diff --git a/examples/community/checkpoint_merger.py b/examples/community/checkpoint_merger.py
index 9df5943a86b1..f702bf0cea9b 100644
--- a/examples/community/checkpoint_merger.py
+++ b/examples/community/checkpoint_merger.py
@@ -138,7 +138,6 @@ def merge(self, pretrained_model_name_or_path_list: List[Union[str, os.PathLike]
             comparison_result &= self._compare_model_configs(config_dicts[idx - 1], config_dicts[idx])
             if not force and comparison_result is False:
                 raise ValueError("Incompatible checkpoints. Please check model_index.json for the models.")
-                print(config_dicts[0], config_dicts[1])
         print("Compatible model_index.json files found")
         # Step 2: Basic Validation has succeeded. Let's download the models and save them into our local files.
         cached_folders = []
diff --git a/examples/community/latent_consistency_img2img.py b/examples/community/latent_consistency_img2img.py
index 98078a2eef96..3c5ffa845699 100644
--- a/examples/community/latent_consistency_img2img.py
+++ b/examples/community/latent_consistency_img2img.py
@@ -240,14 +240,6 @@ def prepare_latents(
 
         return latents
 
-        if latents is None:
-            latents = torch.randn(shape, dtype=dtype).to(device)
-        else:
-            latents = latents.to(device)
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
     def get_w_embedding(self, w, embedding_dim=512, dtype=torch.float32):
         """
         see https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
diff --git a/scripts/convert_zero123_to_diffusers.py b/scripts/convert_zero123_to_diffusers.py
index 669a4962be3c..b46633fae7ff 100644
--- a/scripts/convert_zero123_to_diffusers.py
+++ b/scripts/convert_zero123_to_diffusers.py
@@ -113,7 +113,7 @@ def create_unet_diffusers_config(original_config, image_size: int, controlnet=Fa
             assert "adm_in_channels" in unet_params
             projection_class_embeddings_input_dim = unet_params["adm_in_channels"]
         else:
-            raise NotImplementedError(f"Unknown conditional unet num_classes config: {unet_params["num_classes"]}")
+            raise NotImplementedError(f"Unknown conditional unet num_classes config: {unet_params['num_classes']}")
 
     config = {
         "sample_size": image_size // vae_scale_factor,
diff --git a/src/diffusers/image_processor.py b/src/diffusers/image_processor.py
index 4ccb9d77d627..0f4481570829 100644
--- a/src/diffusers/image_processor.py
+++ b/src/diffusers/image_processor.py
@@ -80,7 +80,6 @@ def __init__(
                 " if you intended to convert the image into RGB format, please set `do_convert_grayscale = False`.",
                 " if you intended to convert the image into grayscale format, please set `do_convert_rgb = False`",
             )
-            self.config.do_convert_rgb = False
 
     @staticmethod
     def numpy_to_pil(images: np.ndarray) -> List[PIL.Image.Image]: