Update `UNet2DConditionModel`'s error messages (#9230)

* refactor

src/diffusers/models/unets/unet_2d_condition.py

@@ -463,7 +463,6 @@ class UNet2DConditionModel(
                 dropout=dropout,
             )
             self.up_blocks.append(up_block)
-            prev_output_channel = output_channel
 
         # out
         if norm_num_groups is not None:
@@ -599,7 +598,7 @@ class UNet2DConditionModel(
             )
         elif encoder_hid_dim_type is not None:
             raise ValueError(
-                f"encoder_hid_dim_type: {encoder_hid_dim_type} must be None, 'text_proj' or 'text_image_proj'."
+                f"`encoder_hid_dim_type`: {encoder_hid_dim_type} must be None, 'text_proj', 'text_image_proj', or 'image_proj'."
             )
         else:
             self.encoder_hid_proj = None
@@ -679,7 +678,9 @@ class UNet2DConditionModel(
             # Kandinsky 2.2 ControlNet
             self.add_embedding = ImageHintTimeEmbedding(image_embed_dim=encoder_hid_dim, time_embed_dim=time_embed_dim)
         elif addition_embed_type is not None:
-            raise ValueError(f"addition_embed_type: {addition_embed_type} must be None, 'text' or 'text_image'.")
+            raise ValueError(
+                f"`addition_embed_type`: {addition_embed_type} must be None, 'text', 'text_image', 'text_time', 'image', or 'image_hint'."
+            )
 
     def _set_pos_net_if_use_gligen(self, attention_type: str, cross_attention_dim: int):
         if attention_type in ["gated", "gated-text-image"]:
@@ -990,7 +991,7 @@ class UNet2DConditionModel(
             image_embs = added_cond_kwargs.get("image_embeds")
             aug_emb = self.add_embedding(image_embs)
         elif self.config.addition_embed_type == "image_hint":
-            # Kandinsky 2.2 - style
+            # Kandinsky 2.2 ControlNet - style
             if "image_embeds" not in added_cond_kwargs or "hint" not in added_cond_kwargs:
                 raise ValueError(
                     f"{self.__class__} has the config param `addition_embed_type` set to 'image_hint' which requires the keyword arguments `image_embeds` and `hint` to be passed in `added_cond_kwargs`"
@@ -1009,7 +1010,7 @@ class UNet2DConditionModel(
             # Kandinsky 2.1 - style
             if "image_embeds" not in added_cond_kwargs:
                 raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'text_image_proj' which requires the keyword argument `image_embeds` to be passed in  `added_conditions`"
+                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'text_image_proj' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
                 )
 
             image_embeds = added_cond_kwargs.get("image_embeds")
@@ -1018,14 +1019,14 @@ class UNet2DConditionModel(
             # Kandinsky 2.2 - style
             if "image_embeds" not in added_cond_kwargs:
                 raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'image_proj' which requires the keyword argument `image_embeds` to be passed in  `added_conditions`"
+                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'image_proj' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
                 )
             image_embeds = added_cond_kwargs.get("image_embeds")
             encoder_hidden_states = self.encoder_hid_proj(image_embeds)
         elif self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "ip_image_proj":
             if "image_embeds" not in added_cond_kwargs:
                 raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'ip_image_proj' which requires the keyword argument `image_embeds` to be passed in  `added_conditions`"
+                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'ip_image_proj' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
                 )
 
             if hasattr(self, "text_encoder_hid_proj") and self.text_encoder_hid_proj is not None:
@@ -1140,7 +1141,6 @@ class UNet2DConditionModel(
         # 1. time
         t_emb = self.get_time_embed(sample=sample, timestep=timestep)
         emb = self.time_embedding(t_emb, timestep_cond)
-        aug_emb = None
 
         class_emb = self.get_class_embed(sample=sample, class_labels=class_labels)
         if class_emb is not None:

src/diffusers/pipelines/deprecated/versatile_diffusion/modeling_text_unet.py

@@ -546,7 +546,7 @@ class UNetFlatConditionModel(ModelMixin, ConfigMixin):
             )
         elif encoder_hid_dim_type is not None:
             raise ValueError(
-                f"encoder_hid_dim_type: {encoder_hid_dim_type} must be None, 'text_proj' or 'text_image_proj'."
+                f"`encoder_hid_dim_type`: {encoder_hid_dim_type} must be None, 'text_proj', 'text_image_proj' or 'image_proj'."
             )
         else:
             self.encoder_hid_proj = None