adding: print statements to all ff_attn_fn affected blocks.

src/diffusers/models/attention.py

@@ -211,6 +211,7 @@ class BasicTransformerBlock(nn.Module):
         final_dropout: bool = False,
     ):
         super().__init__()
+        print(f"Using {activation_fn} as activation_fn in BasicTransformerBlock.")
         self.only_cross_attention = only_cross_attention
 
         self.use_ada_layer_norm_zero = (num_embeds_ada_norm is not None) and norm_type == "ada_norm_zero"

src/diffusers/models/transformer_2d.py

@@ -104,6 +104,7 @@ class Transformer2DModel(ModelMixin, ConfigMixin):
         self.num_attention_heads = num_attention_heads
         self.attention_head_dim = attention_head_dim
         inner_dim = num_attention_heads * attention_head_dim
+        print(f"Using {activation_fn} as activation_fn in Transformer2DModel.")
 
         # 1. Transformer2DModel can process both standard continous images of shape `(batch_size, num_channels, width, height)` as well as quantized image embeddings of shape `(batch_size, num_image_vectors)`
         # Define whether input is continuous or discrete depending on configuration

src/diffusers/models/unet_2d_blocks.py

@@ -468,6 +468,7 @@ class UNetMidBlock2DCrossAttn(nn.Module):
         ff_activation_fn="geglu",
     ):
         super().__init__()
+        print(f"Using {ff_activation_fn} as ff_activation_fn in UNetMidBlock2DCrossAttn")
 
         self.has_cross_attention = True
         self.attn_num_head_channels = attn_num_head_channels

src/diffusers/models/unet_2d_condition.py

@@ -151,6 +151,7 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin)
         ff_activation_fn="geglu",
     ):
         super().__init__()
+        print(f"Using {ff_activation_fn} as ff_activation_fn in UNet2DConditionModel")
 
         self.sample_size = sample_size