocks.3.norm2.weight": "model.safetensors",
388
+ "temporal_vae.encoder.block_res_blocks.0.0.conv1.conv.weight": "model.safetensors",
389
+ "temporal_vae.encoder.block_res_blocks.0.0.conv2.conv.weight": "model.safetensors",
390
+ "temporal_vae.encoder.block_res_blocks.0.0.norm1.bias": "model.safetensors",
391
+ "temporal_vae.encoder.block_res_blocks.0.0.norm1.weight": "model.safetensors",
392
+ "temporal_vae.encoder.block_res_blocks.0.0.norm2.bias": "model.safetensors",
393
+ "temporal_vae.encoder.block_res_blocks.0.0.norm2.weight": "model.safetensors",
394
+ "temporal_vae.encoder.block_res_blocks.0.1.conv1.conv.weight": "model.safetensors",
395
+ "temporal_vae.encoder.block_res_blocks.0.1.conv2.conv.weight": "model.safetensors",
396
+ "temporal_vae.encoder.block_res_blocks.0.1.norm1.bias": "model.safetensors",
397
+ "temporal_vae.encoder.block_res_blocks.0.1.norm1.weight": "model.safetensors",
398
+ "temporal_vae.encoder.block_res_blocks.0.1.norm2.bias": "model.safetensors",
399
+ "temporal_vae.encoder.block_res_blocks.0.1.norm2.weight": "model.safetensors",
400
+ "temporal_vae.encoder.block_res_blocks.0.2.conv1.conv.weight": "model.safetensors",
401
+ "temporal_vae.encoder.block_res_blocks.0.2.conv2.conv.weight": "model.safetensors",
402
+ "temporal_vae.encoder.block_res_blocks.0.2.norm1.bias": "model.safetensors",
403
+ "temporal_vae.encoder.block_res_blocks.0.2.norm1.weight": "model.safetensors",
404
+ "temporal_vae.encoder.block_res_blocks.0.2.norm2.bias": "model.safetensors",
405
+ "temporal_vae.encoder.block_res_blocks.0.2.norm2.weight": "model.safetensors",
406
+ "temporal_vae.encoder.block_res_blocks.0.3.conv1.conv.weight": "model.safetensors",
407
+ "temporal_vae.encoder.block_res_blocks.0.3.conv2.conv.weight": "model.safetensors",
408
+ "temporal_vae.encoder.block_res_blocks.0.3.norm1.bias": "model.safetensors",
409
+ "temporal_vae.encoder.block_res_blocks.0.3.norm1.weight": "model.safetensors",
410
+ "temporal_vae.encoder.block_res_blocks.0.3.norm2.bias": "model.safetensors",
411
+ "temporal_vae.encoder.block_res_blocks.0.3.norm2.weight": "model.safetensors",
412
+ "temporal_vae.encoder.block_res_blocks.1.0.conv1.conv.weight": "model.safetensors",
413
+ "temporal_vae.encoder.block_res_blocks.1.0.conv2.conv.weight": "model.safetensors",
414
+ "temporal_vae.encoder.block_res_blocks.1.0.conv3.conv.weight": "model.safetensors",
415
+ "temporal_vae.encoder.block_res_blocks.1.0.norm1.bias": "model.safetensors",
416
+ "temporal_vae.encoder.block_res_blocks.1.0.norm1.weight": "model.safetensors",
417
+ "temporal_vae.encoder.block_res_blocks.1.0.norm2.bias": "model.safetensors",
418
+ "temporal_vae.encoder.block_res_blocks.1.0.norm2.weight": "model.safetensors",
419
+ "temporal_vae.encoder.block_res_blocks.1.1.conv1.conv.weight": "model.safetensors",
420
+ "temporal_vae.encoder.block_res_blocks.1.1.conv2.conv.weight": "model.safetensors",
421
+ "temporal_vae.encoder.block_res_blocks.1.1.norm1.bias": "model.safetensors",
422
+ "temporal_vae.encoder.block_res_blocks.1.1.norm1.weight": "model.safetensors",
423
+ "temporal_vae.encoder.block_res_blocks.1.1.norm2.bias": "model.safetensors",
424
+ "temporal_vae.encoder.block_res_blocks.1.1.norm2.weight": "model.safetensors",
425
+ "temporal_vae.encoder.block_res_blocks.1.2.conv1.conv.weight": "model.safetensors",
426
+ "temporal_vae.encoder.block_res_blocks.1.2.conv2.conv.weight": "model.safetensors",
427
+ "temporal_vae.encoder.block_res_blocks.1.2.norm1.bias": "model.safetensors",
428
+ "temporal_vae.encoder.block_res_blocks.1.2.norm1.weight": "model.safetensors",
429
+ "temporal_vae.encoder.block_res_blocks.1.2.norm2.bias": "model.safetensors",
430
+ "temporal_vae.encoder.block_res_blocks.1.2.norm2.weight": "model.safetensors",
431
