up

Author: sayakpaul

src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo_edit.py

@@ -274,8 +274,8 @@ def get_prompt_embeds(
         prompt: Union[str, List[str]],
         num_images_per_prompt: int = 1,
         max_sequence_length: int = 2048,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
+        device: torch.device | None = None,
+        dtype: torch.dtype | None = None,
     ):
         device = device or self._execution_device
         dtype = dtype or self.text_encoder.dtype
@@ -359,7 +359,7 @@ def pad_embedding(prompt_embeds, max_tokens, attention_mask=None):
     def encode_prompt(
         self,
         prompt: Union[str, List[str]],
-        device: Optional[torch.device] = None,
+        device: torch.device | None = None,
         num_images_per_prompt: int = 1,
         guidance_scale: float = 5,
         negative_prompt: Optional[Union[str, List[str]]] = None,

src/diffusers/pipelines/chroma/pipeline_chroma_inpainting.py

@@ -111,7 +111,7 @@ def retrieve_timesteps(
     scheduler,
     num_inference_steps: int | None = None,
     device: str | torch.device | None = None,
-    timesteps: Optional[List[int]] = None,
+    timesteps: list[int] | None = None,
     sigmas: list[float] | None = None,
     **kwargs,
 ):
@@ -127,15 +127,15 @@ def retrieve_timesteps(
             must be `None`.
         device (`str` or `torch.device`, *optional*):
             The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
+        timesteps (`list[int]`, *optional*):
             Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
             `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
+        sigmas (`list[float]`, *optional*):
             Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
             `num_inference_steps` and `timesteps` must be `None`.
 
     Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
+        `tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
         second element is the number of inference steps.
     """
     if timesteps is not None and sigmas is not None:
@@ -241,8 +241,8 @@ def _get_t5_prompt_embeds(
         prompt: Union[str, List[str], None] = None,
         num_images_per_prompt: int = 1,
         max_sequence_length: int = 512,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
+        device: torch.device | None = None,
+        dtype: torch.dtype | None = None,
     ):
         device = device or self._execution_device
         dtype = dtype or self.text_encoder.dtype
@@ -294,7 +294,7 @@ def encode_prompt(
         self,
         prompt: Union[str, List[str]],
         negative_prompt: Union[str, List[str], None] = None,
-        device: Optional[torch.device] = None,
+        device: torch.device | None = None,
         num_images_per_prompt: int = 1,
         prompt_embeds: torch.Tensor | None = None,
         negative_prompt_embeds: torch.Tensor | None = None,

src/diffusers/pipelines/cosmos/pipeline_cosmos2_5_transfer.py

@@ -223,8 +223,8 @@ def _get_prompt_embeds(
         self,
         prompt: Union[str, List[str]] = None,
         max_sequence_length: int = 512,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
+        device: torch.device | None = None,
+        dtype: torch.dtype | None = None,
     ):
         device = device or self._execution_device
         dtype = dtype or self.text_encoder.dtype
@@ -295,8 +295,8 @@ def encode_prompt(
         prompt_embeds: torch.Tensor | None = None,
         negative_prompt_embeds: torch.Tensor | None = None,
         max_sequence_length: int = 512,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
+        device: torch.device | None = None,
+        dtype: torch.dtype | None = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -381,8 +381,8 @@ def prepare_latents(
         num_frames_in: int = 93,
         num_frames_out: int = 93,
         do_classifier_free_guidance: bool = True,
-        dtype: Optional[torch.dtype] = None,
-        device: Optional[torch.device] = None,
+        dtype: torch.dtype | None = None,
+        device: torch.device | None = None,
         generator: torch.Generator | list[torch.Generator] | None = None,
         latents: torch.Tensor | None = None,
     ) -> torch.Tensor:

src/diffusers/pipelines/flux2/pipeline_flux2_klein.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 import inspect
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import Any, Callable
 
