• diffusers库中stable Diffusion模块的解析

    diffusers库中stable Diffusion模块的解析

    diffusers中，stable Diffusion v1.5主要由以下几个部分组成

    Out[3]: dict_keys(['vae', 'text_encoder', 'tokenizer', 'unet', 'scheduler', 'safety_checker', 'feature_extractor'])

    • 1

    下面给出具体的结构说明。

    “text_encoder block”

    CLIPTextModel(
  (text_model): CLIPTextTransformer(
    (embeddings): CLIPTextEmbeddings(
      (token_embedding): Embedding(49408, 768)
      (position_embedding): Embedding(77, 768)
    )
    (encoder): CLIPEncoder(
      (layers): ModuleList(
        (0-11): 12 x CLIPEncoderLayer(
          (self_attn): CLIPAttention(
            (k_proj): Linear(in_features=768, out_features=768, bias=True)
            (v_proj): Linear(in_features=768, out_features=768, bias=True)
            (q_proj): Linear(in_features=768, out_features=768, bias=True)
            (out_proj): Linear(in_features=768, out_features=768, bias=True)
          )
          (layer_norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): CLIPMLP(
            (activation_fn): QuickGELUActivation()
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
          )
          (layer_norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
      )
    )
    (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
  )
)

    • 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

    “vae block”

    AutoencoderKL(
  (encoder): Encoder(
    (conv_in): Conv2d(3, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (down_blocks): ModuleList(
      (0): DownEncoderBlock2D(
        (resnets): ModuleList(
          (0-1): 2 x ResnetBlock2D(
            (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
          )
        )
        (downsamplers): ModuleList(
          (0): Downsample2D(
            (conv): LoRACompatibleConv(128, 128, kernel_size=(3, 3), stride=(2, 2))
          )
        )
      )
      (1): DownEncoderBlock2D(
        (resnets): ModuleList(
          (0): ResnetBlock2D(
            (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
            (conv_shortcut): LoRACompatibleConv(128, 256, kernel_size=(1, 1), stride=(1, 1))
          )
          (1): ResnetBlock2D(
            (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
          )
        )
        (downsamplers): ModuleList(
          (0): Downsample2D(
            (conv): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(2, 2))
          )
        )
      )
      (2): DownEncoderBlock2D(
        (resnets): ModuleList(
          (0): ResnetBlock2D(
            (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
            (conv_shortcut): LoRACompatibleConv(256, 512, kernel_size=(1, 1), stride=(1, 1))
          )
          (1): ResnetBlock2D(
            (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
          )
        )
        (downsamplers): ModuleList(
          (0): Downsample2D(
            (conv): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(2, 2))
          )
        )
      )
      (3): DownEncoderBlock2D(
        (resnets): ModuleList(
          (0-1): 2 x ResnetBlock2D(
            (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
          )
        )
      )
    )
    (mid_block): UNetMidBlock2D(
      (attentions): ModuleList(
        (0): Attention(
          (group_norm): GroupNorm(32, 512, eps=1e-06, affine=True)
          (to_q): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
          (to_k): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
          (to_v): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
          (to_out): ModuleList(
            (0): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
            (1): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (resnets): ModuleList(
        (0-1): 2 x ResnetBlock2D(
          (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
          (conv1): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
        )
      )
    )
    (conv_norm_out): GroupNorm(32, 512, eps=1e-06, affine=True)
    (conv_act): SiLU()
    (conv_out): Conv2d(512, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  )
  (decoder): Decoder(
    (conv_in): Conv2d(4, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (up_blocks): ModuleList(
      (0-1): 2 x UpDecoderBlock2D(
        (resnets): ModuleList(
          (0-2): 3 x ResnetBlock2D(
            (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
          )
        )
        (upsamplers): ModuleList(
          (0): Upsample2D(
            (conv): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          )
        )
      )
      (2): UpDecoderBlock2D(
        (resnets): ModuleList(
          (0): ResnetBlock2D(
            (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
            (conv_shortcut): LoRACompatibleConv(512, 256, kernel_size=(1, 1), stride=(1, 1))
          )
          (1-2): 2 x ResnetBlock2D(
            (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
          )
        )
        (upsamplers): ModuleList(
          (0): Upsample2D(
            (conv): LoRACompatibleConv(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          )
        )
      )
      (3): UpDecoderBlock2D(
        (resnets): ModuleList(
          (0): ResnetBlock2D(
            (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
            (conv_shortcut): LoRACompatibleConv(256, 128, kernel_size=(1, 1), stride=(1, 1))
          )
          (1-2): 2 x ResnetBlock2D(
            (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)
            (conv1): LoRACompatibleConv(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)
            (dropout): Dropout(p=0.0, inplace=False)
            (conv2): LoRACompatibleConv(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (nonlinearity): SiLU()
          )
        )
      )
    )
    (mid_block): UNetMidBlock2D(
      (attentions): ModuleList(
        (0): Attention(
          (group_norm): GroupNorm(32, 512, eps=1e-06, affine=True)
          (to_q): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
          (to_k): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
          (to_v): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
          (to_out): ModuleList(
            (0): LoRACompatibleLinear(in_features=512, out_features=512, bias=True)
            (1): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (resnets): ModuleList(
        (0-1): 2 x ResnetBlock2D(
          (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
          (conv1): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
        )
      )
    )
    (conv_norm_out): GroupNorm(32, 128, eps=1e-06, affine=True)
    (conv_act): SiLU()
    (conv_out): Conv2d(128, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  )
  (quant_conv): Conv2d(8, 8, kernel_size=(1, 1), stride=(1, 1))
  (post_quant_conv): Conv2d(4, 4, kernel_size=(1, 1), stride=(1, 1))
)

