diff --git a/src/diffusers/models/adapter.py b/src/diffusers/models/adapter.py
index bc0c58dc29..0a79995cb4 100644
--- a/src/diffusers/models/adapter.py
+++ b/src/diffusers/models/adapter.py
@@ -136,7 +136,6 @@ class FullAdapter(nn.Module):
         downscale_factor: int = 8,
     ):
         super().__init__()
-        print(f"From {self.__class__} channels: {channels}.")
 
         in_channels = in_channels * downscale_factor**2
 
@@ -164,7 +163,7 @@ class FullAdapter(nn.Module):
         for block in self.body:
             x = block(x)
             features.append(x)
-        print(f"Number of features: {len(features)}")
+        
         return features
 
 
@@ -293,7 +292,7 @@ class LightAdapter(nn.Module):
         for block in self.body:
             x = block(x)
             features.append(x)
-        print(f"Number of features: {len(features)}")
+        
         return features
 
 
diff --git a/src/diffusers/models/unet_2d_condition.py b/src/diffusers/models/unet_2d_condition.py
index f041bf56ae..5695429489 100644
--- a/src/diffusers/models/unet_2d_condition.py
+++ b/src/diffusers/models/unet_2d_condition.py
@@ -920,7 +920,6 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin)
         is_adapter = mid_block_additional_residual is None and down_block_additional_residuals is not None
 
         down_block_res_samples = (sample,)
-        print(f"From UNet before down blocks: {len(down_block_additional_residuals)}")
         for downsample_block in self.down_blocks:
             if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
                 # For t2i-adapter CrossAttnDownBlock2D
@@ -967,7 +966,6 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin)
                 encoder_attention_mask=encoder_attention_mask,
             )
             # To support T2I-Adapter-XL
-            print(f"From UNet in mid block: {len(down_block_additional_residuals)}")
             if is_adapter and len(down_block_additional_residuals) > 0:
                 sample += down_block_additional_residuals.pop(0)
 
diff --git a/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py b/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py
index 3f7e19c754..4aa911198a 100644
--- a/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py
+++ b/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py
@@ -711,7 +711,6 @@ class StableDiffusionAdapterPipeline(DiffusionPipeline):
 
         # 7. Denoising loop
         adapter_state = self.adapter(adapter_input)
-        print(f"From pipeline (before rejigging): {len(adapter_state)}.")
         for k, v in enumerate(adapter_state):
             adapter_state[k] = v * adapter_conditioning_scale
         if num_images_per_prompt > 1:
@@ -720,7 +719,6 @@ class StableDiffusionAdapterPipeline(DiffusionPipeline):
         if do_classifier_free_guidance:
             for k, v in enumerate(adapter_state):
                 adapter_state[k] = torch.cat([v] * 2, dim=0)
-        print(f"From pipeline (after rejigging): {len(adapter_state)}.")
 
         num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
         with self.progress_bar(total=num_inference_steps) as progress_bar: