The downsampling blocks have several layers that downsample the images. 

Start by adding different layers in the downsampling blocks. The code in this section is pretty explanatory and can be understood easily:

x = Conv2D(64, (4, 4), padding='same', strides=2, input_shape=(256, 256, 3), use_bias=False)(input_layer)
x = LeakyReLU(alpha=0.2)(x)

x = Conv2D(128, (4, 4), padding='same', strides=2, use_bias=False)(x)
x = BatchNormalization()(x)
x = LeakyReLU(alpha=0.2)(x)

x = Conv2D(256, (4, 4), padding='same', strides=2, use_bias=False)(x)
x = BatchNormalization()(x)
x = LeakyReLU(alpha=0.2)(x)

x = Conv2D(512, (4, 4), padding='same', strides=2, use_bias=False)(x)
x = BatchNormalization()(x)
x = LeakyReLU(alpha=0.2)(x)

x = Conv2D(1024, (4, 4), padding='same', strides=2, use_bias=False)(x)
x = BatchNormalization()(x)
x = LeakyReLU(alpha=0.2)(x)

x = Conv2D(2048, (4, 4), padding='same', strides=2, use_bias=False)(x)
x = BatchNormalization()(x)
x = LeakyReLU(alpha=0.2)(x)

x = Conv2D(1024, (1, 1), padding='same', strides=1, use_bias=False)(x)
x = BatchNormalization()(x)
x = LeakyReLU(alpha=0.2)(x)

x = Conv2D(512, (1, 1), padding='same', strides=1, use_bias=False)(x)
x = BatchNormalization()(x)

x2 = Conv2D(128, (1, 1), padding='same', strides=1, use_bias=False)(x)
x2 = BatchNormalization()(x2)
x2 = LeakyReLU(alpha=0.2)(x2)

x2 = Conv2D(128, (3, 3), padding='same', strides=1, use_bias=False)(x2)
x2 = BatchNormalization()(x2)
x2 = LeakyReLU(alpha=0.2)(x2)

x2 = Conv2D(512, (3, 3), padding='same', strides=1, use_bias=False)(x2)
x2 = BatchNormalization()(x2)

After that, we have two outputs, which are x and x2. Add these two tensors to create a tensor of the same shape. We also need to apply the LeakyReLU activation function:

added_x = add([x, x2])
added_x = LeakyReLU(alpha=0.2)(added_x)