diff --git a/examples/community/checkpoint_merger.py b/examples/community/checkpoint_merger.py
index 24f187b41c07..3e29ae50078b 100644
--- a/examples/community/checkpoint_merger.py
+++ b/examples/community/checkpoint_merger.py
@@ -199,24 +199,20 @@ def merge(self, pretrained_model_name_or_path_list: List[Union[str, os.PathLike]
             if not attr.startswith("_"):
                 checkpoint_path_1 = os.path.join(cached_folders[1], attr)
                 if os.path.exists(checkpoint_path_1):
-                    files = list(
-                        (
-                            *glob.glob(os.path.join(checkpoint_path_1, "*.safetensors")),
-                            *glob.glob(os.path.join(checkpoint_path_1, "*.bin")),
-                        )
-                    )
+                    files = [
+                        *glob.glob(os.path.join(checkpoint_path_1, "*.safetensors")),
+                        *glob.glob(os.path.join(checkpoint_path_1, "*.bin")),
+                    ]
                     checkpoint_path_1 = files[0] if len(files) > 0 else None
                 if len(cached_folders) < 3:
                     checkpoint_path_2 = None
                 else:
                     checkpoint_path_2 = os.path.join(cached_folders[2], attr)
                     if os.path.exists(checkpoint_path_2):
-                        files = list(
-                            (
-                                *glob.glob(os.path.join(checkpoint_path_2, "*.safetensors")),
-                                *glob.glob(os.path.join(checkpoint_path_2, "*.bin")),
-                            )
-                        )
+                        files = [
+                            *glob.glob(os.path.join(checkpoint_path_2, "*.safetensors")),
+                            *glob.glob(os.path.join(checkpoint_path_2, "*.bin")),
+                        ]
                         checkpoint_path_2 = files[0] if len(files) > 0 else None
                 # For an attr if both checkpoint_path_1 and 2 are None, ignore.
                 # If atleast one is present, deal with it according to interp method, of course only if the state_dict keys match.
diff --git a/examples/community/imagic_stable_diffusion.py b/examples/community/imagic_stable_diffusion.py
index 03917b187af7..dc8ce5f259dc 100644
--- a/examples/community/imagic_stable_diffusion.py
+++ b/examples/community/imagic_stable_diffusion.py
@@ -48,7 +48,7 @@
 
 def preprocess(image):
     w, h = image.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = np.array(image).astype(np.float32) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
diff --git a/examples/community/lpw_stable_diffusion.py b/examples/community/lpw_stable_diffusion.py
index 80b7b90c8bbd..072f7cde17ad 100644
--- a/examples/community/lpw_stable_diffusion.py
+++ b/examples/community/lpw_stable_diffusion.py
@@ -376,7 +376,7 @@ def get_weighted_text_embeddings(
 
 def preprocess_image(image):
     w, h = image.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = np.array(image).astype(np.float32) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
@@ -387,7 +387,7 @@ def preprocess_image(image):
 def preprocess_mask(mask, scale_factor=8):
     mask = mask.convert("L")
     w, h = mask.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     mask = mask.resize((w // scale_factor, h // scale_factor), resample=PIL_INTERPOLATION["nearest"])
     mask = np.array(mask).astype(np.float32) / 255.0
     mask = np.tile(mask, (4, 1, 1))
diff --git a/examples/community/lpw_stable_diffusion_onnx.py b/examples/community/lpw_stable_diffusion_onnx.py
index 817bae262e94..1e0764de5d4d 100644
--- a/examples/community/lpw_stable_diffusion_onnx.py
+++ b/examples/community/lpw_stable_diffusion_onnx.py
@@ -403,7 +403,7 @@ def get_weighted_text_embeddings(
 
 def preprocess_image(image):
     w, h = image.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = np.array(image).astype(np.float32) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
@@ -413,7 +413,7 @@ def preprocess_image(image):
 def preprocess_mask(mask, scale_factor=8):
     mask = mask.convert("L")
     w, h = mask.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     mask = mask.resize((w // scale_factor, h // scale_factor), resample=PIL_INTERPOLATION["nearest"])
     mask = np.array(mask).astype(np.float32) / 255.0
     mask = np.tile(mask, (4, 1, 1))
diff --git a/examples/community/stable_unclip.py b/examples/community/stable_unclip.py
index 8ff9c44d19fd..1b438c8fcb3e 100644
--- a/examples/community/stable_unclip.py
+++ b/examples/community/stable_unclip.py
@@ -46,7 +46,7 @@ def __init__(
     ):
         super().__init__()
 
-        decoder_pipe_kwargs = dict(image_encoder=None) if decoder_pipe_kwargs is None else decoder_pipe_kwargs
+        decoder_pipe_kwargs = {"image_encoder": None} if decoder_pipe_kwargs is None else decoder_pipe_kwargs
 
         decoder_pipe_kwargs["torch_dtype"] = decoder_pipe_kwargs.get("torch_dtype", None) or prior.dtype
 
diff --git a/examples/instruct_pix2pix/train_instruct_pix2pix.py b/examples/instruct_pix2pix/train_instruct_pix2pix.py
index 57430b7f150a..6e51e86a9f16 100644
--- a/examples/instruct_pix2pix/train_instruct_pix2pix.py
+++ b/examples/instruct_pix2pix/train_instruct_pix2pix.py
@@ -673,7 +673,7 @@ def preprocess_train(examples):
         examples["edited_pixel_values"] = edited_images
 
         # Preprocess the captions.
-        captions = [caption for caption in examples[edit_prompt_column]]
+        captions = list(examples[edit_prompt_column])
         examples["input_ids"] = tokenize_captions(captions)
         return examples
 
diff --git a/examples/rl/run_diffuser_locomotion.py b/examples/rl/run_diffuser_locomotion.py
index e64a20500bea..adf6d1443d1c 100644
--- a/examples/rl/run_diffuser_locomotion.py
+++ b/examples/rl/run_diffuser_locomotion.py
@@ -4,17 +4,17 @@
 from diffusers.experimental import ValueGuidedRLPipeline
 
