Method forward

ldm/modules/diffusionmodules/model.py:758–795

(self, z, enc_fea)

                                        padding=1)

    def forward(self, z, enc_fea):
        #assert z.shape[1:] == self.z_shape[1:]
        self.last_z_shape = z.shape

        # timestep embedding
        temb = None

        # z to block_in
        h = self.conv_in(z)

        # middle
        h = self.mid.block_1(h, temb)
        h = self.mid.attn_1(h)
        h = self.mid.block_2(h, temb)

        # upsampling
        for i_level in reversed(range(self.num_resolutions)):
            for i_block in range(self.num_res_blocks+1):
                h = self.up[i_level].block[i_block](h, temb)
                if len(self.up[i_level].attn) > 0:
                    h = self.up[i_level].attn[i_block](h)

            if i_level != self.num_resolutions-1 and i_level != 0:
                cur_fuse_layer = getattr(self, 'fusion_layer_{}'.format(i_level))
                h = cur_fuse_layer(enc_fea[i_level-1], h, self.fusion_w)

            if i_level != 0:
                h = self.up[i_level].upsample(h)
        # end
        if self.give_pre_end:
            return h

        h = self.norm_out(h)
        h = nonlinearity(h)
        h = self.conv_out(h)
        if self.tanh_out:
            h = torch.tanh(h)
        return h

class ResBlock(nn.Module):
    def __init__(self, in_channels, out_channels=None):