Add support for unCLIP SD2.x models.

See _for_testing/unclip in the UI for the new nodes.

unCLIPCheckpointLoader is used to load them.

unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.

comfy/ldm/modules/diffusionmodules/openaimodel.py

@@ -409,6 +409,15 @@ class QKVAttention(nn.Module):
         return count_flops_attn(model, _x, y)
 
 
+class Timestep(nn.Module):
+    def __init__(self, dim):
+        super().__init__()
+        self.dim = dim
+
+    def forward(self, t):
+        return timestep_embedding(t, self.dim)
+
+
 class UNetModel(nn.Module):
     """
     The full UNet model with attention and timestep embedding.
@@ -470,6 +479,7 @@ class UNetModel(nn.Module):
         num_attention_blocks=None,
         disable_middle_self_attn=False,
         use_linear_in_transformer=False,
+        adm_in_channels=None,
     ):
         super().__init__()
         if use_spatial_transformer:
@@ -538,6 +548,15 @@ class UNetModel(nn.Module):
             elif self.num_classes == "continuous":
                 print("setting up linear c_adm embedding layer")
                 self.label_emb = nn.Linear(1, time_embed_dim)
+            elif self.num_classes == "sequential":
+                assert adm_in_channels is not None
+                self.label_emb = nn.Sequential(
+                    nn.Sequential(
+                        linear(adm_in_channels, time_embed_dim),
+                        nn.SiLU(),
+                        linear(time_embed_dim, time_embed_dim),
+                    )
+                )
             else:
                 raise ValueError()