 
-config = dict(
-    n_samples=64,
-    horizon=32,
-    num_inference_steps=20,
-    n_guide_steps=2,  # can set to 0 for faster sampling, does not use value network
-    scale_grad_by_std=True,
-    scale=0.1,
-    eta=0.0,
-    t_grad_cutoff=2,
-    device="cpu",
-)
+config = {
+    "n_samples": 64,
+    "horizon": 32,
+    "num_inference_steps": 20,
+    "n_guide_steps": 2,  # can set to 0 for faster sampling, does not use value network
+    "scale_grad_by_std": True,
+    "scale": 0.1,
+    "eta": 0.0,
+    "t_grad_cutoff": 2,
+    "device": "cpu",
+}
 
 
 if __name__ == "__main__":
diff --git a/pyproject.toml b/pyproject.toml
index 5ec7ae51be15..a5fe70af9ca7 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,8 +4,8 @@ target-version = ['py37']
 
 [tool.ruff]
 # Never enforce `E501` (line length violations).
-ignore = ["E501", "E741", "W605"]
-select = ["E", "F", "I", "W"]
+ignore = ["C901", "E501", "E741", "W605"]
+select = ["C", "E", "F", "I", "W"]
 line-length = 119
 
 # Ignore import violations in all `__init__.py` files.
diff --git a/scripts/convert_ddpm_original_checkpoint_to_diffusers.py b/scripts/convert_ddpm_original_checkpoint_to_diffusers.py
index 4222327c23de..46595784b0ba 100644
--- a/scripts/convert_ddpm_original_checkpoint_to_diffusers.py
+++ b/scripts/convert_ddpm_original_checkpoint_to_diffusers.py
@@ -404,7 +404,7 @@ def convert_vq_autoenc_checkpoint(checkpoint, config):
         config = json.loads(f.read())
 
     # unet case
-    key_prefix_set = set(key.split(".")[0] for key in checkpoint.keys())
+    key_prefix_set = {key.split(".")[0] for key in checkpoint.keys()}
     if "encoder" in key_prefix_set and "decoder" in key_prefix_set:
         converted_checkpoint = convert_vq_autoenc_checkpoint(checkpoint, config)
     else:
diff --git a/scripts/convert_models_diffuser_to_diffusers.py b/scripts/convert_models_diffuser_to_diffusers.py
index 9475f7da93fb..cc5321e33fe0 100644
--- a/scripts/convert_models_diffuser_to_diffusers.py
+++ b/scripts/convert_models_diffuser_to_diffusers.py
@@ -24,29 +24,29 @@ def unet(hor):
         up_block_types = ("UpResnetBlock1D", "UpResnetBlock1D", "UpResnetBlock1D")
     model = torch.load(f"/Users/bglickenhaus/Documents/diffuser/temporal_unet-hopper-mediumv2-hor{hor}.torch")
     state_dict = model.state_dict()
-    config = dict(
-        down_block_types=down_block_types,
-        block_out_channels=block_out_channels,
-        up_block_types=up_block_types,
-        layers_per_block=1,
-        use_timestep_embedding=True,
-        out_block_type="OutConv1DBlock",
-        norm_num_groups=8,
-        downsample_each_block=False,
-        in_channels=14,
-        out_channels=14,
-        extra_in_channels=0,
-        time_embedding_type="positional",
-        flip_sin_to_cos=False,
-        freq_shift=1,
-        sample_size=65536,
-        mid_block_type="MidResTemporalBlock1D",
-        act_fn="mish",
-    )
+    config = {
+        "down_block_types": down_block_types,
+        "block_out_channels": block_out_channels,
+        "up_block_types": up_block_types,
+        "layers_per_block": 1,
+        "use_timestep_embedding": True,
+        "out_block_type": "OutConv1DBlock",
+        "norm_num_groups": 8,
+        "downsample_each_block": False,
+        "in_channels": 14,
+        "out_channels": 14,
+        "extra_in_channels": 0,
+        "time_embedding_type": "positional",
+        "flip_sin_to_cos": False,
+        "freq_shift": 1,
+        "sample_size": 65536,
+        "mid_block_type": "MidResTemporalBlock1D",
+        "act_fn": "mish",
+    }
     hf_value_function = UNet1DModel(**config)
     print(f"length of state dict: {len(state_dict.keys())}")
     print(f"length of value function dict: {len(hf_value_function.state_dict().keys())}")
-    mapping = dict((k, hfk) for k, hfk in zip(model.state_dict().keys(), hf_value_function.state_dict().keys()))
+    mapping = dict(zip(model.state_dict().keys(), hf_value_function.state_dict().keys()))
     for k, v in mapping.items():
         state_dict[v] = state_dict.pop(k)
     hf_value_function.load_state_dict(state_dict)
@@ -57,25 +57,25 @@ def unet(hor):
 
 
 def value_function():
-    config = dict(
-        in_channels=14,
-        down_block_types=("DownResnetBlock1D", "DownResnetBlock1D", "DownResnetBlock1D", "DownResnetBlock1D"),
-        up_block_types=(),
-        out_block_type="ValueFunction",
-        mid_block_type="ValueFunctionMidBlock1D",
-        block_out_channels=(32, 64, 128, 256),
-        layers_per_block=1,
-        downsample_each_block=True,
-        sample_size=65536,
-        out_channels=14,
-        extra_in_channels=0,
-        time_embedding_type="positional",
-        use_timestep_embedding=True,
-        flip_sin_to_cos=False,
-        freq_shift=1,
-        norm_num_groups=8,
-        act_fn="mish",
-    )
+    config = {
+        "in_channels": 14,
+        "down_block_types": ("DownResnetBlock1D", "DownResnetBlock1D", "DownResnetBlock1D", "DownResnetBlock1D"),
+        "up_block_types": (),
+        "out_block_type": "ValueFunction",
+        "mid_block_type": "ValueFunctionMidBlock1D",
+        "block_out_channels": (32, 64, 128, 256),
+        "layers_per_block": 1,
+        "downsample_each_block": True,
+        "sample_size": 65536,
+        "out_channels": 14,
+        "extra_in_channels": 0,
+        "time_embedding_type": "positional",
+        "use_timestep_embedding": True,
+        "flip_sin_to_cos": False,
+        "freq_shift": 1,
+        "norm_num_groups": 8,
+        "act_fn": "mish",
+    }
 
     model = torch.load("/Users/bglickenhaus/Documents/diffuser/value_function-hopper-mediumv2-hor32.torch")
     state_dict = model
@@ -83,7 +83,7 @@ def value_function():
     print(f"length of state dict: {len(state_dict.keys())}")
     print(f"length of value function dict: {len(hf_value_function.state_dict().keys())}")
 
-    mapping = dict((k, hfk) for k, hfk in zip(state_dict.keys(), hf_value_function.state_dict().keys()))
+    mapping = dict(zip(state_dict.keys(), hf_value_function.state_dict().keys()))
     for k, v in mapping.items():
         state_dict[v] = state_dict.pop(k)
 
diff --git a/scripts/convert_original_audioldm_to_diffusers.py b/scripts/convert_original_audioldm_to_diffusers.py
index bd671e3a7b70..189b165c0a01 100644
--- a/scripts/convert_original_audioldm_to_diffusers.py
+++ b/scripts/convert_original_audioldm_to_diffusers.py
@@ -246,19 +246,19 @@ def create_unet_diffusers_config(original_config, image_size: int):
     )
     class_embeddings_concat = unet_params.extra_film_use_concat if "extra_film_use_concat" in unet_params else None
 
-    config = dict(
-        sample_size=image_size // vae_scale_factor,
-        in_channels=unet_params.in_channels,
-        out_channels=unet_params.out_channels,
-        down_block_types=tuple(down_block_types),
-        up_block_types=tuple(up_block_types),
-        block_out_channels=tuple(block_out_channels),
-        layers_per_block=unet_params.num_res_blocks,
-        cross_attention_dim=cross_attention_dim,
-        class_embed_type=class_embed_type,
-        projection_class_embeddings_input_dim=projection_class_embeddings_input_dim,
-        class_embeddings_concat=class_embeddings_concat,
-    )
+    config = {
+        "sample_size": image_size // vae_scale_factor,
+        "in_channels": unet_params.in_channels,
+        "out_channels": unet_params.out_channels,
+        "down_block_types": tuple(down_block_types),
+        "up_block_types": tuple(up_block_types),
+        "block_out_channels": tuple(block_out_channels),
+        "layers_per_block": unet_params.num_res_blocks,
+        "cross_attention_dim": cross_attention_dim,
+        "class_embed_type": class_embed_type,
+        "projection_class_embeddings_input_dim": projection_class_embeddings_input_dim,
+        "class_embeddings_concat": class_embeddings_concat,
+    }
 
     return config
 
@@ -278,17 +278,17 @@ def create_vae_diffusers_config(original_config, checkpoint, image_size: int):
 
     scaling_factor = checkpoint["scale_factor"] if "scale_by_std" in original_config.model.params else 0.18215
 
-    config = dict(
-        sample_size=image_size,
-        in_channels=vae_params.in_channels,
-        out_channels=vae_params.out_ch,
-        down_block_types=tuple(down_block_types),
-        up_block_types=tuple(up_block_types),
-        block_out_channels=tuple(block_out_channels),
-        latent_channels=vae_params.z_channels,
-        layers_per_block=vae_params.num_res_blocks,
-        scaling_factor=float(scaling_factor),
-    )
+    config = {
+        "sample_size": image_size,
+        "in_channels": vae_params.in_channels,
+        "out_channels": vae_params.out_ch,
+        "down_block_types": tuple(down_block_types),
+        "up_block_types": tuple(up_block_types),
+        "block_out_channels": tuple(block_out_channels),
+        "latent_channels": vae_params.z_channels,
+        "layers_per_block": vae_params.num_res_blocks,
+        "scaling_factor": float(scaling_factor),
+    }
     return config
 
 
@@ -670,18 +670,18 @@ def create_transformers_vocoder_config(original_config):
     """
     vocoder_params = original_config.model.params.vocoder_config.params
 
-    config = dict(
-        model_in_dim=vocoder_params.num_mels,
-        sampling_rate=vocoder_params.sampling_rate,
-        upsample_initial_channel=vocoder_params.upsample_initial_channel,
-        upsample_rates=list(vocoder_params.upsample_rates),
-        upsample_kernel_sizes=list(vocoder_params.upsample_kernel_sizes),
-        resblock_kernel_sizes=list(vocoder_params.resblock_kernel_sizes),
-        resblock_dilation_sizes=[
+    config = {
+        "model_in_dim": vocoder_params.num_mels,
+        "sampling_rate": vocoder_params.sampling_rate,
+        "upsample_initial_channel": vocoder_params.upsample_initial_channel,
+        "upsample_rates": list(vocoder_params.upsample_rates),
+        "upsample_kernel_sizes": list(vocoder_params.upsample_kernel_sizes),
+        "resblock_kernel_sizes": list(vocoder_params.resblock_kernel_sizes),
+        "resblock_dilation_sizes": [
             list(resblock_dilation) for resblock_dilation in vocoder_params.resblock_dilation_sizes
         ],
-        normalize_before=False,
-    )
+        "normalize_before": False,
+    }
 
     return config
 
diff --git a/scripts/convert_versatile_diffusion_to_diffusers.py b/scripts/convert_versatile_diffusion_to_diffusers.py
index 06b0cec03448..b895e08e9de9 100644
--- a/scripts/convert_versatile_diffusion_to_diffusers.py
+++ b/scripts/convert_versatile_diffusion_to_diffusers.py
@@ -280,17 +280,17 @@ def create_image_unet_diffusers_config(unet_params):
     if not all(n == unet_params.num_noattn_blocks[0] for n in unet_params.num_noattn_blocks):
         raise ValueError("Not all num_res_blocks are equal, which is not supported in this script.")
 