+ "temporal_vae.encoder.block_res_blocks.1.3.conv1.conv.weight": "model.safetensors",
432
+ "temporal_vae.encoder.block_res_blocks.1.3.conv2.conv.weight": "model.safetensors",
433
+ "temporal_vae.encoder.block_res_blocks.1.3.norm1.bias": "model.safetensors",
434
+ "temporal_vae.encoder.block_res_blocks.1.3.norm1.weight": "model.safetensors",
435
+ "temporal_vae.encoder.block_res_blocks.1.3.norm2.bias": "model.safetensors",
436
+ "temporal_vae.encoder.block_res_blocks.1.3.norm2.weight": "model.safetensors",
437
+ "temporal_vae.encoder.block_res_blocks.2.0.conv1.conv.weight": "model.safetensors",
438
+ "temporal_vae.encoder.block_res_blocks.2.0.conv2.conv.weight": "model.safetensors",
439
+ "temporal_vae.encoder.block_res_blocks.2.0.norm1.bias": "model.safetensors",
440
+ "temporal_vae.encoder.block_res_blocks.2.0.norm1.weight": "model.safetensors",
441
+ "temporal_vae.encoder.block_res_blocks.2.0.norm2.bias": "model.safetensors",
442
+ "temporal_vae.encoder.block_res_blocks.2.0.norm2.weight": "model.safetensors",
443
+ "temporal_vae.encoder.block_res_blocks.2.1.conv1.conv.weight": "model.safetensors",
444
+ "temporal_vae.encoder.block_res_blocks.2.1.conv2.conv.weight": "model.safetensors",
445
+ "temporal_vae.encoder.block_res_blocks.2.1.norm1.bias": "model.safetensors",
446
+ "temporal_vae.encoder.block_res_blocks.2.1.norm1.weight": "model.safetensors",
447
+ "temporal_vae.encoder.block_res_blocks.2.1.norm2.bias": "model.safetensors",
448
+ "temporal_vae.encoder.block_res_blocks.2.1.norm2.weight": "model.safetensors",
449
+ "temporal_vae.encoder.block_res_blocks.2.2.conv1.conv.weight": "model.safetensors",
450
+ "temporal_vae.encoder.block_res_blocks.2.2.conv2.conv.weight": "model.safetensors",
451
+ "temporal_vae.encoder.block_res_blocks.2.2.norm1.bias": "model.safetensors",
452
+ "temporal_vae.encoder.block_res_blocks.2.2.norm1.weight": "model.safetensors",
453
+ "temporal_vae.encoder.block_res_blocks.2.2.norm2.bias": "model.safetensors",
454
+ "temporal_vae.encoder.block_res_blocks.2.2.norm2.weight": "model.safetensors",
455
+ "temporal_vae.encoder.block_res_blocks.2.3.conv1.conv.weight": "model.safetensors",
456
+ "temporal_vae.encoder.block_res_blocks.2.3.conv2.conv.weight": "model.safetensors",
457
+ "temporal_vae.encoder.block_res_blocks.2.3.norm1.bias": "model.safetensors",
458
+ "temporal_vae.encoder.block_res_blocks.2.3.norm1.weight": "model.safetensors",
459
+ "temporal_vae.encoder.block_res_blocks.2.3.norm2.bias": "model.safetensors",
460
+ "temporal_vae.encoder.block_res_blocks.2.3.norm2.weight": "model.safetensors",
461
+ "temporal_vae.encoder.block_res_blocks.3.0.conv1.conv.weight": "model.safetensors",
462
+ "temporal_vae.encoder.block_res_blocks.3.0.conv2.conv.weight": "model.safetensors",
463
+ "temporal_vae.encoder.block_res_blocks.3.0.conv3.conv.weight": "model.safetensors",
464
+ "temporal_vae.encoder.block_res_blocks.3.0.norm1.bias": "model.safetensors",
465
+ "temporal_vae.encoder.block_res_blocks.3.0.norm1.weight": "model.safetensors",
466
+ "temporal_vae.encoder.block_res_blocks.3.0.norm2.bias": "model.safetensors",
467
+ "temporal_vae.encoder.block_res_blocks.3.0.norm2.weight": "model.safetensors",
468
+ "temporal_vae.encoder.block_res_blocks.3.1.conv1.conv.weight": "model.safetensors",
469
+ "temporal_vae.encoder.block_res_blocks.3.1.conv2.conv.weight": "model.safetensors",
470
+ "temporal_vae.encoder.block_res_blocks.3.1.norm1.bias": "model.safetensors",
471
+ "temporal_vae.encoder.block_res_blocks.3.1.norm1.weight": "model.safetensors",
472
+ "temporal_vae.encoder.block_res_blocks.3.1.norm2.bias": "model.safetensors",
473
+ "temporal_vae.encoder.block_res_blocks.3.1.norm2.weight": "model.safetensors",
474
+ "temporal_vae.encoder.block_res_blocks.3.2.conv1.conv.weight": "model.safetensors",