    • 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
    • 112
    • 113
    • 114
    • 115
    • 116
    • 117
    • 118
    • 119
    • 120
    • 121
    • 122
    • 123
    • 124
    • 125
    • 126
    • 127
    • 128
    • 129
    • 130
    • 131
    • 132
    • 133
    • 134
    • 135
    • 136
    • 137
    • 138
    • 139
    • 140
    • 141
    • 142
    • 143
    • 144
    • 145
    • 146
    • 147
    • 148
    • 149
    • 150
    • 151
    • 152
    • 153
    • 154
    • 155
    • 156
    • 157
    • 158
    • 159
    • 160
    • 161
    • 162
    • 163
    • 164
    • 165
    • 166
    • 167
    • 168
    • 169
    • 170
    • 171
    • 172
    • 173
    • 174
    • 175
    • 176
    • 177
    • 178
    • 179
    • 180
    • 181
    • 182
    • 183
    • 184
    • 185
    • 186
    • 187
    • 188
    • 189
    • 190
    • 191
    • 192
    • 193
    • 194
    • 195
    • 196
    • 197
    • 198
    • 199
    • 200
    • 201
    • 202
    • 203
    • 204
    • 205
    • 206
    • 207
    • 208
    • 209
    • 210
    • 211
    • 212
    • 213

    “unet block”

    UNet2DConditionModel(
  (conv_in): Conv2d(4, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (time_proj): Timesteps()
  (time_embedding): TimestepEmbedding(
    (linear_1): LoRACompatibleLinear(in_features=320, out_features=1280, bias=True)
    (act): SiLU()
    (linear_2): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
  )
  (down_blocks): ModuleList(
    (0): CrossAttnDownBlock2D(
      (attentions): ModuleList(
        (0-1): 2 x Transformer2DModel(
          (norm): GroupNorm(32, 320, eps=1e-06, affine=True)
          (proj_in): LoRACompatibleConv(320, 320, kernel_size=(1, 1), stride=(1, 1))
          (transformer_blocks): ModuleList(
            (0): BasicTransformerBlock(
              (norm1): LayerNorm((320,), eps=1e-05, elementwise_affine=True)
              (attn1): Attention(
                (to_q): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_k): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_v): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=320, out_features=320, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm2): LayerNorm((320,), eps=1e-05, elementwise_affine=True)
              (attn2): Attention(
                (to_q): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_k): LoRACompatibleLinear(in_features=768, out_features=320, bias=False)
                (to_v): LoRACompatibleLinear(in_features=768, out_features=320, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=320, out_features=320, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm3): LayerNorm((320,), eps=1e-05, elementwise_affine=True)
              (ff): FeedForward(
                (net): ModuleList(
                  (0): GEGLU(
                    (proj): LoRACompatibleLinear(in_features=320, out_features=2560, bias=True)
                  )
                  (1): Dropout(p=0.0, inplace=False)
                  (2): LoRACompatibleLinear(in_features=1280, out_features=320, bias=True)
                )
              )
            )
          )
          (proj_out): LoRACompatibleConv(320, 320, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (resnets): ModuleList(
        (0-1): 2 x ResnetBlock2D(
          (norm1): GroupNorm(32, 320, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=320, bias=True)
          (norm2): GroupNorm(32, 320, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
        )
      )
      (downsamplers): ModuleList(
        (0): Downsample2D(
          (conv): LoRACompatibleConv(320, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
        )
      )
    )
    (1): CrossAttnDownBlock2D(
      (attentions): ModuleList(
        (0-1): 2 x Transformer2DModel(
          (norm): GroupNorm(32, 640, eps=1e-06, affine=True)
          (proj_in): LoRACompatibleConv(640, 640, kernel_size=(1, 1), stride=(1, 1))
          (transformer_blocks): ModuleList(
            (0): BasicTransformerBlock(
              (norm1): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
              (attn1): Attention(
                (to_q): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_k): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_v): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=640, out_features=640, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm2): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
              (attn2): Attention(
                (to_q): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_k): LoRACompatibleLinear(in_features=768, out_features=640, bias=False)
                (to_v): LoRACompatibleLinear(in_features=768, out_features=640, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=640, out_features=640, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm3): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
              (ff): FeedForward(
                (net): ModuleList(
                  (0): GEGLU(
                    (proj): LoRACompatibleLinear(in_features=640, out_features=5120, bias=True)
                  )
                  (1): Dropout(p=0.0, inplace=False)
                  (2): LoRACompatibleLinear(in_features=2560, out_features=640, bias=True)
                )
              )
            )
          )
          (proj_out): LoRACompatibleConv(640, 640, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (resnets): ModuleList(
        (0): ResnetBlock2D(
          (norm1): GroupNorm(32, 320, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(320, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=640, bias=True)
          (norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(320, 640, kernel_size=(1, 1), stride=(1, 1))
        )
        (1): ResnetBlock2D(
          (norm1): GroupNorm(32, 640, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=640, bias=True)
          (norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
        )
      )
      (downsamplers): ModuleList(
        (0): Downsample2D(
          (conv): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
        )
      )
    )
    (2): CrossAttnDownBlock2D(
      (attentions): ModuleList(
        (0-1): 2 x Transformer2DModel(
          (norm): GroupNorm(32, 1280, eps=1e-06, affine=True)
          (proj_in): LoRACompatibleConv(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
          (transformer_blocks): ModuleList(
            (0): BasicTransformerBlock(
              (norm1): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
              (attn1): Attention(
                (to_q): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_k): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_v): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm2): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
              (attn2): Attention(
                (to_q): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_k): LoRACompatibleLinear(in_features=768, out_features=1280, bias=False)
                (to_v): LoRACompatibleLinear(in_features=768, out_features=1280, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm3): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
              (ff): FeedForward(
                (net): ModuleList(
                  (0): GEGLU(
                    (proj): LoRACompatibleLinear(in_features=1280, out_features=10240, bias=True)
                  )
                  (1): Dropout(p=0.0, inplace=False)
                  (2): LoRACompatibleLinear(in_features=5120, out_features=1280, bias=True)
                )
              )
            )
          )
          (proj_out): LoRACompatibleConv(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (resnets): ModuleList(
        (0): ResnetBlock2D(
          (norm1): GroupNorm(32, 640, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(640, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
          (norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(640, 1280, kernel_size=(1, 1), stride=(1, 1))
        )
        (1): ResnetBlock2D(
          (norm1): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
          (norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
        )
      )
      (downsamplers): ModuleList(
        (0): Downsample2D(
          (conv): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
        )
      )
    )
    (3): DownBlock2D(
      (resnets): ModuleList(
        (0-1): 2 x ResnetBlock2D(
          (norm1): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
          (norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
        )
      )
    )
  )
  (up_blocks): ModuleList(
    (0): UpBlock2D(
      (resnets): ModuleList(
        (0-2): 3 x ResnetBlock2D(
          (norm1): GroupNorm(32, 2560, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(2560, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
          (norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(2560, 1280, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (upsamplers): ModuleList(
        (0): Upsample2D(
          (conv): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        )
      )
    )
    (1): CrossAttnUpBlock2D(
      (attentions): ModuleList(
        (0-2): 3 x Transformer2DModel(
          (norm): GroupNorm(32, 1280, eps=1e-06, affine=True)
          (proj_in): LoRACompatibleConv(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
          (transformer_blocks): ModuleList(
            (0): BasicTransformerBlock(
              (norm1): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
              (attn1): Attention(
                (to_q): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_k): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_v): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm2): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
              (attn2): Attention(
                (to_q): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
                (to_k): LoRACompatibleLinear(in_features=768, out_features=1280, bias=False)
                (to_v): LoRACompatibleLinear(in_features=768, out_features=1280, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm3): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
              (ff): FeedForward(
                (net): ModuleList(
                  (0): GEGLU(
                    (proj): LoRACompatibleLinear(in_features=1280, out_features=10240, bias=True)
                  )
                  (1): Dropout(p=0.0, inplace=False)
                  (2): LoRACompatibleLinear(in_features=5120, out_features=1280, bias=True)
                )
              )
            )
          )
          (proj_out): LoRACompatibleConv(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (resnets): ModuleList(
        (0-1): 2 x ResnetBlock2D(
          (norm1): GroupNorm(32, 2560, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(2560, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
          (norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(2560, 1280, kernel_size=(1, 1), stride=(1, 1))
        )
        (2): ResnetBlock2D(
          (norm1): GroupNorm(32, 1920, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(1920, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
          (norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(1920, 1280, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (upsamplers): ModuleList(
        (0): Upsample2D(
          (conv): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        )
      )
    )
    (2): CrossAttnUpBlock2D(
      (attentions): ModuleList(
        (0-2): 3 x Transformer2DModel(
          (norm): GroupNorm(32, 640, eps=1e-06, affine=True)
          (proj_in): LoRACompatibleConv(640, 640, kernel_size=(1, 1), stride=(1, 1))
          (transformer_blocks): ModuleList(
            (0): BasicTransformerBlock(
              (norm1): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
              (attn1): Attention(
                (to_q): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_k): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_v): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=640, out_features=640, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm2): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
              (attn2): Attention(
                (to_q): LoRACompatibleLinear(in_features=640, out_features=640, bias=False)
                (to_k): LoRACompatibleLinear(in_features=768, out_features=640, bias=False)
                (to_v): LoRACompatibleLinear(in_features=768, out_features=640, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=640, out_features=640, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm3): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
              (ff): FeedForward(
                (net): ModuleList(
                  (0): GEGLU(
                    (proj): LoRACompatibleLinear(in_features=640, out_features=5120, bias=True)
                  )
                  (1): Dropout(p=0.0, inplace=False)
                  (2): LoRACompatibleLinear(in_features=2560, out_features=640, bias=True)
                )
              )
            )
          )
          (proj_out): LoRACompatibleConv(640, 640, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (resnets): ModuleList(
        (0): ResnetBlock2D(
          (norm1): GroupNorm(32, 1920, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(1920, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=640, bias=True)
          (norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(1920, 640, kernel_size=(1, 1), stride=(1, 1))
        )
        (1): ResnetBlock2D(
          (norm1): GroupNorm(32, 1280, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(1280, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=640, bias=True)
          (norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(1280, 640, kernel_size=(1, 1), stride=(1, 1))
        )
        (2): ResnetBlock2D(
          (norm1): GroupNorm(32, 960, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(960, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=640, bias=True)
          (norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(960, 640, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (upsamplers): ModuleList(
        (0): Upsample2D(
          (conv): LoRACompatibleConv(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        )
      )
    )
    (3): CrossAttnUpBlock2D(
      (attentions): ModuleList(
        (0-2): 3 x Transformer2DModel(
          (norm): GroupNorm(32, 320, eps=1e-06, affine=True)
          (proj_in): LoRACompatibleConv(320, 320, kernel_size=(1, 1), stride=(1, 1))
          (transformer_blocks): ModuleList(
            (0): BasicTransformerBlock(
              (norm1): LayerNorm((320,), eps=1e-05, elementwise_affine=True)
              (attn1): Attention(
                (to_q): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_k): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_v): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=320, out_features=320, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm2): LayerNorm((320,), eps=1e-05, elementwise_affine=True)
              (attn2): Attention(
                (to_q): LoRACompatibleLinear(in_features=320, out_features=320, bias=False)
                (to_k): LoRACompatibleLinear(in_features=768, out_features=320, bias=False)
                (to_v): LoRACompatibleLinear(in_features=768, out_features=320, bias=False)
                (to_out): ModuleList(
                  (0): LoRACompatibleLinear(in_features=320, out_features=320, bias=True)
                  (1): Dropout(p=0.0, inplace=False)
                )
              )
              (norm3): LayerNorm((320,), eps=1e-05, elementwise_affine=True)
              (ff): FeedForward(
                (net): ModuleList(
                  (0): GEGLU(
                    (proj): LoRACompatibleLinear(in_features=320, out_features=2560, bias=True)
                  )
                  (1): Dropout(p=0.0, inplace=False)
                  (2): LoRACompatibleLinear(in_features=1280, out_features=320, bias=True)
                )
              )
            )
          )
          (proj_out): LoRACompatibleConv(320, 320, kernel_size=(1, 1), stride=(1, 1))
        )
      )
      (resnets): ModuleList(
        (0): ResnetBlock2D(
          (norm1): GroupNorm(32, 960, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(960, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=320, bias=True)
          (norm2): GroupNorm(32, 320, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(960, 320, kernel_size=(1, 1), stride=(1, 1))
        )
        (1-2): 2 x ResnetBlock2D(
          (norm1): GroupNorm(32, 640, eps=1e-05, affine=True)
          (conv1): LoRACompatibleConv(640, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=320, bias=True)
          (norm2): GroupNorm(32, 320, eps=1e-05, affine=True)
          (dropout): Dropout(p=0.0, inplace=False)
          (conv2): LoRACompatibleConv(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (nonlinearity): SiLU()
          (conv_shortcut): LoRACompatibleConv(640, 320, kernel_size=(1, 1), stride=(1, 1))
        )
      )
    )
  )
  (mid_block): UNetMidBlock2DCrossAttn(
    (attentions): ModuleList(
      (0): Transformer2DModel(
        (norm): GroupNorm(32, 1280, eps=1e-06, affine=True)
        (proj_in): LoRACompatibleConv(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
        (transformer_blocks): ModuleList(
          (0): BasicTransformerBlock(
            (norm1): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
            (attn1): Attention(
              (to_q): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
              (to_k): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
              (to_v): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
              (to_out): ModuleList(
                (0): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
                (1): Dropout(p=0.0, inplace=False)
              )
            )
            (norm2): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
            (attn2): Attention(
              (to_q): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=False)
              (to_k): LoRACompatibleLinear(in_features=768, out_features=1280, bias=False)
              (to_v): LoRACompatibleLinear(in_features=768, out_features=1280, bias=False)
              (to_out): ModuleList(
                (0): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
                (1): Dropout(p=0.0, inplace=False)
              )
            )
            (norm3): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
            (ff): FeedForward(
              (net): ModuleList(
                (0): GEGLU(
                  (proj): LoRACompatibleLinear(in_features=1280, out_features=10240, bias=True)
                )
                (1): Dropout(p=0.0, inplace=False)
                (2): LoRACompatibleLinear(in_features=5120, out_features=1280, bias=True)
              )
            )
          )
        )
        (proj_out): LoRACompatibleConv(1280, 1280, kernel_size=(1, 1), stride=(1, 1))
      )
    )
    (resnets): ModuleList(
      (0-1): 2 x ResnetBlock2D(
        (norm1): GroupNorm(32, 1280, eps=1e-05, affine=True)
        (conv1): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (time_emb_proj): LoRACompatibleLinear(in_features=1280, out_features=1280, bias=True)
        (norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
        (dropout): Dropout(p=0.0, inplace=False)
        (conv2): LoRACompatibleConv(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (nonlinearity): SiLU()
      )
    )
  )
  (conv_norm_out): GroupNorm(32, 320, eps=1e-05, affine=True)
  (conv_act): SiLU()
  (conv_out): Conv2d(320, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)

    • 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
    • 112
    • 113
    • 114
    • 115
    • 116
    • 117
    • 118
    • 119
    • 120
    • 121
    • 122
    • 123
    • 124
    • 125
    • 126
    • 127
    • 128
    • 129
    • 130
    • 131
    • 132
    • 133
    • 134
    • 135
    • 136
    • 137
    • 138
    • 139
    • 140
    • 141
    • 142
    • 143
    • 144
    • 145
    • 146
    • 147
    • 148
    • 149
    • 150
    • 151
    • 152
    • 153
    • 154
    • 155
    • 156
    • 157
    • 158
    • 159
    • 160
    • 161
    • 162
    • 163
    • 164
    • 165
    • 166
    • 167
    • 168
    • 169
    • 170
    • 171
    • 172
    • 173
    • 174
    • 175
    • 176
    • 177
    • 178
    • 179
    • 180
    • 181
    • 182
    • 183
    • 184
    • 185
    • 186
    • 187
    • 188
    • 189
    • 190
    • 191
    • 192
    • 193
    • 194
    • 195
    • 196
    • 197
    • 198
    • 199
    • 200
    • 201
    • 202
    • 203
    • 204
    • 205
    • 206
    • 207
    • 208
    • 209
    • 210
    • 211
    • 212
    • 213
    • 214
    • 215
    • 216
    • 217
    • 218
    • 219
    • 220
    • 221
    • 222
    • 223
    • 224
    • 225
    • 226
    • 227
    • 228
    • 229
    • 230
    • 231
    • 232
    • 233
    • 234
    • 235
    • 236
    • 237
    • 238
    • 239
    • 240
    • 241
    • 242
    • 243
    • 244
    • 245
    • 246
    • 247
    • 248
    • 249
    • 250
    • 251
    • 252
    • 253
    • 254
    • 255
    • 256
    • 257
    • 258
    • 259
    • 260
    • 261
    • 262
    • 263
    • 264
    • 265
    • 266
    • 267
    • 268
    • 269
    • 270
    • 271
    • 272
    • 273
    • 274
    • 275
    • 276
    • 277
    • 278
    • 279
    • 280
    • 281
    • 282
    • 283
    • 284
    • 285
    • 286
    • 287
    • 288
    • 289
    • 290
    • 291
    • 292
    • 293
    • 294
    • 295
    • 296
    • 297
    • 298
    • 299
    • 300
    • 301
    • 302
    • 303
    • 304
    • 305
    • 306
    • 307
    • 308
    • 309
    • 310
    • 311
    • 312
    • 313
    • 314
    • 315
    • 316
    • 317
    • 318
    • 319
    • 320
    • 321
    • 322
    • 323
    • 324
    • 325
    • 326
    • 327
    • 328
    • 329
    • 330
    • 331
    • 332
    • 333
    • 334
    • 335
    • 336
    • 337
    • 338
    • 339
    • 340
    • 341
    • 342
    • 343
    • 344
    • 345
    • 346
    • 347
    • 348
    • 349
    • 350
    • 351
    • 352
    • 353
    • 354
    • 355
    • 356
    • 357
    • 358
    • 359
    • 360
    • 361
    • 362
    • 363
    • 364
    • 365
    • 366
    • 367
    • 368
    • 369
    • 370
    • 371
    • 372
    • 373
    • 374
    • 375
    • 376
    • 377
    • 378
    • 379
    • 380
    • 381
    • 382
    • 383
    • 384
    • 385
    • 386
    • 387
    • 388
    • 389
    • 390
    • 391
    • 392
    • 393
    • 394
    • 395
    • 396
    • 397
    • 398
    • 399
    • 400
    • 401
    • 402
    • 403
    • 404
    • 405
    • 406
    • 407
    • 408
    • 409
    • 410
    • 411
    • 412
    • 413
    • 414
    • 415
    • 416
    • 417
    • 418
    • 419
    • 420
    • 421
    • 422
    • 423
    • 424
    • 425
    • 426
    • 427
    • 428
    • 429
    • 430
    • 431
    • 432
    • 433
    • 434
    • 435
    • 436
    • 437
    • 438
    • 439
    • 440
    • 441
    • 442
    • 443
    • 444
    • 445
    • 446
    • 447
    • 448
    • 449
    • 450
    • 451
    • 452
    • 453
    • 454
    • 455
    • 456
    • 457
    • 458
    • 459
    • 460
    • 461
    • 462
    • 463
    • 464
    • 465
    • 466
    • 467
    • 468
    • 469
    • 470
    • 471
    • 472
    • 473
    • 474
    • 475
    • 476
    • 477
    • 478
    • 479
    • 480
    • 481
    • 482
    • 483
    • 484
    • 485
    • 486
    • 487
    • 488
    • 489
    • 490
    • 491
    • 492
    • 493
    • 494
    • 495
    • 496
    • 497
    • 498
    • 499
    • 500
    • 501
    • 502
    • 503
    • 504
    • 505
    • 506
    • 507
    • 508
    • 509
    • 510
    • 511
    • 512
    • 513
    • 514

    “feature extractor block”

    CLIPImageProcessor {
  "crop_size": {
    "height": 224,
    "width": 224
  },
  "do_center_crop": true,
  "do_convert_rgb": true,
  "do_normalize": true,
  "do_rescale": true,
  "do_resize": true,
  "feature_extractor_type": "CLIPFeatureExtractor",
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "CLIPImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "shortest_edge": 224
  },
  "use_square_size": false
}

    • 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

    “tokenizer block”

    CLIPTokenizer(name_or_path='/home/tiger/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/tokenizer', vocab_size=49408, model_max_length=77, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<|startoftext|>', 'eos_token': '<|endoftext|>', 'unk_token': '<|endoftext|>', 'pad_token': '<|endoftext|>'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
        49406: AddedToken("<|startoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),
        49407: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),
}

    • 1
    • 2
    • 3
    • 4

    “safety_checker block”

    StableDiffusionSafetyChecker(
  (vision_model): CLIPVisionModel(
    (vision_model): CLIPVisionTransformer(
      (embeddings): CLIPVisionEmbeddings(
        (patch_embedding): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14), bias=False)
        (position_embedding): Embedding(257, 1024)
      )
      (pre_layrnorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
      (encoder): CLIPEncoder(
        (layers): ModuleList(
          (0-23): 24 x CLIPEncoderLayer(
            (self_attn): CLIPAttention(
              (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
              (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
            )
            (layer_norm1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
            (mlp): CLIPMLP(
              (activation_fn): QuickGELUActivation()
              (fc1): Linear(in_features=1024, out_features=4096, bias=True)
              (fc2): Linear(in_features=4096, out_features=1024, bias=True)
            )
            (layer_norm2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          )
        )
      )
      (post_layernorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
    )
  )
  (visual_projection): Linear(in_features=1024, out_features=768, bias=False)
)

    • 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

    “scheduler block”

    PNDMScheduler {
  "_class_name": "PNDMScheduler",
  "_diffusers_version": "0.22.3",
  "beta_end": 0.012,
  "beta_schedule": "scaled_linear",
  "beta_start": 0.00085,
  "clip_sample": false,
  "num_train_timesteps": 1000,
  "prediction_type": "epsilon",
  "set_alpha_to_one": false,
  "skip_prk_steps": true,
  "steps_offset": 1,
  "timestep_spacing": "leading",
  "trained_betas": null
}

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    • 8
    • 9
    • 10
    • 11
    • 12
    • 13
    • 14
    • 15
  • 相关阅读:
    JAVA微服务知识概述
    quarkus依赖注入之十：学习和改变bean懒加载规则
    【数字电路基础】格雷码、二进制码与格雷码的转换、独热码
    Java项目-文件搜索工具
    第一百四十五回 如何给组件添加阴影
    基于Bézier曲线的三维造型与渲染
    MobileNetv1论文详解
    Git命令总结-常用-后续使用频繁的再添加~
    06-spring的beanFactoryPostProcessor的执行
    〖全域运营实战白宝书 - 高转化文案速成篇②〗- 快速找到产品卖点的N个小技巧
  • 原文地址：https://blog.csdn.net/u012526003/article/details/134356299