-    config = dict(
-        sample_size=None,
-        in_channels=unet_params.input_channels,
-        out_channels=unet_params.output_channels,
-        down_block_types=tuple(down_block_types),
-        up_block_types=tuple(up_block_types),
-        block_out_channels=tuple(block_out_channels),
-        layers_per_block=unet_params.num_noattn_blocks[0],
-        cross_attention_dim=unet_params.context_dim,
-        attention_head_dim=unet_params.num_heads,
-    )
+    config = {
+        "sample_size": None,
+        "in_channels": unet_params.input_channels,
+        "out_channels": unet_params.output_channels,
+        "down_block_types": tuple(down_block_types),
+        "up_block_types": tuple(up_block_types),
+        "block_out_channels": tuple(block_out_channels),
+        "layers_per_block": unet_params.num_noattn_blocks[0],
+        "cross_attention_dim": unet_params.context_dim,
+        "attention_head_dim": unet_params.num_heads,
+    }
 
     return config
 
@@ -319,17 +319,17 @@ def create_text_unet_diffusers_config(unet_params):
     if not all(n == unet_params.num_noattn_blocks[0] for n in unet_params.num_noattn_blocks):
         raise ValueError("Not all num_res_blocks are equal, which is not supported in this script.")
 
-    config = dict(
-        sample_size=None,
-        in_channels=(unet_params.input_channels, 1, 1),
-        out_channels=(unet_params.output_channels, 1, 1),
-        down_block_types=tuple(down_block_types),
-        up_block_types=tuple(up_block_types),
-        block_out_channels=tuple(block_out_channels),
-        layers_per_block=unet_params.num_noattn_blocks[0],
-        cross_attention_dim=unet_params.context_dim,
-        attention_head_dim=unet_params.num_heads,
-    )
+    config = {
+        "sample_size": None,
+        "in_channels": (unet_params.input_channels, 1, 1),
+        "out_channels": (unet_params.output_channels, 1, 1),
+        "down_block_types": tuple(down_block_types),
+        "up_block_types": tuple(up_block_types),
+        "block_out_channels": tuple(block_out_channels),
+        "layers_per_block": unet_params.num_noattn_blocks[0],
+        "cross_attention_dim": unet_params.context_dim,
+        "attention_head_dim": unet_params.num_heads,
+    }
 
     return config
 
@@ -343,16 +343,16 @@ def create_vae_diffusers_config(vae_params):
     down_block_types = ["DownEncoderBlock2D"] * len(block_out_channels)
     up_block_types = ["UpDecoderBlock2D"] * len(block_out_channels)
 
-    config = dict(
-        sample_size=vae_params.resolution,
-        in_channels=vae_params.in_channels,
-        out_channels=vae_params.out_ch,
-        down_block_types=tuple(down_block_types),
-        up_block_types=tuple(up_block_types),
-        block_out_channels=tuple(block_out_channels),
-        latent_channels=vae_params.z_channels,
-        layers_per_block=vae_params.num_res_blocks,
-    )
+    config = {
+        "sample_size": vae_params.resolution,
+        "in_channels": vae_params.in_channels,
+        "out_channels": vae_params.out_ch,
+        "down_block_types": tuple(down_block_types),
+        "up_block_types": tuple(up_block_types),
+        "block_out_channels": tuple(block_out_channels),
+        "latent_channels": vae_params.z_channels,
+        "layers_per_block": vae_params.num_res_blocks,
+    }
     return config
 
 
diff --git a/src/diffusers/configuration_utils.py b/src/diffusers/configuration_utils.py
index 20b7b273d5af..ce6e77b03f57 100644
--- a/src/diffusers/configuration_utils.py
+++ b/src/diffusers/configuration_utils.py
@@ -420,7 +420,7 @@ def _get_init_keys(cls):
     @classmethod
     def extract_init_dict(cls, config_dict, **kwargs):
         # 0. Copy origin config dict
-        original_dict = {k: v for k, v in config_dict.items()}
+        original_dict = dict(config_dict.items())
 
         # 1. Retrieve expected config attributes from __init__ signature
         expected_keys = cls._get_init_keys(cls)
@@ -610,7 +610,7 @@ def init(self, *args, **kwargs):
             )
 
         # Ignore private kwargs in the init. Retrieve all passed attributes
-        init_kwargs = {k: v for k, v in kwargs.items()}
+        init_kwargs = dict(kwargs.items())
 
         # Retrieve default values
         fields = dataclasses.fields(self)
diff --git a/src/diffusers/experimental/rl/value_guided_sampling.py b/src/diffusers/experimental/rl/value_guided_sampling.py
index 7de33a795c77..e4af4986faad 100644
--- a/src/diffusers/experimental/rl/value_guided_sampling.py
+++ b/src/diffusers/experimental/rl/value_guided_sampling.py
@@ -52,13 +52,13 @@ def __init__(
         self.scheduler = scheduler
         self.env = env
         self.data = env.get_dataset()
-        self.means = dict()
+        self.means = {}
         for key in self.data.keys():
             try:
                 self.means[key] = self.data[key].mean()
             except:  # noqa: E722
                 pass
-        self.stds = dict()
+        self.stds = {}
         for key in self.data.keys():
             try:
                 self.stds[key] = self.data[key].std()
diff --git a/src/diffusers/image_processor.py b/src/diffusers/image_processor.py
index de6543800b2d..80e3412991cf 100644
--- a/src/diffusers/image_processor.py
+++ b/src/diffusers/image_processor.py
@@ -99,7 +99,7 @@ def resize(self, images: PIL.Image.Image) -> PIL.Image.Image:
         Resize a PIL image. Both height and width will be downscaled to the next integer multiple of `vae_scale_factor`
         """
         w, h = images.size
-        w, h = map(lambda x: x - x % self.vae_scale_factor, (w, h))  # resize to integer multiple of vae_scale_factor
+        w, h = (x - x % self.vae_scale_factor for x in (w, h))  # resize to integer multiple of vae_scale_factor
         images = images.resize((w, h), resample=PIL_INTERPOLATION[self.resample])
         return images
 
diff --git a/src/diffusers/loaders.py b/src/diffusers/loaders.py
index 31fdc46d9e1b..d6bb6fde6ac1 100644
--- a/src/diffusers/loaders.py
+++ b/src/diffusers/loaders.py
@@ -37,7 +37,7 @@ class AttnProcsLayers(torch.nn.Module):
     def __init__(self, state_dict: Dict[str, torch.Tensor]):
         super().__init__()
         self.layers = torch.nn.ModuleList(state_dict.values())
-        self.mapping = {k: v for k, v in enumerate(state_dict.keys())}
+        self.mapping = dict(enumerate(state_dict.keys()))
         self.rev_mapping = {v: k for k, v in enumerate(state_dict.keys())}
 
