Hugging Face's logo

mit-han-lab
/
dc-ae-f128c512-in-1.0-diffusers

Diffusers
Safetensors
Model card Files Community
dc-ae-f128c512-in-1.0-diffusers
File size: 1,572 Bytes 
91f26ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
 
{
  "_class_name": "AutoencoderDC",
  "_diffusers_version": "0.32.0.dev0",
  "attention_head_dim": 32,
  "decoder_act_fns": [
    "relu",
    "relu",
    "relu",
    "silu",
    "silu",
    "silu",
    "silu",
    "silu"
  ],
  "decoder_block_out_channels": [
    128,
    256,
    512,
    512,
    1024,
    1024,
    2048,
    2048
  ],
  "decoder_block_types": [
    "ResBlock",
    "ResBlock",
    "ResBlock",
    "EfficientViTBlock",
    "EfficientViTBlock",
    "EfficientViTBlock",
    "EfficientViTBlock",
    "EfficientViTBlock"
  ],
  "decoder_layers_per_block": [
    0,
    5,
    10,
    2,
    2,
    2,
    2,
    2
  ],
  "decoder_norm_types": [
    "batch_norm",
    "batch_norm",
    "batch_norm",
    "rms_norm",
    "rms_norm",
    "rms_norm",
    "rms_norm",
    "rms_norm"
  ],
  "decoder_qkv_multiscales": [
    [],
    [],
    [],
    [],
    [],
    [],
    [],
    []
  ],
  "downsample_block_type": "pixel_unshuffle",
  "encoder_block_out_channels": [
    128,
    256,
    512,
    512,
    1024,
    1024,
    2048,
    2048
  ],
  "encoder_block_types": [
    "ResBlock",
    "ResBlock",
    "ResBlock",
    "EfficientViTBlock",
    "EfficientViTBlock",
    "EfficientViTBlock",
    "EfficientViTBlock",
    "EfficientViTBlock"
  ],
  "encoder_layers_per_block": [
    0,
    4,
    8,
    2,
    2,
    2,
    2,
    2
  ],
  "encoder_qkv_multiscales": [
    [],
    [],
    [],
    [],
    [],
    [],
    [],
    []
  ],
  "in_channels": 3,
  "latent_channels": 512,
  "scaling_factor": 0.4883,
  "upsample_block_type": "pixel_shuffle"
}