 import numpy as np
 import PIL
@@ -83,7 +83,7 @@ def retrieve_timesteps(
     scheduler,
     num_inference_steps: int | None = None,
     device: str | torch.device | None = None,
-    timesteps: Optional[List[int]] = None,
+    timesteps: list[int] | None = None,
     sigmas: list[float] | None = None,
     **kwargs,
 ):
@@ -99,15 +99,15 @@ def retrieve_timesteps(
             must be `None`.
         device (`str` or `torch.device`, *optional*):
             The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
+        timesteps (`list[int]`, *optional*):
             Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
             `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
+        sigmas (`list[float]`, *optional*):
             Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
             `num_inference_steps` and `timesteps` must be `None`.
 
     Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
+        `tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
         second element is the number of inference steps.
     """
     if timesteps is not None and sigmas is not None:
@@ -208,11 +208,11 @@ def __init__(
     def _get_qwen3_prompt_embeds(
         text_encoder: Qwen3ForCausalLM,
         tokenizer: Qwen2TokenizerFast,
-        prompt: Union[str, List[str]],
-        dtype: Optional[torch.dtype] = None,
-        device: Optional[torch.device] = None,
+        prompt: str | list[str],
+        dtype: torch.dtype | None = None,
+        device: torch.device | None = None,
         max_sequence_length: int = 512,
-        hidden_states_layers: List[int] = (9, 18, 27),
+        hidden_states_layers: list[int] = (9, 18, 27),
     ):
         dtype = text_encoder.dtype if dtype is None else dtype
         device = text_encoder.device if device is None else device
@@ -317,7 +317,7 @@ def _prepare_latent_ids(
     @staticmethod
     # Copied from diffusers.pipelines.flux2.pipeline_flux2.Flux2Pipeline._prepare_image_ids
     def _prepare_image_ids(
-        image_latents: List[torch.Tensor],  # [(1, C, H, W), (1, C, H, W), ...]
+        image_latents: list[torch.Tensor],  # [(1, C, H, W), (1, C, H, W), ...]
         scale: int = 10,
     ):
         r"""
@@ -327,7 +327,7 @@ def _prepare_image_ids(
         dimensions.
 
         Args:
-            image_latents (List[torch.Tensor]):
+            image_latents (list[torch.Tensor]):
                 A list of image latent feature tensors, typically of shape (C, H, W).
             scale (int, optional):
                 A factor used to define the time separation (T-coordinate) between latents. T-coordinate for the i-th
@@ -424,12 +424,12 @@ def _unpack_latents_with_ids(x: torch.Tensor, x_ids: torch.Tensor) -> list[torch
 
     def encode_prompt(
         self,
-        prompt: Union[str, List[str]],
-        device: Optional[torch.device] = None,
+        prompt: str | list[str],
+        device: torch.device | None = None,
         num_images_per_prompt: int = 1,
         prompt_embeds: torch.Tensor | None = None,
         max_sequence_length: int = 512,
-        text_encoder_out_layers: Tuple[int] = (9, 18, 27),
+        text_encoder_out_layers: tuple[int] = (9, 18, 27),
     ):
         device = device or self._execution_device
 