         # we add a hook to state_dict() and load_state_dict() so that the
diff --git a/src/diffusers/models/modeling_utils.py b/src/diffusers/models/modeling_utils.py
index e51b40ce4509..aa4e2b0ea487 100644
--- a/src/diffusers/models/modeling_utils.py
+++ b/src/diffusers/models/modeling_utils.py
@@ -647,7 +647,7 @@ def _load_pretrained_model(
     ):
         # Retrieve missing & unexpected_keys
         model_state_dict = model.state_dict()
-        loaded_keys = [k for k in state_dict.keys()]
+        loaded_keys = list(state_dict.keys())
 
         expected_keys = list(model_state_dict.keys())
 
diff --git a/src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion_img2img.py b/src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion_img2img.py
index ab80072fa78f..23f4886f06c1 100644
--- a/src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion_img2img.py
+++ b/src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion_img2img.py
@@ -74,7 +74,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py b/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py
index 8f0925ac4aaa..1b88270cbbe6 100644
--- a/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py
+++ b/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py
@@ -201,12 +201,12 @@ def __call__(
         images = images.cpu().permute(0, 2, 3, 1).numpy()
         images = (images * 255).round().astype("uint8")
         images = list(
-            map(lambda _: Image.fromarray(_[:, :, 0]), images)
+            (Image.fromarray(_[:, :, 0]) for _ in images)
             if images.shape[3] == 1
-            else map(lambda _: Image.fromarray(_, mode="RGB").convert("L"), images)
+            else (Image.fromarray(_, mode="RGB").convert("L") for _ in images)
         )
 
-        audios = list(map(lambda _: self.mel.image_to_audio(_), images))
+        audios = [self.mel.image_to_audio(_) for _ in images]
         if not return_dict:
             return images, (self.mel.get_sample_rate(), audios)
 
diff --git a/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion_superresolution.py b/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion_superresolution.py
index 2ecf5f24a4a7..6887068f3443 100644
--- a/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion_superresolution.py
+++ b/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion_superresolution.py
@@ -21,7 +21,7 @@
 
 def preprocess(image):
     w, h = image.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = np.array(image).astype(np.float32) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
diff --git a/src/diffusers/pipelines/pipeline_flax_utils.py b/src/diffusers/pipelines/pipeline_flax_utils.py
index d3fc415ab4d7..9d91ff757799 100644
--- a/src/diffusers/pipelines/pipeline_flax_utils.py
+++ b/src/diffusers/pipelines/pipeline_flax_utils.py
@@ -491,7 +491,7 @@ def _get_signature_keys(obj):
         parameters = inspect.signature(obj.__init__).parameters
         required_parameters = {k: v for k, v in parameters.items() if v.default == inspect._empty}
         optional_parameters = set({k for k, v in parameters.items() if v.default != inspect._empty})
-        expected_modules = set(required_parameters.keys()) - set(["self"])
+        expected_modules = set(required_parameters.keys()) - {"self"}
         return expected_modules, optional_parameters
 
     @property
diff --git a/src/diffusers/pipelines/pipeline_utils.py b/src/diffusers/pipelines/pipeline_utils.py
index 8f33b506827a..d3578745b8b3 100644
--- a/src/diffusers/pipelines/pipeline_utils.py
+++ b/src/diffusers/pipelines/pipeline_utils.py
@@ -204,11 +204,11 @@ def variant_compatible_siblings(filenames, variant=None) -> Union[List[os.PathLi
     non_variant_file_regex = re.compile(f"{'|'.join(weight_names)}")
 
     if variant is not None:
-        variant_filenames = set(f for f in filenames if variant_file_regex.match(f.split("/")[-1]) is not None)
+        variant_filenames = {f for f in filenames if variant_file_regex.match(f.split("/")[-1]) is not None}
     else:
         variant_filenames = set()
 
-    non_variant_filenames = set(f for f in filenames if non_variant_file_regex.match(f.split("/")[-1]) is not None)
+    non_variant_filenames = {f for f in filenames if non_variant_file_regex.match(f.split("/")[-1]) is not None}
 
     usable_filenames = set(variant_filenames)
     for f in non_variant_filenames:
@@ -225,7 +225,7 @@ def warn_deprecated_model_variant(pretrained_model_name_or_path, use_auth_token,
         use_auth_token=use_auth_token,
         revision=None,
     )
-    filenames = set(sibling.rfilename for sibling in info.siblings)
+    filenames = {sibling.rfilename for sibling in info.siblings}
     comp_model_filenames, _ = variant_compatible_siblings(filenames, variant=revision)
     comp_model_filenames = [".".join(f.split(".")[:1] + f.split(".")[2:]) for f in comp_model_filenames]
 
@@ -1115,7 +1115,7 @@ def download(cls, pretrained_model_name, **kwargs) -> Union[str, os.PathLike]:
             # retrieve all folder_names that contain relevant files
             folder_names = [k for k, v in config_dict.items() if isinstance(v, list)]
 
-            filenames = set(sibling.rfilename for sibling in info.siblings)
+            filenames = {sibling.rfilename for sibling in info.siblings}
             model_filenames, variant_filenames = variant_compatible_siblings(filenames, variant=variant)
 
