question about the model architecture

[MaltoseFlower]

I use the following script to print the architecture of BK-SDM-base / SD1.4. I cannot find which block was removed.
from diffusers import DiffusionPipeline pipe = DiffusionPipeline.from_pretrained("nota-ai/bk-sdm-base") # or load CompVis/SD1.4 print(pipe.unet)

SD1.4:
(0): CrossAttnDownBlock2D(
(attentions): ModuleList(
(0-1): 2 x Transformer2DModel(
(norm): GroupNorm(32, 320, eps=1e-06, affine=True)
(proj_in): Conv2d(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): Linear(in_features=320, out_features=320, bias=False)
(to_k): Linear(in_features=320, out_features=320, bias=False)
(to_v): Linear(in_features=320, out_features=320, bias=False)
(to_out): ModuleList(
(0): Linear(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): Linear(in_features=320, out_features=320, bias=False)
(to_k): Linear(in_features=768, out_features=320, bias=False)
(to_v): Linear(in_features=768, out_features=320, bias=False)
(to_out): ModuleList(
(0): Linear(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): Linear(in_features=320, out_features=2560, bias=True)
)
(1): Dropout(p=0.0, inplace=False)
(2): Linear(in_features=1280, out_features=320, bias=True)
)
)
)
)
(proj_out): Conv2d(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): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(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): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(downsamplers): ModuleList(
(0): Downsample2D(
(conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
)

BK-SDM-base
(0): CrossAttnDownBlock2D(
(attentions): ModuleList(
(0): Transformer2DModel(
(norm): GroupNorm(32, 320, eps=1e-06, affine=True)
(proj_in): Conv2d(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): Linear(in_features=320, out_features=320, bias=False)
(to_k): Linear(in_features=320, out_features=320, bias=False)
(to_v): Linear(in_features=320, out_features=320, bias=False)
(to_out): ModuleList(
(0): Linear(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): Linear(in_features=320, out_features=320, bias=False)
(to_k): Linear(in_features=768, out_features=320, bias=False)
(to_v): Linear(in_features=768, out_features=320, bias=False)
(to_out): ModuleList(
(0): Linear(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): Linear(in_features=320, out_features=2560, bias=True)
)
(1): Dropout(p=0.0, inplace=False)
(2): Linear(in_features=1280, out_features=320, bias=True)
)
)
)
)
(proj_out): Conv2d(320, 320, kernel_size=(1, 1), stride=(1, 1))
)
)
(resnets): ModuleList(
(0): ResnetBlock2D(
(norm1): GroupNorm(32, 320, eps=1e-05, affine=True)
(conv1): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(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): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(downsamplers): ModuleList(
(0): Downsample2D(
(conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
)

can u explain about it? thks.