Hugging Face's logo

openai
/
consistency-decoder

Diffusers
Safetensors
stable-diffusion
Model card Files Community
5
consistency-decoder
File size: 2,058 Bytes 
5e6b742
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "_class_name": "ConsistencyDecoderVae",
  "_diffusers_version": "0.23.0.dev0",
  "block_out_channels": [
    128,
    256,
    512,
    512
  ],
  "decoder_args": {
    "_use_default_values": [
      "downsample_type",
      "flip_sin_to_cos",
      "mid_block_scale_factor",
      "num_class_embeds",
      "attention_head_dim",
      "sample_size",
      "act_fn",
      "freq_shift",
      "class_embed_type",
      "attn_norm_num_groups",
      "downsample_padding",
      "upsample_type",
      "dropout",
      "center_input_sample"
    ],
    "act_fn": "silu",
    "add_attention": false,
    "attention_head_dim": 8,
    "attn_norm_num_groups": null,
    "block_out_channels": [
      320,
      640,
      1024,
      1024
    ],
    "center_input_sample": false,
    "class_embed_type": null,
    "down_block_types": [
      "ResnetDownsampleBlock2D",
      "ResnetDownsampleBlock2D",
      "ResnetDownsampleBlock2D",
      "ResnetDownsampleBlock2D"
    ],
    "downsample_padding": 1,
    "downsample_type": "conv",
    "dropout": 0.0,
    "flip_sin_to_cos": true,
    "freq_shift": 0,
    "in_channels": 7,
    "layers_per_block": 3,
    "mid_block_scale_factor": 1,
    "norm_eps": 1e-05,
    "norm_num_groups": 32,
    "num_class_embeds": null,
    "num_train_timesteps": 1024,
    "out_channels": 6,
    "resnet_time_scale_shift": "scale_shift",
    "sample_size": null,
    "time_embedding_type": "learned",
    "up_block_types": [
      "ResnetUpsampleBlock2D",
      "ResnetUpsampleBlock2D",
      "ResnetUpsampleBlock2D",
      "ResnetUpsampleBlock2D"
    ],
    "upsample_type": "conv"
  },
  "encoder_args": {
    "act_fn": "silu",
    "block_out_channels": [
      128,
      256,
      512,
      512
    ],
    "double_z": true,
    "down_block_types": [
      "DownEncoderBlock2D",
      "DownEncoderBlock2D",
      "DownEncoderBlock2D",
      "DownEncoderBlock2D"
    ],
    "in_channels": 3,
    "layers_per_block": 2,
    "norm_num_groups": 32,
    "out_channels": 4
  },
  "latent_channels": 4,
  "scaling_factor": 0.18215
}