             # if the whole pipeline is cached we don't have to ping the Hub
@@ -1126,7 +1126,7 @@ def download(cls, pretrained_model_name, **kwargs) -> Union[str, os.PathLike]:
                     pretrained_model_name, use_auth_token, variant, revision, model_filenames
                 )
 
-            model_folder_names = set([os.path.split(f)[0] for f in model_filenames])
+            model_folder_names = {os.path.split(f)[0] for f in model_filenames}
 
             # all filenames compatible with variant will be added
             allow_patterns = list(model_filenames)
@@ -1157,8 +1157,8 @@ def download(cls, pretrained_model_name, **kwargs) -> Union[str, os.PathLike]:
             elif use_safetensors and is_safetensors_compatible(model_filenames, variant=variant):
                 ignore_patterns = ["*.bin", "*.msgpack"]
 
-                safetensors_variant_filenames = set([f for f in variant_filenames if f.endswith(".safetensors")])
-                safetensors_model_filenames = set([f for f in model_filenames if f.endswith(".safetensors")])
+                safetensors_variant_filenames = {f for f in variant_filenames if f.endswith(".safetensors")}
+                safetensors_model_filenames = {f for f in model_filenames if f.endswith(".safetensors")}
                 if (
                     len(safetensors_variant_filenames) > 0
                     and safetensors_model_filenames != safetensors_variant_filenames
@@ -1169,8 +1169,8 @@ def download(cls, pretrained_model_name, **kwargs) -> Union[str, os.PathLike]:
             else:
                 ignore_patterns = ["*.safetensors", "*.msgpack"]
 
-                bin_variant_filenames = set([f for f in variant_filenames if f.endswith(".bin")])
-                bin_model_filenames = set([f for f in model_filenames if f.endswith(".bin")])
+                bin_variant_filenames = {f for f in variant_filenames if f.endswith(".bin")}
+                bin_model_filenames = {f for f in model_filenames if f.endswith(".bin")}
                 if len(bin_variant_filenames) > 0 and bin_model_filenames != bin_variant_filenames:
                     logger.warn(
                         f"\nA mixture of {variant} and non-{variant} filenames will be loaded.\nLoaded {variant} filenames:\n[{', '.join(bin_variant_filenames)}]\nLoaded non-{variant} filenames:\n[{', '.join(bin_model_filenames - bin_variant_filenames)}\nIf this behavior is not expected, please check your folder structure."
@@ -1215,7 +1215,7 @@ def _get_signature_keys(obj):
         parameters = inspect.signature(obj.__init__).parameters
         required_parameters = {k: v for k, v in parameters.items() if v.default == inspect._empty}
         optional_parameters = set({k for k, v in parameters.items() if v.default != inspect._empty})
-        expected_modules = set(required_parameters.keys()) - set(["self"])
+        expected_modules = set(required_parameters.keys()) - {"self"}
         return expected_modules, optional_parameters
 
     @property
diff --git a/src/diffusers/pipelines/repaint/pipeline_repaint.py b/src/diffusers/pipelines/repaint/pipeline_repaint.py
index fabcd2610f43..f4914c46db51 100644
--- a/src/diffusers/pipelines/repaint/pipeline_repaint.py
+++ b/src/diffusers/pipelines/repaint/pipeline_repaint.py
@@ -37,7 +37,7 @@ def _preprocess_image(image: Union[List, PIL.Image.Image, torch.Tensor]):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
@@ -58,7 +58,7 @@ def _preprocess_mask(mask: Union[List, PIL.Image.Image, torch.Tensor]):
 
     if isinstance(mask[0], PIL.Image.Image):
         w, h = mask[0].size
-        w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+        w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
         mask = [np.array(m.convert("L").resize((w, h), resample=PIL_INTERPOLATION["nearest"]))[None, :] for m in mask]
         mask = np.concatenate(mask, axis=0)
         mask = mask.astype(np.float32) / 255.0
diff --git a/src/diffusers/pipelines/spectrogram_diffusion/midi_utils.py b/src/diffusers/pipelines/spectrogram_diffusion/midi_utils.py
index 00277adc7fbe..08d0878db588 100644
--- a/src/diffusers/pipelines/spectrogram_diffusion/midi_utils.py
+++ b/src/diffusers/pipelines/spectrogram_diffusion/midi_utils.py
@@ -166,7 +166,7 @@ def __init__(self, max_shift_steps: int, steps_per_second: float, event_ranges:
         self._shift_range = EventRange(type="shift", min_value=0, max_value=max_shift_steps)
         self._event_ranges = [self._shift_range] + event_ranges
         # Ensure all event types have unique names.
-        assert len(self._event_ranges) == len(set([er.type for er in self._event_ranges]))
+        assert len(self._event_ranges) == len({er.type for er in self._event_ranges})
 
     @property
     def num_classes(self) -> int:
diff --git a/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py b/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py
index ef4598433f82..7fbdbdab1fa9 100644
--- a/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py
+++ b/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py
@@ -274,18 +274,18 @@ def create_unet_diffusers_config(original_config, image_size: int, controlnet=Fa
         else:
             raise NotImplementedError(f"Unknown conditional unet num_classes config: {unet_params.num_classes}")
 
-    config = dict(
-        sample_size=image_size // vae_scale_factor,
-        in_channels=unet_params.in_channels,
-        down_block_types=tuple(down_block_types),
-        block_out_channels=tuple(block_out_channels),
-        layers_per_block=unet_params.num_res_blocks,
-        cross_attention_dim=unet_params.context_dim,
-        attention_head_dim=head_dim,
-        use_linear_projection=use_linear_projection,
-        class_embed_type=class_embed_type,
-        projection_class_embeddings_input_dim=projection_class_embeddings_input_dim,
-    )
+    config = {
+        "sample_size": image_size // vae_scale_factor,
+        "in_channels": unet_params.in_channels,
+        "down_block_types": tuple(down_block_types),
+        "block_out_channels": tuple(block_out_channels),
+        "layers_per_block": unet_params.num_res_blocks,
+        "cross_attention_dim": unet_params.context_dim,
+        "attention_head_dim": head_dim,
+        "use_linear_projection": use_linear_projection,
+        "class_embed_type": class_embed_type,
+        "projection_class_embeddings_input_dim": projection_class_embeddings_input_dim,
+    }
 
     if not controlnet:
         config["out_channels"] = unet_params.out_channels
@@ -305,16 +305,16 @@ def create_vae_diffusers_config(original_config, image_size: int):
     down_block_types = ["DownEncoderBlock2D"] * len(block_out_channels)
     up_block_types = ["UpDecoderBlock2D"] * len(block_out_channels)
 