475
+ "temporal_vae.encoder.block_res_blocks.3.2.conv2.conv.weight": "model.safetensors",
476
+ "temporal_vae.encoder.block_res_blocks.3.2.norm1.bias": "model.safetensors",
477
+ "temporal_vae.encoder.block_res_blocks.3.2.norm1.weight": "model.safetensors",
478
+ "temporal_vae.encoder.block_res_blocks.3.2.norm2.bias": "model.safetensors",
479
+ "temporal_vae.encoder.block_res_blocks.3.2.norm2.weight": "model.safetensors",
480
+ "temporal_vae.encoder.block_res_blocks.3.3.conv1.conv.weight": "model.safetensors",
481
+ "temporal_vae.encoder.block_res_blocks.3.3.conv2.conv.weight": "model.safetensors",
482
+ "temporal_vae.encoder.block_res_blocks.3.3.norm1.bias": "model.safetensors",
483
+ "temporal_vae.encoder.block_res_blocks.3.3.norm1.weight": "model.safetensors",
484
+ "temporal_vae.encoder.block_res_blocks.3.3.norm2.bias": "model.safetensors",
485
+ "temporal_vae.encoder.block_res_blocks.3.3.norm2.weight": "model.safetensors",
486
+ "temporal_vae.encoder.conv2.conv.bias": "model.safetensors",
487
+ "temporal_vae.encoder.conv2.conv.weight": "model.safetensors",
488
+ "temporal_vae.encoder.conv_blocks.1.conv.bias": "model.safetensors",
489
+ "temporal_vae.encoder.conv_blocks.1.conv.weight": "model.safetensors",
490
+ "temporal_vae.encoder.conv_blocks.2.conv.bias": "model.safetensors",
491
+ "temporal_vae.encoder.conv_blocks.2.conv.weight": "model.safetensors",
492
+ "temporal_vae.encoder.conv_in.conv.weight": "model.safetensors",
493
+ "temporal_vae.encoder.norm1.bias": "model.safetensors",
494
+ "temporal_vae.encoder.norm1.weight": "model.safetensors",
495
+ "temporal_vae.encoder.res_blocks.0.conv1.conv.weight": "model.safetensors",
496
+ "temporal_vae.encoder.res_blocks.0.conv2.conv.weight": "model.safetensors",
497
+ "temporal_vae.encoder.res_blocks.0.norm1.bias": "model.safetensors",
498
+ "temporal_vae.encoder.res_blocks.0.norm1.weight": "model.safetensors",
499
+ "temporal_vae.encoder.res_blocks.0.norm2.bias": "model.safetensors",
500
+ "temporal_vae.encoder.res_blocks.0.norm2.weight": "model.safetensors",
501
+ "temporal_vae.encoder.res_blocks.1.conv1.conv.weight": "model.safetensors",
502
+ "temporal_vae.encoder.res_blocks.1.conv2.conv.weight": "model.safetensors",
503
+ "temporal_vae.encoder.res_blocks.1.norm1.bias": "model.safetensors",
504
+ "temporal_vae.encoder.res_blocks.1.norm1.weight": "model.safetensors",
505
+ "temporal_vae.encoder.res_blocks.1.norm2.bias": "model.safetensors",
506
+ "temporal_vae.encoder.res_blocks.1.norm2.weight": "model.safetensors",
507
+ "temporal_vae.encoder.res_blocks.2.conv1.conv.weight": "model.safetensors",
508
+ "temporal_vae.encoder.res_blocks.2.conv2.conv.weight": "model.safetensors",
509
+ "temporal_vae.encoder.res_blocks.2.norm1.bias": "model.safetensors",
510
+ "temporal_vae.encoder.res_blocks.2.norm1.weight": "model.safetensors",
511
+ "temporal_vae.encoder.res_blocks.2.norm2.bias": "model.safetensors",
512
+ "temporal_vae.encoder.res_blocks.2.norm2.weight": "model.safetensors",
513
+ "temporal_vae.encoder.res_blocks.3.conv1.conv.weight": "model.safetensors",
514
+ "temporal_vae.encoder.res_blocks.3.conv2.conv.weight": "model.safetensors",
515
+ "temporal_vae.encoder.res_blocks.3.norm1.bias": "model.safetensors",
516
+ "temporal_vae.encoder.res_blocks.3.norm1.weight": "model.safetensors",
517
+ "temporal_vae.encoder.res_blocks.3.norm2.bias": "model.safetensors",
518
+ "temporal_vae.encoder.res_blocks.3.norm2.weight": "model.safetensors",
519
+ "temporal_vae.post_quant_conv.conv.bias": "model.safetensors",
520
+ "temporal_vae.post_quant_conv.conv.weight": "model.safetensors",
521
+ "temporal_vae.quant_conv.conv.bias": "model.safetensors",
522
+ "temporal_vae.quant_conv.conv.weight": "model.safetensors"
523
+ }
524
+ }