Hugging Face's logo

FastVideo
/
FastVideo-FastH3-Trim-8-Step

Text-to-Video
Diffusers
Safetensors
MiniMaxH3ModularPipeline
video-generation
audio
fastvideo
bf16
pruned
Model card Files
xet
 Community
aryan5v commited on
Commit
016911e
·
verified ·
1 Parent(s): 6a7a7b5

Add audio_vae

Browse files
Files changed (2) hide show
  1. audio_vae/config.json +125 -0
  2. audio_vae/diffusion_pytorch_model.safetensors +3 -0
audio_vae/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLMiniMaxH3Audio",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "encoder_dim": 64,
5
+ "encoder_rates": [
6
+ 2,
7
+ 4,
8
+ 4,
9
+ 5,
10
+ 5
11
+ ],
12
+ "latent_dim": 2048,
13
+ "latent_channels": 32,
14
+ "decoder_dim": 1024,
15
+ "decoder_rates": [
16
+ 5,
17
+ 5,
18
+ 2,
19
+ 2,
20
+ 2,
21
+ 2,
22
+ 2
23
+ ],
24
+ "decoder_kernel_sizes": [
25
+ 9,
26
+ 9,
27
+ 4,
28
+ 4,
29
+ 4,
30
+ 4,
31
+ 4
32
+ ],
33
+ "num_attention_heads": 8,
34
+ "resblock_kernel_sizes": [
35
+ 3,
36
+ 7,
37
+ 11
38
+ ],
39
+ "resblock_dilation_sizes": [
40
+ [
41
+ 1,
42
+ 3,
43
+ 5
44
+ ],
45
+ [
46
+ 1,
47
+ 3,
48
+ 5
49
+ ],
50
+ [
51
+ 1,
52
+ 3,
53
+ 5
54
+ ]
55
+ ],
56
+ "sampling_rate": 32000,
57
+ "latents_mean": [
58
+ -0.020211687488382354,
59
+ 0.3876466479950502,
60
+ -0.04398279799186767,
61
+ -0.28591514936373,
62
+ 0.08179686214561671,
63
+ -0.35782641352446604,
64
+ 0.040623809960919084,
65
+ -0.01552534501956604,
66
+ -0.223362481667332,
67
+ 0.1821006842509091,
68
+ 0.2941778783780663,
69
+ -0.07901167601970885,
70
+ -0.056815072777201,
71
+ -0.3699028221860095,
72
+ -0.31616315591624855,
73
+ 0.5905951377425391,
74
+ -0.052139568068853864,
75
+ 0.013673160263486295,
76
+ -0.03691647864630577,
77
+ 0.09732660653298163,
78
+ -0.3394662328788498,
79
+ -0.30685677538541667,
80
+ -0.24504598907458763,
81
+ -0.034698524462007344,
82
+ 0.02868032184767538,
83
+ -0.21217779266454084,
84
+ -0.1678263169941987,
85
+ 0.3221287889040614,
86
+ -0.1223055851554907,
87
+ 0.4356604928128464,
88
+ -0.0502599202236253,
89
+ 0.3979258376211797
90
+ ],
91
+ "latents_std": [
92
+ 1.6895524230479284,
93
+ 2.76263727217653,
94
+ 1.7945344281264435,
95
+ 1.6801681847309828,
96
+ 1.6390226546605453,
97
+ 2.7788298348882177,
98
+ 1.7659090095747236,
99
+ 1.6199757612137327,
100
+ 2.6336525640336896,
101
+ 1.8539356672817833,
102
+ 2.5056497896915633,
103
+ 1.811019237886178,
104
+ 1.9579657790720237,
105
+ 1.6685498243529284,
106
+ 1.4922469314453364,
107
+ 3.298670198067373,
108
+ 1.9491804496832168,
109
+ 1.8720003270431442,
110
+ 1.8334080103291832,
111
+ 1.6488070416529093,
112
+ 1.6176957696319716,
113
+ 1.9131449234774398,
114
+ 1.5695245398428617,
115
+ 1.6943659940415912,
116
+ 1.8318420762504692,
117
+ 1.5540637421583379,
118
+ 1.9344930328968526,
119
+ 1.599198216109855,
120
+ 1.718045989838149,
121
+ 1.6307219190837705,
122
+ 1.8661226051202384,
123
+ 1.5613768203168363
124
+ ]
125
+ }
audio_vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c59e67ba8de5477c81bfbced0327aabf500f1bfdeefd5ee754529241cb26cb
3
+ size 605429340