-    config = dict(
-        sample_size=image_size,
-        in_channels=vae_params.in_channels,
-        out_channels=vae_params.out_ch,
-        down_block_types=tuple(down_block_types),
-        up_block_types=tuple(up_block_types),
-        block_out_channels=tuple(block_out_channels),
-        latent_channels=vae_params.z_channels,
-        layers_per_block=vae_params.num_res_blocks,
-    )
+    config = {
+        "sample_size": image_size,
+        "in_channels": vae_params.in_channels,
+        "out_channels": vae_params.out_ch,
+        "down_block_types": tuple(down_block_types),
+        "up_block_types": tuple(up_block_types),
+        "block_out_channels": tuple(block_out_channels),
+        "latent_channels": vae_params.z_channels,
+        "layers_per_block": vae_params.num_res_blocks,
+    }
     return config
 
 
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_cycle_diffusion.py b/src/diffusers/pipelines/stable_diffusion/pipeline_cycle_diffusion.py
index 67cda0cfef32..4616dc1e4849 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_cycle_diffusion.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_cycle_diffusion.py
@@ -44,7 +44,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_controlnet.py b/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_controlnet.py
index 4dc450cebc84..5af07ec8b9c4 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_controlnet.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_controlnet.py
@@ -530,7 +530,7 @@ def unshard(x: jnp.ndarray):
 def preprocess(image, dtype):
     image = image.convert("RGB")
     w, h = image.size
-    w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+    w, h = (x - x % 64 for x in (w, h))  # resize to integer multiple of 64
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = jnp.array(image).astype(dtype) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_img2img.py b/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_img2img.py
index 95cab9df61e8..2063238df27a 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_img2img.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_img2img.py
@@ -520,7 +520,7 @@ def unshard(x: jnp.ndarray):
 
 def preprocess(image, dtype):
     w, h = image.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = jnp.array(image).astype(dtype) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_inpaint.py b/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_inpaint.py
index 6e9b9ff6d00f..abb57f8b62e9 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_inpaint.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_inpaint.py
@@ -563,7 +563,7 @@ def unshard(x: jnp.ndarray):
 
 def preprocess_image(image, dtype):
     w, h = image.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = jnp.array(image).astype(dtype) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
@@ -572,7 +572,7 @@ def preprocess_image(image, dtype):
 
 def preprocess_mask(mask, dtype):
     w, h = mask.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     mask = mask.resize((w, h))
     mask = jnp.array(mask.convert("L")).astype(dtype) / 255.0
     mask = jnp.expand_dims(mask, axis=(0, 1))
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py b/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py
index 910fbaacfcca..80c4a8692a05 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py
@@ -40,7 +40,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+        w, h = (x - x % 64 for x in (w, h))  # resize to integer multiple of 64
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_inpaint_legacy.py b/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_inpaint_legacy.py
index 987a343c718b..5cb3abb4f54e 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_inpaint_legacy.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_inpaint_legacy.py
@@ -19,7 +19,7 @@
 
 def preprocess(image):
     w, h = image.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     image = image.resize((w, h), resample=PIL.Image.LANCZOS)
     image = np.array(image).astype(np.float32) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
@@ -29,7 +29,7 @@ def preprocess(image):
 def preprocess_mask(mask, scale_factor=8):
     mask = mask.convert("L")
     w, h = mask.size
-    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    w, h = (x - x % 32 for x in (w, h))  # resize to integer multiple of 32
     mask = mask.resize((w // scale_factor, h // scale_factor), resample=PIL.Image.NEAREST)
     mask = np.array(mask).astype(np.float32) / 255.0
     mask = np.tile(mask, (4, 1, 1))
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_upscale.py b/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_upscale.py
index 45b5a50467b0..b91262551b0f 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_upscale.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_upscale.py
@@ -31,7 +31,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 32
+        w, h = (x - x % 64 for x in (w, h))  # resize to integer multiple of 32
 
         image = [np.array(i.resize((w, h)))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py
index b66cfe9b437e..96282771d777 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py
@@ -41,7 +41,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
@@ -442,7 +442,7 @@ def prepare_depth_map(self, image, depth_map, batch_size, do_classifier_free_gui
         if isinstance(image, PIL.Image.Image):
             image = [image]
         else:
-            image = [img for img in image]
+            image = list(image)
 
         if isinstance(image[0], PIL.Image.Image):
             width, height = image[0].size
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
index 1c94c58450ab..ba124ffecbee 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
@@ -78,7 +78,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint_legacy.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint_legacy.py
index 6fafe08285ee..3d1615968369 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint_legacy.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint_legacy.py
@@ -42,7 +42,7 @@
 
 def preprocess_image(image):
     w, h = image.size
-    w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+    w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
     image = image.resize((w, h), resample=PIL_INTERPOLATION["lanczos"])
     image = np.array(image).astype(np.float32) / 255.0
     image = image[None].transpose(0, 3, 1, 2)
@@ -54,7 +54,7 @@ def preprocess_mask(mask, scale_factor=8):
     if not isinstance(mask, torch.FloatTensor):
         mask = mask.convert("L")
         w, h = mask.size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
         mask = mask.resize((w // scale_factor, h // scale_factor), resample=PIL_INTERPOLATION["nearest"])
         mask = np.array(mask).astype(np.float32) / 255.0
         mask = np.tile(mask, (4, 1, 1))
@@ -76,7 +76,7 @@ def preprocess_mask(mask, scale_factor=8):
         # (potentially) reduce mask channel dimension from 3 to 1 for broadcasting to latent shape
         mask = mask.mean(dim=1, keepdim=True)
         h, w = mask.shape[-2:]
-        h, w = map(lambda x: x - x % 8, (h, w))  # resize to integer multiple of 8
+        h, w = (x - x % 8 for x in (h, w))  # resize to integer multiple of 8
         mask = torch.nn.functional.interpolate(mask, (h // scale_factor, w // scale_factor))
         return mask
 
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py
index a45937fd2045..5f4d6685185f 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py
@@ -47,7 +47,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
index 624d0e625828..822bd49ce31c 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
@@ -38,7 +38,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+        w, h = (x - x % 64 for x in (w, h))  # resize to integer multiple of 64
 
         image = [np.array(i.resize((w, h)))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py
index 4c2dbe6ff85d..bc072d4c73e8 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py
@@ -180,7 +180,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 8, (w, h))  # resize to integer multiple of 8
+        w, h = (x - x % 8 for x in (w, h))  # resize to integer multiple of 8
 
         image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py
index 9f8f44a12bb4..b25a91d4caef 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py
@@ -37,7 +37,7 @@ def preprocess(image):
 
     if isinstance(image[0], PIL.Image.Image):
         w, h = image[0].size
-        w, h = map(lambda x: x - x % 64, (w, h))  # resize to integer multiple of 64
+        w, h = (x - x % 64 for x in (w, h))  # resize to integer multiple of 64
 
         image = [np.array(i.resize((w, h)))[None, :] for i in image]
         image = np.concatenate(image, axis=0)
diff --git a/src/diffusers/pipelines/versatile_diffusion/pipeline_versatile_diffusion_image_variation.py b/src/diffusers/pipelines/versatile_diffusion/pipeline_versatile_diffusion_image_variation.py
index f9ae82568e5c..2b47184d7773 100644
--- a/src/diffusers/pipelines/versatile_diffusion/pipeline_versatile_diffusion_image_variation.py
+++ b/src/diffusers/pipelines/versatile_diffusion/pipeline_versatile_diffusion_image_variation.py
@@ -134,7 +134,7 @@ def normalize_embeddings(encoder_output):
             return embeds
 
         if isinstance(prompt, torch.Tensor) and len(prompt.shape) == 4:
-            prompt = [p for p in prompt]
+            prompt = list(prompt)
 
         batch_size = len(prompt) if isinstance(prompt, list) else 1
 
diff --git a/src/diffusers/utils/outputs.py b/src/diffusers/utils/outputs.py
index f91a49b7a8a7..b6e8a219e129 100644
--- a/src/diffusers/utils/outputs.py
+++ b/src/diffusers/utils/outputs.py
@@ -84,7 +84,7 @@ def update(self, *args, **kwargs):
 
     def __getitem__(self, k):
         if isinstance(k, str):
-            inner_dict = {k: v for (k, v) in self.items()}
+            inner_dict = dict(self.items())
             return inner_dict[k]
         else:
             return self.to_tuple()[k]
diff --git a/utils/check_doc_toc.py b/utils/check_doc_toc.py
index c00feb9d8e3f..ff9285c63f16 100644
--- a/utils/check_doc_toc.py
+++ b/utils/check_doc_toc.py
@@ -43,7 +43,7 @@ def clean_doc_toc(doc_list):
 
     new_doc = []
     for duplicate_key in duplicates:
-        titles = list(set(doc["title"] for doc in doc_list if doc["local"] == duplicate_key))
+        titles = list({doc["title"] for doc in doc_list if doc["local"] == duplicate_key})
         if len(titles) > 1:
             raise ValueError(
                 f"{duplicate_key} is present several times in the documentation table of content at "
diff --git a/utils/check_repo.py b/utils/check_repo.py
index 2cdb9af62de9..cfd2964f9dcc 100644
--- a/utils/check_repo.py
+++ b/utils/check_repo.py
@@ -219,7 +219,7 @@ def check_model_list():
     # Get the models from the directory structure of `src/transformers/models/`
     models = [model for model in dir(diffusers.models) if not model.startswith("__")]
 
-    missing_models = sorted(list(set(_models).difference(models)))
+    missing_models = sorted(set(_models).difference(models))
     if missing_models:
         raise Exception(
             f"The following models should be included in {models_dir}/__init__.py: {','.join(missing_models)}."
@@ -429,7 +429,7 @@ def get_all_auto_configured_models():
         for attr_name in dir(diffusers.models.auto.modeling_flax_auto):
             if attr_name.startswith("FLAX_MODEL_") and attr_name.endswith("MAPPING_NAMES"):
                 result = result | set(get_values(getattr(diffusers.models.auto.modeling_flax_auto, attr_name)))
-    return [cls for cls in result]
+    return list(result)
 
 
 def ignore_unautoclassed(model_name):
diff --git a/utils/overwrite_expected_slice.py b/utils/overwrite_expected_slice.py
index 95799f9ca625..7aa66727150a 100644
--- a/utils/overwrite_expected_slice.py
+++ b/utils/overwrite_expected_slice.py
@@ -67,7 +67,7 @@ def overwrite_file(file, class_name, test_name, correct_line, done_test):
 def main(correct, fail=None):
     if fail is not None:
         with open(fail, "r") as f:
-            test_failures = set([l.strip() for l in f.readlines()])
+            test_failures = {l.strip() for l in f.readlines()}
     else:
         test_failures = None
 
diff --git a/utils/stale.py b/utils/stale.py
index 36631b65a3ba..12932f31c243 100644
--- a/utils/stale.py
+++ b/utils/stale.py
@@ -38,7 +38,7 @@ def main():
     open_issues = repo.get_issues(state="open")
 
     for issue in open_issues:
-        comments = sorted([comment for comment in issue.get_comments()], key=lambda i: i.created_at, reverse=True)
+        comments = sorted(issue.get_comments(), key=lambda i: i.created_at, reverse=True)
         last_comment = comments[0] if len(comments) > 0 else None
         if (
             last_comment is not None