@@ -507,7 +507,7 @@ def prepare_latents(
     # Copied from diffusers.pipelines.flux2.pipeline_flux2.Flux2Pipeline.prepare_image_latents
     def prepare_image_latents(
         self,
-        images: List[torch.Tensor],
+        images: list[torch.Tensor],
         batch_size,
         generator: torch.Generator,
         device,
@@ -608,25 +608,25 @@ def interrupt(self):
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
-        image: Optional[Union[List[PIL.Image.Image], PIL.Image.Image]] = None,
-        prompt: Union[str, List[str]] = None,
+        image: list[PIL.Image.Image] | PIL.Image.Image | None = None,
+        prompt: str | list[str] = None,
         height: int | None = None,
         width: int | None = None,
         num_inference_steps: int = 50,
         sigmas: list[float] | None = None,
-        guidance_scale: Optional[float] = 4.0,
+        guidance_scale: float = 4.0,
         num_images_per_prompt: int = 1,
         generator: torch.Generator | list[torch.Generator] | None = None,
         latents: torch.Tensor | None = None,
         prompt_embeds: torch.Tensor | None = None,
-        negative_prompt_embeds: Optional[Union[str, List[str]]] = None,
+        negative_prompt_embeds: str | list[str] | None = None,
         output_type: str = "pil",
         return_dict: bool = True,
-        attention_kwargs: Optional[Dict[str, Any]] = None,
-        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
+        attention_kwargs: dict[str, Any] | None = None,
+        callback_on_step_end: Callable[[int, int, dict], None] | None = None,
+        callback_on_step_end_tensor_inputs: list[str] = ["latents"],
         max_sequence_length: int = 512,
-        text_encoder_out_layers: Tuple[int] = (9, 18, 27),
+        text_encoder_out_layers: tuple[int] = (9, 18, 27),
     ):
         r"""
         Function invoked when calling the pipeline for generation.
@@ -693,7 +693,7 @@ def __call__(
                 will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                 `._callback_tensor_inputs` attribute of your pipeline class.
             max_sequence_length (`int` defaults to 512): Maximum sequence length to use with the `prompt`.
-            text_encoder_out_layers (`Tuple[int]`):
+            text_encoder_out_layers (`tuple[int]`):
                 Layer indices to use in the `text_encoder` to derive the final prompt embeddings.
 
         Examples:

src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py

@@ -107,7 +107,7 @@ def retrieve_timesteps(
     scheduler,
     num_inference_steps: int | None = None,
     device: str | torch.device | None = None,
-    timesteps: Optional[List[int]] = None,
+    timesteps: list[int] | None = None,
     sigmas: list[float] | None = None,
     **kwargs,
 ):
@@ -123,15 +123,15 @@ def retrieve_timesteps(
             must be `None`.
         device (`str` or `torch.device`, *optional*):
             The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
+        timesteps (`list[int]`, *optional*):
             Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
             `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
+        sigmas (`list[float]`, *optional*):
             Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
             `num_inference_steps` and `timesteps` must be `None`.
 
     Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
+        `tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
         second element is the number of inference steps.
     """
     if timesteps is not None and sigmas is not None:
@@ -214,12 +214,12 @@ def __init__(
     # Copied from diffusers.pipelines.z_image.pipeline_z_image.ZImagePipeline.encode_prompt
     def encode_prompt(
         self,
-        prompt: Union[str, List[str]],
-        device: Optional[torch.device] = None,
+        prompt: str | list[str],
+        device: torch.device | None = None,
         do_classifier_free_guidance: bool = True,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[List[torch.FloatTensor]] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        negative_prompt: str | list[str] | None = None,
+        prompt_embeds: list[torch.FloatTensor] | None = None,
+        negative_prompt_embeds: torch.FloatTensor | None = None,
         max_sequence_length: int = 512,
     ):
         prompt = [prompt] if isinstance(prompt, str) else prompt
@@ -249,11 +249,11 @@ def encode_prompt(
     # Copied from diffusers.pipelines.z_image.pipeline_z_image.ZImagePipeline._encode_prompt
     def _encode_prompt(
         self,
-        prompt: Union[str, List[str]],
-        device: Optional[torch.device] = None,
-        prompt_embeds: Optional[List[torch.FloatTensor]] = None,
+        prompt: str | list[str],
+        device: torch.device | None = None,
+        prompt_embeds: list[torch.FloatTensor] | None = None,
         max_sequence_length: int = 512,
-    ) -> List[torch.FloatTensor]:
+    ) -> list[torch.FloatTensor]:
         device = device or self._execution_device
 
         if prompt_embeds is not None: