Skip to content

Instantly share code, notes, and snippets.

@xta0

xta0/gist:c928805a004d5b6bd822c7cc79a66387 Secret

Created April 9, 2025 07:52
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save xta0/c928805a004d5b6bd822c7cc79a66387 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save xta0/c928805a004d5b6bd822c7cc79a66387 to your computer and use it in GitHub Desktop.
Download ZIP
vae_encoder
Raw
gistfile1.txt
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): Conv2d(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): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(downsamplers): ModuleList(
(0): Downsample2D(
(conv): Conv2d(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): Conv2d(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): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): ResnetBlock2D(
(norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
(conv1): Conv2d(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): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(downsamplers): ModuleList(
(0): Downsample2D(
(conv): Conv2d(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): Conv2d(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): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1))
)
(1): ResnetBlock2D(
(norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
(conv1): Conv2d(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): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(downsamplers): ModuleList(
(0): Downsample2D(
(conv): Conv2d(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): Conv2d(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): Conv2d(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): Linear(in_features=512, out_features=512, bias=True)
(to_k): Linear(in_features=512, out_features=512, bias=True)
(to_v): Linear(in_features=512, out_features=512, bias=True)
(to_out): ModuleList(
(0): Linear(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): Conv2d(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): Conv2d(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): Conv2d(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): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(upsamplers): ModuleList(
(0): Upsample2D(
(conv): Conv2d(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): Conv2d(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): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1-2): 2 x ResnetBlock2D(
(norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
(conv1): Conv2d(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): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(upsamplers): ModuleList(
(0): Upsample2D(
(conv): Conv2d(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): Conv2d(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): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
)
(1-2): 2 x ResnetBlock2D(
(norm1): GroupNorm(32, 128, eps=1e-06, affine=True)
(conv1): Conv2d(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): Conv2d(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): Linear(in_features=512, out_features=512, bias=True)
(to_k): Linear(in_features=512, out_features=512, bias=True)
(to_v): Linear(in_features=512, out_features=512, bias=True)
(to_out): ModuleList(
(0): Linear(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): Conv2d(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): Conv2d(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))
)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment